viernes, 22 de abril de 2016
Reconocimiento multimodal de emociones en un entorno inteligente basado en crónicas
Autores—Jorge Cordero, Jose Aguilar
Resumen—En este trabajo se presenta un modelo de reconocimiento multimodal de emociones en tiempo real, para un salón de clases inteligente, basado en crónicas. En nuestro modelo se analizan las emociones a reconocer que están relacionadas con el proceso de aprendizaje, como son: felicidad, tristeza, ira, miedo, y sorpresa. El reconocimiento es multimodal por considerarse diferentes tipos de eventos y formas sensoriales en el proceso de reconocimiento: facial, acústico, lenguaje corporal, y otras variables propias del salón de clases inteligente, como la temperatura, el ruido la luminosidad, entre otros. Este enfoque multimodal permite modelar más precisamente las emociones del usuario, respecto a sistemas de reconocimiento de emociones unimodales.
Palabras claves— computación afectiva, reconocimiento de emociones, crónicas, ambientes inteligentes.
Conferencia
Congreso Internacional de Sistemas Inteligentes y Nuevas Tecnologías -COISINT 2016
Link: https://www.researchgate.net/publication/307888062_Reconocimiento_multimodal_de_emociones_en_un_entorno_inteligente_basado_en_cronicas
Link2: http://www.academia.edu/28352784/Reconocimiento_multimodal_de_emociones_en_un_entorno_inteligente_basado_en_cr%C3%B3nicas
miércoles, 2 de marzo de 2016
Specification of a Smart Classroom Based on Agent Communities
Authors: Jose Aguilar, Luis Chamba-Eras, Jorge Cordero
Abstract
For the development of distributed applications, it is required to define a formalization of the process of implementation. Particularly, we are interested in one type of Ambient Intelligence (AmI), the Smart Classroom. In this paper we propose the implementation of a Smart Classroom, called SaCI, using the concept of communities of agents. With this concept, we carry out the definition and implementation of sets of agents according to their roles, functionalities, characteristics, among others, in SaCI. Each community can be designed and implemented independently and later be integrated in SaCI. In this paper we present this approach and its implementation in SaCI.
Keywords
Smart educational environment, Multi-agent system, Ambient intelligence
Link: http://link.springer.com/chapter/10.1007%2F978-3-319-31232-3_95
DOI: 10.1007/978-3-319-31232-3_95
Abstract
For the development of distributed applications, it is required to define a formalization of the process of implementation. Particularly, we are interested in one type of Ambient Intelligence (AmI), the Smart Classroom. In this paper we propose the implementation of a Smart Classroom, called SaCI, using the concept of communities of agents. With this concept, we carry out the definition and implementation of sets of agents according to their roles, functionalities, characteristics, among others, in SaCI. Each community can be designed and implemented independently and later be integrated in SaCI. In this paper we present this approach and its implementation in SaCI.
Keywords
Smart educational environment, Multi-agent system, Ambient intelligence
Link: http://link.springer.com/chapter/10.1007%2F978-3-319-31232-3_95
DOI: 10.1007/978-3-319-31232-3_95
Cloud Computing in Smart Educational Environments: Application in Learning Analytics as Service
Authors: Manuel Sánchez, Jose Aguilar, Jorge Cordero, Priscila Valdiviezo-Díaz, Luis
Barba-Guamán, Luis Chamba-Eras
Abstract
In this paper, we present an extension of a Middleware for Smart Educational Environments based in agents, using the paradigm of Cloud Computing. In that sense, we detail the Middleware components, which enable the process of management of the Cloud Computing. We also present the utilization of this Middleware to provide services on the cloud about task of Learning Analytics that allow processing of data of students and learning environments, to understand and optimize the learning processes.
Keywords
Cloud computing, Smart educational environment, Learning analytics
Link: http://link.springer.com/chapter/10.1007/978-3-319-31232-3_94
DOI: 10.1007/978-3-319-31232-3_94
Barba-Guamán, Luis Chamba-Eras
Abstract
In this paper, we present an extension of a Middleware for Smart Educational Environments based in agents, using the paradigm of Cloud Computing. In that sense, we detail the Middleware components, which enable the process of management of the Cloud Computing. We also present the utilization of this Middleware to provide services on the cloud about task of Learning Analytics that allow processing of data of students and learning environments, to understand and optimize the learning processes.
Keywords
Cloud computing, Smart educational environment, Learning analytics
Link: http://link.springer.com/chapter/10.1007/978-3-319-31232-3_94
DOI: 10.1007/978-3-319-31232-3_94
miércoles, 21 de octubre de 2015
A business intelligence model for online tutoring process
Authors: Priscila Valdiviezo-Díaz, Jorge Cordero, Ruth Reátegui, Jose Aguilar
Abstract:
This work aims to implement business intelligence strategies in an educational institution based on the distance education, particularly in the online tutoring process. In this paper we propose to use the business intelligence paradigm to analyze the online tutoring process, based on the data collected on the interactions of students and teachers in a virtual learning environment, and the results recorded in the institutional academic system of evaluations. This analysis should answer the following questions: 1) Can we define a model of online tutoring that can adapt to each student profile? 2) Can we predict the success of an online tutoring process for a course and a student given? To this purpose, this paper presents three aspects: characterize and determine the key elements in an online tutoring process, build a descriptive model of the online tutoring process, and build a predictive model of the success of the online tutoring process. The models to be defined will be based on data mining techniques, and will be obtained from the current data stored in transactional databases of the University. This data is preprocessed with ETL techniques to build a multidimensional model, and the key elements are obtained through operations OLAP.
Keywords—Business Intelligence Systems, Data Warehouses, Learning Analytics, Online Tutoring
Published in: Frontiers in Education Conference (FIE), 2015. 32614 2015. IEEE
DOI: 10.1109/FIE.2015.7344385
Link: http://ieeexplore.ieee.org/document/7344385/
Abstract:
This work aims to implement business intelligence strategies in an educational institution based on the distance education, particularly in the online tutoring process. In this paper we propose to use the business intelligence paradigm to analyze the online tutoring process, based on the data collected on the interactions of students and teachers in a virtual learning environment, and the results recorded in the institutional academic system of evaluations. This analysis should answer the following questions: 1) Can we define a model of online tutoring that can adapt to each student profile? 2) Can we predict the success of an online tutoring process for a course and a student given? To this purpose, this paper presents three aspects: characterize and determine the key elements in an online tutoring process, build a descriptive model of the online tutoring process, and build a predictive model of the success of the online tutoring process. The models to be defined will be based on data mining techniques, and will be obtained from the current data stored in transactional databases of the University. This data is preprocessed with ETL techniques to build a multidimensional model, and the key elements are obtained through operations OLAP.
Keywords—Business Intelligence Systems, Data Warehouses, Learning Analytics, Online Tutoring
Published in: Frontiers in Education Conference (FIE), 2015. 32614 2015. IEEE
DOI: 10.1109/FIE.2015.7344385
Link: http://ieeexplore.ieee.org/document/7344385/
jueves, 30 de julio de 2015
Conceptual Design of a Smart Classroom Based on Multiagent Systems
Authors: Jose Aguilar, Priscila Valdiviezo, Jorge Cordero and Manuel Sánchez
Abstract - The smart environments have been used in different domains: home, educational and health centers, etc. Particularly, a smart environment in education must integrate different aspects linked to virtual and presencial education, the profile of the students, to the pedagogical paradigm used, etc., in real time. In this paper we characterize a smart classroom considering these aspects, using the multiagent systems paradigm. Particularly, we define the different components of a smart classroom with their properties. Based on that, we describe these components like agents using MASINA, a methodology to specify multiagent systems. We define two frameworks of agents which describe the different types of components in a smart classroom (of software and of hardware), and give examples of applications of these two frameworks in a device and a software of a smart classroom. Finally, we show an example of conversation in a smart classroom based on our multiagents approach, specifically in a work session.
Keywords: Smart Classroom, Multiagent System, AmI, Middleware
Proceedings on the International Conference on Artificial Intelligence (ICAI): 471-477. Athens: The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp). (2015)
Link: http://search.proquest.com/openview/930c8d0a31e0faf9bbd8a2a44137e85a/1?pq-origsite=gscholar
Abstract - The smart environments have been used in different domains: home, educational and health centers, etc. Particularly, a smart environment in education must integrate different aspects linked to virtual and presencial education, the profile of the students, to the pedagogical paradigm used, etc., in real time. In this paper we characterize a smart classroom considering these aspects, using the multiagent systems paradigm. Particularly, we define the different components of a smart classroom with their properties. Based on that, we describe these components like agents using MASINA, a methodology to specify multiagent systems. We define two frameworks of agents which describe the different types of components in a smart classroom (of software and of hardware), and give examples of applications of these two frameworks in a device and a software of a smart classroom. Finally, we show an example of conversation in a smart classroom based on our multiagents approach, specifically in a work session.
Keywords: Smart Classroom, Multiagent System, AmI, Middleware
Proceedings on the International Conference on Artificial Intelligence (ICAI): 471-477. Athens: The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp). (2015)
Link: http://search.proquest.com/openview/930c8d0a31e0faf9bbd8a2a44137e85a/1?pq-origsite=gscholar
Suscribirse a:
Entradas (Atom)