https://reunir.unir.net/handle/123456789/12669 2026-03-30T23:06:23Z 2026-03-30T23:06:23Z García, Vicente Wu, Shaofei https://reunir.unir.net/handle/123456789/12841 2022-05-19T06:46:43Z

Editor’s Note García, Vicente; Wu, Shaofei 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 on Artificial Intelligence (AI) tools or tools that use AI with interactive multimedia techniques. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-08T09:56:59Z No. of bitstreams: 1 ijimai_6_4_0.pdf: 490509 bytes, checksum: 85e87cc3d0eb1adf225a8da55469b83c (MD5); Made available in DSpace on 2022-04-08T09:56:59Z (GMT). No. of bitstreams: 1 ijimai_6_4_0.pdf: 490509 bytes, checksum: 85e87cc3d0eb1adf225a8da55469b83c (MD5)

Zang, Jingfeng Xu, Ningxue Liu, Riu Shi, Yuhuan https://reunir.unir.net/handle/123456789/12840 2022-04-08T09:52:20Z

Deraining and Desnowing Algorithm on Adaptive Tolerance and Dual-tree Complex Wavelet Fusion Zang, Jingfeng; Xu, Ningxue; Liu, Riu; Shi, Yuhuan Severe weather conditions such as rain and snow often reduce the visual perception quality of the video image system, the traditional methods of deraining and desnowing usually rarely consider adaptive parameters. In order to enhance the effect of video deraining and desnowing, this paper proposes a video deraining and desnowing algorithm based on adaptive tolerance and dual-tree complex wavelet. This algorithm can be widely used in security surveillance, military defense, biological monitoring, remote sensing and other fields. First, this paper introduces the main work of the adaptive tolerance method for the video of dynamic scenes. Second, the algorithm of dual-tree complex wavelet fusion is analyzed and introduced. Using principal component analysis fusion rules to process low-frequency sub-bands, the fusion rule of local energy matching is used to process the high-frequency sub-bands. Finally, this paper used various rain and snow videos to verify the validity and superiority of image reconstruction. Experimental results show that the algorithm has achieved good results in improving the image clarity and restoring the image details obscured by raindrops and snows. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-08T09:52:20Z No. of bitstreams: 1 ijimai_6_4_14.pdf: 1449944 bytes, checksum: 78c7983b43bb2495d53e4e396d24648e (MD5); Made available in DSpace on 2022-04-08T09:52:20Z (GMT). No. of bitstreams: 1 ijimai_6_4_14.pdf: 1449944 bytes, checksum: 78c7983b43bb2495d53e4e396d24648e (MD5)

Xu, Guiming https://reunir.unir.net/handle/123456789/12839 2022-04-08T09:46:27Z

The Construction Site Management of Concrete Prefabricated Buildings by ISM-ANP Network Structure Model and BIM under Big Data Text Mining Analytic Network Process (ANP) Xu, Guiming In the construction industry, prefabricated buildings have developed rapidly in recent years due to their various excellent properties. To expand the application of big data text mining and Building Information Model (BIM) in prefabricated building construction, with concrete as a form of expression, the construction management of concrete prefabricated buildings is discussed. Based on the Interpretative Structural Model (ISM) and Analytic Network Process (ANP), the importance of the safety factors on the construction sites of concrete prefabricated buildings are assessed. Based on BIM, an optimized construction management platform for concrete prefabricated buildings is built, whose realization effects are characterized. The results show that prefabricated buildings have developed rapidly from 2017 to 2019. Compared with traditional buildings, they can significantly reduce the waste of resources and energy, and the savings of water resource utilization can reach 80%. Among the various safety impact elements, construction management has the greatest impact on construction safety, and the corresponding weight value is 0.3653. The corresponding weight of construction personnel is 0.2835, the corresponding weight of construction objects is 0.1629, the corresponding weight of construction technology is 0.1436, and the corresponding weight of construction environment is 0.0448. This building construction management platform is able to control the construction progress in real-time and avoid the occurrence of construction safety accidents. The final layout of the construction site shows a good effect, and the deviation between the actual construction schedule and the expected construction schedule is small, which is of great significance for the smooth development of concrete prefabricated buildings. This is a catalyst for the future development of concrete prefabricated buildings and the application of big data technology. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-08T09:46:27Z No. of bitstreams: 1 ijimai_6_4_15.pdf: 979715 bytes, checksum: 14f5a152ff648b1f2ce6d7e6728b1d72 (MD5); Made available in DSpace on 2022-04-08T09:46:27Z (GMT). No. of bitstreams: 1 ijimai_6_4_15.pdf: 979715 bytes, checksum: 14f5a152ff648b1f2ce6d7e6728b1d72 (MD5)

Li, You Wang, Juan Ji, Yiming https://reunir.unir.net/handle/123456789/12838 2022-04-08T09:23:42Z

Function Analysis of Industrial Robot under Cubic Polynomial Interpolation in Animation Simulation Environment Li, You; Wang, Juan; Ji, Yiming In order to study the effect of cubic polynomial interpolation in the trajectory planning of polishing robot manipulator, firstly, the articular robot operating arm is taken as the research object, and the overall system of polishing robot operating arm with 7 degrees of freedom is constructed. Then through the transformation of space motion and pose coordinate system, Denavit-Hartenberg (D-H) Matrix is introduced to describe the coordinate direction and parameters of the adjacent connecting rod of the polishing robot, and the kinematic model of the robot is built, and the coordinate direction and parameters of its adjacent link are described. A multi-body Dynamic simulation software, Automatic Dynamic Analysis of Mechanical Systems (ADAMS), is used to analyze the kinematic simulation of the robot operating arm system. Finally, the trajectory of the robot manipulator is planned based on the cubic polynomial difference method, and the simulation is verified by Matrix Laboratory (MATLAB). Through calculation, it is found that the kinematic model of polishing robot operating arm constructed in this study is in line with the reality; ADAMS software is used to generate curves of the rotation angles of different joint axes and the displacement of end parts of the polishing robot operating arm changing with time. After obtaining relevant parameters, they are put into the kinematic equation constructed in this study, and the calculated position coordinates are consistent with the detection results; moreover, the polishing robot constructed in this study can realize the functions of deburring, polishing, trimming, and turning table. MATLAB software is used to generate the simulation of the movement trajectory of the polishing robot operating arm, which can show the change curve of angle and angular velocity. The difference between the angle at which the polishing robot reaches the polishing position, the change curve of angular velocity, and the time spent before and after the path optimization is compared. It is found that after path optimization based on cubic polynomial, the change curve of the polishing robot's angle and angular velocity is smoother, and the time is shortened by 17.21s. It indicates that the cubic polynomial interpolation method can realize the trajectory planning of the polishing robot operating arm, moreover, the optimized polishing robot has a continuous and smooth trajectory, which can improve the working efficiency of the robot. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-08T09:23:42Z No. of bitstreams: 1 ijimai_6_4_11.pdf: 1076311 bytes, checksum: 37abc286f9822efb9dcabe5238f06721 (MD5); Made available in DSpace on 2022-04-08T09:23:42Z (GMT). No. of bitstreams: 1 ijimai_6_4_11.pdf: 1076311 bytes, checksum: 37abc286f9822efb9dcabe5238f06721 (MD5)

Heydarpour, F. Abbasi, E. Ebadi, M. J. Karbassi, S. M. https://reunir.unir.net/handle/123456789/12837 2022-04-08T09:17:48Z

Solving an Optimal Control Problem of Cancer Treatment by Artificial Neural Networks Heydarpour, F.; Abbasi, E.; Ebadi, M. J.; Karbassi, S. M. Cancer is an uncontrollable growth of abnormal cells in any tissue of the body. Many researchers have focused on machine learning and artificial intelligence (AI) based on approaches for cancer treatment. Dissimilar to traditional methods, these approaches are efficient and are able to find the optimal solutions of cancer chemotherapy problems. In this paper, a system of ordinary differential equations (ODEs) with the state variables of immune cells, tumor cells, healthy cells and drug concentration is proposed to anticipate the tumor growth and to show their interactions in the body. Then, an artificial neural network (ANN) is applied to solve the ODEs system through minimizing the error function and modifying the parameters consisting of weights and biases. The mean square errors (MSEs) between the analytical and ANN results corresponding to four state variables are 1.54e-06, 6.43e-07, 6.61e-06, and 3.99e-07, respectively. These results show the good performance and efficiency of the proposed method. Moreover, the optimal dose of chemotherapy drug and the amount of drug needed to continue the treatment process are achieved. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-08T09:17:48Z No. of bitstreams: 1 ijimai_6_4_2.pdf: 1191973 bytes, checksum: 343ea97ecbb1518af534e6b5dccfdb70 (MD5); Made available in DSpace on 2022-04-08T09:17:48Z (GMT). No. of bitstreams: 1 ijimai_6_4_2.pdf: 1191973 bytes, checksum: 343ea97ecbb1518af534e6b5dccfdb70 (MD5)

Magdin, Martin Držík, D. Reichel, J. Koprda, S . https://reunir.unir.net/handle/123456789/12836 2022-04-08T08:58:38Z

The Possibilities of Classification of Emotional States Based on User Behavioral Characteristics Magdin, Martin; Držík, D.; Reichel, J.; Koprda, S . The classification of user's emotions based on their behavioral characteristic, namely their keyboard typing and mouse usage pattern is an effective and non-invasive way of gathering user's data without imposing any limitations on their ability to perform tasks. To gather data for the classifier we used an application, the Emotnizer, which we had developed for this purpose. The output of the classification is categorized into 4 emotional categories from Russel's complex circular model - happiness, anger, sadness and the state of relaxation. The sample of the reference database consisted of 50 students. Multiple regression analyses gave us a model, that allowed us to predict the valence and arousal of the subject based on the input from the keyboard and mouse. Upon re-testing with another test group of 50 students and processing the data we found out our Emotnizer program can classify emotional states with an average success rate of 82.31%. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-08T08:58:38Z No. of bitstreams: 1 ijimai_6_4_10.pdf: 1062017 bytes, checksum: b37a6b2c6c7d6758145e11aa052a7150 (MD5); Made available in DSpace on 2022-04-08T08:58:38Z (GMT). No. of bitstreams: 1 ijimai_6_4_10.pdf: 1062017 bytes, checksum: b37a6b2c6c7d6758145e11aa052a7150 (MD5)

Sánchez-Prieto, José Carlos Cruz-Benito, Juan Therón, Roberto García-Peñalvo, Francisco https://reunir.unir.net/handle/123456789/12835 2022-04-08T08:40:36Z

Assessed by Machines: Development of a TAM-Based Tool to Measure AI-based Assessment Acceptance Among Students Sánchez-Prieto, José Carlos; Cruz-Benito, Juan; Therón, Roberto; García-Peñalvo, Francisco In recent years, the use of more and more technology in education has been a trend. The shift of traditional learning procedures into more online and tech-ish approaches has contributed to a context that can favor integrating Artificial-Intelligence-based or algorithm-based assessment of learning. Even more, with the current acceleration because of the COVID-19 pandemic, more and more learning processes are becoming online and are incorporating technologies related to automatize assessment or help instructors in the process. While we are in an initial stage of that integration, it is the moment to reflect on the students' perceptions of being assessed by a non-conscious software entity like a machine learning model or any other artificial intelligence application. As a result of the paper, we present a TAM-based model and a ready-to-use instrument based on five aspects concerning understanding technology adoption like the AI-based assessment on education. These aspects are perceived usefulness, perceived ease of use, attitude towards use, behavioral intention, and actual use. The paper's outcomes can be relevant to the research community since there is a lack of this kind of proposal in the literature. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-08T08:40:35Z No. of bitstreams: 1 ijimai_6_4_8.pdf: 674624 bytes, checksum: 4af5d563c8d56c0f37fb2189ae2ccb1d (MD5); Made available in DSpace on 2022-04-08T08:40:36Z (GMT). No. of bitstreams: 1 ijimai_6_4_8.pdf: 674624 bytes, checksum: 4af5d563c8d56c0f37fb2189ae2ccb1d (MD5)

Muñoz Lezcano, Sergio López Hernández, Fernando Carlos Corbi, Alberto https://reunir.unir.net/handle/123456789/12834 2023-05-03T10:03:15Z

