Sökning: id:"swepub:oai:DiVA.org:hb-32070" >
Initializing the we...
Initializing the weights of a multilayer perceptron for activity and emotion recognition
-
- Mohino-Herranz, Inma (författare)
- National Institute of Aerospace Technology, Madrid, Spain
-
- Gil-Pita, Roberto (författare)
- Signal Theory and Communications Department at the University of Alcalá, Madrid, Spain
-
- García-Gómez, Joaquín (författare)
- Signal Theory and Communications Department at the University of Alcalá, Madrid, Spain
-
visa fler...
-
- Alonso-Diaz, Sagrario (författare)
- National Institute of Aerospace Technology, Madrid, Spain
-
- Rosa-Zurera, Manuel (författare)
- Signal Theory and Communications Department at the University of Alcalá, Madrid, Spain
-
- Seoane, Fernando, 1976- (författare)
- Högskolan i Borås,Akademin för textil, teknik och ekonomi,Akademin för vård, arbetsliv och välfärd,Karolinska Institutet Department of Clinical Science, Sweden; Departments of Medical Technology and Clinical Physiology at Karolinska University Hospital, Sweden
-
visa färre...
-
(creator_code:org_t)
- 2024
- 2024
- Engelska.
-
Ingår i: Expert systems with applications. - 0957-4174 .- 1873-6793. ; 253
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Conducting an analysis of human behavior is an intriguing topic for many researchers. Within this field, machine learning can be applied to classify activities and emotions by analyzing physiological signals. However, the limited size of available databases poses challenges for the generalization of classifiers. This paper proposes a method to enhance the generalization of neural network-based classifiers by intelligently initializing weights for emotion and activity recognition. The signals under consideration are electrocardiogram, thoracic electrical bioimpedance, and electrodermal activity. The database used comprises recordings from 40 subjects performing various tasks that induce emotions and activities. The performance of the proposed method is compared with several standard machine learning and deep learning classifiers typically employed in emotion and activity recognition. This study involves two primary assessments. First is the activity recognition task, encompassing classes such as neutral, emotional, mental, and physical activity, where results close to 20% accuracy are achieved using the three physiological signals. Second, the emotion recognition assessment aims to differentiate between emotions like neutral, sadness, and disgust. An error probability close to 15% is obtained using thoracic electrical bioimpedance and electrodermal activity. The proposed method yields the best results among the approaches evaluated.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Signalbehandling (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Signal Processing (hsv//eng)
Nyckelord
- Activity recognition
- Emotion recognition
- Physiological signals
- Weights initialization neural networks
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas