GRIAL resources
Permanent URI for this communityhttps://repositorio.grial.eu/handle/123456789/1
Browse
42 results
Search Results
Item ModelViz: A Model-Driven Engineering Approach for Visual Analytics System Design(IEEE, 2024-03-29) Khakpour, A.; Vázquez-Ingelmo, A.; Colomo-Palacios, R.; García-Peñalvo, F. J.; Martini, A.Visual analytics systems should be able to consolidate data from disparate sources, conduct exploratory analysis, create visualizations that suit different users, and integrate seamlessly with decision-making activities to support data-driven decision-making. However, current mainstream visual analytics solutions often lack support for all these requirements. To address this gap, we propose the use of model-driven engineering to design visual analytics systems. To demonstrate the feasibility of this approach, we developed a Domain-Specific Modeling Language (DSML) named ModelViz to design visual analytics systems for consumer goods supply chain applications. Furthermore, we present the work of our DSML, using data from a manufacturing company as a case study. Finally, we evaluated ModelViz quantitatively by comparing it with other similar works from the literature. Our results demonstrate that this approach meets the requirements and provides a promising direction for designing visual analytics systems by considering domain-specific aspects to help achieve business goals.Item KoopaML: Application for receiving and processing DICOM images(CEUR-WS.org, 2023-12-05) Fraile-Sanchón, R.; Vázquez-Ingelmo, A.; García-Holgado, A.; García-Peñalvo, F. J.AI algorithms application to medical data has gained relevance due to their powerful benefits among different research tasks. However, medical data is heterogeneous and diverse, and these algorithms need technological support to tackle these data management challenges. KoopaML enables users to unify medical data, especially DICOM images and apply AI algorithms to them in a straightforward way through an online web application. This work presents a new feature in the KoopaML platform: a Machine Learning platform to assist non-expert users in defining and applying ML pipelines. The feature comprises the reception, storage, and management of DICOM images. These images are received through a connection with a PACS (Picture Archiving Communication System) system already configured by users on the platform and, after storing the images, it is possible to apply AI algorithms to them and make modifications or annotations.Item Usability Study of a Pilot Database Interface for Consulting Open Educational Resources in the Context of the ENCORE Project(Springer, 2023-07-23) Vázquez-Ingelmo, A.; García-Holgado, A.; García-Peñalvo, F. J.; Chiarello, F.Open educational resources (OER) are materials such as textbooks, lessons, and other teaching and learning tools that are freely accessible for use. OER are gaining popularity as a means for educators to give their students access to high-quality, economical educational materials. OER can encourage sharing infor-mation and resources throughout the educational community while also helping lower the cost of education for both students and teachers. In this context, the ENCORE project seeks, among other goals, to assist students and workers in acquiring the skills necessary to deal with economic, ecological, and technolog-ical challenges as well as to address the skills gap between the supply of educa-tional institutions and the demand of employers and assist educators in staying abreast of the constantly changing landscape of skills. One of the first steps to reach the project’s goals is to build a robust database that contains quality OERs linked to green, digital, and entrepreneurial (GDE) skills. A graphical interface has been developed to retrieve and display information about the OERs, and, in turn, to make these resources available for any stakeholder. However, due to the significant quantity of information, it is important to develop an interface that enhances user experience. This work presents a usability study of the ENCORE project’s OER database interface carried out through a System Usability Scale (SUS) questionnaire, as well as future interface improvements based on the results.Item Designing Learning Paths with Open Educational Resources: An Investigation in Model-Driven Engineering(IEEE, 2023-06-20) Bucchiarone, A.; Vázquez-Ingelmo, A.; Schiavo, G.; García-Holgado, A.; García-Peñalvo, F. J.; Zschaler, S.This paper presents a methodology for supporting educators and learners in designing and delivering learning paths using Open Educational Resources (OERs). While OERs provide free and unlimited access to high-quality learning resources, their scattered nature presents significant challenges in finding relevant and high-quality materials. Furthermore, the lack of a centralized repository for OERs makes it difficult to ensure the accuracy and quality of the materials being queried. To address these issues, the paper presents the ENCORE methodology that provides software components, or ENCORE enablers, to enable educators to include relevant OERs that target specific skills in their learning paths. The methodology also leverages notebook interfaces and gamification mechanisms to promote stu- dents’ learning engagement. The paper illustrates the ENCORE methodology through a case study, where the methodology is applied to an OER repository of educational resources developed by the expert network on model-driven engineering (MDEnet). The case study demonstrates that designing the database and enablers as independent but holistic components enables the use of OERs to accomplish a wider range of educational goals, such as supporting the creation of learning paths. The paper concludes with indications on how to extend the ENCORE methodology to further enhance the creation and delivery of personalized learning experiences, supporting the reuse of open educational resources and the automatic generation of personalized learning paths.Item Are Textual Recommendations Enough? Guiding Physicians Toward the Design of Machine Learning Pipelines Through a Visual Platform(Springer, 2023-09-05) Vázquez-Ingelmo, A.; García-Holgado, A.; García-Peñalvo, F. J.; Pérez-Sánchez, P.; Antúnez-Muiños, P.; Sánchez-Puente, A.; Vicente-Palacios, V.; Dorado-Díaz, P. I.; Sánchez, P. L.The prevalence of artificial intelligence (AI) in our daily lives is often exaggerated by the media, leading to a positive public perception while overlook-ing potential problems. In the field of medicine, it is crucial to educate future health-care professionals on the advantages and disadvantages of AI and to emphasize the importance of creating fair, ethical, and reproducible models. The KoopaML platform was developed to provide an educational and user-friendly interface for inexperienced users to create AI pipelines. This study analyzes the quantitative and interaction data gathered from a usability test involving physicians from the University Hospital of Salamanca, with the aim of identifying new interaction paradigms to improve the platform’s usability. The results shown that the plat-form is difficult to learn for inexperienced users due to its contents related to AI. Following these results, a set of improvements are proposed for the next version of KoopaML, focusing on reducing the interactions needed to create the pipelines.Item Testing and Improvements of KoopaML: A Platform to Ease the Development of Machine Learning Pipelines in the Medical Domain(Springer, 2023-05-01) Vázquez-Ingelmo, A.; García-Holgado, A.; García-Peñalvo, F. J.; Fraile-Sanchón, R.; Pérez-Sánchez, P.; Antúnez-Muiños, P.; Sánchez-Puente, A.; Vicente-Palacios, V.; Dorado-Díaz, P. I.; Cruz-González, I.; Sánchez, P. L.Machine Learning (ML) applications in complex domains, such as the medical domain, can be highly beneficial, but also hazardous if some concepts are overlooked. In this context, however, health professionals denote expertise in their domain, but they often lack skills in terms of ML. In this sense, to leverage ML applications in the medical domain, it is important to combine both domain expertise and ML-related skills. In previous works, we tackled this challenge in the health context through a visual platform (KoopaML) that enables lay users to build ML pipelines. The present work describes the challenges derived from the first version of the platform and the prototypes for the new features designed to address them. The prototypes have been validated by two experts, obtaining highly valuable feedback.Item Fostering Decision-Making Processes in Health Ecosystems Through Visual Analytics and Machine Learning(Springer, 2022-06-26) García-Peñalvo, F. J.; Vázquez-Ingelmo, A.; García-Holgado, A.Data-intensive contexts, such as health, use information systems to merge, synthesize, represent, and visualize data by using interfaces to ease decision-making processes. All data management processes play an essential role in exploiting data’s strategic value from acquisition to visualization. Technologi-cal ecosystems allow the deployment of highly complex services while supporting their evolutionary nature. However, there is a challenge regarding the design of high-level