Publicación: Detección de emociones con pulsera inteligente Fitbit
Cargando...
Fecha
2022-09-26
Autores
Editor/a
Director/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
Atribución-NoComercial-SinDerivadas 4.0 Internacional
info:eu-repo/semantics/openAccess
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial
Resumen
En el campo de la detección de emociones, las pulseras inteligentes o smartbands son un posible sustituto de dispositivos más especializados. Este proyecto estudia la capacidad de la pulsera comercial Fibit Sense de detectar emociones. Se diseñó un experimento en el que se inducían distintas emociones a los participantes mientras la pulsera registraba su frecuencia cardíaca. Los participantes debían además evaluar su propio estado emocional. Se aplicó una serie de transformaciones a los datos obtenidos y se extrajeron varias características. Se eligió el modelo de regresión lineal múltiple para intentar predecir las emociones a partir de las medidas realizadas. Tras realizar varias pruebas los modelos finales no consiguieron una buena precisión diferenciando entre estados emocionales. No se ha podido determinar si la pulsera Fitbit Sense puede usarse para detectar emociones.
In the field of emotion detection, smartbands are a possible substitute for more specialized devices. This project studies the ability of the commercial smartband Fibit Sense to detect emotions. An experiment was designed in which different emotions were induced to the participants while the smartband recorded their heart rate. Participants also had to assess their own emotional state. A series of transformations were applied to the data obtained and several characteristics were extracted. The multiple linear regression model was chosen to try to predict emotions from the measurements made. After performing several tests, the final models did not achieve good accuracy differentiating between emotional states. It has not been possible to determine whether the Fitbit Sense can be used to detect emotions.
In the field of emotion detection, smartbands are a possible substitute for more specialized devices. This project studies the ability of the commercial smartband Fibit Sense to detect emotions. An experiment was designed in which different emotions were induced to the participants while the smartband recorded their heart rate. Participants also had to assess their own emotional state. A series of transformations were applied to the data obtained and several characteristics were extracted. The multiple linear regression model was chosen to try to predict emotions from the measurements made. After performing several tests, the final models did not achieve good accuracy differentiating between emotional states. It has not been possible to determine whether the Fitbit Sense can be used to detect emotions.
Descripción
Categorías UNESCO
Palabras clave
Citación
Centro
Facultades y escuelas::E.T.S. de Ingeniería Informática
Departamento
Inteligencia Artificial