Data Science Techniques for COVID-19 in Intensive Care Units Muñoz Lezcano, Sergio; López Hernández, Fernando Carlos; Corbi, Alberto Data scientists aim to provide techniques and tools to the clinicians to manage the new coronavirus disease. Nowadays, new emerging tools based on Artificial Intelligence (AI), Image Processing (IP) and Machine Learning (ML) are contributing to the improvement of healthcare and treatments of different diseases. This paper reviews the most recent research efforts and approaches related to these new data driven techniques and tools in combination with the exploitation of the already available COVID-19 datasets. The tools can assist clinicians and nurses in efficient decision making with complex and heavily heterogeneous data, even in hectic and overburdened Intensive Care Units (ICU) scenarios. The datasets and techniques underlying these tools can help finding a more correct diagnosis. The paper also describes how these innovative AI+IP+ML-based methods (e.g., conventional X-ray imaging, clinical laboratory data, respiratory monitoring and automatic adjustments, etc.) can assist in the process of easing both the care of infected patients in ICUs and Emergency Rooms and the discovery of new treatments (drugs). Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-08T08:26:44Z No. of bitstreams: 1 ijimai_6_4_1_0.pdf: 1529347 bytes, checksum: 4fa2a340718d14f8bdf39735c1674fc7 (MD5); Made available in DSpace on 2022-04-08T08:26:44Z (GMT). No. of bitstreams: 1 ijimai_6_4_1_0.pdf: 1529347 bytes, checksum: 4fa2a340718d14f8bdf39735c1674fc7 (MD5)

Jin, Xin Xiao, Yong Li, Shiqi Wang, Suying https://reunir.unir.net/handle/123456789/12833 2022-04-08T08:18:18Z

Deep Learning-based Side Channel Attack on HMAC SM3 Jin, Xin; Xiao, Yong; Li, Shiqi; Wang, Suying SM3 is a Chinese hash standard. HMAC SM3 uses a secret key to encrypt the input text and gives an output as the HMAC of the input text. If the key is recovered, adversaries can easily forge a valid HMAC. We can choose different methods, such as traditional side channel analysis, template attack-based side channel analysis to recover the secret key. Deep Learning has recently been introduced as a new alternative to perform Side-Channel analysis. In this paper, we try to recover the secret key with deep learning-based side channel analysis. We should train the network recursively for different parameters by using the same dataset and attack the target dataset with the trained network to recover different parameters. The experiment results show that the secret key can be recovered with deep learning-based side channel analysis. This work demonstrates the interests of this new method and show that this attack can be performed in practice. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-08T08:18:18Z No. of bitstreams: 1 ijimai_6_4_12.pdf: 1220803 bytes, checksum: be1a251509cad3220ce9b37f8440a5e1 (MD5); Made available in DSpace on 2022-04-08T08:18:18Z (GMT). No. of bitstreams: 1 ijimai_6_4_12.pdf: 1220803 bytes, checksum: be1a251509cad3220ce9b37f8440a5e1 (MD5)

Zhou, Shenghan Chen, Bang Zhang, Yue Liu, HouXiang Xiao, Yiyong Pan, Xing https://reunir.unir.net/handle/123456789/12816 2022-04-05T10:29:29Z

A Feature Extraction Method Based on Feature Fusion and its Application in the Text-Driven Failure Diagnosis Field Zhou, Shenghan; Chen, Bang; Zhang, Yue; Liu, HouXiang; Xiao, Yiyong; Pan, Xing As a basic task in NLP (Natural Language Processing), feature extraction directly determines the quality of text clustering and text classification. However, the commonly used TF-IDF (Term Frequency & Inverse Document Frequency) and LDA (Latent Dirichlet Allocation) text feature extraction methods have shortcomings in not considering the text’s context and blindness to the topic of the corpus. This study builds a feature extraction algorithm and application scenarios in the field of failure diagnosis. A text-driven failure diagnosis model is designed to classify and automatically judge which failure mode the failure described in the text belongs to once a failure-description text is entered. To verify the effectiveness of the proposed feature extraction algorithm and failure diagnosis model, a long-term accumulated failure description text of an aircraft maintenance and support system was used as a subject to conduct an empirical study. The final experimental results also show that the proposed feature extraction method can effectively improve the effect of clustering, and the proposed failure diagnosis model achieves high accuracies and low false alarm rates. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-05T10:29:29Z No. of bitstreams: 1 ijimai_6_4_13.pdf: 1302128 bytes, checksum: d2a3fbe28ce1fbeef4eeca8c4caacbc6 (MD5); Made available in DSpace on 2022-04-05T10:29:29Z (GMT). No. of bitstreams: 1 ijimai_6_4_13.pdf: 1302128 bytes, checksum: d2a3fbe28ce1fbeef4eeca8c4caacbc6 (MD5)

García Nieto, Paulino José García-Gonzalo, Esperanza Sánchez Lasheras, Fernando Bernardo Sánchez, Antonio https://reunir.unir.net/handle/123456789/12815 2022-04-05T10:04:50Z

Chrome Layer Thickness Modelling in a Hard Chromium Plating Process Using a Hybrid PSO/ RBF–SVM–Based Model García Nieto, Paulino José; García-Gonzalo, Esperanza; Sánchez Lasheras, Fernando; Bernardo Sánchez, Antonio The purpose of chromium plating is the creation of a hard and wear-resistant layer of chromium over a metallic surface. The principal feature of chromium plating is its endurance in the face of the wear and corrosion. This industrial process has a vast range of applications in many different areas. In the performance of this process, some difficulties can be found. Some of the most common are melt deposition, milky white chromium deposition, rough or sandy chromium deposition and lack of toughness of the layer or wear and lack of thickness of the layer deposited. This study builds a novel nonparametric method relied on the statistical machine learning that employs a hybrid support vector machines (SVMs) model for the hard chromium layer thickness forecast. The SVM hyperparameters optimization was made with the help of the Particle Swarm Optimizer (PSO). The outcomes indicate that PSO/SVM–based model together with radial basis function (RBF) kernel has permitted to foretell the thickness of the chromium layer created in this industrial process satisfactorily. Thus, two kinds of outcomes have been obtained: firstly, this model permits to determine the ranking of relevance of the seven independent input variables investigated in this industrial process. Finally, the high achievement and lack of complexity of the model indicate that the PSO/SVM method is very interesting compared to other conventional foretelling techniques, since a coefficient of determination of 0.9952 is acquired. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-05T10:04:50Z No. of bitstreams: 1 ijimai_6_4_4.pdf: 1114067 bytes, checksum: d4b8380c297df951f27b5f54089ec2f8 (MD5); Made available in DSpace on 2022-04-05T10:04:50Z (GMT). No. of bitstreams: 1 ijimai_6_4_4.pdf: 1114067 bytes, checksum: d4b8380c297df951f27b5f54089ec2f8 (MD5)

Rehman, I Ullah, S Khan, Dawar https://reunir.unir.net/handle/123456789/12814 2022-04-05T09:59:03Z

Multi Layered Multi Task Marker Based Interaction in Information Rich Virtual Environments Rehman, I; Ullah, S; Khan, Dawar Simple and cheap interaction has a key role in the operation and exploration of any Virtual Environment (VE). In this paper, we propose an interaction technique that provides two different ways of interaction (information and control) on complex objects in a simple and computationally cheap way. The interaction is based on the use of multiple embedded markers in a specialized manner. The proposed marker like an interaction peripheral works just like a touch paid which can perform any type of interaction in a 3D VE. The proposed marker is not only used for interaction with Augmented Reality (AR), but also with Mixed Reality. A biological virtual learning application is developed which is used for evaluation and experimentation. We conducted our experiments in two phases. First, we compared a simple VE with the proposed layered VE. Second, a comparative study is conducted between the proposed marker, a simple layered marker, and multiple single markers. We found the proposed marker with improved learning, easiness in interaction, and comparatively less task execution time. The results gave improved learning for layered VE as compared to simple VE. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-05T09:59:03Z No. of bitstreams: 1 ijimai_6_4_6.pdf: 1665600 bytes, checksum: 49124bc089a60d2f9492c14012ecbe4f (MD5); Made available in DSpace on 2022-04-05T09:59:03Z (GMT). No. of bitstreams: 1 ijimai_6_4_6.pdf: 1665600 bytes, checksum: 49124bc089a60d2f9492c14012ecbe4f (MD5)

Jain, Minni Jaswani, Aman Mehra, Ankita Mudgal, Laqshay https://reunir.unir.net/handle/123456789/12813 2022-04-05T09:54:02Z

Rumour Source Detection Using Game Theory Jain, Minni; Jaswani, Aman; Mehra, Ankita; Mudgal, Laqshay Social networks have become a critical part of our lives as they enable us to interact with a lot of people. These networks have become the main sources for creating, sharing and also extracting information regarding various subjects. But all this information may not be true and may contain a lot of unverified rumours that have the potential of spreading incorrect information to the masses, which may even lead to situations of widespread panic. Thus, it is of great importance to identify those nodes and edges that play a crucial role in a network in order to find the most influential sources of rumour spreading. Generally, the basic idea is to classify the nodes and edges in a network with the highest criticality. Most of the existing work regarding the same focuses on using simple centrality measures which focus on the individual contribution of a node in a network. Game-theoretic approaches such as Shapley Value (SV) algorithms suggest that individual marginal contribution should be measured for a given player as the weighted average marginal increase in the yield of any coalition that this player might join. For our experiment, we have played five SV-based games to find the top 10 most influential nodes on three network datasets (Enron, USAir97 and Les Misérables). We have compared our results to the ones obtained by using primitive centrality measures. Our results show that SVbased approach is better at understanding the marginal contribution, and therefore the actual influence, of each node to the entire network. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-05T09:54:02Z No. of bitstreams: 1 ijimai_6_4_5.pdf: 883619 bytes, checksum: 28c8eb329098e5d62a8071fbf03b8175 (MD5); Made available in DSpace on 2022-04-05T09:54:02Z (GMT). No. of bitstreams: 1 ijimai_6_4_5.pdf: 883619 bytes, checksum: 28c8eb329098e5d62a8071fbf03b8175 (MD5)

Dejene, Dawit Tiwari, Basant Tiwari, Vivek https://reunir.unir.net/handle/123456789/12812 2022-04-05T09:40:11Z

TD2SecIoT: Temporal, Data-Driven and Dynamic Network Layer Based Security Architecture for Industrial IoT Dejene, Dawit; Tiwari, Basant; Tiwari, Vivek The Internet of Things (IoT) is an emerging technology, which comprises wireless smart sensors and actuators. Nowadays, IoT is implemented in different areas such as Smart Homes, Smart Cities, Smart Industries, Military, eHealth, and several real-world applications by connecting domain-specific sensors. Designing a security model for these applications is challenging for researchers since attacks (for example, zero-day) are increasing tremendously. Several security methods have been developed to ensure the CIA (Confidentiality, Integrity, and Availability) for Industrial IoT (IIoT). Though these methods have shown promising results, there are still some security issues that are open. Thus, the security and authentication of IoT based applications become quite significant. In this paper, we propose TD2SecIoT (Temporal, Data-Driven and Dynamic Network Layer Based Security Architecture for Industrial IoT), which incorporates Elliptic Curve Cryptography (ECC) and Nth-degree Truncated Polynomial Ring Units (NTRU) methods to ensure confidentiality and integrity. The proposed method has been evaluated against different attacks and performance measures (quantitative and qualitative) using the Cooja network simulator with Contiki-OS. The TD2SecIoT has shown a higher security level with reduced computational cost and time. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-05T09:40:11Z No. of bitstreams: 1 ijimai_6_4_16.pdf: 1476946 bytes, checksum: 16dcdb17bb3d3585f2a3c21f1d4786ac (MD5); Made available in DSpace on 2022-04-05T09:40:11Z (GMT). No. of bitstreams: 1 ijimai_6_4_16.pdf: 1476946 bytes, checksum: 16dcdb17bb3d3585f2a3c21f1d4786ac (MD5)

Cantabella, Magdalena Martínez-España, Raquel López, Belén Muñoz, Andrés https://reunir.unir.net/handle/123456789/12811 2022-04-05T09:13:52Z

A Fine-Grained Model to Assess Learner-Content and Methodology Satisfaction in Distance Education Cantabella, Magdalena; Martínez-España, Raquel; López, Belén; Muñoz, Andrés Learning Management System (LMS) platforms have led to a transformation in Universities in the last decade, helping them to adapt and expand their services to new technological challenges. These platforms have made possible the expansion of distance education. A current trend in this area is focused on the evaluation and improvement of the students’ satisfaction. In this work a new tool to assess student satisfaction using emoticons (smileys) is proposed to evaluate the quality of the learning content and the methodology at unit level for any course and at any time. The results indicate that the assessment of student satisfaction is sensitive to the period when the survey is performed and to the student’s study level. Moreover, the results of this new proposal are compared to the satisfaction results using traditional surveys, showing different results due to a more accuracy and flexibility when using the tool proposed in this work. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-05T09:13:52Z No. of bitstreams: 1 ijimai_6_4_9.pdf: 844527 bytes, checksum: 5678413b7c54c73f979a94a5d43c68e4 (MD5); Made available in DSpace on 2022-04-05T09:13:52Z (GMT). No. of bitstreams: 1 ijimai_6_4_9.pdf: 844527 bytes, checksum: 5678413b7c54c73f979a94a5d43c68e4 (MD5)

