https://reunir.unir.net/handle/123456789/13132 Fri, 13 Feb 2026 00:48:19 GMT 2026-02-13T00:48:19Z https://reunir.unir.net/handle/123456789/13947 Editor's Note González-Crespo, Rubén The International Journal of Interactive Multimedia and Artificial Intelligence – IJIMAI – provides an interdisciplinary forum in which scientists and professionals can share their research results and report new advances in Artificial Intelligence (AI) tools or tools that use AI with interactive multimedia techniques. The present regular issue includes 13 articles. The first block of articles deals with problems related to images as diverse as the artificial generation of images or the optimization of their storage and transmission through compression techniques. The applications are very diverse, including the identification of forgeries, tumors or even misplaced face masks. Another block contains only one paper on speech recognition targeted on specific users suffering from dysarthria. Other block of two articles focuses on the education field problems of automation of teachers’ certification processes or prediction of students’ academic failure. Last block of articles covers services and products, commerce, marketing and user experience issues, as well as the ethical implications of AI. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-20T11:00:57Z No. of bitstreams: 1 ijimai7_7_0.pdf: 66853 bytes, checksum: 0aba5440ad126684b1d595a028e101c5 (MD5); Made available in DSpace on 2022-12-20T11:00:57Z (GMT). No. of bitstreams: 1 ijimai7_7_0.pdf: 66853 bytes, checksum: 0aba5440ad126684b1d595a028e101c5 (MD5) https://reunir.unir.net/handle/123456789/13947 https://reunir.unir.net/handle/123456789/13946 Adaptive Deep Learning Detection Model for Multi-Foggy Images Hussein Arif, Zainab; Mahmoud, Moamin; Hameed Abdulkareem, Karrar; Kadry, Seifedine; Abed Mohammed, Mazin; Nasser Al-Mhiqani, Mohammed; Al-Waisy, Alaa S.; Nedoma, Jan The fog has different features and effects within every single environment. Detection whether there is fog in the image is considered a challenge and giving the type of fog has a substantial enlightening effect on image defogging. Foggy scenes have different types such as scenes based on fog density level and scenes based on fog type. Machine learning techniques have a significant contribution to the detection of foggy scenes. However, most of the existing detection models are based on traditional machine learning models, and only a few studies have adopted deep learning models. Furthermore, most of the existing machines learning detection models are based on fog density-level scenes. However, to the best of our knowledge, there is no such detection model based on multi-fog type scenes have presented yet. Therefore, the main goal of our study is to propose an adaptive deep learning model for the detection of multi-fog types of images. Moreover, due to the lack of a publicly available dataset for inhomogeneous, homogenous, dark, and sky foggy scenes, a dataset for multi-fog scenes is presented in this study (https://github.com/Karrar-H-Abdulkareem/Multi-Fog-Dataset). Experiments were conducted in three stages. First, the data collection phase is based on eight resources to obtain the multi-fog scene dataset. Second, a classification experiment is conducted based on the ResNet-50 deep learning model to obtain detection results. Third, evaluation phase where the performance of the ResNet-50 detection model has been compared against three different models. Experimental results show that the proposed model has presented a stable classification performance for different foggy images with a 96% score for each of Classification Accuracy Rate (CAR), Recall, Precision, F1-Score which has specific theoretical and practical significance. Our proposed model is suitable as a pre-processing step and might be considered in different real-time applications. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-20T10:24:11Z No. of bitstreams: 1 ijimai7_7_3.pdf: 602150 bytes, checksum: 528455ea70d04817764aeae63ad6fb9d (MD5); Made available in DSpace on 2022-12-20T10:24:11Z (GMT). No. of bitstreams: 1 ijimai7_7_3.pdf: 602150 bytes, checksum: 528455ea70d04817764aeae63ad6fb9d (MD5) https://reunir.unir.net/handle/123456789/13946 https://reunir.unir.net/handle/123456789/13945 UX Poker: Estimating the Influence of User Stories on User Experience in Early Stage of Agile Development Hinderks, Andreas; Winter, Dominique; Domínguez Mayo, Francisco José; Escalona, María José; Thomaschewski, Jörg Agile methods are used more and more frequently to develop products by reducing development time. Requirements are typically written in user stories or epics. In this paper, a new method called UX Poker is presented. This is a method to estimate the impact of a user story on user experience before development. Thus, there is the opportunity that the product backlog can also be sorted according to the expected UX. To evaluate UX Poker, a case study was conducted with four agile teams. Besides, a workshop followed by a questionnaire was conducted with all four agile teams. The goal of being able to estimate the UX even before development was achieved. Using UX Poker to create another way to sort the product backlog can be considered achieved in this first evaluation. The results show that UX Poker can be implemented in a real- life application. Additionally, during the use of UX Poker, it was found that a shared understanding of UX began. The participants clarified in the team discussion about UX Poker what related to influence the user stories had on UX and what UX meant for their product. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-20T10:13:18Z No. of bitstreams: 1 ijimai7_7_11.pdf: 256171 bytes, checksum: 2c20e6e6daddf62c4d9ebf8cd2908e2a (MD5); Made available in DSpace on 2022-12-20T10:13:18Z (GMT). No. of bitstreams: 1 ijimai7_7_11.pdf: 256171 bytes, checksum: 2c20e6e6daddf62c4d9ebf8cd2908e2a (MD5) https://reunir.unir.net/handle/123456789/13945 https://reunir.unir.net/handle/123456789/13944 Empirical Analysis of Ethical Principles Applied to Different AI Uses Cases López Rivero, Alfonso José; Beato, M. Encarnación; Muñoz Martínez, César; Cortiñas Vázquez, Pedro Gonzalo In this paper, we present an empirical study on the perception of the ethical challenges of artificial intelligence groups in the classification made by the European Union (EU). The study seeks to identify the ethical principles that cause the greatest concern among the population, analyzing these characteristics among different actors. The main study analyses the difference between Information and Communications Technology (ICT) professionals and the rest of the population. Along with this study, we conducted a gender study; in addition, we studied differences between university students, classified as future professionals who can work in Artificial Intelligence, and other university students. We believe that this work is a starting point for an informed debate in the scientific community and industry on the ethical implications of artificial intelligence based on the classification of ethical principles made by the EU, which can be extrapolated to any analysis carried out on the use of data to apply them in algorithms based on Artificial Intelligence. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-20T10:04:49Z No. of bitstreams: 1 ijimai7_7_12.pdf: 395197 bytes, checksum: c1aa6db4da4fc00ea66c89e3f05f3920 (MD5); Made available in DSpace on 2022-12-20T10:04:49Z (GMT). No. of bitstreams: 1 ijimai7_7_12.pdf: 395197 bytes, checksum: c1aa6db4da4fc00ea66c89e3f05f3920 (MD5) https://reunir.unir.net/handle/123456789/13944 https://reunir.unir.net/handle/123456789/13943 A Rule-Based Expert System for Teachers’ Certification in the Use of Learning Management Systems Regueras, Luisa M.; Verdú, María J; de Castro, Juan-Pablo In recent years and accelerated by the arrival of the COVID-19 pandemic, Learning Management Systems (LMS) are increasingly used as a complement to university teaching. LMS provide an important number of resources and activities that teachers can freely select to complement their teaching, which means courses with different usage patterns difficult to characterize. This study proposes an expert system to automatically classify courses and certify teachers’ LMS competence from LMS logs. The proposed system uses clustering to stablish the classification scheme. From the output of this algorithm, it defines the rules used to classify courses. Data registered from a university virtual campus with 3,303 courses and two million interactive events have been used to obtain the classification scheme and rules. The system has been validated against a group of experts. Results show that it performs successfully. Therefore, it can be concluded that the system can automatically and satisfactorily evaluate and certify the teachers’ LMS competence evidenced in their courses. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-20T09:57:57Z No. of bitstreams: 1 ijimai7_7_8.pdf: 405410 bytes, checksum: 9fd1999cc93eae210c239882c736428c (MD5); Made available in DSpace on 2022-12-20T09:57:57Z (GMT). No. of bitstreams: 1 ijimai7_7_8.pdf: 405410 bytes, checksum: 9fd1999cc93eae210c239882c736428c (MD5) https://reunir.unir.net/handle/123456789/13943 https://reunir.unir.net/handle/123456789/13936 Painting Authorship and Forgery Detection Challenges with AI Image Generation Algorithms: Rembrandt and 17th Century Dutch Painters as a Case Study Fraile-Narvaez, Marcelo; Sagredo-Olivenza, Ismael; McGowan, Nadia Image authorship attribution presents many challenges and difficulties which have increased with the capabilities presented by synthetic image generation through different artificial intelligence algorithms available today. The hypothesis in this research considers the possibility of using artificial intelligence as a tool to detect forgeries through the usage of a deep learning algorithm. The proposed algorithm was trained using a dataset comprised of paintings by Rembrandt and other 17th century Dutch painters. Three experiments were performed with the proposed algorithm. The first was to build a classifier able to ascertain whether a painting belongs to the Rembrandt or non-Rembrandt category, depending on whether it was painted by this author or not. The second tests included other 17th century painters in four categories. Artworks could be classified as Rembrandt, Eeckhout, Leveck or other Dutch painters. The third experiment used paintings generated by Dall-e 2 and attempted to classify them using the prior categories. Experiments confirmed the hypothesis with best executions reaching accuracy rates of more than 90%. Future research with extended datasets and improved image resolution are suggested to improve the obtained results. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-16T11:36:31Z No. of bitstreams: 1 ijimai7_7_1.pdf: 357350 bytes, checksum: 54def274ce6c750fdcc43ac62677a515 (MD5); Made available in DSpace on 2022-12-16T11:36:31Z (GMT). No. of bitstreams: 1 ijimai7_7_1.pdf: 357350 bytes, checksum: 54def274ce6c750fdcc43ac62677a515 (MD5) https://reunir.unir.net/handle/123456789/13936 https://reunir.unir.net/handle/123456789/13935 Brain Tumor Segmentation and Identification Using Particle Imperialist Deep Convolutional Neural Network in MRI Images Khemchandani, Maahi Amit; Jadhav, Shivajirao Manikra; Iyer, B. R. For the past few years, segmentation for medical applications using Magnetic Resonance (MR) images is concentrated. Segmentation of Brain tumors using MRIpaves an effective platform to plan the treatment and diagnosis of tumors. Thus, segmentation is necessary to be improved, for a novel framework. The Particle Imperialist Deep Convolutional Neural Network (PI-Deep CNN) suggested framework is intended to address the problems with segmenting and categorizing the brain tumor. Using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) Algorithm, the input MRI brain image is segmented, and then features are extracted using the Scatter Local Neighborhood Structure (SLNS) descriptor. Combining the scattering transform and the Local Neighborhood Structure (LNS) descriptor yields the proposed descriptor. A suggested Particle Imperialist algorithm-trained Deep CNN is then used to achieve the tumor-level classification. Different levels of the tumor are classified by the classifier, including Normal without tumor, Abnormal, Malignant tumor, and Non-malignant tumor. The cell is identified as a tumor cell and is subjected to additional diagnostics, with the exception of the normal cells that are tumor-free. The proposed method obtained a maximum accuracy of 0.965 during the experimentation utilizing the BRATS database and performance measures. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-16T10:45:19Z No. of bitstreams: 1 ijimai7_7_4.pdf: 1266936 bytes, checksum: 9ba9c6bbe3fef052c28a25d529aad2d6 (MD5); Made available in DSpace on 2022-12-16T10:45:19Z (GMT). No. of bitstreams: 1 ijimai7_7_4.pdf: 1266936 bytes, checksum: 9ba9c6bbe3fef052c28a25d529aad2d6 (MD5) https://reunir.unir.net/handle/123456789/13935 https://reunir.unir.net/handle/123456789/13934 A Fuzzy-Based Multimedia Content Retrieval Method Using Mood Tags and Their Synonyms in Social Networks Moon, Chang Bae; Lee, Jong Yeol; Kim, Byeong Man The preferences of Web information purchasers are rapidly evolving. Cost-effectiveness is now becoming less regarded than cost-satisfaction, which emphasizes the purchaser’s psychological satisfaction. One method to improve a user’s cost-satisfaction in multimedia content retrieval is to utilize the mood inherent in multimedia items. An example of applications using this method is SNS (Social Network Services), which is based on folksonomy, but its applications encounter problems due to synonyms. In order to solve the problem of synonyms in our previous study, the mood of multimedia content is represented with arousal and valence (AV) in Thayer’s two-dimensional model as its internal tag. Although some problems of synonyms could now be solved, the retrieval performance of the previous study was less than that of a keyword-based method. In this paper, a new method that can solve the synonym problem is proposed, while simultaneously maintaining the same performance as the keyword-based approach. In the proposed method, a mood of multimedia content is represented with a fuzzy set of 12 moods of the Thayer model. For the analysis, the proposed method is compared with two methods, one based on AV value and the other based on keyword. The analysis results demonstrate that the proposed method is superior to the two methods. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-16T10:00:55Z No. of bitstreams: 1 ijimai7_7_7.pdf: 768608 bytes, checksum: d517d301ec21de2de6abdb13ee3f430c (MD5); Made available in DSpace on 2022-12-16T10:00:55Z (GMT). No. of bitstreams: 1 ijimai7_7_7.pdf: 768608 bytes, checksum: d517d301ec21de2de6abdb13ee3f430c (MD5) https://reunir.unir.net/handle/123456789/13934 https://reunir.unir.net/handle/123456789/13933 Modeling Sub-Band Information Through Discrete Wavelet Transform to Improve Intelligibility Assessment of Dysarthric Speech Sahu, Laxmi Priya; Pradhan, Gayadhar; Singh, Jyoti Prakash The speech signal within a sub-band varies at a fine level depending on the type, and level of dysarthria. The Mel-frequency filterbank used in the computation process of cepstral coefficients smoothed out this fine level information in the higher frequency regions due to the larger bandwidth of filters. To capture the sub-band information, in this paper, four-level discrete wavelet transform (DWT) decomposition is firstly performed to decompose the input speech signal into approximation and detail coefficients, respectively, at each level. For a particular input speech signal, five speech signals representing different sub-bands are then reconstructed using inverse DWT (IDWT). The log filterbank energies are computed by analyzing the short-term discrete Fourier transform magnitude spectra of each reconstructed speech using a 30-channel Mel-filterbank. For each analysis frame, the log filterbank energies obtained across all reconstructed speech signals are pooled together, and discrete cosine transform is performed to represent the cepstral feature, here termed as discrete wavelet transform reconstructed (DWTR)- Mel frequency cepstral coefficient (MFCC). The i-vector based dysarthric level assessment system developed on the universal access speech corpus shows that the proposed DTWRMFCC feature outperforms the conventional MFCC and several other cepstral features reported for a similar task. The usages of DWTR- MFCC improve the detection accuracy rate (DAR) of the dysarthric level assessment system in the text and the speaker-independent test case to 60.094 % from 56.646 % MFCC baseline. Further analysis of the confusion matrices shows that confusion among different dysarthric classes is quite different for MFCC and DWTR-MFCC features. Motivated by this observation, a two-stage classification approach employing discriminating power of both kinds of features is proposed to improve the overall performance of the developed dysarthric level assessment system. The two-stage classification scheme further improves the DAR to 65.813 % in the text and speaker- independent test case. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-16T08:21:37Z No. of bitstreams: 1 ijimai7_7_6.pdf: 355090 bytes, checksum: 2b3f70053a83aef40a9570661816538e (MD5); Made available in DSpace on 2022-12-16T08:21:37Z (GMT). No. of bitstreams: 1 ijimai7_7_6.pdf: 355090 bytes, checksum: 2b3f70053a83aef40a9570661816538e (MD5) https://reunir.unir.net/handle/123456789/13933 https://reunir.unir.net/handle/123456789/13932 Marketing Intelligence: Boom or Bust of Service Marketing? Lies, Jan Marketing intelligence fosters two major developments within digital service marketing. On the one hand, a boom of services seems to have evolved, accelerated by the opportunities of marketing intelligence. It has contributed to the optimization of customer experiences, e.g., supported by mobile, personalized, and customized marketing services. On the other hand, (digital) self-services are likely to pervert the term “service”. Lifecycle marketing, including annoying marketing communication in real-time, automated price adjustment and programmatic advertising based on artificial intelligence, affects the vision of fully standardized marketing automation. Additionally, there are incentives to pollute the digital information in order to manufacture opinions. Fake news is one popular example. This leads to the (open) question if marketing intelligence means service boom or bust of marketing. This contribution aims to elaborate the boom-and-bust aspects of marketing intelligence and suggests a trade-off. The method applied in this paper will be a descriptive and conceptual literature review, through which the paradigmatic thoughts will be juxtaposed from the perspective of service. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-16T08:07:54Z No. of bitstreams: 1 ijimai7_7_13.pdf: 169541 bytes, checksum: ff93eba5b42aa5bd7aeada5b596b4573 (MD5); Made available in DSpace on 2022-12-16T08:07:54Z (GMT). No. of bitstreams: 1 ijimai7_7_13.pdf: 169541 bytes, checksum: ff93eba5b42aa5bd7aeada5b596b4573 (MD5) https://reunir.unir.net/handle/123456789/13932 https://reunir.unir.net/handle/123456789/13931 Teaching through Learning Analytics: Predicting Student Learning Profiles in a Physics Course at a Higher Education Institution Rincón-Flores, Elvira G.; López-Camacho, Eunice; Mena, Juanjo; Olmos, Omar Learning Analytics (LA) is increasingly used in Education to set prediction models from artificial intelligence to determine learning profiles. This study aims to determine to what extent K-nearest neighbor and random forest algorithms could become a useful tool for improving the teaching-learning process and reducing academic failure in two Physics courses at the Technological Institute of Monterrey, México (n = 268). A quasi-experimental and mixed method approach was conducted. The main results showed significant differences between the first and second term evaluations in the two groups. One of the main findings of the study is that the predictions were not very accurate for each student in the first term evaluation. However, the predictions became more accurate as the algorithm was fed with larger datasets from the second term evaluation. This result indicates how predictive algorithms based on decision trees, can offer a close approximation to the academic performance that will occur in the class, and this information could be use along with the personal impressions coming from the teacher. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-16T07:52:47Z No. of bitstreams: 1 ijimai7_7_9.pdf: 977826 bytes, checksum: 622f301873713d52a8e6b1096e914ca3 (MD5); Made available in DSpace on 2022-12-16T07:52:47Z (GMT). No. of bitstreams: 1 ijimai7_7_9.pdf: 977826 bytes, checksum: 622f301873713d52a8e6b1096e914ca3 (MD5) https://reunir.unir.net/handle/123456789/13931 https://reunir.unir.net/handle/123456789/13930 Optimizing Fast Fourier Transform (FFT) Image Compression using Intelligent Water Drop (IWD) Algorithm Kaur, Surinder; Chaudhary, Gopal; Dinesh Kumar, Javalkar; Pillai, Manu S.; Gupta, Yash; Khari, Manju; García-Díaz, Vicente; Parra Fuente, Javier Digital image compression is the technique in digital image processing where special attention is provided in decreasing the number of bits required to represent a digital image. A wide range of techniques have been developed over the years, and novel approaches continue to emerge. This paper proposes a new technique for optimizing image compression using Fast Fourier Transform (FFT) and Intelligent Water Drop (IWD) algorithm. IWD-based FFT Compression is a emerging ethodology, and we expect compression findings to be much better than the methods currently being applied in the domain. This work aims to enhance the degree of compression of the image while maintaining the features that contribute most. It optimizes the FFT threshold values using swarm-based optimization technique (IWD) and compares the results in terms of Structural Similarity Index Measure (SSIM). The criterion of structural similarity of image quality is based on the premise that the human visual system is highly adapted to obtain structural information from the scene, so a measure of structural similarity provides a reasonable estimate of the perceived image quality. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-14T13:34:35Z No. of bitstreams: 1 ijimai7_7_5.pdf: 1424355 bytes, checksum: 2c436692e61ddc6c505755cec07a1376 (MD5); Made available in DSpace on 2022-12-14T13:34:35Z (GMT). No. of bitstreams: 1 ijimai7_7_5.pdf: 1424355 bytes, checksum: 2c436692e61ddc6c505755cec07a1376 (MD5) https://reunir.unir.net/handle/123456789/13930 https://reunir.unir.net/handle/123456789/13929 Detection of Improperly Worn Face Masks using Deep Learning – A Preventive Measure Against the Spread of COVID-19 Bhaik, Anubha; Singh, Vaishnavi; Gandotra, Ekta; Gupta, Deepak Coronavirus disease 2019 has had a pressing impact on people all around the world. Ceasing the spread of this infectious disease is the urgent need of the hour. A vital method of protection against the virus is wearing masks in public areas. Not merely wearing masks but wearing masks properly can ensure that the respiratory droplets do not get transmitted to other people. In this paper, we have proposed a deep learning-based model, which can be used to detect people who are not wearing their face masks properly. A convolutional neural network model based on the concept of transfer learning is trained on a self-made dataset of images and implemented with light-weighted neural network called MobileNetV2 for mobile architectures. OpenCV is used with Caffe framework to detect faces in an input frame which are further forwarded to our trained convolutional neural network for classification. The method has been implemented on various input images and classification results have been obtained for the same. The experimental results show that the proposed model achieves a testing accuracy and training accuracy of 93.58% and 92.27% respectively. Optimal results with high confidence scores and correct classification have also been achieved when the proposed model was tested on individual input images. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-14T13:18:35Z No. of bitstreams: 1 ijimai7_7_2.pdf: 700700 bytes, checksum: e8748c9b4bcea9a2e54cd3b267c2a1a6 (MD5); Made available in DSpace on 2022-12-14T13:18:35Z (GMT). No. of bitstreams: 1 ijimai7_7_2.pdf: 700700 bytes, checksum: e8748c9b4bcea9a2e54cd3b267c2a1a6 (MD5) https://reunir.unir.net/handle/123456789/13929 https://reunir.unir.net/handle/123456789/13928 Balance Your Work-Life: Personal Interactive Web-Interface Majumder, Soumi; Chowdhury, Soumalya; Dey, Nilanjan; Santosh, K. C. The term work-life balance can be described as a path to manage stresses and burnouts in the workplace. In this Covid-19 pandemic, work-from-home practice includes both personal and professional spaces as employees, more often, stay digitally connected. As a result, personal life hardly can be separated, which will potentially create imbalanced life, which creates problems regarding physical and mental health of the employees. In such unprecedented situations, we are required to maintain and/or integrate balanced work-life. A balanced work-life gives employees a stress-free environment to work and improves employees' mental and physical health conditions and relationships. In this study, we focus on maintaining a proper work-life balance through a monitoring tool, the ‘Wheel of Life.’ Considering the drastic changes in work culture (due to Covid-19, for example), we introduce an interactive interface based on ‘Wheel of life’ concept. Our interface helps tune various important factors, such as business, creative, social, love and life purpose, and provides multiple recommendations. The purpose of the study is to assist web users to balance their work-life, improve psychological well-being and quality of life in this unforeseen situation. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-14T13:10:14Z No. of bitstreams: 1 ijimai7_7_10.pdf: 671815 bytes, checksum: 0f10b3440a65c2a8d054c5a8ebe8c0bd (MD5); Made available in DSpace on 2022-12-14T13:10:14Z (GMT). No. of bitstreams: 1 ijimai7_7_10.pdf: 671815 bytes, checksum: 0f10b3440a65c2a8d054c5a8ebe8c0bd (MD5) https://reunir.unir.net/handle/123456789/13928 https://reunir.unir.net/handle/123456789/13906 Editor's Note de Paz Santana, Juan F.; Villarrubia González, Gabriel The international conference “Disruptive Technologies Tech Ethics and Artificial Intelligence” (DITTET) provides a forum to present and discuss the latest scientific and technical advances and their implications in the field of ethics. It also provides a forum for experts to present their latest research in disruptive technologies, promoting knowledge transfer. It provides a unique opportunity to bring together experts in different fields, academics, and professionals to exchange their experience in the development and deployment of disruptive technologies, artificial intelligence, and their ethical problems. This Special Issue contains extended versions of selected works presented at the 1st International Conference on Disruptive Technologies, Tech Ethics and Artificial Intelligence (DiTTEt 2021), held in Salamanca (Spain) in September 2021. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T13:06:03Z No. of bitstreams: 1 ijimai7_6_0_0.pdf: 50552 bytes, checksum: 81c326ba05451a619d4113f762da9c59 (MD5); Made available in DSpace on 2022-12-13T13:06:03Z (GMT). No. of bitstreams: 1 ijimai7_6_0_0.pdf: 50552 bytes, checksum: 81c326ba05451a619d4113f762da9c59 (MD5) https://reunir.unir.net/handle/123456789/13906 https://reunir.unir.net/handle/123456789/13905 Board of Directors' Profile: A Case for Deep Learning as a Valid Methodology to Finance Research Vaca, César; Tejerina, Fernando; Sahelices, Benjamín This paper presents a Deep Learning (DL) model for natural language processing of unstructured CVs to generate a six-dimensional profile of the professional experience of the Spanish companies' board of directors. We show the complete process starting with open data extraction and cleaning, the generation of a labeled dataset for supervised learning, the development, training and validation of a DL model capable of accurately analyzing the dataset, and, finally, a data analysis work based on the automated generation of the professional profiles of more than 6,000 directors of Spanish listed companies between 2003 and 2020. An RNN-LSTM neural network has been trained in three phases starting from a random initial state, (1) learning of basic structures of the Spanish language, (2) fine tuning for scientific texts in the field of economics and finance, and (3) regression modeling to generate a six-dimensional profile based on a generalization of sentiment classification systems. The complete training has been carried out with very low computational requirements, having a total duration of 120 hours of processing in a low-end GPU. The results obtained in the validation of the DL model show great accuracy, obtaining a value for the standard deviation of the mean error between 0.015 and 0.033. As a result, we have been able to outline with a high degree of reliability the profile of the listed Spanish companies' board of directors. We found that the predominant profile is that of directors with experience in executive or consultancy positions, followed by the financial profile. The results achieved show the potential of DL in social science research, particularly in Finance. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T12:59:08Z No. of bitstreams: 1 ijimai7_6_7.pdf: 1262285 bytes, checksum: 0ceb0b306c3da73d936b42f485d3c6de (MD5); Made available in DSpace on 2022-12-13T12:59:08Z (GMT). No. of bitstreams: 1 ijimai7_6_7.pdf: 1262285 bytes, checksum: 0ceb0b306c3da73d936b42f485d3c6de (MD5) https://reunir.unir.net/handle/123456789/13905 https://reunir.unir.net/handle/123456789/13904 A Clustering Algorithm Based on an Ensemble of Dissimilarities: An Application in the Bioinformatics Domain Martín Merino, Manuel; López Rivero, Alfonso José; Alonso, Vidal; Vallejo, Marcelo; Ferreras, Antonio Clustering algorithms such as k-means depend heavily on choosing an appropriate distance metric that reflect accurately the object proximities. A wide range of dissimilarities may be defined that often lead to different clustering results. Choosing the best dissimilarity is an ill-posed problem and learning a general distance from the data is a complex task, particularly for high dimensional problems. Therefore, an appealing approach is to learn an ensemble of dissimilarities. In this paper, we have developed a semi-supervised clustering algorithm that learns a linear combination of dissimilarities considering incomplete knowledge in the form of pairwise constraints. The minimization of the loss function is based on a robust and efficient quadratic optimization algorithm. Besides, a regularization term is considered that controls the complexity of the distance metric learned avoiding overfitting. The algorithm has been applied to the identification of tumor samples using the gene expression profiles, where domain experts provide often incomplete knowledge in the form of pairwise constraints. We report that the algorithm proposed outperforms a standard semi-supervised clustering technique available in the literature and clustering results based on a single dissimilarity. The improvement is particularly relevant for applications with high level of noise. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T12:20:55Z No. of bitstreams: 1 ijimai7_6_1.pdf: 2597861 bytes, checksum: 9159982e29f2b2ab8468a339c3b4743d (MD5); Made available in DSpace on 2022-12-13T12:20:55Z (GMT). No. of bitstreams: 1 ijimai7_6_1.pdf: 2597861 bytes, checksum: 9159982e29f2b2ab8468a339c3b4743d (MD5) https://reunir.unir.net/handle/123456789/13904 https://reunir.unir.net/handle/123456789/13903 Normative Affordances Through and By Technology: Technological Mediation and Human Enhancement Döbler, Niklas Alexander; Bartnik, Clemens Human activity is fundamentally embedded in and constituted by technology. In this regard, technology influences not only how people experience the world, but also which possibilities for action offered by the environment (affordances) can be perceived and ultimately acted upon. As having socio-cultural and normative aspects, affordances are deeply relational to the technological human form of life. Postphenomenology describes several human-technology relations and their perception and action mediating effects. Therefore, it provides a suitable framework to examine how technology mediates the perception of affordances and leads to different behavioral outcomes. Technology can reveal hitherto hidden affordances but can also result in the manipulation and concealment of action possibilities. Both aspects can be deliberately controlled by using a particular technology and/or interfering with the technological hermeneutic process. Technological mal-functions, limitations, purposeful corruption, or human error can disrupt the hermeneutic qualities of technology and may lead to false conclusions about affordances and respective maladaptive behavioral outcomes. Technology can also be applied to humans to form “better” versions of them. One consequence of these so-called Human Enhancement technologies is the emergence of different affordances for the enhanced individual and the possible establishment of new affordances inside a form of life. Manipulating the perception and emergence of affordances through technological mediation or Human Enhancement can have severe political and ethical consequences. It is necessary to engage in an open debate about the perception and action mediating power of technology and the human reliance on them in our current and future form of life. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T12:14:14Z No. of bitstreams: 1 ijimai7_6_2.pdf: 532117 bytes, checksum: 6a7869b1df78391dbfdf57c14b9bdb19 (MD5); Made available in DSpace on 2022-12-13T12:14:14Z (GMT). No. of bitstreams: 1 ijimai7_6_2.pdf: 532117 bytes, checksum: 6a7869b1df78391dbfdf57c14b9bdb19 (MD5) https://reunir.unir.net/handle/123456789/13903 https://reunir.unir.net/handle/123456789/13902 Integrating Emotion Recognition Tools for Developing Emotionally Intelligent Agents Marcos-Pablos, Samuel; Lobato, Fernando; García-Peñalvo, Francisco Emotionally responsive agents that can simulate emotional intelligence increase the acceptance of users towards them, as the feeling of empathy reduces negative perceptual feedback. This has fostered research on emotional intelligence during last decades, and nowadays numerous cloud and local tools for automatic emotional recognition are available, even for inexperienced users. These tools however usually focus on the recognition of discrete emotions sensed from one communication channel, even though multimodal approaches have been shown to have advantages over unimodal approaches. Therefore, the objective of this paper is to show our approach for multimodal emotion recognition using Kalman filters for the fusion of available discrete emotion recognition tools. The proposed system has been modularly developed based on an evolutionary approach so to be integrated in our digital ecosystems, and new emotional recognition sources can be easily integrated. Obtained results show improvements over unimodal tools when recognizing naturally displayed emotions. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T12:08:57Z No. of bitstreams: 1 ijimai7_6_8.pdf: 1705376 bytes, checksum: e9d27ecbbd80b0f5456b358fd9ea2eb6 (MD5); Made available in DSpace on 2022-12-13T12:08:57Z (GMT). No. of bitstreams: 1 ijimai7_6_8.pdf: 1705376 bytes, checksum: e9d27ecbbd80b0f5456b358fd9ea2eb6 (MD5) https://reunir.unir.net/handle/123456789/13902 https://reunir.unir.net/handle/123456789/13901 An Event Mesh for Event Driven IoT Applications Berjón, Roberto; Mateos, Montserrat; Beato, M. Encarnación; Fermoso García, Ana In IoT contexts, software solutions are required to have components located in different environments: mobile, edge, fog or cloud. To design this type of application, event driven architecture (EDA) is used to develop distributed, scalable, decoupled, desynchronized and real-time components. The interconnection between the different components is done through event brokers that allow communication based on messages (events). Although the design of the components is independent of the environment in which they are deployed, this environment can determine the infrastructure to be used, for example the event brokers, so it is common to have to make modifications to the applications to adapt them to these environments, which complicates their design and maintenance. It is therefore necessary to have an event mesh that allows the connection between event brokers to simplify the development of applications. This paper presents the SCIFI-II system, an event mesh that allows the distribution of events between event brokers. Its use will allow the design of components decoupling them from the event brokers, which will facilitate their deployment in any environment. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T11:54:07Z No. of bitstreams: 1 ijimai7_6_6.pdf: 1950920 bytes, checksum: b752a4668767f65fedf0ef48eaa650ce (MD5); Made available in DSpace on 2022-12-13T11:54:07Z (GMT). No. of bitstreams: 1 ijimai7_6_6.pdf: 1950920 bytes, checksum: b752a4668767f65fedf0ef48eaa650ce (MD5) https://reunir.unir.net/handle/123456789/13901 https://reunir.unir.net/handle/123456789/13900 Promoting Social Media Dissemination of Digital Images Through CBR-Based Tag Recommendation Martín-Gómez, Lucía; Pérez-Marcos, Javier; Cordero-Gutiérrez, Rebeca; De La Iglesia, Daniel H. Multimedia content has become an essential tool to share knowledge, sell products or disseminate messages. Some social networks use multimedia content to promote information and create social communities. In order to increase the impact of the digital content, those images or videos are labeled with different words, denominated tags. In this paper, we propose a recommender system which analyzes multimedia content and suggests tags to maximize its influence in the social community. It implements a Case-Based Reasoning architecture (CBR), which allows to learn from previous tagged content. The system has been evaluated through cross fold validation with a training and validation sets carefully constructed and extracted from Instagram. The results demonstrate that the system can suggest good options to label our image and maximize the influence of the multimedia content. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T11:38:52Z No. of bitstreams: 1 ijimai7_6_5.pdf: 1618020 bytes, checksum: c83bebe1b826a3865aa64c98c2fcf281 (MD5); Made available in DSpace on 2022-12-13T11:38:52Z (GMT). No. of bitstreams: 1 ijimai7_6_5.pdf: 1618020 bytes, checksum: c83bebe1b826a3865aa64c98c2fcf281 (MD5) https://reunir.unir.net/handle/123456789/13900 https://reunir.unir.net/handle/123456789/13899 Edge Face Recognition System Based on One-Shot Augmented Learning Jiménez-Bravo, Diego M.; Lozano Murciego, Álvaro; Sales, A.; Augusto Silva, Luis; De La Iglesia, Daniel H. There is growing concern among users of computer systems about how their data is handled. In this sense, IT (Information Technology) professionals are not unaware of this problem and are looking for solutions to meet the requirements and concerns of their users. During the last few years, various techniques and technologies have emerged that allow us to answer to the problem posed by users. Technologies such as edge computing and techniques such as one-shot learning and data augmentation enable progress in this regard. Thus, in this article, we propose the creation of a system that makes use of these techniques and technologies to solve the problem of face recognition and form a low-cost security system. The results obtained show that the combination of these techniques is effective in most of the face detection algorithms and allows an effective solution to the problem raised. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T11:27:02Z No. of bitstreams: 1 ijimai7_6_4.pdf: 4275272 bytes, checksum: fe696c449ced17867c0c7589e008fb04 (MD5); Made available in DSpace on 2022-12-13T11:27:02Z (GMT). No. of bitstreams: 1 ijimai7_6_4.pdf: 4275272 bytes, checksum: fe696c449ced17867c0c7589e008fb04 (MD5) https://reunir.unir.net/handle/123456789/13899 https://reunir.unir.net/handle/123456789/13898 A Model for Planning TELCO Work-Field Activities Enabled by Genetic and Ant Colony Algorithms Henriques, João; Caldeira, Filipe Telecommunication Company’s (TELCO) are continuously delivering their efforts on the effectiveness of their daily work. Planning the activities for their workers is a crucial sensitive, and time-consuming task usually taken by experts. This plan aims to find an optimized solution maximizing the number of activities assigned to workers and minimizing the inherent costs (e.g., labor from workers, fuel, and other transportation costs). This paper proposes a model that allows computing a maximized plan for the activities assigned to their workers, allowing to alleviate the burden of the existing experts, even if supported by software implementing rule-based heuristic models. The proposed model is inspired by nature and relies on two stages supported by Genetic and Ant Colony evolutionary algorithms. At the first stage, a Genetic Algorithms (GA) identifies the optimal set of activities to be assigned to workers as the way to maximize the revenues. At a second step, an Ant Colony algorithm searches for an efficient path among the activities to minimize the costs. The conducted experimental work validates the effectiveness of the proposed model in the optimization of the planning TELCO work-field activities in comparison to a rule-based heuristic model. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T11:15:29Z No. of bitstreams: 1 ijimai7_6_3.pdf: 1213846 bytes, checksum: 5725afaa75f98da6dca5fc8ad1ba448b (MD5); Made available in DSpace on 2022-12-13T11:15:29Z (GMT). No. of bitstreams: 1 ijimai7_6_3.pdf: 1213846 bytes, checksum: 5725afaa75f98da6dca5fc8ad1ba448b (MD5) https://reunir.unir.net/handle/123456789/13898 https://reunir.unir.net/handle/123456789/13896 Editor's Note Shu, Lei; Rodrigues, Joel J.P.C.; Cohn, Anthony G.; Mao, Qirong; Li, Maozhen As the Internet of Things (IoT) further develops and expands to the Internet of Everything (IoE), high-speed multimedia streaming data processing, analysis, and shorter response times are increasingly becoming the demands of today. Driven by the Internet of Things (IoT), a new computing paradigm, Edge computing, is currently developing rapidly. Compared with traditional centralized generalpurpose computing, Edge computing is a distributed architecture. The operations of applications, data and services are moved from the central node of the network to the edge nodes on the network logic for processing. Under this structure, the analysis of data and the generation of knowledge are closer to the source of the data, so it is more suitable for processing. However, with the rapid development of 5G, IoT and other services and scenarios, there are more and more intelligent terminal devices. Multimedia streaming processing in IoT becomes a very prominent problem. To overcome this problem, the adoption of intelligent Edge or Artificial Intelligence (AI) powered Edge computing (Edge-AI) can achieve the goals of lower cost, higher security, lower latency, and ease of management. Recently, many network modeling methods, computing algorithms, and signal processing technologies have been successfully developed and applied to multimedia streaming processing in IoT with Edge Intelligence. A total of 13 papers are presented in this special issue for the purpose of collecting the latest developments and results on this research topic. We divide them into three categories: production and life applications, security, and text and image processing. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T11:02:05Z No. of bitstreams: 1 ijimai_7_5_0 (1).pdf: 57934 bytes, checksum: f5174c18dbace77d839513db23c74daa (MD5); Made available in DSpace on 2022-12-13T11:02:05Z (GMT). No. of bitstreams: 1 ijimai_7_5_0 (1).pdf: 57934 bytes, checksum: f5174c18dbace77d839513db23c74daa (MD5) https://reunir.unir.net/handle/123456789/13896 https://reunir.unir.net/handle/123456789/13713 Electromiographic Signal Processing Using Embedded Artificial Intelligence: An Adaptive Filtering Approach Proaño-Guevara, Daniel; Blanco Valencia, Xiomara Patricia; Rosero-Montalvo, Paul D.; Peluffo-Ordóñez, Diego H. In recent times, Artificial Intelligence (AI) has become ubiquitous in technological fields, mainly due to its ability to perform computations in distributed systems or the cloud. Nevertheless, for some applications -as the case of EMG signal processing- it may be highly advisable or even mandatory an on-the-edge processing, i.e., an embedded processing methodology. On the other hand, sEMG signals have been traditionally processed using LTI techniques for simplicity in computing. However, making this strong assumption leads to information loss and spurious results. Considering the current advances in silicon technology and increasing computer power, it is possible to process these biosignals with AI-based techniques correctly. This paper presents an embedded-processing-based adaptive filtering system (here termed edge AI) being an outstanding alternative in contrast to a sensor-computer- actuator system and a classical digital signal processor (DSP) device. Specifically, a PYNQ-Z1 embedded system is used. For experimental purposes, three methodologies on similar processing scenarios are compared. The results show that the edge AI methodology is superior to benchmark approaches by reducing the processing time compared to classical DSPs and general standards while maintaining the signal integrity and processing it, considering that the EMG system is not LTI. Likewise, due to the nature of the proposed architecture, handling information exhibits no leakages. Findings suggest that edge computing is suitable for EMG signal processing when an on-device analysis is required. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-24T12:32:00Z No. of bitstreams: 1 ijimai_7_5_5.pdf: 2505299 bytes, checksum: a1cd541c74e13838cb329bb21f83d7ee (MD5); Made available in DSpace on 2022-10-24T12:32:00Z (GMT). No. of bitstreams: 1 ijimai_7_5_5.pdf: 2505299 bytes, checksum: a1cd541c74e13838cb329bb21f83d7ee (MD5) https://reunir.unir.net/handle/123456789/13713 https://reunir.unir.net/handle/123456789/13712 ED-Dehaze Net: Encoder and Decoder Dehaze Network Zhang, Hongqi; Wei, Yixiong; Zhou, Hongqiao; Wu, Qianhao The presence of haze will significantly reduce the quality of images, such as resulting in lower contrast and blurry details. This paper proposes a novel end-to-end dehazing method, called Encoder and Decoder Dehaze Network (ED-Dehaze Net), which contains a Generator and a Discriminator. In particular, the Generator uses an Encoder-Decoder structure to effectively extract the texture and semantic features of hazy images. Between the Encoder and Decoder we use Multi-Scale Convolution Block (MSCB) to enhance the process of feature extraction. The proposed ED-Dehaze Net is trained by combining Adversarial Loss, Perceptual Loss and Smooth L1 Loss. Quantitative and qualitative experimental results showed that our method can obtain the state-of-the-art dehazing performance. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-24T12:19:23Z No. of bitstreams: 1 ijimai_7_5_11.pdf: 1073103 bytes, checksum: d17c5e128ba713f448c3f5ce626236bb (MD5); Made available in DSpace on 2022-10-24T12:19:23Z (GMT). No. of bitstreams: 1 ijimai_7_5_11.pdf: 1073103 bytes, checksum: d17c5e128ba713f448c3f5ce626236bb (MD5) https://reunir.unir.net/handle/123456789/13712 https://reunir.unir.net/handle/123456789/13711 Interactive Causal Correlation Space Reshape for Multi-Label Classification Zhang, Chao; Cheng, Yusheng; Wang, Yibin; Xu, Yuting Most existing multi-label classification models focus on distance metrics and feature spare strategies to extract specific features of labels. Those models use the cosine similarity to construct the label correlation matrix to constraint solution space, and then mine the latent semantic information of the label space. However, the label correlation matrix is usually directly added to the model, which ignores the interactive causality of the correlation between the labels. Considering the label-specific features based on the distance method merely may have the problem of distance measurement failure in the high-dimensional space, while based on the sparse weight matrix method may cause the problem that parameter is dependent on manual selection. Eventually, this leads to poor classifier performance. In addition, it is considered that logical labels cannot describe the importance of different labels and cannot fully express semantic information. Based on these, we propose an Interactive Causal Correlation Space Reshape for Multi-Label Classification (CCSRMC) algorithm. Firstly, the algorithm constructs the label propagation matrix using characteristic that similar instances can be linearly represented by each other. Secondly, label co-occurrence matrix is constructed by combining the conditional probability test method, which is based on the label propagation reshaping the label space to rich label semantics. Then the label co-occurrence matrix combines with the label correlation matrix to construct the label interactive causal correlation matrix to perform multi-label classification learning on the obtained numerical label matrix. Finally, the algorithm in this paper is compared with multiple advanced algorithms on multiple benchmark multi-label datasets. The results show that considering the interactive causal label correlation can reduce the redundant information in the model and improve the performance of the multi-label classifier. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-24T12:11:48Z No. of bitstreams: 1 ijimai_7_5_13.pdf: 1807426 bytes, checksum: 96ad73357576576500aa03ce6588e770 (MD5); Made available in DSpace on 2022-10-24T12:11:48Z (GMT). No. of bitstreams: 1 ijimai_7_5_13.pdf: 1807426 bytes, checksum: 96ad73357576576500aa03ce6588e770 (MD5) https://reunir.unir.net/handle/123456789/13711 https://reunir.unir.net/handle/123456789/13710 Variational Learning for the Inverted Beta-Liouville Mixture Model and Its Application to Text Categorization Ling, Yongfa; Guan, Wenbo; Ruan, Qiang; Song, Heping; Lai, Yuping he finite invert Beta-Liouville mixture model (IBLMM) has recently gained some attention due to its positive data modeling capability. Under the conventional variational inference (VI) framework, the analytically tractable solution to the optimization of the variational posterior distribution cannot be obtained, since the variational object function involves evaluation of intractable moments. With the recently proposed extended variational inference (EVI) framework, a new function is proposed to replace the original variational object function in order to avoid intractable moment computation, so that the analytically tractable solution of the IBLMM can be derived in an effective way. The good performance of the proposed approach is demonstrated by experiments with both synthesized data and a real-world application namely text categorization. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-24T11:57:46Z No. of bitstreams: 1 ijimai_7_5_9.pdf: 1568609 bytes, checksum: dbf2880f5751c6294df6ba662961d4aa (MD5); Made available in DSpace on 2022-10-24T11:57:46Z (GMT). No. of bitstreams: 1 ijimai_7_5_9.pdf: 1568609 bytes, checksum: dbf2880f5751c6294df6ba662961d4aa (MD5) https://reunir.unir.net/handle/123456789/13710 https://reunir.unir.net/handle/123456789/13709 Design of Integrated Artificial Intelligence Techniques for Video Surveillance on IoT Enabled Wireless Multimedia Sensor Networks Mansour, Romany F.; Soto, Carlos; Soto-Díaz, Roosvel; Escorcia Gutierrez, José; Gupta, Deepak; Khanna, Ashish The recent advancements in the Internet of Things (IoT) and Wireless Multimedia Sensor Networks (WMSN) made high-speed multimedia streaming, data processing, and essential analytics processes with minimal delay. Multimedia sensors used in WMSN-based surveillance applications are beneficial helpful in attaining accurate and elaborate details. However, it has become essential to design an effective and lightweight solution for data traffic management in WMSN owing to the massive quantities of data, generated by multimedia sensors. The development of Artificial Intelligence (AI) and Machine Learning (ML) techniques can be leveraged to investigate, collect, store, and process multimedia streaming data for decision-making in real-time scenarios. In this aspect, the current study develops an Integrated AI technique for Video Surveillance in IoT-enabled WMSN, called IAIVS-WMSN. The proposed IAIVS-WMSN technique aims to design a practical scheme for object detection and data transmission in WMSN. The proposed IAIVS-WMSN approach encompasses three stages: object detection, image compression, and clustering. The Mask Regional Convolutional Neural Network (Mask RCNN) technique is primarily utilized for object detection in the target region. Besides, Neighbourhood Correlation Sequence-based Image Compression (NCSIC) technique is applied to reduce data transmission. Finally, Artificial Flora Algorithm (AFA)-based clustering technique is designed for the election of Cluster Heads (CHs) and construction clusters. The design of object detection with compression and clustering techniques for WMSN shows the novelty of the work. These three processes’ designs enable one to accomplish effective data transmission in IoT-enabled WMSN. The researchers conducted multiple simulations to highlight the supreme performance of the IAIVS-WMSN approach. The simulation outcomes inferred the enhanced performance of the IAIVS-WMSN algorithm to the existing approaches. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-24T11:47:16Z No. of bitstreams: 1 ijimai_7_5_2.pdf: 945311 bytes, checksum: 73bae6ed6679f9f2d0cda8b9026fa47d (MD5); Made available in DSpace on 2022-10-24T11:47:16Z (GMT). No. of bitstreams: 1 ijimai_7_5_2.pdf: 945311 bytes, checksum: 73bae6ed6679f9f2d0cda8b9026fa47d (MD5) https://reunir.unir.net/handle/123456789/13709 https://reunir.unir.net/handle/123456789/13708 Content-Based Hyperspectral Image Compression Using a Multi-Depth Weighted Map With Dynamic Receptive Field Convolution Pan, Shaoming; Gu, XiaoLin; Chong, Yanwen; Guo, Yuanyuan In content-based image compression, the importance map guides the bit allocation based on its ability to represent the importance of image contents. In this paper, we improve the representational power of importance map using Squeeze-and-Excitation (SE) block, and propose multi-depth structure to reconstruct non-important channel information at low bit rates. Furthermore, Dynamic Receptive Field convolution (DRFc) is introduced to improve the ability of normal convolution to extract edge information, so as to increase the weight of edge content in the importance map and improve the reconstruction quality of edge regions. Results indicate that our proposed method can extract an importance map with clear edges and fewer artifacts so as to provide obvious advantages for bit rate allocation in content-based image compression. Compared with typical compression methods, our proposed method can greatly improve the performance of Peak Signal-to-Noise Ratio (PSNR), structural similarity (SSIM) and spectral angle (SAM) on three public datasets, and can produce a much better visual result with sharp edges and fewer artifacts. As a result, our proposed method reduces the SAM by 42.8% compared to the recently SOTA method to achieve the same low bpp (0.25) on the KAIST dataset. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-24T11:13:28Z No. of bitstreams: 1 ijimai_7_5_10.pdf: 2184511 bytes, checksum: 5372b03215f7ec31be4ee91a33d8737f (MD5); Made available in DSpace on 2022-10-24T11:13:28Z (GMT). No. of bitstreams: 1 ijimai_7_5_10.pdf: 2184511 bytes, checksum: 5372b03215f7ec31be4ee91a33d8737f (MD5) https://reunir.unir.net/handle/123456789/13708 https://reunir.unir.net/handle/123456789/13682 Improvement in Quality of Service Against Doppelganger Attacks for Connected Network Choudhary, Deepak; Pahuja, Roop Because they are in a high-risk location, remote sensors are vulnerable to malicious ambushes. A doppelganger attack, in which a malicious hub impersonates a legitimate network junction and then attempts to take control of the entire network, is one of the deadliest types of ambushes. Because remote sensor networks are portable, hub doppelganger ambushes are particularly ineffective in astute wellness contexts. Keeping the framework safe from hostile hubs is critical because the information in intelligent health frameworks is so sensitive. This paper developed a new Steering Convention for Vitality Effective Systems (SC-VFS) technique for detecting doppelganger attacks in IoT-based intelligent health applications such as a green corridor for transplant pushback. This method's main advantage is that it improves vitality proficiency, a critical constraint in WSN frameworks. To emphasize the suggested scheme's execution, latency, remaining vitality, throughput, vitality effectiveness, and blunder rate are all used. To see how proper the underutilized technique is compared to the existing Half Breed Multi-Level Clustering (HMLC) computation. The suggested approach yields latency of 0.63ms and 0.6ms, respectively, when using dead hubs and keeping a strategic distance from doppelganger assault. Furthermore, during the 2500 cycles, the suggested system achieves the highest remaining vitality of 49.5J. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-20T11:18:26Z No. of bitstreams: 1 ijimai_7_5_6.pdf: 1342027 bytes, checksum: 7c92439ec000450b620e83a1e9180138 (MD5); Made available in DSpace on 2022-10-20T11:18:26Z (GMT). No. of bitstreams: 1 ijimai_7_5_6.pdf: 1342027 bytes, checksum: 7c92439ec000450b620e83a1e9180138 (MD5) https://reunir.unir.net/handle/123456789/13682 https://reunir.unir.net/handle/123456789/13681 A Security Situation Awareness Approach for IoT Software Chain Based on Markov Game Model Zhu, Xudong; Deng, Honggao Since Internet of Things (IoT) has been widely used in our daily life nowadays, it is regarded as a promising and popular application of the Internet, and has attracted more and more attention. However, IoT is also suffered by some security problems which seriously affect the implementation of IoT system. Similar to traditional software, IoT software is always threated by many vulnerabilities, thus how to evaluate the security situation of IoT software chain becomes a basic requirement. In this paper, A framework of security situation awareness for IoT software chain is proposed, which mainly includes two processes: IoT security situation classification based on support vector machine and security situation awareness based on Markov game model. The proposed method firstly constructs a classification model using support vector machine (IoT) to automatically evaluates the security situation of IoT software chain. Based on the situation classification, we further proposed to adopt Markov model to simulate and predict the next behaviors of participants that involved in IoT system. Additionally, we have designed and developed a security situation awareness system for IoT software chain, the developed system supports the detection of typical IoT vulnerabilities and inherits more than 20 vulnerability detection methods, which shows great potential in IoT system protection. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-20T11:14:03Z No. of bitstreams: 1 ijimai_7_5_7.pdf: 448210 bytes, checksum: a3a6c4eb9dbbf54f4b39f20b17f5037a (MD5); Made available in DSpace on 2022-10-20T11:14:03Z (GMT). No. of bitstreams: 1 ijimai_7_5_7.pdf: 448210 bytes, checksum: a3a6c4eb9dbbf54f4b39f20b17f5037a (MD5) https://reunir.unir.net/handle/123456789/13681 https://reunir.unir.net/handle/123456789/13680 A Diverse Domain Generative Adversarial Network for Style Transfer on Face Photographs Tahir, Rabia; Cheng, Keyang; Memon, Bilal Ahmed; Liu, Qing The applications of style transfer on real time photographs are very trending now. This is used in various applications especially in social networking sites such as SnapChat and beauty cameras. A number of style transfer algorithms have been proposed but they are computationally expensive and generate artifacts in output image. Besides, most of research work only focuses on some traditional painting style transfer on real photographs. However, our work is unique as it considers diverse style domains to be transferred on real photographs by using one model. In this paper, we propose a Diverse Domain Generative Adversarial Network (DD-GAN) which performs fast diverse domain style translation on human face images. Our work is highly efficient and focused on applying different attractive and unique painting styles to human photographs while keeping the content preserved after translation. Moreover, we adopt a new loss function in our model and use PReLU activation function which improves and fastens the training procedure and helps in achieving high accuracy rates. Our loss function helps the proposed model in achieving better reconstructed images. The proposed model also occupies less memory space during training. We use various evaluation parameters to inspect the accuracy of our model. The experimental results demonstrate the effectiveness of our method as compared to state-of-the-art results. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-20T11:09:34Z No. of bitstreams: 1 ijimai_7_5_12.pdf: 1419197 bytes, checksum: f6514d66ec1ea8bc2bb0aaa16de27c0e (MD5); Made available in DSpace on 2022-10-20T11:09:35Z (GMT). No. of bitstreams: 1 ijimai_7_5_12.pdf: 1419197 bytes, checksum: f6514d66ec1ea8bc2bb0aaa16de27c0e (MD5) https://reunir.unir.net/handle/123456789/13680 https://reunir.unir.net/handle/123456789/13677 STAIBT: Blockchain and CP-ABE Empowered Secure and Trusted Agricultural IoT Blockchain Terminal Zhang, Guofeng; Chen, Xiao; Zhang, Lei; Feng, Bin; Guo, Xuchao; Liang, Jingyun; Zhang, Yanan The integration of agricultural Internet of Things (IoT) and blockchain has become the key technology of precision agriculture. How to protect data privacy and security from data source is one of the difficult issues in agricultural IoT research. This work integrates cryptography, blockchain and Interplanetary File System (IPFS) technologies, and proposes a general IoT blockchain terminal system architecture, which strongly supports the integration of the IoT and blockchain technology. This research innovatively designed a fine-grained and flexible terminal data access control scheme based on the ciphertext-policy attribute-based encryption (CP-ABE) algorithm. Based on CP-ABE and DES algorithms, a hybrid data encryption scheme is designed to realize 1-to-N encrypted data sharing. A "horizontal + vertical" IoT data segmentation scheme under blockchain technology is proposed to realize the classified release of different types of data on the blockchain. The experimental results show that the design scheme can ensure data access control security, privacy data confidentiality, and data high-availability security. This solution significantly reduces the complexity of key management, can realize efficient sharing of encrypted data, flexibly set access control strategies, and has the ability to store large data files in the agricultural IoT. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-19T13:36:18Z No. of bitstreams: 1 ijimai_7_5_8.pdf: 1468614 bytes, checksum: f7a8958add3d998f5b782372ef4574b2 (MD5); Made available in DSpace on 2022-10-19T13:36:18Z (GMT). No. of bitstreams: 1 ijimai_7_5_8.pdf: 1468614 bytes, checksum: f7a8958add3d998f5b782372ef4574b2 (MD5) https://reunir.unir.net/handle/123456789/13677 https://reunir.unir.net/handle/123456789/13676 A Method of the Coverage Ratio of Street Trees Based on Deep Learning Han, Wen; Cao, Lei; Xu, Sheng The street trees coverage ratio provides reliable data support for urban ecological environment assessment, which plays an important part in the ecological environment index calculation. Aiming at the statistical estimation of urban street trees coverage ratio, an integrated model based on YOLOv4 and Unet network for detecting and extracting street trees from remote sensing images is proposed, and obtain the estimated street trees coverage ratio in images accurately. The experiments are carried out under self-made dataset, and the results show that the accuracy of street trees detection is 94.91%, and the street trees coverage ratio is 16.30% and 13.81% in the two experimental urban scenes. The MIoU of contour extraction is 98.25%, and the estimated coverage accuracy is improved by 6.89% and 5.79%, respectively. The result indicates that the proposed model achieves the automation of contour extraction of street trees and more accurate estimation of street trees coverage ratio. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-19T13:29:33Z No. of bitstreams: 1 ijimai_7_5_3.pdf: 1317222 bytes, checksum: c7affc1942dda0dbd6e289c687e80f75 (MD5); Made available in DSpace on 2022-10-19T13:29:33Z (GMT). No. of bitstreams: 1 ijimai_7_5_3.pdf: 1317222 bytes, checksum: c7affc1942dda0dbd6e289c687e80f75 (MD5) https://reunir.unir.net/handle/123456789/13676 https://reunir.unir.net/handle/123456789/13675 Improved GWO Algorithm for UAV Path Planning on Crop Pest Monitoring Ding, Qun; Xu, Xiaolong Agricultural information monitoring is the monitoring of the agricultural production process, and its task is to monitor the growth process of major crops systematically. When assessing the pest situation of crops in this process, the traditional satellite monitoring method has the defects of poor real-time and high operating cost, whereas the pest monitoring through Unmanned Aerial Vehicles (UAVs) effectively solves the above problems, so this method is widely used. An important key issue involved in monitoring technology is path planning. In this paper, we proposed an Improved Grey Wolf Optimization algorithm, IGWO, to realize the flight path planning of UAV in crop pest monitoring. A map environment model is simulated, and information traversal is performed, then the search of feasible paths for UAV flight is carried out by the Grey Wolf Optimization algorithm (GWO). However, the algorithm search process has the defect of falling into local optimum which leading to path planning failure. To avoid such a situation, we introduced the probabilistic leap mechanism of the Simulated Annealing algorithm (SA). Besides, the convergence factor is modified with an exponential decay mode for improving the convergence rate of the algorithm. Compared with the GWO algorithm, IGWO has the 8.3%, 16.7%, 28.6% and 39.6% lower total cost of path distance on map models with precision of 15, 20, 25 and 30 respectively, and also has better path planning results in contrast to other swarm intelligence algorithms. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-19T13:19:20Z No. of bitstreams: 1 ijimai_7_5_4.pdf: 1625214 bytes, checksum: f64c3c28f5c8645d6ca6a10ead4fcc1e (MD5); Made available in DSpace on 2022-10-19T13:19:20Z (GMT). No. of bitstreams: 1 ijimai_7_5_4.pdf: 1625214 bytes, checksum: f64c3c28f5c8645d6ca6a10ead4fcc1e (MD5) https://reunir.unir.net/handle/123456789/13675 https://reunir.unir.net/handle/123456789/13674 An EEG Signal Recognition Algorithm During Epileptic Seizure Based on Distributed Edge Computing Qiu, Shi; Cheng, Keyang; Zhou, Tao; Tahir, Rabia; Ting, Liang Epilepsy is one kind of brain diseases, and its sudden unpredictability is the main cause of disability and even death. Thus, it is of great significance to identify electroencephalogram (EEG) during the seizure quickly and accurately. With the rise of cloud computing and edge computing, the interface between local detection and cloud recognition is established, which promotes the development of portable EEG detection and diagnosis. Thus, we construct a framework for identifying EEG signals in epileptic seizure based on cloud-edge computing. The EEG signals are obtained in real time locally, and the horizontal viewable model is established at the edge to enhance the internal correlation of the signals. The Takagi-Sugeno-Kang (TSK) fuzzy system is established to analyze the epileptic signals. In the cloud, the fusion of clinical features and signal features is established to establish a deep learning framework. Through local signal acquisition, edge signal processing and cloud signal recognition, the diagnosis of epilepsy is realized, which can provide a new idea for the real-time diagnosis and feedback of EEG during epileptic seizure. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-19T13:13:42Z No. of bitstreams: 1 ijimai_7_5_1.pdf: 1175870 bytes, checksum: e40110c06e611ff697052c4273db5617 (MD5); Made available in DSpace on 2022-10-19T13:13:42Z (GMT). No. of bitstreams: 1 ijimai_7_5_1.pdf: 1175870 bytes, checksum: e40110c06e611ff697052c4273db5617 (MD5) https://reunir.unir.net/handle/123456789/13674 https://reunir.unir.net/handle/123456789/13588 Editor's Note Dey, Nilanjan The International Journal of Interactive Multimedia and Artificial Intelligence – IJIMAI (ISSN 1989-1660) provides an interdisciplinary forum in which scientists and professionals can share their research results and report new advances in Artificial Intelligence (AI) tools or tools that use AI with interactive multimedia techniques. The present volume (June 2022), consists of 20 articles of diverse applications of great impact in several fields. The issue consistently showcases the utilization of AI techniques or mathematical models with an artificial intelligence base, as a standard element. Different manuscripts on usability and satisfaction, machine learning models, genetic algorithms, computer entertainment technologies, oral pathologies, optimistic motion planning, data analysis for decision making, etc. can be found in this volume. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-10T11:52:59Z No. of bitstreams: 1 ijimai_7_4_0.pdf: 69053 bytes, checksum: a695e4b34ddc8592cf4f4ed7c4ad72c5 (MD5); Made available in DSpace on 2022-10-10T11:52:59Z (GMT). No. of bitstreams: 1 ijimai_7_4_0.pdf: 69053 bytes, checksum: a695e4b34ddc8592cf4f4ed7c4ad72c5 (MD5) https://reunir.unir.net/handle/123456789/13588 https://reunir.unir.net/handle/123456789/13587 Optimistic Motion Planning Using Recursive Sub- Sampling: A New Approach to Sampling-Based Motion Planning Kenye, Lhilo; Kala, Rahul Sampling-based motion planning in the field of robot motion planning has provided an effective approach to finding path for even high dimensional configuration space and with the motivation from the concepts of sampling based-motion planners, this paper presents a new sampling-based planning strategy called Optimistic Motion Planning using Recursive Sub-Sampling (OMPRSS), for finding a path from a source to a destination sanguinely without having to construct a roadmap or a tree. The random sample points are generated recursively and connected by straight lines. Generating sample points is limited to a range and edge connectivity is prioritized based on their distances from the line connecting through the parent samples with the intention to shorten the path. The planner is analysed and compared with some sampling strategies of probabilistic roadmap method (PRM) and the experimental results show agile planning with early convergence. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-10T11:49:55Z No. of bitstreams: 1 ijimai_7_4_8.pdf: 762337 bytes, checksum: a07f5f3fddbfa898a9ef7915ac5a0749 (MD5); Made available in DSpace on 2022-10-10T11:49:55Z (GMT). No. of bitstreams: 1 ijimai_7_4_8.pdf: 762337 bytes, checksum: a07f5f3fddbfa898a9ef7915ac5a0749 (MD5) https://reunir.unir.net/handle/123456789/13587 https://reunir.unir.net/handle/123456789/13586 ERBM-SE: Extended Restricted Boltzmann Machine for Multi-Objective Single-Channel Speech Enhancement Khattak, Muhammad Irfan; Saleem, Nasir; Nawaz, Aamir; Ahmed Almani, Aftab; Umer, Farhana; Verdú, Elena Machine learning-based supervised single-channel speech enhancement has achieved considerable research interest over conventional approaches. In this paper, an extended Restricted Boltzmann Machine (RBM) is proposed for the spectral masking-based noisy speech enhancement. In conventional RBM, the acoustic features for the speech enhancement task are layerwise extracted and the feature compression may result in loss of vital information during the network training. In order to exploit the important information in the raw data, an extended RBM is proposed for the acoustic feature representation and speech enhancement. In the proposed RBM, the acoustic features are progressively extracted by multiple-stacked RBMs during the pre-training phase. The hidden acoustic features from the previous RBM are combined with the raw input data that serve as the new inputs to the present RBM. By adding the raw data to RBMs, the layer-wise features related to the raw data are progressively extracted, that is helpful to mine valuable information in the raw data. The results using the TIMIT database showed that the proposed method successfully attenuated the noise and gained improvements in the speech quality and intelligibility. The STOI, PESQ and SDR are improved by 16.86%, 25.01% and 3.84dB over the unprocessed noisy speech. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-10T11:41:09Z No. of bitstreams: 1 ijimai_7_4_16.pdf: 1617071 bytes, checksum: 924724aff644ee8bb4ddccaf3ab83aff (MD5); Made available in DSpace on 2022-10-10T11:41:09Z (GMT). No. of bitstreams: 1 ijimai_7_4_16.pdf: 1617071 bytes, checksum: 924724aff644ee8bb4ddccaf3ab83aff (MD5) https://reunir.unir.net/handle/123456789/13586 https://reunir.unir.net/handle/123456789/13585 Predictive Model for Taking Decision to Prevent University Dropout Urbina-Nájera, Argelia B.; Méndez-Ortega, Luis A. Dropout is an educational phenomenon studied for decades due to the diversity of its causes, whose effects fall on society's development. This document presents an experimental study to obtain a predictive model that allows anticipating a university dropout. The study uses 51,497 instances with 26 attributes obtained from social sciences, administrative sciences, and engineering collected from 2010 to 2019. Artificial neural networks and decision trees were implemented as classification algorithms, and also, algorithms of attribute selection and resampling methods were used to balance the main class. The results show that the best performing model was that of Random Forest with a Matthew correlation coefficient of 87.43% against 53.39% obtained by artificial neural networks and 94.34% accuracy by Random Forest. The model has allowed predicting an approximate number of possible dropouts per period, contributing to the involved instances in preventing or reducing dropout in higher education. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-10T11:24:45Z No. of bitstreams: 1 ijimai_7_4_18.pdf: 902273 bytes, checksum: 5b285eb589a27c9f23853cd8fb2adae9 (MD5); Made available in DSpace on 2022-10-10T11:24:45Z (GMT). No. of bitstreams: 1 ijimai_7_4_18.pdf: 902273 bytes, checksum: 5b285eb589a27c9f23853cd8fb2adae9 (MD5) https://reunir.unir.net/handle/123456789/13585 https://reunir.unir.net/handle/123456789/13584 A Novel Technique to Detect and Track Multiple Objects in Dynamic Video Surveillance Systems Adimoolam, M.; Mohan, Senthilkumar; A., John; Srivastava, Gautam Video surveillance is one of the important state of the art systems to be utilized in order to monitor different areas of modern society surveillance like the general public surveillance system, city traffic monitoring system, and forest monitoring system. Hence, surveillance systems have become especially relevant in the digital era. The needs of the video surveillance systems and its video analytics have become inevitable due to an increase in crimes and unethical behavior. Thus enabling the tracking of individuals object in video surveillance is an essential part of modern society. With the advent of video surveillance, performance measures for such surveillance also need to be improved to keep up with the ever increasing crime rates. So far, many methodologies relating to video surveillance have been introduced ranging from single object detection with a single or multiple cameras to multiple object detection using single or multiple cameras. Despite this, performance benchmarks and metrics need further improvements. While mechanisms exist for single or multiple object detection and prediction on videos or images, none can meet the criteria of detection and tracking of multiple objects in static as well as dynamic environments. Thus, real-world multiple object detection and prediction systems need to be introduced that are both accurate as well as fast and can also be adopted in static and dynamic environments. This paper introduces the Densely Feature selection Convolutional neural Network – Hyper Parameter tuning (DFCNHP) and it is a hybrid protocol with faster prediction time and high accuracy levels. The proposed system has successfully tracked multiple objects from multiple channels and is a combination of dense block, feature selection, background subtraction and Bayesian methods. The results of the experiment conducted demonstrated an accuracy of 98% and 1.11 prediction time and these results have also been compared with existing methods such as Kalman Filtering (KF) and Deep Neural Network (DNN). Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-10T11:18:19Z No. of bitstreams: 1 ijimai_7_4_10.pdf: 990877 bytes, checksum: b9671b8b61f9af6d09f47c0ac796232a (MD5); Made available in DSpace on 2022-10-10T11:18:19Z (GMT). No. of bitstreams: 1 ijimai_7_4_10.pdf: 990877 bytes, checksum: b9671b8b61f9af6d09f47c0ac796232a (MD5) https://reunir.unir.net/handle/123456789/13584 https://reunir.unir.net/handle/123456789/13583 Automatic Finding Trapezoidal Membership Functions in Mining Fuzzy Association Rules Based on Learning Automata Anari, Z.; Hatamlou, A.; Anari, B. Association rule mining is an important data mining technique used for discovering relationships among all data items. Membership functions have a significant impact on the outcome of the mining association rules. An important challenge in fuzzy association rule mining is finding an appropriate membership functions, which is an optimization issue. In the most relevant studies of fuzzy association rule mining, only triangle membership functions are considered. This study, as the first attempt, used a team of continuous action-set learning automata (CALA) to find both the appropriate number and positions of trapezoidal membership functions (TMFs). The spreads and centers of the TMFs were taken into account as parameters for the research space and a new approach for the establishment of a CALA team to optimize these parameters was introduced. Additionally, to increase the convergence speed of the proposed approach and remove bad shapes of membership functions, a new heuristic approach has been proposed. Experiments on two real data sets showed that the proposed algorithm improves the efficiency of the extracted rules by finding optimized membership functions. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-10T10:55:42Z No. of bitstreams: 1 ijimai_7_4_3.pdf: 2909923 bytes, checksum: 99e7b28cabb8d299891af90b3a8ce380 (MD5); Made available in DSpace on 2022-10-10T10:55:42Z (GMT). No. of bitstreams: 1 ijimai_7_4_3.pdf: 2909923 bytes, checksum: 99e7b28cabb8d299891af90b3a8ce380 (MD5) https://reunir.unir.net/handle/123456789/13583 https://reunir.unir.net/handle/123456789/13582 Towards a Robust Thermal-Visible Heterogeneous Face Recognition Approach Based on a Cycle Generative Adversarial Network Kamel Benamara, Nadir; Zigh, Ehlem; Boudghene Stambouli, Tarik; Keche, Mokhtar Security is a sensitive area that concerns all authorities around the world due to the emerging terrorism phenomenon. Contactless biometric technologies such as face recognition have grown in interest for their capacity to identify probe subjects without any human interaction. Since traditional face recognition systems use visible spectrum sensors, their performances decrease rapidly when some visible imaging phenomena occur, mainly illumination changes. Unlike the visible spectrum, Infrared spectra are invariant to light changes, which makes them an alternative solution for face recognition. However, in infrared, the textural information is lost. We aim, in this paper, to benefit from visible and thermal spectra by proposing a new heterogeneous face recognition approach. This approach includes four scientific contributions. The first one is the annotation of a thermal face database, which has been shared via Github with all the scientific community. The second is the proposition of a multi-sensors face detector model based on the last YOLO v3 architecture, able to detect simultaneously faces captured in visible and thermal images. The third contribution takes up the challenge of modality gap reduction between visible and thermal spectra, by applying a new structure of CycleGAN, called TV-CycleGAN, which aims to synthesize visible-like face images from thermal face images. This new thermal-visible synthesis method includes all extreme poses and facial expressions in color space. To show the efficacy and the robustness of the proposed TV-CycleGAN, experiments have been applied on three challenging benchmark databases, including different real-world scenarios: TUFTS and its aligned version, NVIE and PUJ. The qualitative evaluation shows that our method generates more realistic faces. The quantitative one demonstrates that the proposed TV -CycleGAN gives the best improvement on face recognition rates. Therefore, instead of applying a direct matching from thermal to visible images which allows a recognition rate of 47,06% for TUFTS Database, a proposed TV-CycleGAN ensures accuracy of 57,56% for the same database. It contributes to a rate enhancement of 29,16%, and 15,71% for NVIE and PUJ databases, respectively. It reaches an accuracy enhancement of 18,5% for the aligned TUFTS database. It also outperforms some recent state of the art methods in terms of F1-Score, AUC/EER and other evaluation metrics. Furthermore, it should be mentioned that the obtained visible synthesized face images using TV-CycleGAN method are very promising for thermal facial landmark detection as a fourth contribution of this paper. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-10T10:48:59Z No. of bitstreams: 1 ijimai_7_4_12.pdf: 2334388 bytes, checksum: 8b23aedc9101f894bb60fa7392804bbd (MD5); Made available in DSpace on 2022-10-10T10:48:59Z (GMT). No. of bitstreams: 1 ijimai_7_4_12.pdf: 2334388 bytes, checksum: 8b23aedc9101f894bb60fa7392804bbd (MD5) https://reunir.unir.net/handle/123456789/13582 https://reunir.unir.net/handle/123456789/13581 Social Relations and Methods in Recommender Systems: A Systematic Review Medel, Diego; González-González, Carina; V. Aciar, Silvana With the constant growth of information, data sparsity problems, and cold start have become a complex problem in obtaining accurate recommendations. Currently, authors consider the user's historical behavior and find contextual information about the user, such as social relationships, time information, and location. In this work, a systematic review of the literature on recommender systems that use the information on social relationships between users was carried out. As the main findings, social relations were classified into three groups: trust, friend activities, and user interactions. Likewise, the collaborative filtering approach was the most used, and with the best results, considering the methods based on memory and model. The most used metrics that we found, and the recommendation methods studied in mobile applications are presented. The information provided by this study can be valuable to increase the precision of the recommendations. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-10T10:34:17Z No. of bitstreams: 1 ijimai_7_4_1.pdf: 420403 bytes, checksum: 2eb5843e3904855c004b7899a5fde684 (MD5); Made available in DSpace on 2022-10-10T10:34:17Z (GMT). No. of bitstreams: 1 ijimai_7_4_1.pdf: 420403 bytes, checksum: 2eb5843e3904855c004b7899a5fde684 (MD5) https://reunir.unir.net/handle/123456789/13581 https://reunir.unir.net/handle/123456789/13580 Towards the Grade’s Prediction. A Study of Different Machine Learning Approaches to Predict Grades from Student Interaction Data Alonso-Misol Gerlache, Héctor; Moreno-Ger, Pablo; de-la-Fuente-Valentín, Luis There is currently an open problem within the field of Artificial Intelligence applied to the educational field, which is the prediction of students’ grades. This problem aims to predict early school failure and dropout, and to determine the well-founded analysis of student performance for the improvement of educational quality. This document deals the problem of predicting grades of UNIR university master’s degree students in the on-line mode, proposing a working model and comparing different technologies to determine which one fits best with the available data set. In order to make the predictions, the dataset was submitted to a cleaning and analysis phases, being prepared for the use of Machine Learning algorithms, such as Naive Bayes, Decision Tree, Random Forest and Neural Networks. A comparison is made that addresses a double prediction on a homogeneous set of input data, predicting the final grade per subject and the final master’s degree grade. The results were obtained demonstrate that the use of these techniques makes possible the grade predictions. The data gives some figures in which we can see how Artificial Intelligence is able to predict situations with an accuracy above 96%. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-10T10:27:59Z No. of bitstreams: 1 ijimai_7_4_17.pdf: 951607 bytes, checksum: 7f940735fa1bb87d7f4622b3cc05daae (MD5); Made available in DSpace on 2022-10-10T10:27:59Z (GMT). No. of bitstreams: 1 ijimai_7_4_17.pdf: 951607 bytes, checksum: 7f940735fa1bb87d7f4622b3cc05daae (MD5) https://reunir.unir.net/handle/123456789/13580 https://reunir.unir.net/handle/123456789/13579 LIPSNN: A Light Intrusion-Proving Siamese Neural Network Model for Facial Verification Alcaide, Asier; Patricio, Miguel A.; Berlanga, Antonio; Arroyo, Angel; Cuadrado Gallego, Juan J. Facial verification has experienced a breakthrough in recent years, not only due to the improvement in accuracy of the verification systems but also because of their increased use. One of the main reasons for this has been the appearance and use of new models of Deep Learning to address this problem. This extension in the use of facial verification has had a high impact due to the importance of its applications, especially on security, but the extension of its use could be significantly higher if the problem of the required complex calculations needed by the Deep Learning models, that usually need to be executed on machines with specialised hardware, were solved. That would allow the use of facial verification to be extended, making it possible to run this software on computers with low computing resources, such as Smartphones or tablets. To solve this problem, this paper presents the proposal of a new neural model, called Light Intrusion-Proving Siamese Neural Network, LIPSNN. This new light model, which is based on Siamese Neural Networks, is fully presented from the description of its two block architecture, going through its development, including its training with the well- known dataset Labeled Faces in the Wild, LFW; to its benchmarking with other traditional and deep learning models for facial verification in order to compare its performance for its use in low computing resources systems for facial recognition. For this comparison the attribute parameters, storage, accuracy and precision have been used, and from the results obtained it can be concluded that the LIPSNN can be an alternative to the existing models to solve the facet problem of running facial verification in low computing resource devices. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-10T10:21:24Z No. of bitstreams: 1 ijimai_7_4_11.pdf: 666771 bytes, checksum: 2b1ac5da5fc7c530be14580f1b8cf2a2 (MD5); Made available in DSpace on 2022-10-10T10:21:24Z (GMT). No. of bitstreams: 1 ijimai_7_4_11.pdf: 666771 bytes, checksum: 2b1ac5da5fc7c530be14580f1b8cf2a2 (MD5) https://reunir.unir.net/handle/123456789/13579 https://reunir.unir.net/handle/123456789/13570 Multimodal Human Eye Blink Recognition Using Z-score Based Thresholding and Weighted Features Singh Lamba, Puneet; Virmani, Deepali; Pillai, Manu S.; Chaudhary, Gopal A novel real-time multimodal eye blink detection method using an amalgam of five unique weighted features extracted from the circle boundary formed from the eye landmarks is proposed. The five features, namely (Vertical Head Positioning, Orientation Factor, Proportional Ratio, Area of Intersection, and Upper Eyelid Radius), provide imperative gen (z score threshold) accurately predicting the eye status and thus the blinking status. An accurate and precise algorithm employing the five weighted features is proposed to predict eye status (open/close). One state-of-the-art dataset ZJU (eye-blink), is used to measure the performance of the method. Precision, recall, F1-score, and ROC curve measure the proposed method performance qualitatively and quantitatively. Increased accuracy (of around 97.2%) and precision (97.4%) are obtained compared to other existing unimodal approaches. The efficiency of the proposed method is shown to outperform the state-of-the-art methods. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-07T09:48:08Z No. of bitstreams: 1 ijimai_7_4_9.pdf: 1644982 bytes, checksum: aa8f04a311082d578e06a4b2e090bb6f (MD5); Made available in DSpace on 2022-10-07T09:48:08Z (GMT). No. of bitstreams: 1 ijimai_7_4_9.pdf: 1644982 bytes, checksum: aa8f04a311082d578e06a4b2e090bb6f (MD5) https://reunir.unir.net/handle/123456789/13570 https://reunir.unir.net/handle/123456789/13569 Obtaining Anti-Missile Decoy Launch Solution from a Ship Using Machine Learning Techniques Touza, Ramón; Martínez Torres, Javier; Álvarez, María; Roca, Javier One of the most dangerous situations a warship may face is a missile attack launched from other ships, aircrafts, submarines or land. In addition, given the current scenario, it is not ruled out that a terrorist group may acquire missiles and use them against ships operating close to the coast, which increases their vulnerabilitydue to the limited reaction time. One of the means the ship has for its defense are decoys, designed to deceive the enemy missile. However, for their use to be effective it is necessary to obtain, in a quick way, a valid launching solution. The purpose of this article is to design a methodology to solve the problem of decoy launching and to provide the ship immediately with the necessary data to make the firing decision. To solve the problem machine learning models (neural networks and support vector machines) and a set of training data obtained in simulations will be used. The performance measures obtained with the implementation of multilayer perceptron models allow the replacement of the current procedures based on tables and launching rules with machine learning algorithms that are more flexible and adaptable to a larger number of scenarios. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-07T09:37:22Z No. of bitstreams: 1 ijimai_7_4_14.pdf: 1088848 bytes, checksum: 5bcc4cde49dc064dda3c1146ecf9f6e4 (MD5); Made available in DSpace on 2022-10-07T09:37:22Z (GMT). No. of bitstreams: 1 ijimai_7_4_14.pdf: 1088848 bytes, checksum: 5bcc4cde49dc064dda3c1146ecf9f6e4 (MD5) https://reunir.unir.net/handle/123456789/13569 https://reunir.unir.net/handle/123456789/13568 Automatic Classification of Oral Pathologies Using Orthopantomogram Radiography Images Based on Convolutional Neural Network Laishram, Anuradha; Thongam, Khelchandra An attempt has been made to device a robust method to classify different oral pathologies using Orthopantomogram (OPG) images based on Convolutional Neural Network (CNN). This system will provide a novel approach for the classification of types of teeth (viz., incisors and molar teeth) and also some underlying oral anomalies such as fixed partial denture (cap) and impacted teeth. To this end, various image preprocessing techniques are performed. The input OPG images are resized, pixels are scaled and erroneous data are excluded. The proposed algorithm is implemented using CNN with Dropout and the fully connected layer has been trained using hybrid GA-BP learning. Using the Dropout regularization technique, over fitting has been avoided and thereby making the network to correctly classify the objects. The CNN has been implemented with different convolutional layers and the highest accuracy of 97.92% has been obtained with two convolutional layers. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-07T09:29:14Z No. of bitstreams: 1 ijimai_7_4_6.pdf: 928867 bytes, checksum: c993b0942ed94e191524a4b12964d850 (MD5); Made available in DSpace on 2022-10-07T09:29:14Z (GMT). No. of bitstreams: 1 ijimai_7_4_6.pdf: 928867 bytes, checksum: c993b0942ed94e191524a4b12964d850 (MD5) https://reunir.unir.net/handle/123456789/13568 https://reunir.unir.net/handle/123456789/13567 Improving Pipelining Tools for Pre-processing Data Novo-Lourés, María; Lage, Yeray; Pavón, Reyes; Laza, Rosalía; Ruano-Ordás, David; Méndez, José Ramón The last several years have seen the emergence of data mining and its transformation into a powerful tool that adds value to business and research. Data mining makes it possible to explore and find unseen connections between variables and facts observed in different domains, helping us to better understand reality. The programming methods and frameworks used to analyse data have evolved over time. Currently, the use of pipelining schemes is the most reliable way of analysing data and due to this, several important companies are currently offering this kind of services. Moreover, several frameworks compatible with different programming languages are available for the development of computational pipelines and many research studies have addressed the optimization of data processing speed. However, as this study shows, the presence of early error detection techniques and developer support mechanisms is very limited in these frameworks. In this context, this study introduces different improvements, such as the design of different types of constraints for the early detection of errors, the creation of functions to facilitate debugging of concrete tasks included in a pipeline, the invalidation of erroneous instances and/or the introduction of the burst-processing scheme. Adding these functionalities, we developed Big Data Pipelining for Java (BDP4J, https://github.com/sing-group/bdp4j), a fully functional new pipelining framework that shows the potential of these features. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-07T08:59:09Z No. of bitstreams: 1 ijimai_7_4_19.pdf: 796775 bytes, checksum: 2f9a55a24d7cdaefca917b6c0cd3a578 (MD5); Made available in DSpace on 2022-10-07T08:59:09Z (GMT). No. of bitstreams: 1 ijimai_7_4_19.pdf: 796775 bytes, checksum: 2f9a55a24d7cdaefca917b6c0cd3a578 (MD5) https://reunir.unir.net/handle/123456789/13567 https://reunir.unir.net/handle/123456789/13566 MDFRCNN: Malware Detection using Faster Region Proposals Convolution Neural Network Deore, Mahendra; Kulkarni, Uday Technological advancement of smart devices has opened up a new trend: Internet of Everything (IoE), where all devices are connected to the web. Large scale networking benefits the community by increasing connectivity and giving control of physical devices. On the other hand, there exists an increased ‘Threat’ of an ‘Attack’. Attackers are targeting these devices, as it may provide an easier ‘backdoor entry to the users’ network’.MALicious softWARE (MalWare) is a major threat to user security. Fast and accurate detection of malware attacks are the sine qua non of IoE, where large scale networking is involved. The paper proposes use of a visualization technique where the disassembled malware code is converted into gray images, as well as use of Image Similarity based Statistical Parameters (ISSP) such as Normalized Cross correlation (NCC), Average difference (AD), Maximum difference (MaxD), Singular Structural Similarity Index Module (SSIM), Laplacian Mean Square Error (LMSE), MSE and PSNR. A vector consisting of gray image with statistical parameters is trained using a Faster Region proposals Convolution Neural Network (F-RCNN) classifier. The experiment results are promising as the proposed method includes ISSP with F-RCNN training. Overall training time of learning the semantics of higher-level malicious behaviors is less. Identification of malware (testing phase) is also performed in less time. The fusion of image and statistical parameter enhances system performance with greater accuracy. The benchmark database from Microsoft Malware Classification challenge has been used to analyze system performance, which is available on the Kaggle website. An overall average classification accuracy of 98.12% is achieved by the proposed method. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-07T08:51:31Z No. of bitstreams: 1 ijimai_7_4_13.pdf: 2185179 bytes, checksum: 7e73cb85b1421ad1e8b871a6a5ffd9e9 (MD5); Made available in DSpace on 2022-10-07T08:51:31Z (GMT). No. of bitstreams: 1 ijimai_7_4_13.pdf: 2185179 bytes, checksum: 7e73cb85b1421ad1e8b871a6a5ffd9e9 (MD5) https://reunir.unir.net/handle/123456789/13566 https://reunir.unir.net/handle/123456789/13565 CDPS-IoT: Cardiovascular Disease Prediction System Based on IoT using Machine Learning Ahamed, Jameel; Manan Koli, Abdul; Ahmad, Khaleel; Alam Jamal, Mohd.; Gupta, B. B. Internet of Things, Machine learning, and Cloud computing are the emerging domains of information communication and technology. These techniques can help to save the life of millions in the medical assisted environment and can be utilized in health-care system where health expertise is less available. Fast food consumption increased from the past few decades, which makes up cholesterol, diabetes, and many more problems that affect the heart and other organs of the body. Changing lifestyle is another parameter that results in health issues including cardio-vascular diseases. Affirming to the World Health Organization, the cardiovascular diseases, or heart diseases lead to more death than any other disease globally. The objective of this research is to analyze the available data pertaining to cardiovascular diseases for prediction of heart diseases at an earlier stage to prevent it from occurring. The dataset of heart disease patients was taken from Jammu and Kashmir, India and stored over the cloud. Stored data is then pre-processed and further analyzed using machine learning techniques for the prediction of heart diseases. The analysis of the dataset using numerous machines learning techniques like Random Forest, Decision Tree, Naive based, K-nearest neighbors, and Support Vector Machine revealed the performance metrics (F1 Score, Precision and Recall) for all the techniques which shows that Naive Bayes is better without parameter tuning while Random Forest algorithm proved as the best technique with hyperparameter tuning. In this paper, the proposed model is developed in such a systematic way that the clinical data can be obtained through the use of IoT with the help of available medical sensors to predict cardiovascular diseases on a real-time basis. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-07T08:26:31Z No. of bitstreams: 1 ijimai_7_4_7.pdf: 503531 bytes, checksum: 7e4b62c1a9e3651de585e8e4a5703f64 (MD5); Made available in DSpace on 2022-10-07T08:26:31Z (GMT). No. of bitstreams: 1 ijimai_7_4_7.pdf: 503531 bytes, checksum: 7e4b62c1a9e3651de585e8e4a5703f64 (MD5) https://reunir.unir.net/handle/123456789/13565 https://reunir.unir.net/handle/123456789/13564 Neural Collaborative Filtering Classification Model to Obtain Prediction Reliabilities Bobadilla, Jesús; Gutiérrez, Abraham; Alonso, Santiago; González-Prieto, Ángel Neural collaborative filtering is the state of art field in the recommender systems area; it provides some models that obtain accurate predictions and recommendations. These models are regression-based, and they just return rating predictions. This paper proposes the use of a classification-based approach, returning both rating predictions and their reliabilities. The extra information (prediction reliabilities) can be used in a variety of relevant collaborative filtering areas such as detection of shilling attacks, recommendations explanation or navigational tools to show users and items dependences. Additionally, recommendation reliabilities can be gracefully provided to users: “probably you will like this film”, “almost certainly you will like this song”, etc. This paper provides the proposed neural architecture; it also tests that the quality of its recommendation results is as good as the state of art baselines. Remarkably, individual rating predictions are improved by using the proposed architecture compared to baselines. Experiments have been performed making use of four popular public datasets, showing generalizable quality results. Overall, the proposed architecture improves individual rating predictions quality, maintains recommendation results and opens the doors to a set of relevant collaborative filtering fields. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-07T08:19:01Z No. of bitstreams: 1 ijimai_7_4_2.pdf: 812772 bytes, checksum: 1d0ba7a63f430bcaefa94dd684e0e3d7 (MD5); Made available in DSpace on 2022-10-07T08:19:01Z (GMT). No. of bitstreams: 1 ijimai_7_4_2.pdf: 812772 bytes, checksum: 1d0ba7a63f430bcaefa94dd684e0e3d7 (MD5) https://reunir.unir.net/handle/123456789/13564 https://reunir.unir.net/handle/123456789/13563 Research on the Application of Computer Graphic Advertisement Design Based on a Genetic Algorithm and TRIZ Theory Song, Yang In view of the shortcomings of the traditional thinking of computer graphic advertising design, this paper introduces TRIZ innovative thinking to design computer advertising. First of all, combined with specific cases of computer creative print advertising, this paper analyzes the creative methods of stimulating divergent thinking, aggregation thinking and transformation thinking from the innovation principle of TRIZ theory as the origin, and applies them to the creative mechanism and application program of print advertising creativity. The whole process is led by rational principles of perceptual thinking, driven by specific principles of abstract imagination, to explore the thinking source of creative design essence of print advertising. The theory and its application mechanism become a new thinking method and application attempt in the creative field of print advertisement. Then, based on the TRIZ innovation theory, the business model of advertising content arrangement is constructed, and the mathematical model is constructed according to the planning business media resource planning on the business model to realize the multi-objective optimization of efficient use of orders and precise delivery of time. Finally, a multi-objective optimization mathematical model of parallel genetic algorithm is designed to solve the advertisement content arrangement. The innovative thinking of TRIZ and the application of genetic algorithm in content arrangement of computer graphic advertisement design are verified by experiments. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-07T08:08:16Z No. of bitstreams: 1 ijimai_7_4_4.pdf: 668673 bytes, checksum: 98d196361d54488f275d18da8a88f9a8 (MD5); Made available in DSpace on 2022-10-07T08:08:16Z (GMT). No. of bitstreams: 1 ijimai_7_4_4.pdf: 668673 bytes, checksum: 98d196361d54488f275d18da8a88f9a8 (MD5) https://reunir.unir.net/handle/123456789/13563 https://reunir.unir.net/handle/123456789/13562 CompareML: A Novel Approach to Supporting Preliminary Data Analysis Decision Making Fernández-García, Antonio Jesús; Preciado, Juan Carlos; Prieto, Álvaro E.; Sánchez-Figueroa, Fernando; Gutiérrez, Juan D. There are a large number of machine learning algorithms as well as a wide range of libraries and services that allow one to create predictive models. With machine learning and artificial intelligence playing a major role in dealing with engineering problems, practising engineers often come to the machine learning field so overwhelmed with the multitude of possibilities that they find themselves needing to address difficulties before actually starting on carrying out any work. Datasets have intrinsic properties that make it hard to select the algorithm that is best suited to some specific objective, and the ever-increasing number of providers together make this selection even harder. These were the reasons underlying the design of CompareML, an approach to supporting the evaluation and comparison of machine learning libraries and services without deep machine learning knowledge. CompareML makes it easy to compare the performance of different models by using well-known classification and regression algorithms already made available by some of the most widely used providers. It facilitates the practical application of methods and techniques of artificial intelligence that let a practising engineer decide whether they might be used to resolve hitherto intractable problems. Thus, researchers and engineering practitioners can uncover the potential of their datasets for the inference of new knowledge by selecting the most appropriate machine learning algorithm and determining the provider best suited to their data. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-07T08:02:37Z No. of bitstreams: 1 ijimai_7_4_20.pdf: 1548182 bytes, checksum: 3c51065ee7e9093b4a0eeba4466c21da (MD5); Made available in DSpace on 2022-10-07T08:02:37Z (GMT). No. of bitstreams: 1 ijimai_7_4_20.pdf: 1548182 bytes, checksum: 3c51065ee7e9093b4a0eeba4466c21da (MD5) https://reunir.unir.net/handle/123456789/13562 https://reunir.unir.net/handle/123456789/13561 Computer Entertainment Technologies for the Visually Impaired: An Overview López Ibáñez, Manuel; Romero-Hernández, Alejandro; Manero, Borja; Guijarro, María Over the last years, works related to accessible technologies have increased both in number and in quality. This work presents a series of articles which explore different trends in the field of accessible video games for the blind or visually impaired. Reviewed articles are distributed in four categories covering the following subjects: (1) video game design and architecture, (2) video game adaptations, (3) accessible games as learning tools or treatments and (4) navigation and interaction in virtual environments. Current trends in accessible game design are also analysed, and data is presented regarding keyword use and thematic evolution over time. As a conclusion, a relative stagnation in the field of human-computer interaction for the blind is detected. However, as the video game industry is becoming increasingly interested in accessibility, new research opportunities are starting to appear. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-07T07:48:35Z No. of bitstreams: 1 ijimai_7_4_5.pdf: 611853 bytes, checksum: de5b9d70e405c0656b23bed7fe0e6913 (MD5); Made available in DSpace on 2022-10-07T07:48:35Z (GMT). No. of bitstreams: 1 ijimai_7_4_5.pdf: 611853 bytes, checksum: de5b9d70e405c0656b23bed7fe0e6913 (MD5) https://reunir.unir.net/handle/123456789/13561 https://reunir.unir.net/handle/123456789/13560 Writing Order Recovery in Complex and Long Static Handwriting Diaz, Moises; Crispo, Gioele; Parziale, Antonio; Marcelli, Angelo; Ferrer, Miguel A. The order in which the trajectory is executed is a powerful source of information for recognizers. However, there is still no general approach for recovering the trajectory of complex and long handwriting from static images. Complex specimens can result in multiple pen-downs and in a high number of trajectory crossings yielding agglomerations of pixels (also known as clusters). While the scientific literature describes a wide range of approaches for recovering the writing order in handwriting, these approaches nevertheless lack a common evaluation metric. In this paper, we introduce a new system to estimate the order recovery of thinned static trajectories, which allows to effectively resolve the clusters and select the order of the executed pendowns. We evaluate how knowing the starting points of the pen-downs affects the quality of the recovered writing. Once the stability and sensitivity of the system is analyzed, we describe a series of experiments with three publicly available databases, showing competitive results in all cases. We expect the proposed system, whose code is made publicly available to the research community, to reduce potential confusion when the order of complex trajectories are recovered, and this will in turn make the trajectories recovered to be viable for further applications, such as velocity estimation. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-10-07T07:33:24Z No. of bitstreams: 1 ijimai_7_4_15.pdf: 1326471 bytes, checksum: f521c2d83796761e8152f7b955502258 (MD5); Made available in DSpace on 2022-10-07T07:33:24Z (GMT). No. of bitstreams: 1 ijimai_7_4_15.pdf: 1326471 bytes, checksum: f521c2d83796761e8152f7b955502258 (MD5) https://reunir.unir.net/handle/123456789/13560 https://reunir.unir.net/handle/123456789/13151 Research Collaboration Influence Analysis Using Dynamic Co-authorship and Citation Networks Razzaq, Sidra; Kamran Malik, Ahmad; Raza, Basit; Ali Khattak, Hasan; Moscoso Zegarra, Giomar W.; Díaz Zelada, Yvan Collaborative research is increasing in terms of publications, skills, and formal interactions, which certainly makes it the hotspot in both academia and the industrial sector. Knowing the factors and behavior of dynamic collaboration network provides insights that helps in improving the researcher’s profile and coordinator’s productivity of research. Despite rapid developments in the research collaboration process with various outcomes, its validity is still difficult to address. Existing approaches have used bibliometric network analysis with different aspects to understand collaboration patterns that measure the quality of their corresponding relationships. At this point in time, we would like to investigate an efficient method to outline the credibility of findings in publication—author relations. In this research, we propose a new collaboration method to analyze the structure of research articles using four types of graphs for discerning authors’ influence. We apply different combinations of network relationships and bibliometric analysis on the G-index parameter to disclose their interrelated differences. Our model is designed to find the dynamic indicators of co-authored collaboration with an influence on the author’s behavior in terms of change in research area/interest. In the research we investigate the dynamic relations in an academic field using metadata of openly available articles and collaborating international authors in interrelated areas/domains. Based on filtered evidence of relationship networks and their statistical results, the research shows an increment in productivity and better influence over time. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-23T08:56:54Z No. of bitstreams: 1 ijimai7_3_10_0.pdf: 1917831 bytes, checksum: 18756ee4e984bc423bb9c79843b0ee00 (MD5); Made available in DSpace on 2022-05-23T08:56:54Z (GMT). No. of bitstreams: 1 ijimai7_3_10_0.pdf: 1917831 bytes, checksum: 18756ee4e984bc423bb9c79843b0ee00 (MD5) https://reunir.unir.net/handle/123456789/13151 https://reunir.unir.net/handle/123456789/13150 Machine Learning in Business Intelligence 4.0: Cost Control in a Destination Hotel Sánchez-Torres, Fulgencio; González, Iván; Dobrescu, Cosmin C. Cost control is a recurring problem in companies where studies have provided different solutions. The main objective of this research is to propose and validate an alternative to cost control using data science to support decision-making using the business intelligence 4.0 paradigm. The work uses Machine Learning (ML) to support decision-making in company cost-control management. Specifically, we used the ability of hierarchical agglomerative clustering (HAC) algorithms to generate clusters and suggest possible candidate products that could be substituted for other, more cost-effective ones. These candidate products were analyzed by a panel of company experts, facilitating decisions based on business costs. We needed to analyze and modify the company's ecosystem and its associated variables to obtain an adequate data warehouse during the study, which was developed over three years and validated HAC as a support to decision-making in cost control. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-23T08:50:20Z No. of bitstreams: 1 ijimai7_3_8_0.pdf: 662619 bytes, checksum: e14c1821a0007cbf28e6fe80ba05e3d4 (MD5); Made available in DSpace on 2022-05-23T08:50:20Z (GMT). No. of bitstreams: 1 ijimai7_3_8_0.pdf: 662619 bytes, checksum: e14c1821a0007cbf28e6fe80ba05e3d4 (MD5) https://reunir.unir.net/handle/123456789/13150 https://reunir.unir.net/handle/123456789/13149 Editor's Note Golpe, Antonio A.; Isasi, Pedro; Martín-Álvarez, Juan Manuel; Quintana, David Machine learning (ML) is generating new opportunities for innovative research in areas apparently unrelated such as, economics, business or/and finance. Specifically, it has also been widely used in applications related to the economic and financial analysis, such as economic recessions prediction, labor market trends, risk management, prices analysis among others. However, it is important to note the differences between classical statistics/econometrics and machine learning. On the one hand, econometrics set out to build models designed to describe economic problems, while machine learning uses algorithms, generally for prediction, classification, and also, can manage a large amount of structured and unstructured data and make fast decisions or forecasts. As S. Athey points out, perhaps “a key advantage of ML is that it frames empirical analysis in terms of algorithms that estimate and compare many alternative models. This approach contrasts with econometrics, where (in principle, though rarely in reality) the researcher picks a model based on principles and estimates it once”. This Special Issue presents nine contributions that illustrate both approaches in the domain of economics, finance and business. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-23T08:12:34Z No. of bitstreams: 1 ijimai7_3_0.pdf: 58542 bytes, checksum: 521ed0728cdb1a2bd1e04486981d07b4 (MD5); Made available in DSpace on 2022-05-23T08:12:34Z (GMT). No. of bitstreams: 1 ijimai7_3_0.pdf: 58542 bytes, checksum: 521ed0728cdb1a2bd1e04486981d07b4 (MD5) https://reunir.unir.net/handle/123456789/13149 https://reunir.unir.net/handle/123456789/13148 Foreword Velarde Molina, Jehovanni Fabricio This time, in the Special Issue on Artificial Intelligence in Economics, Finance and Business, we present a series of publications focused on artificial intelligence and finance. This compilation of research will bring new information to researchers in different disciplines, and at the same time, it will be an ideal space to present studies that have an international scope. UNIR, dedicated to the training of professionals in different academic programs, through its journal is consolidating a culture of research and expanding the knowledge that contributes to an excellent education. For this reason, we consider the dissemination of scientific articles essential, since this guarantees the transfer of results, in addition to the conclusions of high-impact research. Currently the world is going through a complicated scenario, a fluctuating economy and problems in health services that require immediate attention; in this sense, science and knowledge management open space to opportunities in search of medium and long-term solutions. It is a great honor to present this issue of the International Journal of Interactive Multimedia and Artificial Intelligence, whose contribution to the knowledge society is invaluable. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-23T07:57:14Z No. of bitstreams: 1 ijimai7_3_00.pdf: 59365 bytes, checksum: 8d7e35f96ee9570c6b66e9776f9b0049 (MD5); Made available in DSpace on 2022-05-23T07:57:14Z (GMT). No. of bitstreams: 1 ijimai7_3_00.pdf: 59365 bytes, checksum: 8d7e35f96ee9570c6b66e9776f9b0049 (MD5) https://reunir.unir.net/handle/123456789/13148 https://reunir.unir.net/handle/123456789/13147 Finite Sample Properties of Parameterized Expectations Algorithm Solutions; Is the Length So Determinant? Sánchez-Fuentes, A. Jesús The solution of the Parameterized Expectations Algorithm (PEA) is well defined based on asymptotic properties. In practice, it depends on the specific replication of the exogenous shock(s) used for the resolution process. Typically, this problem is reduced when a sufficiently long replication is considered. In this paper, we suggest an alternative approach which consists of using several, shorter replications. A centrality measure (the median) is used then to discriminate among the different solutions using two different criteria, which differ in the information used. On the one hand, the distance to the vector composed by median values of PEA coefficients is minimized. On the other hand, distances to the median impulse response is minimized. Finally, we explore the impact of considering alternative approaches in an empirical illustration. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-23T07:53:55Z No. of bitstreams: 1 ijimai7_3_3.pdf: 1717721 bytes, checksum: 24b382e746f4eb2114f3cea8942e70e7 (MD5); Made available in DSpace on 2022-05-23T07:53:55Z (GMT). No. of bitstreams: 1 ijimai7_3_3.pdf: 1717721 bytes, checksum: 24b382e746f4eb2114f3cea8942e70e7 (MD5) https://reunir.unir.net/handle/123456789/13147 https://reunir.unir.net/handle/123456789/13140 The Yield Curve as a Recession Leading Indicator. An Application for Gradient Boosting and Random Forest Cadahia Delgado, Pedro; Congregado, Emilio; Golpe, Antonio A.; Vides, José Carlos Most representative decision-tree ensemble methods have been used to examine the variable importance of Treasury term spreads to predict US economic recessions with a balance of generating rules for US economic recession detection. A strategy is proposed for training the classifiers with Treasury term spreads data and the results are compared in order to select the best model for interpretability. We also discuss the use of SHapley Additive exPlanations (SHAP) framework to understand US recession forecasts by analyzing feature importance. Consistently with the existing literature we find the most relevant Treasury term spreads for predicting US economic recession and a methodology for detecting relevant rules for economic recession detection. In this case, the most relevant term spread found is 3-month–6-month, which is proposed to be monitored by economic authorities. Finally, the methodology detected rules with high lift on predicting economic recession that can be used by these entities for this propose. This latter result stands in contrast to a growing body of literature demonstrating that machine learning methods are useful for interpretation comparing many alternative algorithms and we discuss the interpretation for our result and propose further research lines aligned with this work. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-20T10:35:56Z No. of bitstreams: 1 ijimai7_3_1.pdf: 1003194 bytes, checksum: ac975a0f6cfa3fb863045bc8c7aeed35 (MD5); Made available in DSpace on 2022-05-20T10:35:56Z (GMT). No. of bitstreams: 1 ijimai7_3_1.pdf: 1003194 bytes, checksum: ac975a0f6cfa3fb863045bc8c7aeed35 (MD5) https://reunir.unir.net/handle/123456789/13140 https://reunir.unir.net/handle/123456789/13139 Comparative Analysis of Building Insurance Prediction Using Some Machine Learning Algorithms Ejiyi, Chukwuebuka Joseph; Qin, Zhen; Salako, Abdulhaq Adetunji; Happy, Monday Nkanta; Nneji, Grace Ugochi; Ukwuoma, Chiagoziem Chima; Chikwendu, Ijeoma Amuche; Gen, Ji In finance and management, insurance is a product that tends to reduce or eliminate in totality or partially the loss caused due to different risks. Various factors affect house insurance claims, some of which contribute to formulating insurance policies including specific features that the house has. Machine Learning (ML) when brought into the field of insurance would enable seamless formulation of insurance policies with a better performance which will also save time. Various classification algorithms have been used since they have a long history and have also got some modifications for optimum functionality. To illustrate the performance of each of the ML algorithms that we used here, we analyzed an insurance dataset drawn from Zindi Africa competition which is said to be from Olusola Insurance Company in Lagos Nigeria. This study therefore, compares the performance of Logistic Regression (LR), Decision Tree (DT), K-Nearest Neighbor (KNN), Kernel Support Vector Machine (kSVM), Naïve Bayes (NB), and Random Forest (RF) Regressors on a dataset got from Zindi.africa competition and their performances are checked using not only accuracy and precision metrics but also recall, and F1 score metrics, all displayed on the confusion matrix. The accuracy result shows that logistic regression and Kernel SVM both gave 78% but kSVM outperformed LR in precision with a percentage of 70.8% for kSVM and 64.8% for LR showing that kSVM offered the best result. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-20T09:53:30Z No. of bitstreams: 1 ijimai7_3_7.pdf: 543039 bytes, checksum: c8857d0579cf9c51fddf8466a5e61ba2 (MD5); Made available in DSpace on 2022-05-20T09:53:30Z (GMT). No. of bitstreams: 1 ijimai7_3_7.pdf: 543039 bytes, checksum: c8857d0579cf9c51fddf8466a5e61ba2 (MD5) https://reunir.unir.net/handle/123456789/13139 https://reunir.unir.net/handle/123456789/13138 An Ensemble Classifier for Stock Trend Prediction Using Sentence-Level Chinese News Sentiment and Technical Indicators Chen, Chun-Hao; Chen, Po-Yeh; Chun-Wei Lin, Jerry In the financial market, predicting stock trends based on stock market news is a challenging task, and researchers are devoted to developing forecasting models. From the existing literature, the performance of the forecasting model is better when news sentiment and technical analysis are considered than when only one of them is used. However, analyzing news sentiment for trend forecasting is a difficult task, especially for Chinese news, because it is unstructured data and extracting the most important features is difficult. Moreover, positive or negative news does not always affect stock prices in a certain way. Therefore, in this paper, we propose an approach to build an ensemble classifier using sentiment in Chinese news at sentence level and technical indicators to predict stock trends. In the training stages, we first divide each news item into a set of sentences. TextRank and word2vec are then used to generate a predefined number of key sentences. The sentiment scores of these key sentences are computed using the given financial lexicon. The sentiment values of the key phrases, the three values of the technical indicators and the stock trend label are merged as a training instance. Based on the sentiment values of the key sets, the corpora are divided into positive and negative news datasets. The two datasets formed are then used to build positive and negative stock trend prediction models using the support vector machine. To increase the reliability of the prediction model, a third classifier is created using the Bollinger Bands. These three classifiers are combined to form an ensemble classifier. In the testing phase, a voting mechanism is used with the trained ensemble classifier to make the final decision based on the trading signals generated by the three classifiers. Finally, experiments were conducted on five years of news and stock prices of one company to show the effectiveness of the proposed approach, and results show that the accuracy and P / L ratio of the proposed approach are 61% and 4.0821 are better than the existing approach. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-20T09:00:06Z No. of bitstreams: 1 ijimai7_3_5.pdf: 786085 bytes, checksum: d6a9561d04496b63178d717866109231 (MD5); Made available in DSpace on 2022-05-20T09:00:06Z (GMT). No. of bitstreams: 1 ijimai7_3_5.pdf: 786085 bytes, checksum: d6a9561d04496b63178d717866109231 (MD5) https://reunir.unir.net/handle/123456789/13138 https://reunir.unir.net/handle/123456789/13137 AWS PredSpot: Machine Learning for Predicting the Price of Spot Instances in AWS Cloud Baldominos Gómez, Alejandro; Saez, Yago; Quintana, David; Isasi, Pedro Elastic Cloud Compute (EC2) is one of the most well-known services provided by Amazon for provisioning cloud computing resources, also known as instances. Besides the classical on-demand scheme, where users purchase compute capacity at a fixed cost, EC2 supports so-called spot instances, which are offered following a bidding scheme, where users can save up to 90% of the cost of the on-demand instance. EC2 spot instances can be a useful alternative for attaining an important reduction in infrastructure cost, but designing bidding policies can be a difficult task, since bidding under their cost will either prevent users from provisioning instances or losing those that they already own. Towards this extent, accurate forecasting of spot instance prices can be of an outstanding interest for designing working bidding policies. In this paper, we propose the use of different machine learning techniques to estimate the future price of EC2 spot instances. These include linear, ridge and lasso regressions, multilayer perceptrons, K-nearest neighbors, extra trees and random forests. The obtained performance varies significantly between instances types, and root mean squared errors ranges between values very close to zero up to values over 60 in some of the most expensive instances. Still, we can see that for most of the instances, forecasting performance is remarkably good, encouraging further research in this field of study. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-20T08:30:51Z No. of bitstreams: 1 ijimai7_3_6.pdf: 791834 bytes, checksum: ff2030e80f5bb96f91d3b2fbc0e9feef (MD5); Made available in DSpace on 2022-05-20T08:30:51Z (GMT). No. of bitstreams: 1 ijimai7_3_6.pdf: 791834 bytes, checksum: ff2030e80f5bb96f91d3b2fbc0e9feef (MD5) https://reunir.unir.net/handle/123456789/13137 https://reunir.unir.net/handle/123456789/13136 A Comparative Analysis of Machine Learning Models for Banking News Extraction by Multiclass Classification With Imbalanced Datasets of Financial News: Challenges and Solutions Dogra, Varun; Verma, Sahil; Verma, Kavita; Jhanjhi, NZ; Ghosh, Uttam; Le, Dac-Nhuong Online portals provide an enormous amount of news articles every day. Over the years, numerous studies have concluded that news events have a significant impact on forecasting and interpreting the movement of stock prices. The creation of a framework for storing news-articles and collecting information for specific domains is an important and untested problem for the Indian stock market. When online news portals produce financial news articles about many subjects simultaneously, finding news articles that are important to the specific domain is nontrivial. A critical component of the aforementioned system should, therefore, include one module for extracting and storing news articles, and another module for classifying these text documents into a specific domain(s). In the current study, we have performed extensive experiments to classify the financial news articles into the predefined four classes Banking, Non-Banking, Governmental, and Global. The idea of multi-class classification was to extract the Banking news and its most correlated news articles from the pool of financial news articles scraped from various web news portals. The news articles divided into the mentioned classes were imbalanced. Imbalance data is a big difficulty with most classifier learning algorithms. However, as recent works suggest, class imbalances are not in themselves a problem, and degradation in performance is often correlated with certain variables relevant to data distribution, such as the existence in noisy and ambiguous instances in the adjacent class boundaries. A variety of solutions to addressing data imbalances have been proposed recently, over-sampling, down-sampling, and ensemble approach. We have presented the various challenges that occur with data imbalances in multiclass classification and solutions in dealing with these challenges. The paper has also shown a comparison of the performances of various machine learning models with imbalanced data and data balances using sampling and ensemble techniques. From the result, it’s clear that the performance of Random Forest classifier with data balances using the over-sampling technique SMOTE is best in terms of precision, recall, F-1, and accuracy. From the ensemble classifiers, the Balanced Bagging classifier has shown similar results as of the Random Forest classifier with SMOTE. Random forest classifier's accuracy, however, was 100% and it was 99% with the Balanced Bagging classifier. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-20T08:12:13Z No. of bitstreams: 1 ijimai7_3_4.pdf: 763331 bytes, checksum: bc3ebf945c8c25485f193bf223598f87 (MD5); Made available in DSpace on 2022-05-20T08:12:13Z (GMT). No. of bitstreams: 1 ijimai7_3_4.pdf: 763331 bytes, checksum: bc3ebf945c8c25485f193bf223598f87 (MD5) https://reunir.unir.net/handle/123456789/13136 https://reunir.unir.net/handle/123456789/13135 Using Customer Knowledge Surveys to Explain Sales of Postgraduate Programs: A Machine Learning Approach Asensio, Eva; Almeida, Alejandro; Galiano, Aida; Martín-Álvarez, Juan Manuel Universities collect information from each customer that contacts them through their websites and social media profiles. Customer knowledge surveys are the main information-gathering tool used to obtain this information about potential students. In this paper, we propose using the information gained via surveys along with enrolment databases, to group customers into homogeneous clusters in order to identify target customers who are more likely to enroll. The use of such a cluster strategy will increase the probability of converting contacts into customers and will allow the marketing and admission departments to focus on those customers with a greater probability of enrolling, thereby increasing efficiency. The specific characteristics of each cluster and those postgraduate programs that are more likely to be selected are identified. In addition, better insight into customers regarding their enrolment choices thanks to our cluster strategy, will allow universities to personalize their services resulting in greater satisfaction and, consequently, in increased future enrolment. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-20T07:48:35Z No. of bitstreams: 1 ijimai7_3_9.pdf: 745086 bytes, checksum: a0984f3cd37a6e5e718556a73abeaa0d (MD5); Made available in DSpace on 2022-05-20T07:48:35Z (GMT). No. of bitstreams: 1 ijimai7_3_9.pdf: 745086 bytes, checksum: a0984f3cd37a6e5e718556a73abeaa0d (MD5) https://reunir.unir.net/handle/123456789/13135 https://reunir.unir.net/handle/123456789/13134 Re-Evaluating the Relationship Between Economic Development and Self-Employment, at the Macro-Level: A Bayesian Model Averaging Approach Rodriguez-Santiago, Ana We re-evaluate the relationship between stages of economic development and entrepreneurship, at the macro level. We first conduct a literature review of previous empirical research on cross-country determinants of entrepreneurship in order to put our contribution in perspective. To circumvent problems related to model uncertainty we use Bayesian Model Averaging (BMA) to evaluate the robustness of determinants of economic growth in a new dataset of 117 countries in the 2005-2019 period, allowing fixed effects and investigating the existence of heterogeneity allowing interactions of our focus variable with other regressors. Our empirical analysis then shows that the variation of self-employment rates across countries are mainly determined by variations in the unemployment, the stage of economic development and the variations in labor market frictions. When interactions are taken into account, results confirm that there is a differential effect of labor market frictions in countries with different levels of income. Frictions in labor market may encourage becoming self-employed in richer countries. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-20T07:20:53Z No. of bitstreams: 1 ijimai7_3_2.pdf: 672659 bytes, checksum: 8bc024d1f11be3e9c2717950ddc43015 (MD5); Made available in DSpace on 2022-05-20T07:20:53Z (GMT). No. of bitstreams: 1 ijimai7_3_2.pdf: 672659 bytes, checksum: 8bc024d1f11be3e9c2717950ddc43015 (MD5) https://reunir.unir.net/handle/123456789/13134