Search results

Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG ; [Abstract] The number of interconnected devices, such as personal wearables, cars, and smart-homes, surrounding us every day has recently increased. The Internet of Things devices monitor many processes, and have the capacity of using machine learning models for pattern recognition, and even making decisions, with the added advantage of diminishing network congestion by allowing computations near to the data sources. The main restriction is the low computation capacity of these devices. Thus, machine learning algorithms capable of maintaining accuracy while using mechanisms that exploit certain characteristics, such as low-precision versions, are needed. In this paper, low-precision mutual information-based feature selection algorithms are employed over DNA microarray datasets, showing that 16-bit and some times even 8-bit representations of these algorithms can be used without significant variations in the final classification results achieved. ; This work has been supported by the grant Machine Learning on the Edge - Ayudas Fundación BBVA a Equipos de Investigación Científica 2019. It has also been possible thanks to the support received by the National Plan for Scientific and Technical Research and Innovation of the Spanish Government (Grant PID2019-109238GB-C2), and by the Xunta de Galicia (Grant ED431C 2018/34) with the European Union ERDF funds. CITIC, as Research Center accredited by Galician University System, is funded by "Consellería de Cultura, Educación e Universidades from Xunta de Galicia", supported in an 80% through ERDF Funds, ERDF Operational Programme Galicia 2014-2020, and the remaining 20% by "Secretaría Xeral de Universidades" (Grant ED431G 2019/01). Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature ; Xunta de Galicia; ED431C 2018/34 ; Xunta de Galicia; ED431G 2019/01

Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG ; [Abstract] The task of choosing the appropriate classifier for a given scenario is not an easy-to-solve question. First, there is an increasingly high number of algorithms available belonging to different families. And also there is a lack of methodologies that can help on recommending in advance a given family of algorithms for a certain type of datasets. Besides, most of these classification algorithms exhibit a degradation in the performance when faced with datasets containing irrelevant and/or redundant features. In this work we analyze the impact of feature selection in classification over several synthetic and real datasets. The experimental results obtained show that the significance of selecting a classifier decreases after applying an appropriate preprocessing step and, not only this alleviates the choice, but it also improves the results in almost all the datasets tested. ; This work has been supported by the National Plan for Scientific and Technical Research and Innovation of the Spanish Government (Grant PID2019-109238 GB-C2), and by the Xunta de Galicia (Grant ED431C 2018/34) with the European Union ERDF funds. CITIC, as Research Center accredited by Galician University System, is funded by "Consellería de Cultura, Educación e Universidades from Xunta de Galicia", supported in an 80% through ERDF Funds, ERDF Operational Programme Galicia 2014–2020, and the remaining 20% by "Secretaría Xeral de Universidades" (Grant ED431G 2019/01). Funding for open access charge: Universidade da Coruña/CISUG ; Xunta de Galicia; ED431C 2018/34 ; Xunta de Galicia; ED431G 2019/01

[Abstract] Over the years, the success of recommender systems has become remarkable. Due to the massive arrival of options that a consumer can have at his/her reach, a collaborative environment was generated, where users from all over the world seek and share their opinions based on all types of products. Specifically, millions of images tagged with users' tastes are available on the web. Therefore, the application of deep learning techniques to solve these types of tasks has become a key issue, and there is a growing interest in the use of images to solve them, particularly through feature extraction. This work explores the potential of using only images as sources of information for modeling users' tastes and proposes a method to provide gastronomic recommendations based on them. To achieve this, we focus on the pre-processing and encoding of the images, proposing the use of a pre-trained convolutional autoencoder as feature extractor. We compare our method with the standard approach of using convolutional neural networks and study the effect of applying transfer learning, reflecting how it is better to use only the specific knowledge of the target domain in this case, even if fewer examples are available. ; This research has been financially supported in part by European Union FEDER funds, by the Spanish Ministerio de Economía y Competitividad (research project PID2019-109238GB), by the Consellería de Industria of the Xunta de Galicia (research project GRC2014/035), and by the Principado de Asturias Regional Government (research project IDI-2018-000176). CITIC as a Research Center of the Galician University System is financed by the Consellería de Educación, Universidades e Formación Profesional (Xunta de Galicia) through the ERDF (80%), Operational Programme ERDF Galicia 2014–2020 and the remaining 20% by the Secretaria Xeral de Universidades (ref. ED431G 2019/01). ; Xunta de Galicia; GRC2014/035 ; Gobierno del Principado de Asturias; IDI-2018-000176 ; Xunta de Galicia; ED431G 2019/01