Mahmoud, Karar Abdel-Nasser, Mohamed Kashef, Heba Puig, Domenec Lehtonen, Matti https://reunir.unir.net/handle/123456789/12810 2022-04-05T09:08:16Z

Machine Learning Based Method for Estimating Energy Losses in Large-Scale Unbalanced Distribution Systems with Photovoltaics Mahmoud, Karar; Abdel-Nasser, Mohamed; Kashef, Heba; Puig, Domenec; Lehtonen, Matti In the recent years, the penetration of photovoltaics (PV) has obviously been increased in unbalanced power distribution systems. Driven by this trend, comprehensive simulation tools are required to accurately analyze large-scale distribution systems with a fast-computational speed. In this paper, we propose an efficient method for performing time-series simulations for unbalanced power distribution systems with PV. Unlike the existing iterative methods, the proposed method is based on machine learning. Specifically, we propose a fast, reliable and accurate method for determining energy losses in distribution systems with PV. The proposed method is applied to a large-scale unbalanced distribution system (the IEEE 906 Bus European LV Test Feeder) with PV grid-connected units. The method is validated using OpenDSS software. The results demonstrate the high accuracy and computational performance of the proposed method. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-05T09:08:16Z No. of bitstreams: 1 ijimai_6_4_17.pdf: 963471 bytes, checksum: 044ebe7277c34bcd250cf9b400fdfc0a (MD5); Made available in DSpace on 2022-04-05T09:08:16Z (GMT). No. of bitstreams: 1 ijimai_6_4_17.pdf: 963471 bytes, checksum: 044ebe7277c34bcd250cf9b400fdfc0a (MD5)

Das, Apangshu Pradhan, Sambhu Nath https://reunir.unir.net/handle/123456789/12809 2022-04-05T09:01:12Z

An Elitist Non-Dominated Multi-Objective Genetic Algorithm Based Temperature Aware Circuit Synthesis Das, Apangshu; Pradhan, Sambhu Nath At sub-nanometre technology, temperature is one of the important design parameters to be taken care of during the target implementation for the circuit for its long term and reliable operation. High device package density leads to high power density that generates high temperatures. The temperature of a chip is directly proportional to the power density of the chip. So, the power density of a chip can be minimized to reduce the possibility of the high temperature generation. Temperature minimization approaches are generally addressed at the physical design level but it incurs high cooling cost. To reduce the cooling cost, the temperature minimization approaches can be addressed at the logic level. In this work, the Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) based multi-objective heuristic approach is proposed to select the efficient input variable polarity of Mixed Polarity Reed-Muller (MPRM) expansion for simultaneous optimization of area, power, and temperature. A Pareto optimal solution set is obtained from the vast solution set of 3n (‘n’ is the number of input variables) different polarities of MPRM. Tabular technique is used for input polarity conversion from Sum-of-Product (SOP) form to MPRM form. Finally, using CADENCE and HotSpot tool absolute temperature, silicon area and power consumption of the synthesized circuits are calculated and are reported. The proposed algorithm saves around 76.20% silicon area, 29.09% power dissipation and reduces 17.06% peak temperature in comparison with the reported values in the literature. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-05T09:01:12Z No. of bitstreams: 1 ijimai_6_4_3.pdf: 1460901 bytes, checksum: 851af4d29c4bcbb38d17213b7b1d39a7 (MD5); Made available in DSpace on 2022-04-05T09:01:12Z (GMT). No. of bitstreams: 1 ijimai_6_4_3.pdf: 1460901 bytes, checksum: 851af4d29c4bcbb38d17213b7b1d39a7 (MD5)

Prasad Mudigonda, Krishna Siva Sharma, Poonam https://reunir.unir.net/handle/123456789/12808 2022-04-05T08:56:48Z

Multi-sense Embeddings Using Synonym Sets and Hypernym Information from Wordnet Prasad Mudigonda, Krishna Siva; Sharma, Poonam Word embedding approaches increased the efficiency of natural language processing (NLP) tasks. Traditional word embeddings though robust for many NLP activities, do not handle polysemy of words. The tasks of semantic similarity between concepts need to understand relations like hypernymy and synonym sets to produce efficient word embeddings. The outcomes of any expert system are affected by the text representation. Systems that understand senses, context, and definitions of concepts while deriving vector representations handle the drawbacks of single vector representations. This paper presents a novel idea for handling polysemy by generating Multi-Sense Embeddings using synonym sets and hypernyms information of words. This paper derives embeddings of a word by understanding the information of a word at different levels, starting from sense to context and definitions. Proposed sense embeddings of words obtained prominent results when tested on word similarity tasks. The proposed approach is tested on nine benchmark datasets, which outperformed several state-of-the-art systems. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-05T08:56:48Z No. of bitstreams: 1 ijimai_6_4_7.pdf: 691431 bytes, checksum: ce25fc0f7aa8a30f00141ace94a4ce6a (MD5); Made available in DSpace on 2022-04-05T08:56:48Z (GMT). No. of bitstreams: 1 ijimai_6_4_7.pdf: 691431 bytes, checksum: ce25fc0f7aa8a30f00141ace94a4ce6a (MD5)

Baldominos Gómez, Alejandro Mochón, Francisco https://reunir.unir.net/handle/123456789/12783 2022-04-01T08:12:58Z

Editor’s Note. Towards Blockchain Intelligence Baldominos Gómez, Alejandro; Mochón, Francisco In this special issue, we want to gather some innovative applications that are currently pushing forward the research on Blockchain technologies. In particular, we are interested also in those applications that put the focus on the data, enabling new processes that are able to leverage relevant knowledge from the data. This special issue will be successful if readers gain a better understanding on how Blockchain can be applied to very diverse areas, and might even be interested in designing, implementing and deploying an innovative solution to a completely different field of knowledge. We hope this Special Issue can provide a better understanding and key insights to readers on how Blockchain and artificial intelligence are cross-fertilizing to revolutionize many aspects in our societies. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-01T08:12:58Z No. of bitstreams: 1 ijimai_6_3_0.pdf: 602540 bytes, checksum: cf06c948841e77b6fd71225a7c1b83de (MD5); Made available in DSpace on 2022-04-01T08:12:58Z (GMT). No. of bitstreams: 1 ijimai_6_3_0.pdf: 602540 bytes, checksum: cf06c948841e77b6fd71225a7c1b83de (MD5)

García Sáez, M. Inmaculada https://reunir.unir.net/handle/123456789/12782 2022-04-01T07:59:45Z

Blockchain-Enabled Platforms: Challenges and Recommendations García Sáez, M. Inmaculada Not even a tenth of blockchain-enabled platforms survive their first anniversary. The volatility of cryptomarkets has brought negative attention and led some to question the applicability of blockchain technology. This paper argues that the challenges for startups and incumbents behind these platforms are numerous, and that the speculative bubble around cryptocurrencies is only one of them. Blockchain still needs to demonstrate fully its disruptive potential and so far, entrepreneurs have not managed to significantly impact incumbents’ market shares. This transitory period requires incumbents to let go of traditional control mechanisms, and startups to scale down their global decentralised hopes. Indeed, whilst the technology can indeed scale fast, starting in a controlled market and managing growth is a counterintuitive but essential strategy for blockchain-enabled platforms to implement. Given the diverging nature of the technology, at present at least, the combined shortage of skills in blockchain and security, and the trust blockchain is built on, rushing to the global market is high risk. Nonetheless, given the potential returns, the risk appetite is high and both entrepreneurs and corporate executives share unrealistic expectations about a technology they cannot fully understand since it has not yet converged. In light of the above, this article identifies the main challenges faced when building blockchainenabled platforms and provides recommendations for startups and incumbents to overcome these. In order to reach these conclusions, the information obtained from twenty semi-structured interviews with leading actors in the field has been fundamental. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-01T07:59:45Z No. of bitstreams: 1 ijimai_6_3_9_0.pdf: 941493 bytes, checksum: d38fa9842b639738ec58d30a2a7a4e0f (MD5); Made available in DSpace on 2022-04-01T07:59:45Z (GMT). No. of bitstreams: 1 ijimai_6_3_9_0.pdf: 941493 bytes, checksum: d38fa9842b639738ec58d30a2a7a4e0f (MD5)

Lopez, Miguel Angel Lombardo, Juan Manuel López, Mabel Álvarez, David Velasco, Susana Terrón, Sara https://reunir.unir.net/handle/123456789/12781 2022-04-01T07:55:33Z

Traceable Ecosystem and Strategic Framework for the Creation of an Integrated Pest Management System for Intensive Farming Lopez, Miguel Angel; Lombardo, Juan Manuel; López, Mabel; Álvarez, David; Velasco, Susana; Terrón, Sara The appearance of pests is one of the major problems that exist in the growth of crops, as they can damage the production if the appropriate measures are not taken. Within the framework of the Integrated Pest Management strategy (IPM), early detection of pests is an essential step in order to provide the most appropriate treatment and avoid losses. This paper proposes the architecture of a system intensive farming in greenhouses featuring the ability to detect environmental variations that may favour the appearance of pests. This system can suggest a plan or treatment that will help mitigate the effects that the identified pest would produce otherwise. Furthermore, the system will learn from the actions carried out by the humans throughout the different stages of crop growing and will add it as knowledge for the prediction of future actions. The data collected from sensors, through computer vision, or the experiences provided by the experts, along with the historical data related to the crop, will allow for the development of a model that contrasts the predictions of the actions that could be implemented with those already performed by technicians. Within the technological ecosystems in which the Integrated Pest Management systems develop their action, traceability models must be incorporated. This will guarantee that the data used for the exploitation of the information and, therefore for the parameterization of the predictive models, are adequate. Thus, the integration of blockchain technologies is considered key to provide them with security and confidence. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-01T07:55:33Z No. of bitstreams: 1 ijimai_6_3_6.pdf: 1120024 bytes, checksum: 0861caab5862d06336738d0136b9b5c8 (MD5); Made available in DSpace on 2022-04-01T07:55:33Z (GMT). No. of bitstreams: 1 ijimai_6_3_6.pdf: 1120024 bytes, checksum: 0861caab5862d06336738d0136b9b5c8 (MD5)

Lopez, Miguel Angel Lombardo, Juan Manuel López, Mabel Alba, Carmen María Velasco, Susana Braojos, Manuel Alonso Fuentes-García, Marta https://reunir.unir.net/handle/123456789/12780 2022-04-01T07:44:29Z

Intelligent Detection and Recovery from Cyberattacks for Small and Medium-Sized Enterprises Lopez, Miguel Angel; Lombardo, Juan Manuel; López, Mabel; Alba, Carmen María; Velasco, Susana; Braojos, Manuel Alonso; Fuentes-García, Marta Cyberattacks threaten continuously computer security in companies. These attacks evolve everyday, being more and more sophisticated and robust. In addition, they take advantage of security breaches in organizations and companies, both public and private. Small and Medium-sized Enterprises (SME), due to their structure and economic characteristics, are particularly damaged when a cyberattack takes place. Although organizations and companies put lots of efforts in implementing security solutions, they are not always effective. This is specially relevant for SMEs, which do not have enough economic resources to introduce such solutions. Thus, there is a need of providing SMEs with affordable, intelligent security systems with the ability of detecting and recovering from the most detrimental attacks. In this paper, we propose an intelligent cybersecurity platform, which has been designed with the objective of helping SMEs to make their systems and network more secure. The aim of this platform is to provide a solution optimizing detection and recovery from attacks. To do this, we propose the application of proactive security techniques in combination with both Machine Learning (ML) and blockchain. Our proposal is enclosed in the IASEC project, which allows providing security in each of the phases of an attack. Like this, we help SMEs in prevention, avoiding systems and network from being attacked; detection, identifying when there is something potentially harmful for the systems; containment, trying to stop the effects of an attack; and response, helping to recover the systems to a normal state. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-01T07:44:29Z No. of bitstreams: 1 ijimai_6_3_7.pdf: 1126197 bytes, checksum: 374045403446b2cd93a125c9b7731874 (MD5); Made available in DSpace on 2022-04-01T07:44:29Z (GMT). No. of bitstreams: 1 ijimai_6_3_7.pdf: 1126197 bytes, checksum: 374045403446b2cd93a125c9b7731874 (MD5)