interfaces that adapt to the evolving nature of data. The AVisSA project is focused on tackling the development of an automatic dashboard generation system (meta-dashboard) using Domain Engineering and Artificial Intelligence techniques. This approach makes it possible to obtain dashboards from data flows in technological ecosystems adapted to specific domains. The implementation of the meta-dashboard will make intensive use of user experience testing throughout its development, which will allow the involvement of other actors in the ecosystem as stakeholders (public administration, health managers, etc.). These actors will be able to use the data for decision-making and design improvements in health provision.Item Flexible Heuristics for Supporting RecommendationsWithin an AI Platform Aimed at Non-expert Users(Springer, 2023-05-01) Vázquez-Ingelmo, A.; García-Holgado, A.; García-Peñalvo, F. J.; Andrés-Fraile, E.; Pérez-Sánchez, P.; Antúnez-Muiños, P.; Sánchez-Puente, A.; Vicente-Palacios, V.; Dorado-Díaz, P. I.; Cruz-González, I.; Sánchez, P. L.The use of Machine Learning (ML) to resolve complex tasks has become popular in several contexts. While these approaches are very effective and have many related benefits, they are still very tricky for the general audi-ence. In this sense, expert knowledge is crucial to apply ML algorithms properly and to avoid potential issues. However, in some situations, it is not possible to rely on experts to guide the development of ML pipelines. To tackle this issue, we present an approach to provide customized heuristics and recommendations through a graphical platform to build ML pipelines, namely KoopaML, focused on the medical domain. With this approach, we aim not only at providing an easy way to apply ML for non-expert users, but also at providing a learning experience for them to understand how these methods work.Item Emotional AI in Healthcare: a pilot architecture proposal to merge emotion recognition tools(ACM, 2021-10-27) Marcos-Pablos, S.; García-Peñalvo, F. J.; Vázquez-Ingelmo, A.The use of emotional artificial intelligence (EAI) looks promising and is continuing to improve during the last years. However, in order to effectively use EAI to help in the diagnose and treat health conditions there are still significant challenges to be tackled. Be-cause EAI is still under development, one of the most important challenges is to integrate the technology into the health provision process. In this sense, it is important to complement EAI technolo-gies with expert supervision, and to provide health professionals with the necessary tools to make the best of EAI without a deep knowledge of the technology. The present work aims to provide an initial architecture proposal for making use of different available technologies for emotion recognition, where their combination could enhance emotion detection. The proposed architecture is based on an evolutionary approach so to be integrated in digital health ecosystems, so new modules can be easily integrated. In addition, internal data exchange utilizes Robot Operating System (ROS) syntax, so it can also be suitable for physical agents.Item Recursos Educativos Abiertos para mejorar la protección de datos de los estudiantes en las escuelas(Servicio de Publicaciones Universidad de Zaragoza, 2023-10-18) Amo-Filva, D.; Fonseca-Escudero, D.; Sanchez-Sepulveda, M. V.; Hasti, H.; Aguayo Mauri, S.; García-Holgado, A.; García-Holgado, L.; Vázquez-Ingelmo, A.; García-Peñalvo, F. J.; Orehovački, T.; Krašna, M.; Pesek, I.; Marchetti, E.; Valente, A.; Witfelt, C.; Ružić, I.; Fraoua, K. E.; Moreira, F.; Santos Pereira, C.; Paes, C.Las escuelas están recurriendo a software de terceros que se ejecuta en la nube. Este cambio presenta desafíos, problemas y preocupaciones únicas relacionadas con la privacidad y la seguridad de los datos de los estudiantes. El proyecto SPADATAS promueve el uso responsable de las tecnologías digitales y mejorar la protección de datos en las prácticas de gestión de datos académicos dentro de los entornos educativos. Uno de nuestros objetivos es abordar esas preocupaciones sobre privacidad y seguridad de datos, particularmente en los procesos de tratamiento de datos académicos. Para aumentar la conciencia y mejorar la protección de datos en las escuelas, realizamos una búsqueda exhaustiva de recursos en línea y abiertos relevantes. Este trabajo presenta la metodología utilizada y los resultados. Existe una gran cantidad de recursos para las escuelas, pero se requiere un análisis meticuloso para discernir cuáles son los más efectivos para mejorar la protección de datos