Santi Fort
Santi Fort has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Laia Subirats
Universitat Oberta de Catalunya
6 shared publications - Arijit Nandi
Universitat Politècnica de Catalunya (BarcelonaTech)
3 shared publications - Fatos Xhafa
Universitat Politecnica de Catalunya
3 shared publications - Gomez Monivas Sacha
Autonomous University of Madrid
3 shared publications - Alun Evans
Universitat Pompeu Fabra, Barcelona, Spain
1 shared publication - Apoorwa Hooda
Faculty of Education and Psychology, University of Jyväskylä, P.O. Box 35, 40014 Jyväskylä, Finland
1 shared publication
Latest Publications
- Open Access
- 10 February 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (4) , 2269
Gamification Based on User Types: When and Where It Is Worth Applying
Students’ motivation is one of the most relevant factors when improving the quality of the learning process. In this context, gamification is a powerful tool for increasing motivation at all levels of teaching. Since gamification methodologies can be applied in many different ways, personalizing gamified activities as a function of gamification user types is a promising strategy. Knowing the user types is also an advantage to understand the nature of learners in the class. In this article, we present the findings from several pilot exercises, where we identified gamification user types among students from Spain and Finland, analyzing their prevalence as a function of age, gender, country, and field of study. We also designed a gamification experience where activities were designed to fit the preferences of different user types. From these pilot experiences, we found that gamification user types are only relevant when other variables, such as the difficulty of the tasks or the presence of students who do not work well in groups, are not present. Based on our findings, we conclude that distance learning and subjects where previous knowledge is not present are good choices when gamifying a subject.
- 10 February 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (4) , 2269
Open AccessGamification Based on User Types: When and Where It Is Worth Applying
Students’ motivation is one of the most relevant factors when improving the quality of the learning process. In this context, gamification is a powerful tool for increasing motivation at all levels of teaching. Since gamification methodologies can be applied in many different ways, personalizing gamified activities as a function of gamification user types is a promising strategy. Knowing the user types is also an advantage to understand the nature of learners in the class. In this article, we present the findings from several pilot exercises, where we identified gamification user types among students from Spain and Finland, analyzing their prevalence as a function of age, gender, country, and field of study. We also designed a gamification experience where activities were designed to fit the preferences of different user types. From these pilot experiences, we found that gamification user types are only relevant when other variables, such as the difficulty of the tasks or the presence of students who do not work well in groups, are not present. Based on our findings, we conclude that distance learning and subjects where previous knowledge is not present are good choices when gamifying a subject.
- 1 January 2023
- Published by Springer Nature
- p. 123-133
Federated Learning with Exponentially Weighted Moving Average for Real-Time Emotion Classification
- 1 January 2023
- Published by Springer Nature
- p. 123-133
Federated Learning with Exponentially Weighted Moving Average for Real-Time Emotion Classification
- Open Access
- 23 October 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (21) , 9923
Artificial Intelligence to Counterweight the Effect of COVID-19 on Learning in a Sustainable Environment
Distance learning has been adopted as a very extended model during COVID-19-related confinement. It is also a methodology that can be applied in environments where people do not have easy access to schools. In this study, we automatically classify students as a function of their performance and we describe the best self-learning methodologies in distance learning, which will be useful both in confinement or for people with difficult access to schools. Due to the different learning scenarios provided by the different confinement conditions in the COVID-19 pandemic, we have performed the classification considering data before, during, and after COVID-19 confinement. Using a field experiment of 396 students, we have described the temporal evolution of students during all courses from 2016/2017 to 2020/2021. We have found that data obtained in the last month before the final exam of the subject include the most relevant information for a correct detection of students at risk of failure. On the other hand, students who obtain high scores are much easier to identify. Finally, we have concluded that the distance learning applied in COVID-19 confinement changed not only teaching strategies but also students’ strategies when learning autonomously.
- 23 October 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (21) , 9923
Open AccessArtificial Intelligence to Counterweight the Effect of COVID-19 on Learning in a Sustainable Environment
Distance learning has been adopted as a very extended model during COVID-19-related confinement. It is also a methodology that can be applied in environments where people do not have easy access to schools. In this study, we automatically classify students as a function of their performance and we describe the best self-learning methodologies in distance learning, which will be useful both in confinement or for people with difficult access to schools. Due to the different learning scenarios provided by the different confinement conditions in the COVID-19 pandemic, we have performed the classification considering data before, during, and after COVID-19 confinement. Using a field experiment of 396 students, we have described the temporal evolution of students during all courses from 2016/2017 to 2020/2021. We have found that data obtained in the last month before the final exam of the subject include the most relevant information for a correct detection of students at risk of failure. On the other hand, students who obtain high scores are much easier to identify. Finally, we have concluded that the distance learning applied in COVID-19 confinement changed not only teaching strategies but also students’ strategies when learning autonomously.