El Ghazouani, Mohamed El kiram, My Ahmed Latifa, ER-RAJY El Khanboubi, Yassine https://reunir.unir.net/handle/123456789/12779 2022-04-01T07:33:14Z

Efficient Method Based on Blockchain Ensuring Data Integrity Auditing with Deduplication in Cloud El Ghazouani, Mohamed; El kiram, My Ahmed; Latifa, ER-RAJY; El Khanboubi, Yassine With the rapid development of cloud storage, more and more cloud clients can store and access their data anytime, from anywhere and using any device. Data deduplication may be considered an excellent choice to ensure data storage efficiency. Although cloud technology offers many advantages for storage service, it also introduces security challenges, especially with regards to data integrity, which is one of the most critical elements in any system. A data owner should thus enable data integrity auditing mechanisms. Much research has recently been undertaken to deal with these issues. In this paper, we propose a novel blockchain-based method, which can preserve cloud data integrity checking with data deduplication. In our method, a mediator performs data deduplication on the client side, which permits a reduction in the amount of outsourced data and a decrease in the computation time and the bandwidth used between the enterprise and the cloud service provider. This method supports private and public auditability. Our method also ensures the confidentiality of a client's data against auditors during the auditing process. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-04-01T07:33:14Z No. of bitstreams: 1 ijimai_6_3_4.pdf: 1512817 bytes, checksum: 6c6412d5010d5d959b75a218d8c2c4f3 (MD5); Made available in DSpace on 2022-04-01T07:33:14Z (GMT). No. of bitstreams: 1 ijimai_6_3_4.pdf: 1512817 bytes, checksum: 6c6412d5010d5d959b75a218d8c2c4f3 (MD5)

Triana Casallas, Jenny Alexandra Cueva-Lovelle, Juan Manuel Rodríguez Molano, José Ignacio https://reunir.unir.net/handle/123456789/12777 2022-03-31T12:31:30Z

Smart Contracts with Blockchain in the Public Sector Triana Casallas, Jenny Alexandra; Cueva-Lovelle, Juan Manuel; Rodríguez Molano, José Ignacio The appearance of so-called block chains or Blockchain with the promise of transforming trust and the way value is exchanged, joins the expansion of the technological capabilities of organizations to achieve higher levels of productivity and innovation. This is how Blockchain-based techniques are being applied to many fields, focusing in this article on the public sector, as a possible solution to the demands for transparency, participation and citizen cooperation that society demands; due to the possibility of disintermediation based on automated transactions and on the responsibility and security in the management of official blockchain records. This could obstruct corruption and make government services more transparent and efficient. Although, it investigates about applications in the public sector under the Blockchain system, such as transactions, agreements, property registries and innovations, developments and other assets; Special emphasis is placed on the possibility of implementing Smart Contracts (mechanisms that aim to eliminate intermediaries to simplify processes) in public procurement procedures, given that it is in this type of activity where high levels of corruption are generated. It is concluded then that Europe has the largest number of blockchain initiatives worldwide, while Latin America, except for the case of Peru, lacks this type of applications, being this continent exactly where there are the countries with the highest levels of corruption. It concludes with a recommendation to use blockchain along with smart contracts through platforms such as Ethereum or Lisk, mainly given its flexibility and current development on topics with similar functionalities. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-31T12:31:30Z No. of bitstreams: 1 ijimai_6_3_8.pdf: 881822 bytes, checksum: 45fc900fa9d5b9959ed57b1094cf0f6f (MD5); Made available in DSpace on 2022-03-31T12:31:30Z (GMT). No. of bitstreams: 1 ijimai_6_3_8.pdf: 881822 bytes, checksum: 45fc900fa9d5b9959ed57b1094cf0f6f (MD5)

Jennath, H. S. Anoop, V S Asharaf, S https://reunir.unir.net/handle/123456789/12763 2022-03-30T10:09:51Z

Blockchain for Healthcare: Securing Patient Data and Enabling Trusted Artificial Intelligence Jennath, H. S.; Anoop, V S; Asharaf, S Advances in information technology are digitizing the healthcare domain with the aim of improved medical services, diagnostics, continuous monitoring using wearables, etc., at reduced costs. This digitization improves the ease of computation, storage and access of medical records which enables better treatment experiences for patients. However, it comes with a risk of cyber attacks and security and privacy concerns on this digital data. In this work, we propose a Blockchain based solution for healthcare records to address the security and privacy concerns which are currently not present in existing e-Health systems. This work also explores the potential of building trusted Artificial Intelligence models over Blockchain in e-Health, where a transparent platform for consent-based data sharing is designed. Provenance of the consent of individuals and traceability of data sources used for building and training the AI model is captured in an immutable distributed data store. The audit trail of the data access captured using Blockchain provides the data owner to understand the exposure of the data. It also helps the user to understand the revenue models that could be built on top of this framework for commercial data sharing to build trusted AI models. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-30T10:09:51Z No. of bitstreams: 1 ijimai_6_3_2.pdf: 897690 bytes, checksum: 94df0f314329e49d43e51a06d8407c92 (MD5); Made available in DSpace on 2022-03-30T10:09:51Z (GMT). No. of bitstreams: 1 ijimai_6_3_2.pdf: 897690 bytes, checksum: 94df0f314329e49d43e51a06d8407c92 (MD5)

Jurado, Francisco Delgado, Oscar Ortigosa, Álvaro https://reunir.unir.net/handle/123456789/12762 2022-03-30T09:45:47Z

Tracking News Stories Using Blockchain to Guarantee their Traceability and Information Analysis Jurado, Francisco; Delgado, Oscar; Ortigosa, Álvaro Nowadays, having a mechanism to guarantee the traceability of the information and to monitor the evolution of the news from its origin, and having elements to know the reputation and credibility of the media, analyze the news as well as its evolution and possible manipulation, etc. is becoming increasingly significant. Transparency in journalism is currently a key element in performing serious and rigorous journalism. End-users and fact-checking agencies need to be able to check and verify the information published in different media. This transparency principle enables the tracking of news stories and allows direct access to the source of essential content to contrast the information it contains and to know whether it has been manipulated. Additionally, the traceability of news constitutes another instrument in the fight against the lack of credibility, the manipulation of information, misinformation campaigns and the propagation of fake news. This article aims to show how to use Blockchain to facilitate the tracking and traceability of news so that it can provide support to the automatic indexing and extraction of relevant information from newspaper articles to facilitate the monitoring of the news story and allows users to verify the veracity of what they are reading. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-30T09:45:47Z No. of bitstreams: 1 ijimai_6_3_5.pdf: 1192296 bytes, checksum: c9b57310b6c1319658160073c28c039b (MD5); Made available in DSpace on 2022-03-30T09:45:47Z (GMT). No. of bitstreams: 1 ijimai_6_3_5.pdf: 1192296 bytes, checksum: c9b57310b6c1319658160073c28c039b (MD5)

Baldominos Gómez, Alejandro López-Sánchez, J. L. Acevedo-Aguilar, M. https://reunir.unir.net/handle/123456789/12761 2022-03-30T09:40:34Z

Blockverse: A Cloud Blockchain-based Platform for Tracking in Affiliate Systems Baldominos Gómez, Alejandro; López-Sánchez, J. L.; Acevedo-Aguilar, M. Affiliate systems are a crucial piece of today’s online advertising. In affiliate systems, web traffic is directed from certain sites displaying ads to the websites of those company whose products or services are advertised. The way in which these ads are monetized is diverse and can respond to different models. In many cases, affiliates establish a cost based on impressions (displays of the ad) or on clicks. However, more intricate models are becoming widespread, such as the cost per action, where the affiliate incomes are due to the users performing certain actions in the target website. In particular, in the world of iGaming, it is frequent that affiliates charges are based on registrations, deposits or money lost on bets. In this scenario, Blockverse is a tool whose objective is to record transactions occurring in affiliate systems at large scale, using a permissioned blockchain implemented atop state-of-the-art cloud technology. Additionally, the system will be able to execute smart deals that generate income for affiliates based on the agreed conditions, and to provide real-time analytics in the context of the affiliate system. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-30T09:40:34Z No. of bitstreams: 1 ijimai_6_3_3.pdf: 1247230 bytes, checksum: ebfcf1ff751be66d4c81cdd1a227531d (MD5); Made available in DSpace on 2022-03-30T09:40:34Z (GMT). No. of bitstreams: 1 ijimai_6_3_3.pdf: 1247230 bytes, checksum: ebfcf1ff751be66d4c81cdd1a227531d (MD5)

Arjun, R Suprabha, K R https://reunir.unir.net/handle/123456789/12760 2022-03-30T09:24:44Z

Innovation and Challenges of Blockchain in Banking: A Scientometric View Arjun, R; Suprabha, K R Blockchain has been gaining focus in research and development for diverse industries in recent years. Nevertheless, innovations that impact to the banking nurture a potential for disruptive impact globally for economic reasons; however it has received less scholarly attention. Hence the effect of blockchain technologies on banking industry is systematically reviewed. The relevant literature is extracted from Scopus, Web of Science and bibliometric techniques are applied. While a bulk of earlier papers focuses only on bit coins, a broader framework is envisaged that synthesizes interdisciplinary thematic areas for advancement; hence novelty in current work. A few practical and theoretical implications for stakeholders in view of technology, law and management are discussed. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-30T09:24:44Z No. of bitstreams: 1 ijimai_6_3_1.pdf: 1058825 bytes, checksum: 4d30739e16aa26da9722d9b2b738e812 (MD5); Made available in DSpace on 2022-03-30T09:24:44Z (GMT). No. of bitstreams: 1 ijimai_6_3_1.pdf: 1058825 bytes, checksum: 4d30739e16aa26da9722d9b2b738e812 (MD5)

Verdú, Elena https://reunir.unir.net/handle/123456789/12758 2022-03-30T09:05:50Z

Editor's Note Verdú, Elena 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 on Artificial Intelligence (AI) tools or tools that use AI with interactive multimedia techniques. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-30T09:05:50Z No. of bitstreams: 1 ijimai_6_2_0_0.pdf: 218730 bytes, checksum: fb02c3bff097ce53b5a827ec0f0ad6e5 (MD5); Made available in DSpace on 2022-03-30T09:05:50Z (GMT). No. of bitstreams: 1 ijimai_6_2_0_0.pdf: 218730 bytes, checksum: fb02c3bff097ce53b5a827ec0f0ad6e5 (MD5)

García-Holgado, Alicia Marcos-Pablos, Samuel García-Peñalvo, Francisco https://reunir.unir.net/handle/123456789/12757 2022-03-30T09:02:48Z

Guidelines for performing Systematic Research Projects Reviews García-Holgado, Alicia; Marcos-Pablos, Samuel; García-Peñalvo, Francisco There are different methods and techniques to carry out systematic reviews in order to address a set of research questions or getting the state of the art of a particular topic, but there is no a method to carry out a systematic analysis of research projects not only based on scientific publications. The main challenge is the difference between research projects and scientific literature. Research projects are a collection of information in different formats and available in different places. Even projects from the same funding call follow a different structure in most of the cases, despite there were some requirements that they should meet at the end of the funding period. Furthermore, the sources in which the scientific literature is available provide metadata and powerful search tools, meanwhile most of the research projects are not stored in public and accessible databases, or the databases usually do not provide enough information and tools to conduct a systematic search. For this reason, this work provides the guidelines to support systematics reviews of research projects following the method called Systematic Research Projects Review (SRPR). This methodology is based on the Kitchenham’s adaptation of the systematic literature review. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-30T09:02:48Z No. of bitstreams: 1 ijimai_6_2_14.pdf: 440071 bytes, checksum: a53edc965492366b973371efa1c5b57a (MD5); Made available in DSpace on 2022-03-30T09:02:48Z (GMT). No. of bitstreams: 1 ijimai_6_2_14.pdf: 440071 bytes, checksum: a53edc965492366b973371efa1c5b57a (MD5)

Villagrá-Arnedo, Carlos Gallego-Durán, Francisco Llorens-Largo, Faraón Satorre-Cuerda, Rosana Compañ-Rosique, Patricia Molina-Carmona, Rafael https://reunir.unir.net/handle/123456789/12756 2022-03-30T08:55:35Z

