Hrvatska znanstvena Sekcija img
3 gif
 O projektu
4 gif
Pregledavanje radova
Jednostavno pretraživanje
Napredno pretraživanje
Skupni podaci
Upis novih radova
Ispravci prijavljenih radova
Ostale bibliografije
Slični projekti
 Bibliografske baze podataka

Pregled bibliografske jedinice broj: 701966


Autori: Kukolja, Davor; Popović, Siniša; Horvat, Marko; Kovač, Bernard; Ćosić, Krešimir
Naslov: Comparative analysis of emotion estimation methods based on physiological measurements for real-time applications
Izvornik: International journal of human-computer studies (1071-5819) 72 (2014), 10/11; 717-727
Vrsta rada: članak
Ključne riječi: affective computing; physiology; emotion estimation; feature reduction; machine learning
In order to improve intelligent Human-Computer Interaction it is important to create a personalized adaptive emotion estimator that is able to learn over time emotional response idiosyncrasies of individual person and thus enhance estimation accuracy. This paper, with the aim of identifying preferable methods for such a concept, presents an experiment-based comparative study of seven feature reduction and seven machine learning methods commonly used for emotion estimation based on physiological signals. The analysis was performed on data obtained in an emotion elicitation experiment involving 14 participants. Specific discrete emotions were targeted with stimuli from the International Affective Picture System database. The experiment was necessary to achieve the uniformity in the various aspects of emotion elicitation, data processing, feature calculation, self-reporting procedures and estimation evaluation, in order to avoid inconsistency problems that arise when results from studies that use different emotion- related databases are mutually compared. The results of the performed experiment indicate that the combination of a multilayer perceptron (MLP) with sequential floating forward selection (SFFS) exhibited the highest accuracy in discrete emotion classification based on physiological features calculated from ECG, respiration, skin conductance and skin temperature. Using leave-one-session-out crossvalidation method, 60.3% accuracy in classification of 5 discrete emotions (sadness, disgust, fear, happiness and neutral) was obtained. In order to identify which methods may be the most suitable for real-time estimator adaptation, execution and learning times of emotion estimators were also comparatively analyzed. Based on this analysis, preferred feature reduction method for real-time estimator adaptation was minimum redundancy – maximum relevance (mRMR), which was the fastest approach in terms of combined execution and learning time, as well as the second best in accuracy, after SFFS. In combination with mRMR, highest accuracies were achieved by k-nearest neighbor (kNN) and MLP with negligible difference (50.33% versus 50.54%) ; however, mRMR+kNN is preferable option for real-time estimator adaptation due to considerably lower combined execution and learning time of kNN versus MLP.
Projekt / tema: 036-0000000-2029
Izvorni jezik: ENG
Rad je indeksiran u
bazama podataka:
Current Contents Connect (CCC)
Science Citation Index Expanded (SCI-EXP) (sastavni dio Web of Science Core Collectiona)
Social Science Citation Index (SSCI) (sastavni dio Web of Science Core Collectiona)
Kategorija: Znanstveni
Znanstvena područja:
URL Internet adrese:
Broj citata:
DOI: 10.1016/j.ijhcs.2014.05.006
URL cjelovitog teksta:
Google Scholar: Comparative analysis of emotion estimation methods based on physiological measurements for real-time applications
Upisao u CROSBI: Davor Kukolja (, 23. Lip. 2014. u 20:37 sati

  Verzija za printanje   za tiskati