- 1 July 2021
- Published by Springer Nature
- p. 423-435
Real-Time Multimodal Emotion Classification System in E-Learning Context
- 1 July 2021
- Published by Springer Nature
- p. 423-435
Real-Time Multimodal Emotion Classification System in E-Learning Context
- Open Access
Real-Time Emotion Classification Using EEG Data Stream in E-Learning Contexts
In face-to-face and online learning, emotions and emotional intelligence have an influence and play an essential role. Learners’ emotions are crucial for e-learning system because they promote or restrain the learning. Many researchers have investigated the impacts of emotions in enhancing and maximizing e-learning outcomes. Several machine learning and deep learning approaches have also been proposed to achieve this goal. All such approaches are suitable for an offline mode, where the data for emotion classification are stored and can be accessed infinitely. However, these offline mode approaches are inappropriate for real-time emotion classification when the data are coming in a continuous stream and data can be seen to the model at once only. We also need real-time responses according to the emotional state. For this, we propose a real-time emotion classification system (RECS)-based Logistic Regression (LR) trained in an online fashion using the Stochastic Gradient Descent (SGD) algorithm. The proposed RECS is capable of classifying emotions in real-time by training the model in an online fashion using an EEG signal stream. To validate the performance of RECS, we have used the DEAP data set, which is the most widely used benchmark data set for emotion classification. The results show that the proposed approach can effectively classify emotions in real-time from the EEG data stream, which achieved a better accuracy and F1-score than other offline and online approaches. The developed real-time emotion classification system is analyzed in an e-learning context scenario.
Open AccessReal-Time Emotion Classification Using EEG Data Stream in E-Learning Contexts
In face-to-face and online learning, emotions and emotional intelligence have an influence and play an essential role. Learners’ emotions are crucial for e-learning system because they promote or restrain the learning. Many researchers have investigated the impacts of emotions in enhancing and maximizing e-learning outcomes. Several machine learning and deep learning approaches have also been proposed to achieve this goal. All such approaches are suitable for an offline mode, where the data for emotion classification are stored and can be accessed infinitely. However, these offline mode approaches are inappropriate for real-time emotion classification when the data are coming in a continuous stream and data can be seen to the model at once only. We also need real-time responses according to the emotional state. For this, we propose a real-time emotion classification system (RECS)-based Logistic Regression (LR) trained in an online fashion using the Stochastic Gradient Descent (SGD) algorithm. The proposed RECS is capable of classifying emotions in real-time by training the model in an online fashion using an EEG signal stream. To validate the performance of RECS, we have used the DEAP data set, which is the most widely used benchmark data set for emotion classification. The results show that the proposed approach can effectively classify emotions in real-time from the EEG data stream, which achieved a better accuracy and F1-score than other offline and online approaches. The developed real-time emotion classification system is analyzed in an e-learning context scenario.
- Open Access
- 18 November 2019
- Published by MDPI AG in Applied Sciences
- Vol. 9 (22) , 4960
A Granularity-Based Intelligent Tutoring System for Zooarchaeology
This paper presents a tutoring system which uses three different granularities for helping students to classify animals from bone fragments in zooarchaeology. The 3406 bone remains, which have 64 attributes, were obtained from the excavation of the Middle Palaeolithic site of El Salt (Alicante, Spain). The coarse granularity performs a five-class prediction, the medium a twelve-class prediction, and the fine a fifteen-class prediction. In the coarse granularity, the results show that the first 10 most relevant attributes for classification are width, bone, thickness, length, bone fragment, anatomical group, long bone circumference, X, Y, and Z. Based on those results, a user-friendly interface of the tutor has been built in order to train archaeology students to classify new remains using the coarse granularity. A pilot has been performed in the 2019 excavation season in Abric del Pastor (Alicante, Spain), where the automatic tutoring system was used by students to classify 51 new remains. The pilot experience demonstrated the usefulness of the tutoring system both for students when facing their first classification activities and also for seniors since the tutoring system gives them valuable clues for helping in difficult classification problems.