Time-Dependent Performance Prediction System for Early Insight in Learning Trends Villagrá-Arnedo, Carlos; Gallego-Durán, Francisco; Llorens-Largo, Faraón; Satorre-Cuerda, Rosana; Compañ-Rosique, Patricia; Molina-Carmona, Rafael Performance prediction systems allow knowing the learning status of students during a term and produce estimations on future status, what is invaluable information for teachers. The majority of current systems statically classify students once in time and show results in simple visual modes. This paper presents an innovative system with progressive, time-dependent and probabilistic performance predictions. The system produces by-weekly probabilistic classifications of students in three groups: high, medium or low performance. The system is empirically tested and data is gathered, analysed and presented. Predictions are shown as point graphs over time, along with calculated learning trends. Summary blocks are with latest predictions and trends are also provided for teacher efficiency. Moreover, some methods for selecting best moments for teacher intervention are derived from predictions. Evidence gathered shows potential to give teachers insights on students' learning trends, early diagnose learning status and selecting best moment for intervention. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-30T08:55:35Z No. of bitstreams: 1 ijimai_6_2_12.pdf: 1394113 bytes, checksum: cb7d0a7cbf4cf8d8122808ff1f837de4 (MD5); Made available in DSpace on 2022-03-30T08:55:35Z (GMT). No. of bitstreams: 1 ijimai_6_2_12.pdf: 1394113 bytes, checksum: cb7d0a7cbf4cf8d8122808ff1f837de4 (MD5)

Rathore, Pramod Singh Kumar, Abhishek García-Díaz, Vicente https://reunir.unir.net/handle/123456789/12755 2022-03-30T08:31:00Z

A Holistic Methodology for Improved RFID Network Lifetime by Advanced Cluster Head Selection using Dragonfly Algorithm Rathore, Pramod Singh; Kumar, Abhishek; García-Díaz, Vicente Radio Frequency Identification (RFID) networks usually require many tags along with readers and computation facilities. Those networks have limitations with respect to computing power and energy consumption. Thus, for saving energy and to make the best use of the resources, networks should operate and be able to recover in an efficient way. This will also reduce the energy expenditure of RFID readers. In this work, the RFID network life span will be enlarged through an energy-efficient cluster-based protocol used together with the Dragonfly algorithm. There are two stages in the processing of the clustering system: the cluster formation from the whole structure and the election of a cluster leader. After completing those procedures, the cluster leader controls the other nodes that are not leaders. The system works with a large energy node that provides an amount of energy while transmitting aggregated data near a base station. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-30T08:31:00Z No. of bitstreams: 1 ijimai_6_2_6.pdf: 599844 bytes, checksum: f53bc1f2b8cd1e0072373f85570ad7cf (MD5); Made available in DSpace on 2022-03-30T08:31:00Z (GMT). No. of bitstreams: 1 ijimai_6_2_6.pdf: 599844 bytes, checksum: f53bc1f2b8cd1e0072373f85570ad7cf (MD5)

Fyad, Houda Barigou, Fatiha Bouamrane, Karim https://reunir.unir.net/handle/123456789/12752 2022-03-29T12:25:31Z

An Experimental Study on Microarray Expression Data from Plants under Salt Stress by using Clustering Methods Fyad, Houda; Barigou, Fatiha; Bouamrane, Karim Current Genome-wide advancements in Gene chips technology provide in the “Omics (genomics, proteomics and transcriptomics) research”, an opportunity to analyze the expression levels of thousand of genes across multiple experiments. In this regard, many machine learning approaches were proposed to deal with this deluge of information. Clustering methods are one of these approaches. Their process consists of grouping data (gene profiles) into homogeneous clusters using distance measurements. Various clustering techniques are applied, but there is no consensus for the best one. In this context, a comparison of seven clustering algorithms was performed and tested against the gene expression datasets of three model plants under salt stress. These techniques are evaluated by internal and relative validity measures. It appears that the AGNES algorithm is the best one for internal validity measures for the three plant datasets. Also, K-Means profiles a trend for relative validity measures for these datasets. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-29T12:25:31Z No. of bitstreams: 1 ijimai_6_2_5.pdf: 436078 bytes, checksum: f887b8f6a1bb40e3b530450ae5972038 (MD5); Made available in DSpace on 2022-03-29T12:25:31Z (GMT). No. of bitstreams: 1 ijimai_6_2_5.pdf: 436078 bytes, checksum: f887b8f6a1bb40e3b530450ae5972038 (MD5)

Huang, Wenlin Wu, Qun Dey, Nilanjan Ashour, Amira Fong, Simon James González-Crespo, Rubén https://reunir.unir.net/handle/123456789/12751 2024-08-21T09:31:48Z

Adjectives Grouping in a Dimensionality Affective Clustering Model for Fuzzy Perceptual Evaluation Huang, Wenlin; Wu, Qun; Dey, Nilanjan; Ashour, Amira; Fong, Simon James; González-Crespo, Rubén More and more products are no longer limited to the satisfaction of the basic needs, but reflect the emotional interaction between people and environment. The characteristics of user emotions and their evaluation scales are relatively simple. This paper proposes a three-dimensional space model valence-arousal-dominance (VAD) based on the theory of psychological dimensional emotions. It studies the clustering and evaluation of emotional phrases, called VAdC (VAD-dimensional clustering), which is a kind of the affective computing technology. Firstly, a Gaussian Mixture Model (GMM) based information presentation system was introduced, including the type of the presentation, such as single point, plain, and sphere. Subsequently, the border of the presentation was defined. To increase the ability of the proposed algorithm to handle a high dimensional affective space, the distance and inference mechanics were addressed to avoid lacking of local measurement by using fuzzy perceptual evaluation. By comparing the performance of the proposed method with fuzzy c-mean (FCM), k-mean, hard -c-mean (HCM), extra fuzzy c-mean (EFCM), the proposed VADdC performs high effectiveness in fitness, inter-distance, intra-distance, and accuracy. The results were based on the dataset created from a questionnaire on products of the Ming style chairs online evaluation system. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-29T12:19:04Z No. of bitstreams: 1 ijimai_6_2_4.pdf: 1578366 bytes, checksum: b6f221007c63f054582f09f1b62d94a5 (MD5); Made available in DSpace on 2022-03-29T12:19:04Z (GMT). No. of bitstreams: 1 ijimai_6_2_4.pdf: 1578366 bytes, checksum: b6f221007c63f054582f09f1b62d94a5 (MD5)

Rios-Aguilar, Sergio Sarría, Íñigo Beltrán Pardo, Marta https://reunir.unir.net/handle/123456789/12750 2026-03-23T16:40:32Z

NFC and VLC based Mobile Business Information System for Registering Class Attendance Rios-Aguilar, Sergio; Sarría, Íñigo; Beltrán Pardo, Marta This work proposes a Mobile Information System for class attendance control using Visible Light Communications (VLC), and the students’ own mobile devices for automatic clocking in and clocking out. The proposed information system includes (a) VLC physical infrastructure, (b) native Android and iOS apps for the students, and (c) a web application for classroom attendance management. A proof of concept has been developed, setting up a testbed representing a real-world classroom environment for experimentation, using two VLC-enabled LED lighting sources. After three rounds of testing (n=225) under different conditions, it has been concluded that the system is viable and shows consistent positive detections when the smartphones are on the classroom desk within non-overlapped areas of the light circles generated by the LED lighting sources on the table surface. The performed tests also show that if mobile devices are placed within those overlapping areas, the likelihood of a detection error could increase up to nearly 10%, due to multipath effects, and actions can be taken should it happen. Finally, it has to be highlighted that the proposed autonomous class attendance system allows lecturers to focus on making the most of their time in class, transferring knowledge instead of spending time in attendance management task. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-29T11:43:05Z No. of bitstreams: 1 ijimai_6_2_8.pdf: 453041 bytes, checksum: 89edf5d7abd49f4725ef9b1d6e30995a (MD5); Made available in DSpace on 2022-03-29T11:43:05Z (GMT). No. of bitstreams: 1 ijimai_6_2_8.pdf: 453041 bytes, checksum: 89edf5d7abd49f4725ef9b1d6e30995a (MD5)

Saiz, Fátima Barandiaran, Iñigo https://reunir.unir.net/handle/123456789/12749 2022-03-29T11:32:54Z

COVID-19 Detection in Chest X-ray Images using a Deep Learning Approach Saiz, Fátima; Barandiaran, Iñigo The Corona Virus Disease (COVID-19) is an infectious disease caused by a new virus that has not been detected in humans before. The virus causes a respiratory illness like the flu with various symptoms such as cough or fever that, in severe cases, may cause pneumonia. The COVID-19 spreads so quickly between people, affecting to 1,200,000 people worldwide at the time of writing this paper (April 2020). Due to the number of contagious and deaths are continually growing day by day, the aim of this study is to develop a quick method to detect COVID-19 in chest X-ray images using deep learning techniques. For this purpose, an object detection architecture is proposed, trained and tested with a public available dataset composed with 1500 images of non-infected patients and infected with COVID-19 and pneumonia. The main goal of our method is to classify the patient status either negative or positive COVID-19 case. In our experiments using SDD300 model we achieve a 94.92% of sensibility and 92.00% of specificity in COVID-19 detection, demonstrating the usefulness application of deep learning models to classify COVID-19 in X-ray images. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-29T11:32:54Z No. of bitstreams: 1 ijimai_6_2_2.pdf: 562218 bytes, checksum: b0cd720d8a9ec1a16263f8044cd49428 (MD5); Made available in DSpace on 2022-03-29T11:32:54Z (GMT). No. of bitstreams: 1 ijimai_6_2_2.pdf: 562218 bytes, checksum: b0cd720d8a9ec1a16263f8044cd49428 (MD5)

Verma, Kamal Kant Singh, Brij Mohan Mandoria, H L Chauhan, Prachi https://reunir.unir.net/handle/123456789/12733 2022-03-28T09:36:45Z

Two-Stage Human Activity Recognition Using 2D-ConvNet Verma, Kamal Kant; Singh, Brij Mohan; Mandoria, H L; Chauhan, Prachi There is huge requirement of continuous intelligent monitoring system for human activity recognition in various domains like public places, automated teller machines or healthcare sector. Increasing demand of automatic recognition of human activity in these sectors and need to reduce the cost involved in manual surveillance have motivated the research community towards deep learning techniques so that a smart monitoring system for recognition of human activities can be designed and developed. Because of low cost, high resolution and ease of availability of surveillance cameras, the authors developed a new two-stage intelligent framework for detection and recognition of human activity types inside the premises. This paper, introduces a novel framework to recognize single-limb and multi-limb human activities using a Convolution Neural Network. In the first phase single-limb and multi-limb activities are separated. Next, these separated single and multi-limb activities have been recognized using sequence-classification. For training and validation of our framework we have used the UTKinect-Action Dataset having 199 actions sequences performed by 10 users. We have achieved an overall accuracy of 97.88% in real-time recognition of the activity sequences. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-28T09:36:45Z No. of bitstreams: 1 ijimai_6_2_13.pdf: 1246366 bytes, checksum: 03e24ca5fdcf5ed6e210eb3694602aa7 (MD5); Made available in DSpace on 2022-03-28T09:36:45Z (GMT). No. of bitstreams: 1 ijimai_6_2_13.pdf: 1246366 bytes, checksum: 03e24ca5fdcf5ed6e210eb3694602aa7 (MD5)

Dur-e-Ahmad, Muhammad Imran, Mudassar https://reunir.unir.net/handle/123456789/12732 2022-03-28T09:19:04Z

Transmission Dynamics Model of Coronavirus COVID-19 for the Outbreak in Most Affected Countries of the World Dur-e-Ahmad, Muhammad; Imran, Mudassar The wide spread of coronavirus (COVID-19) has threatened millions of lives and damaged the economy worldwide. Due to the severity and damage caused by the disease, it is very important to fore-tell the epidemic lifetime in order to take timely actions. Unfortunately, the lack of accurate information and unavailability of large amount of data at this stage make the task more difficult. In this paper, we used the available data from the mostly affected countries by COVID-19, (China, Iran, South Korea and Italy) and fit this with the SEIR type model in order to estimate the basic reproduction number R_0. We also discussed the development trend of the disease. Our model is quite accurate in predicting the current pattern of the infected population. We also performed sensitivity analysis on all the parameters used that are affecting the value of R0. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-28T09:19:04Z No. of bitstreams: 1 ijimai_6_2_1.pdf: 642181 bytes, checksum: 767b7c1683e6d15fc221c4904e39ffd5 (MD5); Made available in DSpace on 2022-03-28T09:19:04Z (GMT). No. of bitstreams: 1 ijimai_6_2_1.pdf: 642181 bytes, checksum: 767b7c1683e6d15fc221c4904e39ffd5 (MD5)

Kamel, Salah Jurado, Francisco Sultan, Hamdy Menesy, Ahmed https://reunir.unir.net/handle/123456789/12731 2022-03-28T09:00:58Z

Tree Growth Algorithm for Parameter Identification of Proton Exchange Membrane Fuel Cell Models Kamel, Salah; Jurado, Francisco; Sultan, Hamdy; Menesy, Ahmed Demonstrating an accurate mathematical model is a mandatory issue for realistic simulation, optimization and performance evaluation of proton exchange membrane fuel cells (PEMFCs). The main goal of this study is to demonstrate a precise mathematical model of PEMFCs through estimating the optimal values of the unknown parameters of these cells. In this paper, an efficient optimization technique, namely, Tree Growth Algorithm (TGA) is applied for extracting the optimal parameters of different PEMFC stacks. The total of the squared deviations (TSD) between the experimentally measured data and the estimated ones is adopted as the objective function. The effectiveness of the developed parameter identification algorithm is validated through four case studies of commercial PEMFC stacks under various operating conditions. Moreover, comprehensive comparisons with other optimization algorithms under the same study cases are demonstrated. Statistical analysis is presented to evaluate the accuracy and reliability of the developed algorithm in solving the studied optimization problem. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-28T09:00:58Z No. of bitstreams: 1 ijimai_6_2_11.pdf: 1414303 bytes, checksum: 346adb416c4a4a7d1eacf7846db92438 (MD5); Made available in DSpace on 2022-03-28T09:00:58Z (GMT). No. of bitstreams: 1 ijimai_6_2_11.pdf: 1414303 bytes, checksum: 346adb416c4a4a7d1eacf7846db92438 (MD5)

Bobadilla, Jesús Gutiérrez, Abraham Alonso, Santiago Hurtado, Remigio https://reunir.unir.net/handle/123456789/12730 2022-03-28T08:37:43Z

A Collaborative Filtering Probabilistic Approach for Recommendation to Large Homogeneous and Automatically Detected Groups Bobadilla, Jesús; Gutiérrez, Abraham; Alonso, Santiago; Hurtado, Remigio In the collaborative filtering recommender systems (CFRS) field, recommendation to group of users is mainly focused on stablished, occasional or random groups. These groups have a little number of users: relatives, friends, colleagues, etc. Our proposal deals with large numbers of automatically detected groups. Marketing and electronic commerce are typical targets of large homogenous groups. Large groups present a major difficulty in terms of automatically achieving homogeneity, equilibrated size and accurate recommendations. We provide a method that combines diverse machine learning algorithms in an original way: homogeneous groups are detected by means of a clustering based on hidden factors instead of ratings. Predictions are made using a virtual user model, and virtual users are obtained by performing a hidden factors aggregation. Additionally, this paper selects the most appropriate dimensionality reduction for the explained RS aim. We conduct a set of experiments to catch the maximum cumulative deviation of the ratings information. Results show an improvement on recommendations made to large homogeneous groups. It is also shown the desirability of designing specific methods and algorithms to deal with automatically detected groups. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-28T08:37:43Z No. of bitstreams: 1 ijimai_6_2_10.pdf: 1543399 bytes, checksum: 2cb0399275af9245af7cd3074d62a74a (MD5); Made available in DSpace on 2022-03-28T08:37:43Z (GMT). No. of bitstreams: 1 ijimai_6_2_10.pdf: 1543399 bytes, checksum: 2cb0399275af9245af7cd3074d62a74a (MD5)

Núñez-Valdez, Edward Solanki, Vijender Kumar Balakrishna, Sivadi Thirumaran, M https://reunir.unir.net/handle/123456789/12729 2022-03-28T08:10:35Z

Incremental Hierarchical Clustering driven Automatic Annotations for Unifying IoT Streaming Data Núñez-Valdez, Edward; Solanki, Vijender Kumar; Balakrishna, Sivadi; Thirumaran, M In the Internet of Things (IoT), Cyber-Physical Systems (CPS), and sensor technologies huge and variety of streaming sensor data is generated. The unification of streaming sensor data is a challenging problem. Moreover, the huge amount of raw data has implied the insufficiency of manual and semi-automatic annotation and leads to an increase of the research of automatic semantic annotation. However, many of the existing semantic annotation mechanisms require many joint conditions that could generate redundant processing of transitional results for annotating the sensor data using SPARQL queries. In this paper, we present an Incremental Clustering Driven Automatic Annotation for IoT Streaming Data (IHC-AA-IoTSD) using SPARQL to improve the annotation efficiency. The processes and corresponding algorithms of the incremental hierarchical clustering driven automatic annotation mechanism are presented in detail, including data classification, incremental hierarchical clustering, querying the extracted data, semantic data annotation, and semantic data integration. The IHCAA-IoTSD has been implemented and experimented on three healthcare datasets and compared with leading approaches namely- Agent-based Text Labelling and Automatic Selection (ATLAS), Fuzzy-based Automatic Semantic Annotation Method (FBASAM), and an Ontology-based Semantic Annotation Approach (OBSAA), yielding encouraging results with Accuracy of 86.67%, Precision of 87.36%, Recall of 85.48%, and F-score of 85.92% at 100k triple data. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-28T08:10:35Z No. of bitstreams: 1 ijimai_6_2_7_0.pdf: 1930171 bytes, checksum: fd01fa306746a128013500d6eadbf064 (MD5); Made available in DSpace on 2022-03-28T08:10:35Z (GMT). No. of bitstreams: 1 ijimai_6_2_7_0.pdf: 1930171 bytes, checksum: fd01fa306746a128013500d6eadbf064 (MD5)

Shikha, B Gitanjali, P Kumar, D. Pawan https://reunir.unir.net/handle/123456789/12728 2022-03-28T08:04:31Z

An Extreme Learning Machine-Relevance Feedback Framework for Enhancing the Accuracy of a Hybrid Image Retrieval System Shikha, B; Gitanjali, P; Kumar, D. Pawan The process of searching, indexing and retrieving images from a massive database is a challenging task and the solution to these problems is an efficient image retrieval system. In this paper, a unique hybrid Content-based image retrieval system is proposed where different attributes of an image like texture, color and shape are extracted by using Gray level co-occurrence matrix (GLCM), color moment and various region props procedure respectively. A hybrid feature matrix or vector (HFV) is formed by an integration of feature vectors belonging to three individual visual attributes. This HFV is given as an input to an Extreme learning machine (ELM) classifier which is based on a solitary hidden layer of neurons and also is a type of feed-forward neural system. ELM performs efficient class prediction of the query image based on the pre-trained data. Lastly, to capture the high level human semantic information, Relevance feedback (RF) is utilized to retrain or reformulate the training of ELM. The advantage of the proposed system is that a combination of an ELM-RF framework leads to an evolution of a modified learning and intelligent classification system. To measure the efficiency of the proposed system, various parameters like Precision, Recall and Accuracy are evaluated. Average precision of 93.05%, 81.03%, 75.8% and 90.14% is obtained respectively on Corel-1K, Corel-5K, Corel-10K and GHIM-10 benchmark datasets. The experimental analysis portrays that the implemented technique outmatches many state-of-the-art related approaches depicting varied hybrid CBIR system. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-28T08:04:31Z No. of bitstreams: 1 ijimai_6_2_3.pdf: 1610842 bytes, checksum: 966a7ce3d029e4a6814811094f4f3b41 (MD5); Made available in DSpace on 2022-03-28T08:04:31Z (GMT). No. of bitstreams: 1 ijimai_6_2_3.pdf: 1610842 bytes, checksum: 966a7ce3d029e4a6814811094f4f3b41 (MD5)

Saleem, Nasir Khattak, Muhammad Irfan Verdú, Elena https://reunir.unir.net/handle/123456789/12727 2022-05-19T06:46:13Z

On Improvement of Speech Intelligibility and Quality: A Survey of Unsupervised Single Channel Speech Enhancement Algorithms Saleem, Nasir; Khattak, Muhammad Irfan; Verdú, Elena Many forms of human communication exist; for instance, text and nonverbal based. Speech is, however, the most powerful and dexterous form for the humans. Speech signals enable humans to communicate and this usefulness of the speech signals has led to a variety of speech processing applications. Successful use of these applications is, however, significantly aggravated in presence of the background noise distortions. These noise signals overlap and mask the target speech signals. To deal with these overlapping background noise distortions, a speech enhancement algorithm at front end is crucial in order to make noisy speech intelligible and pleasant. Speech enhancement has become a very important research and engineering problem for the last couple of decades. In this paper, we present an all-inclusive survey on unsupervised single-channel speech enhancement (U-SCSE) algorithms. A taxonomy based review of the U-SCSE algorithms is presented and the associated studies regarding improving the intelligibility and quality are outlined. The studies on the speech enhancement algorithms in unsupervised perspective are presented. Objective experiments have been performed to evaluate the potential of the U-SCSE algorithms in terms of improving the speech intelligibility and quality. It is found that unsupervised speech enhancement improves the speech quality but the speech intelligibility improvement is deprived. To finish, several research problems are identified that require further research. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-28T07:57:47Z No. of bitstreams: 1 ijimai_6_2_9.pdf: 775025 bytes, checksum: 8c9cc953150755cb001aceebac2501f5 (MD5); Made available in DSpace on 2022-03-28T07:57:47Z (GMT). No. of bitstreams: 1 ijimai_6_2_9.pdf: 775025 bytes, checksum: 8c9cc953150755cb001aceebac2501f5 (MD5)

Devi, Salam Shuleenda Laskar, Rabul Hussain Singh, Ngangbam Herojit https://reunir.unir.net/handle/123456789/12717 2022-03-24T13:34:44Z

Fuzzy C-Means Clustering with Histogram based Cluster Selection for Skin Lesion Segmentation using Non-Dermoscopic Images Devi, Salam Shuleenda; Laskar, Rabul Hussain; Singh, Ngangbam Herojit Purpose – Pre-screening of skin lesion for malignancy is highly demanded as melanoma being a life-threatening skin cancer due to unpaired DNA damage. In this paper, lesion segmentation based on Fuzzy C-Means clustering using non-dermoscopic images has been proposed. Design/methodology/approach – The proposed methodology consists of automatic cluster selection for FCM using the histogram property. The system used the local maxima along with Euclidean distance to detect the binomial distribution property of the image histogram, to segment the melanoma from normal skin. As the Value channel of HSV color image provides better and distinct histogram distribution based on the entropy, it has been used for segmentation purpose. Findings – The proposed system can effectively segment the lesion region from the normal skin. The system provides a segmentation accuracy of 95.69 % and the comparative analysis has been performed with various segmentation methods. From the analysis, it has been observed that the proposed system can effectively segment the lesion region from normal skin automatically. Originality/Value – This paper suggests a new approach for skin lesion segmentation based on FCM with automatic cluster selection. Here, different color channel has also been analyzed using entropy to select the better channel for segmentation. In future, the classification of melanoma from benign naevi can be performed. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-24T13:34:44Z No. of bitstreams: 1 ijimai20206_1_3_pdf_17885.pdf: 1265459 bytes, checksum: 62187387480274425fa7ca793d82bbb9 (MD5); Made available in DSpace on 2022-03-24T13:34:44Z (GMT). No. of bitstreams: 1 ijimai20206_1_3_pdf_17885.pdf: 1265459 bytes, checksum: 62187387480274425fa7ca793d82bbb9 (MD5)

Dey, Nilanjan Wu, Yao Wu, Qun Sherratt, Simon https://reunir.unir.net/handle/123456789/12716 2022-03-24T13:07:50Z

Learning Models for Semantic Classification of Insufficient Plantar Pressure Images Dey, Nilanjan; Wu, Yao; Wu, Qun; Sherratt, Simon Establishing a reliable and stable model to predict a target by using insufficient labeled samples is feasible and effective, particularly, for a sensor-generated data-set. This paper has been inspired with insufficient data-set learning algorithms, such as metric-based, prototype networks and meta-learning, and therefore we propose an insufficient data-set transfer model learning method. Firstly, two basic models for transfer learning are introduced. A classification system and calculation criteria are then subsequently introduced. Secondly, a dataset of plantar pressure for comfort shoe design is acquired and preprocessed through foot scan system; and by using a pre-trained convolution neural network employing AlexNet and convolution neural network (CNN)- based transfer modeling, the classification accuracy of the plantar pressure images is over 93.5%. Finally, the proposed method has been compared to the current classifiers VGG, ResNet, AlexNet and pre-trained CNN. Also, our work is compared with known-scaling and shifting (SS) and unknown-plain slot (PS) partition methods on the public test databases: SUN, CUB, AWA1, AWA2, and aPY with indices of precision (tr, ts, H) and time (training and evaluation). The proposed method for the plantar pressure classification task shows high performance in most indices when comparing with other methods. The transfer learning-based method can be applied to other insufficient data-sets of sensor imaging fields. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-24T13:07:50Z No. of bitstreams: 1 ijimai20206_1_6_pdf_49479.pdf: 1043257 bytes, checksum: c2abae0a912570173755f564dba3b789 (MD5); Made available in DSpace on 2022-03-24T13:07:50Z (GMT). No. of bitstreams: 1 ijimai20206_1_6_pdf_49479.pdf: 1043257 bytes, checksum: c2abae0a912570173755f564dba3b789 (MD5)