[Abstract] This work presents EADMNC (Explainable Anomaly Detection on Mixed Numerical and Categorical spaces), a novel approach to address explanation using an anomaly detection algorithm, ADMNC, which provides accurate detections on mixed numerical and categorical input spaces. Our improved algorithm leverages the formulation of the ADMNC model to offer pre-hoc explainability based on CART (Classification and Regression Trees). The explanation is presented as a segmentation of the input data into homogeneous groups that can be described with a few variables, offering supervisors novel information for justifications. To prove scalability and interpretability, we list experimental results on real-world large datasets focusing on network intrusion detection domain. ; This research was partially funded by European Union ERDF funds, Ministerio de Ciencia e Innovación grant number PID2019-109238GB-C22, Xunta de Galicia through the accreditation of Centro Singular de Investigación 2016-2020, Ref. ED431G/01 and Grupos de Referencia Competitiva, Ref. GRC2014/035 ; Xunta de Galicia; ED431G/01 ; Xunta de Galicia; GRC2014/035

XoveTIC Conference (3rd. A Coruña, Spain. 2020) ; This research has been financially supported in part by European Union FEDER funds, by the Spanish Ministerio de Economía y Competitividad (research project PID2019-109238GB), by the Consellería de Industria of the Xunta de Galicia (research project GRC2014/035), and by the Principado de Asturias Regional Government (research project IDI-2018-000176). CITIC as a Research Center of the Galician University System is financed by the Consellería de Educación, Universidades e Formación Profesional (Xunta de Galicia) through the ERDF (80%), Operational Programme ERDF Galicia 2014–2020 and the remaining 20% by the Secretaria Xeral de Universidades (ref. ED431G 2019/01).

Workshop ECAI. European Conference on Artificial Intelligence (24th. Santiago de Compostela. 2020) ; Research financed in part by EU ERDF funds, by the Spanish Ministerio de Economía y Competitividad (project TIN2015-65069-C2), by the Xunta de Galicia (projects GRC2014/035 and ED431G/01), and by the Principado de Asturias Regional Government (project IDI-2018-000176). Thanks to NVIDIA Corporation for donating the Titan Xp GPUs used in this research and to Freepik for the graphic design elements provided.

[Abstract] COVID-19 has brought a new normality in society. However, to avoid the situation, the virus must be stopped. There are several ways in which the governments of the world have taken action, from small measures like general cleaning up to large-scale measures like confinement. In this work, we present an agent-based tool that allows for simulating the virus expansion as a function of these containment measures and the Social Behavior based on people needs, beliefs, and social relations. Once this tool has been validated, it will be useful to evaluate the impact of future containment measures so that the most balanced ones can be found for the effectiveness of the measures and their good reception by the population.

International Joint Conference on Neural Networks (IJCNN) (2017. Anchorage, AK) ; This research has been financially supported in part by Spanish Ministerio de Economía y Competitividad (research projects TIN 2015-65069-C2, both1-R and 2-R), by European Union FEDER funds and by Xunta de Galicia (research project GRC2014/035). V. Bolon-Canedo acknowledges Xunta de Galicia postdoctoral funding (grant ED481B 2014/164-0)

Pro-environmental behaviors have been analyzed in the home, with little attention to other important contexts of everyday life, such as the workplace. The research reported here explored three categories of pro-environmental behavior (consumption of materials and energy, waste generation, and work-related commuting) in a public large-scale organization in Spain, with the aim of identifying the most effective policy options for a sustainable organization. Agent-based modeling was used to design a virtual simulation of the organization. Psychologically informed profiles of employees were defined using data gathered through a questionnaire, measuring knowledge, motivations, and ability. Future scenarios were developed using a participatory backcasting scenario development methodology, and policy tracks were derived. Dynamic simulations indicated that, to be effective, organizational policy should strengthen worker participation and autonomy, be sustained over time, and should combine different measures of medium intensity for behavior change, instead of isolated policies of high intensity.

Artificial Intelligence has become nowadays one of the main relevant technologies that is driven us to a new revolution, a change in society, just as well as other human inventions, such as navigation, steam machines, or electricity did in our past. There are several ways in which AI might be developed, and the European Union has chosen a path, a way to transit through this revolution, in which Artificial Intelligence will be a tool at the service of Humanity. That was precisely the motto of the 2020 European Conference on Artificial Intelligence ("Paving the way towards Human-Centric AI"), of which these special issue is a selection of the best papers selected by the organizers of some of the Workshops in ECAI 2020.