- 18 November 2019
- Published by MDPI AG in Applied Sciences
- Vol. 9 (22) , 4960
Open AccessA Granularity-Based Intelligent Tutoring System for Zooarchaeology
This paper presents a tutoring system which uses three different granularities for helping students to classify animals from bone fragments in zooarchaeology. The 3406 bone remains, which have 64 attributes, were obtained from the excavation of the Middle Palaeolithic site of El Salt (Alicante, Spain). The coarse granularity performs a five-class prediction, the medium a twelve-class prediction, and the fine a fifteen-class prediction. In the coarse granularity, the results show that the first 10 most relevant attributes for classification are width, bone, thickness, length, bone fragment, anatomical group, long bone circumference, X, Y, and Z. Based on those results, a user-friendly interface of the tutor has been built in order to train archaeology students to classify new remains using the coarse granularity. A pilot has been performed in the 2019 excavation season in Abric del Pastor (Alicante, Spain), where the automatic tutoring system was used by students to classify 51 new remains. The pilot experience demonstrated the usefulness of the tutoring system both for students when facing their first classification activities and also for seniors since the tutoring system gives them valuable clues for helping in difficult classification problems.
- Open Access
- 29 October 2009
- Published by Association for Computing Machinery (ACM)
- p. 207-214
Assisted animated production creation and programme generation
The creation of animated productions is a labour intensive process. Whether the end result is a large-budget motion picture, or a small-scale internet production, there is invariably a large amount of time spent in creating the timeline, arranging assets, previewing and editing. This iterative process is necessary in large-scale productions but can become repetitive and frustrating when the end result is a small production that may have similar elements to previous work. We present a workflow system and framework that are able to both greatly facilitate animated programme production and introduce an element of procedural generation. We further present the Programme Editor, an application designed to be a powerful front end for the framework. The principal contribution of this work is the creation of an XML-based scripting engine that can be used to create an animated production. This permits several techniques, tools and workflows to interchange information, allows rapid incorporation of further tools, and furthermore facilitates the complete automatisation of the production process.
- 29 October 2009
- Published by Association for Computing Machinery (ACM)
- p. 207-214
Open AccessAssisted animated production creation and programme generation
The creation of animated productions is a labour intensive process. Whether the end result is a large-budget motion picture, or a small-scale internet production, there is invariably a large amount of time spent in creating the timeline, arranging assets, previewing and editing. This iterative process is necessary in large-scale productions but can become repetitive and frustrating when the end result is a small production that may have similar elements to previous work. We present a workflow system and framework that are able to both greatly facilitate animated programme production and introduce an element of procedural generation. We further present the Programme Editor, an application designed to be a powerful front end for the framework. The principal contribution of this work is the creation of an XML-based scripting engine that can be used to create an animated production. This permits several techniques, tools and workflows to interchange information, allows rapid incorporation of further tools, and furthermore facilitates the complete automatisation of the production process.
- Open Access
- 1 July 1999
- Published by Association for Computing Machinery (ACM)
- p. 95
Gaia
The Gaia hypothesis that life on Earth is part of a self-regulating system that binds the atmosphere to the continents and oceans in a quasi physiological process. Gaia posits first that life on Earth is a planetary phenomenon and second that living organisms have to regulate their planetary environment otherwise the forces of physical and chemical evolution would render it uninhabitable. The Gaian perspective has spawned new avenues of scientific inquiry aimed at furthering understanding of biogeochemical cycles, especially in the atmospheric sciences. Gaia caught the public imagination in the 1980s, along with an emerging conviction in the scientific community that the global environment was being seriously affected by human action. It is important to distinguish between the Gaia hypothesis of earth science, and Gaia, the popular symbol of environmentalists, which underpins a call for an ecological egalitarianism to end all forms of human domination of nature.
- 1 July 1999
- Published by Association for Computing Machinery (ACM)
- p. 95
Open AccessGaia
The Gaia hypothesis that life on Earth is part of a self-regulating system that binds the atmosphere to the continents and oceans in a quasi physiological process. Gaia posits first that life on Earth is a planetary phenomenon and second that living organisms have to regulate their planetary environment otherwise the forces of physical and chemical evolution would render it uninhabitable. The Gaian perspective has spawned new avenues of scientific inquiry aimed at furthering understanding of biogeochemical cycles, especially in the atmospheric sciences. Gaia caught the public imagination in the 1980s, along with an emerging conviction in the scientific community that the global environment was being seriously affected by human action. It is important to distinguish between the Gaia hypothesis of earth science, and Gaia, the popular symbol of environmentalists, which underpins a call for an ecological egalitarianism to end all forms of human domination of nature.