Bobadilla, Jesús Ortega, Fernando Gutiérrez, Abraham Alonso, Santiago https://reunir.unir.net/handle/123456789/12715 2022-03-24T12:48:31Z

Classification-based Deep Neural Network Architecture for Collaborative Filtering Recommender Systems Bobadilla, Jesús; Ortega, Fernando; Gutiérrez, Abraham; Alonso, Santiago This paper proposes a scalable and original classification-based deep neural architecture. Its collaborative filtering approach can be generalized to most of the existing recommender systems, since it just operates on the ratings dataset. The learning process is based on the binary relevant/non-relevant vote and the binary voted/non-voted item information. This data reduction provides a new level of abstraction and it makes possible to design the classification-based architecture. In addition to the original architecture, its prediction process has a novel approach: it does not need to make a large number of predictions to get recommendations. Instead to run forward the neural network for each prediction, our approach runs forward the neural network just once to get a set of probabilities in its categorical output layer. The proposed neural architecture has been tested by using the MovieLens and FilmTrust datasets. A state-of-the-art baseline that outperforms current competitive approaches has been used. Results show a competitive recommendation quality and an interesting quality improvement on large number of recommendations, consistent with the architecture design. The architecture originality makes it possible to address a broad range of future works. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-24T12:48:31Z No. of bitstreams: 1 ijimai20206_1_8_pdf_28842.pdf: 2786476 bytes, checksum: b9e4a8262fddfe10d36c1e971d60bd68 (MD5); Made available in DSpace on 2022-03-24T12:48:31Z (GMT). No. of bitstreams: 1 ijimai20206_1_8_pdf_28842.pdf: 2786476 bytes, checksum: b9e4a8262fddfe10d36c1e971d60bd68 (MD5)

Selim, Ali Kamel, Salah Jurado, Francisco Nasrat, Loai https://reunir.unir.net/handle/123456789/12714 2022-03-24T11:11:45Z

Voltage Stability Assessment of Radial Distribution Systems Including Optimal Allocation of Distributed Generators Selim, Ali; Kamel, Salah; Jurado, Francisco; Nasrat, Loai Assessment of power systems voltage stability is considered an important assignment for the operation and planning of power system. In this paper, a voltage stability study using Continuous Power Flow (CPF) is introduced to evaluate the impact of Distribution Generator (DG) on radial distribution systems. On the way to allocate the DG, a hybrid between the Voltage Stability Index (VSI) and Whale Optimization Algorithm (WOA) is developed. The main purpose of using VSI is to find the most sensitive buses for allocating the DG in the system. Hence, Fuzzy logic control with the Normalized VSI (NVSI) and the voltage magnitude at each bus are used to determine the candidate buses. However, the best DG size is calculated using WOA. Four standard radial distribution systems are used in this paper; 12, 33, 69, and 85-bus. The developed hybrid optimization method is compared with other existing analytical and metaheuristic optimization techniques to prove its efficiency. The results prove the ability of the developed method in the allocation of DG. In addition, the influence of the DG integration on enhancing the voltage stability through injecting the proper active and reactive powers is studied. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-24T11:11:45Z No. of bitstreams: 1 ijimai20206_1_4_pdf_13565.pdf: 1437028 bytes, checksum: 7532b8f58bfe4e38be53eab06767b5ca (MD5); Made available in DSpace on 2022-03-24T11:11:45Z (GMT). No. of bitstreams: 1 ijimai20206_1_4_pdf_13565.pdf: 1437028 bytes, checksum: 7532b8f58bfe4e38be53eab06767b5ca (MD5)

Morente-Molinera, Juan Antonio https://reunir.unir.net/handle/123456789/12713 2022-03-24T10:37:50Z

Editor's Note Morente-Molinera, Juan Antonio Soft Computing is an AI branch that focuses on solving problems that have incomplete, inexact or fuzzy information. In other words, Soft Computing area includes algorithms and methods that are typically used when the imprecision or lack of the dealt data make other type of methods to become useless. Deep Learning, Machine learning and Fuzzy Systems related methods have achieved really good results even when the available data is not as good as desired. This success has converted the Soft Computing area in one of the most important ones inside the AI field. This special issue’s goal is to reunite some of the most recent research on the Soft Computing area. The selected research covers different aspects and problems on the AI area in an effort to provide a clear overview of the state of the art on the topic. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-24T10:37:50Z No. of bitstreams: 0; Made available in DSpace on 2022-03-24T10:37:50Z (GMT). No. of bitstreams: 0

González-Crespo, Rubén Herrera-Viedma, Enrique Dey, Nilanjan Fong, Simon James Li, Gloria https://reunir.unir.net/handle/123456789/12712 2022-03-24T10:21:50Z

Finding an Accurate Early Forecasting Model from Small Dataset: A Case of 2019-nCoV Novel Coronavirus Outbreak González-Crespo, Rubén; Herrera-Viedma, Enrique; Dey, Nilanjan; Fong, Simon James; Li, Gloria Epidemic is a rapid and wide spread of infectious disease threatening many lives and economy damages. It is important to fore-tell the epidemic lifetime so to decide on timely and remedic actions. These measures include closing borders, schools, suspending community services and commuters. Resuming such curfews depends on the momentum of the outbreak and its rate of decay. Being able to accurately forecast the fate of an epidemic is an extremely important but difficult task. Due to limited knowledge of the novel disease, the high uncertainty involved and the complex societal-political factors that influence the widespread of the new virus, any forecast is anything but reliable. Another factor is the insufficient amount of available data. Data samples are often scarce when an epidemic just started. With only few training samples on hand, finding a forecasting model which offers forecast at the best efforts is a big challenge in machine learning. In the past, three popular methods have been proposed, they include 1) augmenting the existing little data, 2) using a panel selection to pick the best forecasting model from several models, and 3) fine-tuning the parameters of an individual forecasting model for the highest possible accuracy. In this paper, a methodology that embraces these three virtues of data mining from a small dataset is proposed. An experiment that is based on the recent coronavirus outbreak originated from Wuhan is conducted by applying this methodology. It is shown that an optimized forecasting model that is constructed from a new algorithm, namely polynomial neural network with corrective feedback (PNN+cf) is able to make a forecast that has relatively the lowest prediction error. The results showcase that the newly proposed methodology and PNN+cf are useful in generating acceptable forecast upon the critical time of disease outbreak when the samples are far from abundant. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-24T10:21:50Z No. of bitstreams: 1 ijimai20206_1_15_pdf_18033.pdf: 1038427 bytes, checksum: 72331956a944f7572b62fd73c1db177b (MD5); Made available in DSpace on 2022-03-24T10:21:50Z (GMT). No. of bitstreams: 1 ijimai20206_1_15_pdf_18033.pdf: 1038427 bytes, checksum: 72331956a944f7572b62fd73c1db177b (MD5)

Mohammadpoor, Mojtaba Nooghabi, Mohadese Gerami Ahmedi, Zahra https://reunir.unir.net/handle/123456789/12711 2022-03-24T10:15:16Z

An Intelligent Technique for Grape Fanleaf Virus Detection Mohammadpoor, Mojtaba; Nooghabi, Mohadese Gerami; Ahmedi, Zahra Grapevine Fanleaf Virus (GFLV) is one of the most important viral diseases of grapes, which can damage up to 85% of the crop, if not treated at the right time. The aim of this study is to identify infected leaves with GFLV using artificial intelligent methods using an accessible database. To do this, some pictures are taken from infected and healthy leaves of grapes and labeled by technical specialists using conventional laboratory methods. In order to provide an intelligent method for distinguishing infected leaves from healthy ones, the area of unhealthy parts of each leaf is highlighted using Fuzzy C-mean Algorithm (FCM), and then the percentages of the first two segments area are fed to a Support Vector Machines (SVM). To increase the diagnostic reliability of the system, K-fold cross validation method with k = 3 and k =5 is applied. After applying the proposed method over all images using K-fold validation technique, average confusion matrix is extracted to show the True Positive, True Negative, False Positive and False Negative percentages of classification. The results show that specificity, as the ability of the algorithm to really detect healthy images, is 100%, and sensitivity, as the ability of the algorithm to correctly detect infected images is around 97.3%. The average accuracy of the system is around 98.6%. The results imply the ability of the proposed method compared to previous methods. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-24T10:15:16Z No. of bitstreams: 1 ijimai20206_1_7_pdf_85267.pdf: 775171 bytes, checksum: f558ff64eeb7c4e5b697209e58a9f338 (MD5); Made available in DSpace on 2022-03-24T10:15:16Z (GMT). No. of bitstreams: 1 ijimai20206_1_7_pdf_85267.pdf: 775171 bytes, checksum: f558ff64eeb7c4e5b697209e58a9f338 (MD5)

Kumar, Sumit Kumar-Solanki, Vijender Kumar Choudhary, Saket Selamat, Ali González-Crespo, Rubén https://reunir.unir.net/handle/123456789/12710 2022-03-24T09:55:24Z

Comparative Study on Ant Colony Optimization (ACO) and K-Means Clustering Approaches for Jobs Scheduling and Energy Optimization Model in Internet of Things (IoT) Kumar, Sumit; Kumar-Solanki, Vijender; Kumar Choudhary, Saket; Selamat, Ali; González-Crespo, Rubén The concept of Internet of Things (IoT) was proposed by Professor Kevin Ashton of the Massachusetts Institute of Technology (MIT) in 1999. IoT is an environment that people understand in many different ways depending on their requirement, point of view and purpose. When transmitting data in IoT environment, distribution of network traffic fluctuates frequently. If links of the network or nodes fail randomly, then automatically new nodes get added frequently. Heavy network traffic affects the response time of all system and it consumes more energy continuously. Minimization the network traffic/ by finding the shortest path from source to destination minimizes the response time of all system and also reduces the energy consumption cost. The ant colony optimization (ACO) and K-Means clustering algorithms characteristics conform to the auto-activator and optimistic response mechanism of the shortest route searching from source to destination. In this article, ACO and K-Means clustering algorithms are studied to search the shortest route path from source to destination by optimizing the Quality of Service (QoS) constraints. Resources are assumed in the active and varied IoT network atmosphere for these two algorithms. This work includes the study and comparison between ant colony optimization (ACO) and K-Means algorithms to plan a response time aware scheduling model for IoT. It is proposed to divide the IoT environment into various areas and a various number of clusters depending on the types of networks. It is noticed that this model is more efficient for the suggested routing algorithm in terms of response time, point-to-point delay, throughput and overhead of control bits. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-24T09:55:24Z No. of bitstreams: 1 ijimai20206_1_12_pdf_15248.pdf: 1138748 bytes, checksum: 3677e79d590223438312a4e59f5b9c40 (MD5); Made available in DSpace on 2022-03-24T09:55:24Z (GMT). No. of bitstreams: 1 ijimai20206_1_12_pdf_15248.pdf: 1138748 bytes, checksum: 3677e79d590223438312a4e59f5b9c40 (MD5)

Borhani, Mostafa Akbari, Kamal Matkan, Aliakbar Tanasan, Mohammad https://reunir.unir.net/handle/123456789/12709 2022-03-24T09:07:19Z

A Multicriteria Optimization for Flight Route Networks in Large-Scale Airlines Using Intelligent Spatial Information Borhani, Mostafa; Akbari, Kamal; Matkan, Aliakbar; Tanasan, Mohammad Air route network optimization, one of the airspace planning challenges, effectively manages airspace resources toward increasing airspace capacity and reducing air traffic congestion. In this paper, the structure of the flight network in air transport is analyzed with a multi-objective genetic algorithm regarding Geographic Information System (GIS) which is used to optimize this Iran airlines topology to reduce the number of airways and the aggregation of passengers in aviation industries organization and also to reduce changes in airways and the travel time for travelers. The proposed model of this study is based on the combination of two topologies – point-to-point and Hub-and-spoke – with multiple goals for causing a decrease in airways and travel length per passenger and also to reach the minimum number of air stops per passenger. The proposed Multi-objective Genetic Algorithm (MOGA) is tested and assessed in data of the Iran airlines industry in 2018, as an example to real-world applications, to design Iran airline topology. MOGA is proven to be effective in general to solve a network-wide flight trajectory planning. Using the combination of point-to-point and Hub-and-spoke topologies can improve the performance of the MOGA algorithm. Based on Iran airline traffic patterns in 2018, the proposed model successfully decreased 50.8% of air routes (184 air routes) compared to the current situations while the average travel length and the average changes in routes were increased up to 13.8% (about 100 kilometers) and up to 18%, respectively. The proposed algorithm also suggests that the current air routes of Iran can be decreased up to 24.7% (89 airways) if the travel length and the number of changes increase up to 4.5% (32 kilometers) and 5%, respectively. Two intermediate airports were supposed for these experiments. The computational results show the potential benefits of the proposed model and the advantage of the algorithm. The structure of the flight network in air transport can significantly reduce operational cost while ensuring the operation safety. According to the results, this intelligent multi-object optimization model would be able to be successfully used for a precise design and efficient optimization of existing and new airline topologies. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-24T09:07:19Z No. of bitstreams: 1 IJIMAI20206_1_14.pdf: 3851211 bytes, checksum: 94e85c4b574e6f1eb76e0df81d928791 (MD5); Made available in DSpace on 2022-03-24T09:07:19Z (GMT). No. of bitstreams: 1 IJIMAI20206_1_14.pdf: 3851211 bytes, checksum: 94e85c4b574e6f1eb76e0df81d928791 (MD5)

Harish, B S Nagadarshan, N Manju, N https://reunir.unir.net/handle/123456789/12696 2022-03-21T11:33:54Z

Multilayer Feedforward Neural Network for Internet Traffic Classification Harish, B S; Nagadarshan, N; Manju, N Recently, the efficient internet traffic classification has gained attention in order to improve service quality in IP networks. But the problem with the existing solutions is to handle the imbalanced dataset which has high uneven distribution of flows between the classes. In this paper, we propose a multilayer feedforward neural network architecture to handle the high imbalanced dataset. In the proposed model, we used a variation of multilayer perceptron with 4 hidden layers (called as mountain mirror networks) which does the feature transformation effectively. To check the efficacy of the proposed model, we used Cambridge dataset which consists of 248 features spread across 10 classes. Experimentation is carried out for two variants of the same dataset which is a standard one and a derived subset. The proposed model achieved an accuracy of 99.08% for highly imbalanced dataset (standard). Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-21T11:33:54Z No. of bitstreams: 1 ijimai20206_1_13_pdf_16647.pdf: 369125 bytes, checksum: 5d56354cb826788e282d3f6cb037a7be (MD5); Made available in DSpace on 2022-03-21T11:33:54Z (GMT). No. of bitstreams: 1 ijimai20206_1_13_pdf_16647.pdf: 369125 bytes, checksum: 5d56354cb826788e282d3f6cb037a7be (MD5)

Hans, Rahul Kaur, Harjot https://reunir.unir.net/handle/123456789/12695 2022-03-21T11:10:28Z

Binary Multi-Verse Optimization (BMVO) Approaches for Feature Selection Hans, Rahul; Kaur, Harjot Multi-Verse Optimization (MVO) is one of the newest meta-heuristic optimization algorithms which imitates the theory of Multi-Verse in Physics and resembles the interaction among the various universes. In problem domains like feature selection, the solutions are often constrained to the binary values viz. 0 and 1. With regard to this, in this paper, binary versions of MVO algorithm have been proposed with two prime aims: firstly, to remove redundant and irrelevant features from the dataset and secondly, to achieve better classification accuracy. The proposed binary versions use the concept of transformation functions for the mapping of a continuous version of the MVO algorithm to its binary versions. For carrying out the experiments, 21 diverse datasets have been used to compare the Binary MVO (BMVO) with some binary versions of existing metaheuristic algorithms. It has been observed that the proposed BMVO approaches have outperformed in terms of a number of features selected and the accuracy of the classification process. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-21T11:10:28Z No. of bitstreams: 1 ijimai20206_1_11_pdf_31520.pdf: 937506 bytes, checksum: 4883488ef6b19fedd05372ccf2eecd10 (MD5); Made available in DSpace on 2022-03-21T11:10:28Z (GMT). No. of bitstreams: 1 ijimai20206_1_11_pdf_31520.pdf: 937506 bytes, checksum: 4883488ef6b19fedd05372ccf2eecd10 (MD5)

Kumar, Naresh Sanjay, Ch. Chakravarthy, M https://reunir.unir.net/handle/123456789/12694 2022-03-21T10:44:28Z

Mamdani Fuzzy Expert System Based Directional Relaying Approach for Six-Phase Transmission Line Kumar, Naresh; Sanjay, Ch.; Chakravarthy, M Traditional directional relaying methods for 6-phase transmission lines have complex effort, and so there is still a need for novel direction relaying estimation scheme. This study presents a Mamdani-fuzzy expert system (MFES) approach for discriminating faulty section/zone, classifying faults and locating faults in 6-phase transmission lines. The 6-phase fundamental component of currents, voltages and phase angles are captured at single bus and are used in the protection scheme. Simulation results substantiate that the protection scheme is very successful against many parameters such as different fault types, fault resistances, transmission line fault locations and inception angles. A large number of fault case studies have been carried out to evaluate reach setting and % error of proposed method. It provides primary protection to transmission line length and also offers backup protection for a reverse section of transmission line. The experimental results show that the scheme performs better than the other schemes. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-21T10:44:28Z No. of bitstreams: 1 ijimai20206_1_5_pdf_10077.pdf: 957893 bytes, checksum: e61637c9f5939a170ec2f079a9975fba (MD5); Made available in DSpace on 2022-03-21T10:44:28Z (GMT). No. of bitstreams: 1 ijimai20206_1_5_pdf_10077.pdf: 957893 bytes, checksum: e61637c9f5939a170ec2f079a9975fba (MD5)

Saleem, Nasir Khattak, Muhammad Irfan https://reunir.unir.net/handle/123456789/12693 2022-03-21T09:41:51Z

Deep Neural Networks for Speech Enhancement in Complex-Noisy Environments Saleem, Nasir; Khattak, Muhammad Irfan In this paper, we considered the problem of the speech enhancement similar to the real-world environments where several complex noise sources simultaneously degrade the quality and intelligibility of a target speech. The existing literature on the speech enhancement principally focuses on the presence of one noise source in mixture signals. However, in real-world situations, we generally face and attempt to improve the quality and intelligibility of speech where various complex stationary and nonstationary noise sources are simultaneously mixed with the target speech. Here, we have used deep learning for speech enhancement in complex-noisy environments and used ideal binary mask (IBM) as a binary classification function by using deep neural networks (DNNs). IBM is used as a target function during training and the trained DNNs are used to estimate IBM during enhancement stage. The estimated target function is then applied to the complex-noisy mixtures to obtain the target speech. The mean square error (MSE) is used as an objective cost function at various epochs. The experimental results at different input signal-to-noise ratio (SNR) showed that DNN-based complex-noisy speech enhancement outperformed the competing methods in terms of speech quality by using perceptual evaluation of speech quality (PESQ), segmental signal-to-noise ratio (SNRSeg), log-likelihood ratio (LLR), weighted spectral slope (WSS). Moreover, short-time objective intelligibility (STOI) reinforced the better speech intelligibility. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-21T09:41:51Z No. of bitstreams: 1 ijimai20206_1_10_pdf_20073.pdf: 1358294 bytes, checksum: 34c71933dfa29a7278a5ce6308de80aa (MD5); Made available in DSpace on 2022-03-21T09:41:51Z (GMT). No. of bitstreams: 1 ijimai20206_1_10_pdf_20073.pdf: 1358294 bytes, checksum: 34c71933dfa29a7278a5ce6308de80aa (MD5)

Harish, B S Maheshan, M S Nagadarshan, N https://reunir.unir.net/handle/123456789/12692 2022-03-21T09:18:49Z

A Convolution Neural Network Engine for Sclera Recognition Harish, B S; Maheshan, M S; Nagadarshan, N The world is shifting to the digital era in an enormous pace. This rise in the digital technology has created plenty of applications in the digital space, which demands a secured environment for transacting and authenticating the genuineness of end users. Biometric systems and its applications has seen great potentials in its usability in the tech industries. Among various biometric traits, sclera trait is attracting researchers from experimenting and exploring its characteristics for recognition systems. This paper, which is first of its kind, explores the power of Convolution Neural Network (CNN) for sclera recognition by developing a neural model that trains its neural engine for a recognition system. To do so, the proposed work uses the standard benchmark dataset called Sclera Segmentation and Recognition Benchmarking Competition (SSRBC 2015) dataset, which comprises of 734 images which are captured at different viewing angles from 30 different classes. The proposed methodology results showcases the potential of neural learning towards sclera recognition system. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-21T09:18:49Z No. of bitstreams: 1 ijimai20206_1_9_pdf_52009.pdf: 558901 bytes, checksum: 43647f9ab1756054fb1233e9b5648f2f (MD5); Made available in DSpace on 2022-03-21T09:18:49Z (GMT). No. of bitstreams: 1 ijimai20206_1_9_pdf_52009.pdf: 558901 bytes, checksum: 43647f9ab1756054fb1233e9b5648f2f (MD5)

Borhani, Mostafa Ghasemloo, Nima https://reunir.unir.net/handle/123456789/12688 2022-03-18T13:13:49Z

Soft Computing Modelling of Urban Evolution: Tehran Metropolis Borhani, Mostafa; Ghasemloo, Nima Exploring computational intelligence, geographic information systems and statistical information, a creative and innovative model for urban evolution is presented in this paper. The proposed model employs fuzzy logic and artificial neural network as forecasting tools for describing the urban growth. This dynamic urban evolution model considers the spatial data of population, as well as its time changes and the building usage patterns. For clustering the spatial features, fuzzy algorithms were implemented to represent different levels of urban growth and development. Then, these fuzzy clusters were modeled by the multi-layer neural networks to estimate the urban growth. Based on this novel intelligent model, the current state of development of Tehran’s population and the future of this urban evolution were evaluated by empirical data and the achieved outcomes were detailed in qualitative charts. The input data-set includes four censuses with five-year intervals. Tehran's demographic evolution model forecasts the next five years with an overall accuracy of 81% and Cohen's kappa coefficient up to 74% beside the qualitative charts. These performance indicators are higher than the previous advanced models. The primary objective of this proposed model is to aid planners and decision makers to predict the development trend of urban population. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-18T13:13:49Z No. of bitstreams: 1 ijimai20206_1_1_pdf_16471.pdf: 757262 bytes, checksum: 8ecbe1ebc84543f5409a143f7c009930 (MD5); Made available in DSpace on 2022-03-18T13:13:49Z (GMT). No. of bitstreams: 1 ijimai20206_1_1_pdf_16471.pdf: 757262 bytes, checksum: 8ecbe1ebc84543f5409a143f7c009930 (MD5)

Harish, B S Roopa, C K https://reunir.unir.net/handle/123456789/12687 2022-03-18T13:07:26Z

Automated ECG Analysis for Localizing Thrombus in Culprit Artery Using Rule Based Information Fuzzy Network Harish, B S; Roopa, C K Cardio-vascular diseases are one of the foremost causes of mortality in today’s world. The prognosis for cardiovascular diseases is usually done by ECG signal, which is a simple 12-lead Electrocardiogram (ECG) that gives complete information about the function of the heart including the amplitude and time interval of P-QRST-U segment. This article recommends a novel approach to identify the location of thrombus in culprit artery using the Information Fuzzy Network (IFN). Information Fuzzy Network, being a supervised machine learning technique, takes known evidences based on rules to create a predicted classification model with thrombus location obtained from the vast input ECG data. These rules are well-defined procedures for selecting hypothesis that best fits a set of observations. Results illustrate that the recommended approach yields an accurateness of 92.30%. This novel approach is shown to be a viable ECG analysis approach for identifying the culprit artery and thus localizing the thrombus. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-03-18T13:07:26Z No. of bitstreams: 1 ijimai20206_1_2_pdf_13999.pdf: 771524 bytes, checksum: 891c8db38b0693dd2735f81ba123140f (MD5); Made available in DSpace on 2022-03-18T13:07:26Z (GMT). No. of bitstreams: 1 ijimai20206_1_2_pdf_13999.pdf: 771524 bytes, checksum: 891c8db38b0693dd2735f81ba123140f (MD5)