jueves, 20 de octubre de 2016
A Dynamic Recognition Approach of Emotional States for Car Drivers
Authors: Jose Aguilar, Danilo Chavez, and Jorge Cordero
Abstract:
In this paper, we propose a recognition model of emotional state using multi-modal perception, a temporal logic paradigm (in particular, we use chronicles), and dynamical patterns. In this way, our recognition approach is based on chronicles to model the patterns, a definition of the emotions as dynamic patterns, and the idea that they are perceived in a multi-modal way (sound, vision, etc.). In this paper, we present these elements of our approach, and give one example of an application for the recognition of the emotions of the driver of a vehicle.
Keywords: Recognition of emotions, Chronicles, Dynamic patterns recognition
Link: http://link.springer.com/chapter/10.1007/978-3-319-48024-4_13
DOI: 10.1007/978-3-319-48024-4_13
A general framework for learning analytic in a smart classroom
Authors: Jose Aguilar, Priscila Valdiviezo, Jorge Cordero, Guido Riofrio, and Eduardo Encalada
Abstract. In this paper, we propose the utilization of the “Learning Analytics” paradigm in a Smart Classroom, a classroom that integrates artificial intelligence technology on the educational process. Learning Analytics can extract knowledge from the Smart Classroom platform, to better understand students and his/her learning processes. In this way, a Smart Classroom can understand and optimize
the learning process and the teaching environments proposed. The smart classroom can adapt its components to improve students’ performance, among other aspects. Particularly, this paper proposes a framework about how the Learning Analytics paradigm can be used in a Smart Classroom, in order to provide knowledge about the activities taking place within it. The framework is defined like a closed cycle of Learning Analytics tasks, which generate metrics used like feedback to optimize the pedagogical model proposed by the smart Classroom. The metrics evaluate the learning process and pedagogical practice provided by the smart Classroom. So, our main contribution is about how the Learning Analytics paradigm can be used in a Smart Classroom in order to improve the students’
performance.
Keywords: Learning analytics, Smart classroom, Ambient intelligence, Data mining
Link: http://link.springer.com/chapter/10.1007/978-3-319-48024-4_17
DOI: 10.1007/978-3-319-48024-4_17
Abstract. In this paper, we propose the utilization of the “Learning Analytics” paradigm in a Smart Classroom, a classroom that integrates artificial intelligence technology on the educational process. Learning Analytics can extract knowledge from the Smart Classroom platform, to better understand students and his/her learning processes. In this way, a Smart Classroom can understand and optimize
the learning process and the teaching environments proposed. The smart classroom can adapt its components to improve students’ performance, among other aspects. Particularly, this paper proposes a framework about how the Learning Analytics paradigm can be used in a Smart Classroom, in order to provide knowledge about the activities taking place within it. The framework is defined like a closed cycle of Learning Analytics tasks, which generate metrics used like feedback to optimize the pedagogical model proposed by the smart Classroom. The metrics evaluate the learning process and pedagogical practice provided by the smart Classroom. So, our main contribution is about how the Learning Analytics paradigm can be used in a Smart Classroom in order to improve the students’
performance.
Keywords: Learning analytics, Smart classroom, Ambient intelligence, Data mining
Link: http://link.springer.com/chapter/10.1007/978-3-319-48024-4_17
DOI: 10.1007/978-3-319-48024-4_17
Suscribirse a:
Entradas (Atom)