https://reunir.unir.net/handle/123456789/13897 2024-11-08T18:02:30Z https://reunir.unir.net/handle/123456789/13906 Editor's Note de Paz Santana, Juan F.; Villarrubia González, Gabriel The international conference “Disruptive Technologies Tech Ethics and Artificial Intelligence” (DITTET) provides a forum to present and discuss the latest scientific and technical advances and their implications in the field of ethics. It also provides a forum for experts to present their latest research in disruptive technologies, promoting knowledge transfer. It provides a unique opportunity to bring together experts in different fields, academics, and professionals to exchange their experience in the development and deployment of disruptive technologies, artificial intelligence, and their ethical problems. This Special Issue contains extended versions of selected works presented at the 1st International Conference on Disruptive Technologies, Tech Ethics and Artificial Intelligence (DiTTEt 2021), held in Salamanca (Spain) in September 2021. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T13:06:03Z No. of bitstreams: 1 ijimai7_6_0_0.pdf: 50552 bytes, checksum: 81c326ba05451a619d4113f762da9c59 (MD5); Made available in DSpace on 2022-12-13T13:06:03Z (GMT). No. of bitstreams: 1 ijimai7_6_0_0.pdf: 50552 bytes, checksum: 81c326ba05451a619d4113f762da9c59 (MD5) https://reunir.unir.net/handle/123456789/13905 Board of Directors' Profile: A Case for Deep Learning as a Valid Methodology to Finance Research Vaca, César; Tejerina, Fernando; Sahelices, Benjamín This paper presents a Deep Learning (DL) model for natural language processing of unstructured CVs to generate a six-dimensional profile of the professional experience of the Spanish companies' board of directors. We show the complete process starting with open data extraction and cleaning, the generation of a labeled dataset for supervised learning, the development, training and validation of a DL model capable of accurately analyzing the dataset, and, finally, a data analysis work based on the automated generation of the professional profiles of more than 6,000 directors of Spanish listed companies between 2003 and 2020. An RNN-LSTM neural network has been trained in three phases starting from a random initial state, (1) learning of basic structures of the Spanish language, (2) fine tuning for scientific texts in the field of economics and finance, and (3) regression modeling to generate a six-dimensional profile based on a generalization of sentiment classification systems. The complete training has been carried out with very low computational requirements, having a total duration of 120 hours of processing in a low-end GPU. The results obtained in the validation of the DL model show great accuracy, obtaining a value for the standard deviation of the mean error between 0.015 and 0.033. As a result, we have been able to outline with a high degree of reliability the profile of the listed Spanish companies' board of directors. We found that the predominant profile is that of directors with experience in executive or consultancy positions, followed by the financial profile. The results achieved show the potential of DL in social science research, particularly in Finance. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T12:59:08Z No. of bitstreams: 1 ijimai7_6_7.pdf: 1262285 bytes, checksum: 0ceb0b306c3da73d936b42f485d3c6de (MD5); Made available in DSpace on 2022-12-13T12:59:08Z (GMT). No. of bitstreams: 1 ijimai7_6_7.pdf: 1262285 bytes, checksum: 0ceb0b306c3da73d936b42f485d3c6de (MD5) https://reunir.unir.net/handle/123456789/13904 A Clustering Algorithm Based on an Ensemble of Dissimilarities: An Application in the Bioinformatics Domain Martín Merino, Manuel; López Rivero, Alfonso José; Alonso, Vidal; Vallejo, Marcelo; Ferreras, Antonio Clustering algorithms such as k-means depend heavily on choosing an appropriate distance metric that reflect accurately the object proximities. A wide range of dissimilarities may be defined that often lead to different clustering results. Choosing the best dissimilarity is an ill-posed problem and learning a general distance from the data is a complex task, particularly for high dimensional problems. Therefore, an appealing approach is to learn an ensemble of dissimilarities. In this paper, we have developed a semi-supervised clustering algorithm that learns a linear combination of dissimilarities considering incomplete knowledge in the form of pairwise constraints. The minimization of the loss function is based on a robust and efficient quadratic optimization algorithm. Besides, a regularization term is considered that controls the complexity of the distance metric learned avoiding overfitting. The algorithm has been applied to the identification of tumor samples using the gene expression profiles, where domain experts provide often incomplete knowledge in the form of pairwise constraints. We report that the algorithm proposed outperforms a standard semi-supervised clustering technique available in the literature and clustering results based on a single dissimilarity. The improvement is particularly relevant for applications with high level of noise. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T12:20:55Z No. of bitstreams: 1 ijimai7_6_1.pdf: 2597861 bytes, checksum: 9159982e29f2b2ab8468a339c3b4743d (MD5); Made available in DSpace on 2022-12-13T12:20:55Z (GMT). No. of bitstreams: 1 ijimai7_6_1.pdf: 2597861 bytes, checksum: 9159982e29f2b2ab8468a339c3b4743d (MD5) https://reunir.unir.net/handle/123456789/13903 Normative Affordances Through and By Technology: Technological Mediation and Human Enhancement Döbler, Niklas Alexander; Bartnik, Clemens Human activity is fundamentally embedded in and constituted by technology. In this regard, technology influences not only how people experience the world, but also which possibilities for action offered by the environment (affordances) can be perceived and ultimately acted upon. As having socio-cultural and normative aspects, affordances are deeply relational to the technological human form of life. Postphenomenology describes several human-technology relations and their perception and action mediating effects. Therefore, it provides a suitable framework to examine how technology mediates the perception of affordances and leads to different behavioral outcomes. Technology can reveal hitherto hidden affordances but can also result in the manipulation and concealment of action possibilities. Both aspects can be deliberately controlled by using a particular technology and/or interfering with the technological hermeneutic process. Technological mal-functions, limitations, purposeful corruption, or human error can disrupt the hermeneutic qualities of technology and may lead to false conclusions about affordances and respective maladaptive behavioral outcomes. Technology can also be applied to humans to form “better” versions of them. One consequence of these so-called Human Enhancement technologies is the emergence of different affordances for the enhanced individual and the possible establishment of new affordances inside a form of life. Manipulating the perception and emergence of affordances through technological mediation or Human Enhancement can have severe political and ethical consequences. It is necessary to engage in an open debate about the perception and action mediating power of technology and the human reliance on them in our current and future form of life. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T12:14:14Z No. of bitstreams: 1 ijimai7_6_2.pdf: 532117 bytes, checksum: 6a7869b1df78391dbfdf57c14b9bdb19 (MD5); Made available in DSpace on 2022-12-13T12:14:14Z (GMT). No. of bitstreams: 1 ijimai7_6_2.pdf: 532117 bytes, checksum: 6a7869b1df78391dbfdf57c14b9bdb19 (MD5) https://reunir.unir.net/handle/123456789/13902 Integrating Emotion Recognition Tools for Developing Emotionally Intelligent Agents Marcos-Pablos, Samuel; Lobato, Fernando; García-Peñalvo, Francisco Emotionally responsive agents that can simulate emotional intelligence increase the acceptance of users towards them, as the feeling of empathy reduces negative perceptual feedback. This has fostered research on emotional intelligence during last decades, and nowadays numerous cloud and local tools for automatic emotional recognition are available, even for inexperienced users. These tools however usually focus on the recognition of discrete emotions sensed from one communication channel, even though multimodal approaches have been shown to have advantages over unimodal approaches. Therefore, the objective of this paper is to show our approach for multimodal emotion recognition using Kalman filters for the fusion of available discrete emotion recognition tools. The proposed system has been modularly developed based on an evolutionary approach so to be integrated in our digital ecosystems, and new emotional recognition sources can be easily integrated. Obtained results show improvements over unimodal tools when recognizing naturally displayed emotions. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T12:08:57Z No. of bitstreams: 1 ijimai7_6_8.pdf: 1705376 bytes, checksum: e9d27ecbbd80b0f5456b358fd9ea2eb6 (MD5); Made available in DSpace on 2022-12-13T12:08:57Z (GMT). No. of bitstreams: 1 ijimai7_6_8.pdf: 1705376 bytes, checksum: e9d27ecbbd80b0f5456b358fd9ea2eb6 (MD5) https://reunir.unir.net/handle/123456789/13901 An Event Mesh for Event Driven IoT Applications Berjón, Roberto; Mateos, Montserrat; Beato, M. Encarnación; Fermoso García, Ana In IoT contexts, software solutions are required to have components located in different environments: mobile, edge, fog or cloud. To design this type of application, event driven architecture (EDA) is used to develop distributed, scalable, decoupled, desynchronized and real-time components. The interconnection between the different components is done through event brokers that allow communication based on messages (events). Although the design of the components is independent of the environment in which they are deployed, this environment can determine the infrastructure to be used, for example the event brokers, so it is common to have to make modifications to the applications to adapt them to these environments, which complicates their design and maintenance. It is therefore necessary to have an event mesh that allows the connection between event brokers to simplify the development of applications. This paper presents the SCIFI-II system, an event mesh that allows the distribution of events between event brokers. Its use will allow the design of components decoupling them from the event brokers, which will facilitate their deployment in any environment. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T11:54:07Z No. of bitstreams: 1 ijimai7_6_6.pdf: 1950920 bytes, checksum: b752a4668767f65fedf0ef48eaa650ce (MD5); Made available in DSpace on 2022-12-13T11:54:07Z (GMT). No. of bitstreams: 1 ijimai7_6_6.pdf: 1950920 bytes, checksum: b752a4668767f65fedf0ef48eaa650ce (MD5) https://reunir.unir.net/handle/123456789/13900 Promoting Social Media Dissemination of Digital Images Through CBR-Based Tag Recommendation Martín-Gómez, Lucía; Pérez-Marcos, Javier; Cordero-Gutiérrez, Rebeca; De La Iglesia, Daniel H. Multimedia content has become an essential tool to share knowledge, sell products or disseminate messages. Some social networks use multimedia content to promote information and create social communities. In order to increase the impact of the digital content, those images or videos are labeled with different words, denominated tags. In this paper, we propose a recommender system which analyzes multimedia content and suggests tags to maximize its influence in the social community. It implements a Case-Based Reasoning architecture (CBR), which allows to learn from previous tagged content. The system has been evaluated through cross fold validation with a training and validation sets carefully constructed and extracted from Instagram. The results demonstrate that the system can suggest good options to label our image and maximize the influence of the multimedia content. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T11:38:52Z No. of bitstreams: 1 ijimai7_6_5.pdf: 1618020 bytes, checksum: c83bebe1b826a3865aa64c98c2fcf281 (MD5); Made available in DSpace on 2022-12-13T11:38:52Z (GMT). No. of bitstreams: 1 ijimai7_6_5.pdf: 1618020 bytes, checksum: c83bebe1b826a3865aa64c98c2fcf281 (MD5) https://reunir.unir.net/handle/123456789/13899 Edge Face Recognition System Based on One-Shot Augmented Learning Jiménez-Bravo, Diego M.; Lozano Murciego, Álvaro; Sales, A.; Augusto Silva, Luis; De La Iglesia, Daniel H. There is growing concern among users of computer systems about how their data is handled. In this sense, IT (Information Technology) professionals are not unaware of this problem and are looking for solutions to meet the requirements and concerns of their users. During the last few years, various techniques and technologies have emerged that allow us to answer to the problem posed by users. Technologies such as edge computing and techniques such as one-shot learning and data augmentation enable progress in this regard. Thus, in this article, we propose the creation of a system that makes use of these techniques and technologies to solve the problem of face recognition and form a low-cost security system. The results obtained show that the combination of these techniques is effective in most of the face detection algorithms and allows an effective solution to the problem raised. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T11:27:02Z No. of bitstreams: 1 ijimai7_6_4.pdf: 4275272 bytes, checksum: fe696c449ced17867c0c7589e008fb04 (MD5); Made available in DSpace on 2022-12-13T11:27:02Z (GMT). No. of bitstreams: 1 ijimai7_6_4.pdf: 4275272 bytes, checksum: fe696c449ced17867c0c7589e008fb04 (MD5) https://reunir.unir.net/handle/123456789/13898 A Model for Planning TELCO Work-Field Activities Enabled by Genetic and Ant Colony Algorithms Henriques, João; Caldeira, Filipe Telecommunication Company’s (TELCO) are continuously delivering their efforts on the effectiveness of their daily work. Planning the activities for their workers is a crucial sensitive, and time-consuming task usually taken by experts. This plan aims to find an optimized solution maximizing the number of activities assigned to workers and minimizing the inherent costs (e.g., labor from workers, fuel, and other transportation costs). This paper proposes a model that allows computing a maximized plan for the activities assigned to their workers, allowing to alleviate the burden of the existing experts, even if supported by software implementing rule-based heuristic models. The proposed model is inspired by nature and relies on two stages supported by Genetic and Ant Colony evolutionary algorithms. At the first stage, a Genetic Algorithms (GA) identifies the optimal set of activities to be assigned to workers as the way to maximize the revenues. At a second step, an Ant Colony algorithm searches for an efficient path among the activities to minimize the costs. The conducted experimental work validates the effectiveness of the proposed model in the optimization of the planning TELCO work-field activities in comparison to a rule-based heuristic model. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-12-13T11:15:29Z No. of bitstreams: 1 ijimai7_6_3.pdf: 1213846 bytes, checksum: 5725afaa75f98da6dca5fc8ad1ba448b (MD5); Made available in DSpace on 2022-12-13T11:15:29Z (GMT). No. of bitstreams: 1 ijimai7_6_3.pdf: 1213846 bytes, checksum: 5725afaa75f98da6dca5fc8ad1ba448b (MD5)