TU Darmstadt / ULB / TUbiblio

The Emotive Couch - Learning Emotions by Capacitively Sensed

Rus, Silvia and Joshi, Dhanashree and Braun, Andreas and Kuijper, Arjan (2018):
The Emotive Couch - Learning Emotions by Capacitively Sensed.
In: Procedia Computer Science, Elsevier, pp. 263-270, 130, ISSN 18770509,
DOI: 10.1016/j.procs.2018.04.038,
[Online-Edition: https://doi.org/10.1016/j.procs.2018.04.038],
[Article]

Abstract

Affective computing allows machines to simulate and detect emotional states. The most common method is the observation of the face by camera. However, in our increasingly observed society, more privacy-aware methods are worth exploring that do not require facial images, but instead look at other physiological indicators of emotion. In this work we present the Emotive Couch, a sensor-augmented piece of smart furniture that detects proximity and motion of the human body. We present the design rationale and use standard machine learning techniques to detect the three basic emotions Anxiety, Interest, and Relaxation. We evaluate the performance of our approach with 15 participants in a study that includes various affect elicitation methods, achieving an accuracy of 77.7 %.

Item Type: Article
Erschienen: 2018
Creators: Rus, Silvia and Joshi, Dhanashree and Braun, Andreas and Kuijper, Arjan
Title: The Emotive Couch - Learning Emotions by Capacitively Sensed
Language: English
Abstract:

Affective computing allows machines to simulate and detect emotional states. The most common method is the observation of the face by camera. However, in our increasingly observed society, more privacy-aware methods are worth exploring that do not require facial images, but instead look at other physiological indicators of emotion. In this work we present the Emotive Couch, a sensor-augmented piece of smart furniture that detects proximity and motion of the human body. We present the design rationale and use standard machine learning techniques to detect the three basic emotions Anxiety, Interest, and Relaxation. We evaluate the performance of our approach with 15 participants in a study that includes various affect elicitation methods, achieving an accuracy of 77.7 %.

Journal or Publication Title: Procedia Computer Science
Volume: 130
Publisher: Elsevier
Uncontrolled Keywords: Affective computing, Emotion detection, Capacitive proximity sensing
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Mathematical and Applied Visual Computing
Date Deposited: 10 Jul 2019 08:26
DOI: 10.1016/j.procs.2018.04.038
Official URL: https://doi.org/10.1016/j.procs.2018.04.038
Export:

Optionen (nur für Redakteure)

View Item View Item