SwePub
Sök i LIBRIS databas

  Utökad sökning

WFRF:(Rosa Zurera Manuel)
 

Sökning: WFRF:(Rosa Zurera Manuel) > (2020-2024) > Initializing the we...

  • Mohino-Herranz, InmaNational Institute of Aerospace Technology, Madrid, Spain (författare)

Initializing the weights of a multilayer perceptron for activity and emotion recognition

  • Artikel/kapitelEngelska2024

Förlag, utgivningsår, omfång ...

  • 2024
  • printrdacarrier

Nummerbeteckningar

  • LIBRIS-ID:oai:DiVA.org:hb-32070
  • https://urn.kb.se/resolve?urn=urn:nbn:se:hb:diva-32070URI
  • https://doi.org/10.1016/j.eswa.2024.124305DOI
  • http://kipublications.ki.se/Default.aspx?queryparsed=id:158557426URI

Kompletterande språkuppgifter

  • Språk:engelska
  • Sammanfattning på:engelska

Ingår i deldatabas

Klassifikation

  • Ämneskategori:ref swepub-contenttype
  • Ämneskategori:art swepub-publicationtype

Anmärkningar

  • 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 och genrebeteckningar

Biuppslag (personer, institutioner, konferenser, titlar ...)

  • Gil-Pita, RobertoSignal Theory and Communications Department at the University of Alcalá, Madrid, Spain (författare)
  • García-Gómez, JoaquínSignal Theory and Communications Department at the University of Alcalá, Madrid, Spain (författare)
  • Alonso-Diaz, SagrarioNational Institute of Aerospace Technology, Madrid, Spain (författare)
  • Rosa-Zurera, ManuelSignal Theory and Communications Department at the University of Alcalá, Madrid, Spain (författare)
  • Seoane, Fernando,1976-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(Swepub:hb)fsm (författare)
  • National Institute of Aerospace Technology, Madrid, SpainSignal Theory and Communications Department at the University of Alcalá, Madrid, Spain (creator_code:org_t)

Sammanhörande titlar

  • Ingår i:Expert systems with applications2530957-41741873-6793

Internetlänk

Hitta via bibliotek

Till lärosätets databas

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy