TY - JOUR
T1 - Using Black Hole Algorithm to Improve EEG-Based Emotion Recognition
AU - Munoz, Roberto
AU - Olivares, Rodrigo
AU - Taramasco, Carla
AU - Villarroel, Rodolfo
AU - Soto, Ricardo
AU - Barcelos, Thiago S.
AU - Merino, Erick
AU - Alonso-Sánchez, María Francisca
N1 - Funding Information:
Roberto Munoz and Rodrigo Olivares are supported by Postgraduate Grant of Pontificia Universidad Católica de Valparaíso (INF-PUCV 2015). Carla Taramasco and Rodrigo Olivares are supported by CONICYT/FONDEF/IDeA/ ID16I10449, CONICYT/STIC-AMSUD/17STIC-03, and CONICYT/MEC/MEC80170097 and CENS (National Center for Health Information Systems). Rodolfo Villarroel is funded by the VRIEA-PUCV 2017 039.440/2017 Grant. RicardoSoto is supportedbyGrantCONICYT/FONDECYT/ REGULAR/1160455. María Francisca Alonso-Sánchez is supported by CONICYT, FONDECYT INICIACION 11160212. Roberto Munoz and Carla Taramasco also acknowledge the Center for Research and Development inHealth Engineering of the Universidad de Valparaíso. Finally, the authors would like to thank Travis Jones for his valuable contributions to the elaboration of this paper.
Funding Information:
Roberto Munoz and Rodrigo Olivares are supported by Postgraduate Grant of Pontificia Universidad Católica de Valparaíso (INF-PUCV 2015). Carla Taramasco and Rodrigo Olivares are supported by CONICYT/FONDEF/IDeA/ ID16I10449, CONICYT/STIC-AMSUD/17STIC-03, and CONICYT/MEC/MEC80170097 and CENS (National Center for Health Information Systems). Rodolfo Villarroel is funded by the VRIEA-PUCV 2017 039.440/2017 Grant. RicardoSotoissupported byGrantCONICYT/FONDECYT/ REGULAR/1160455. María Francisca Alonso-Sánchez is supported by CONICYT, FONDECYT INICIACION 11160212. Roberto Munoz and Carla Taramasco also acknowledge the Center for Research and Development in Health Engineering of the Universidad de Valparaíso. Finally, the authors would like to thank Travis Jones for his valuable contributions to the elaboration of this paper.
Publisher Copyright:
© 2018 Roberto Munoz et al.
PY - 2018
Y1 - 2018
N2 - Emotions are a critical aspect of human behavior. One widely used technique for research in emotion measurement is based on the use of EEG signals. In general terms, the first step of signal processing is the elimination of noise, which can be done in manual or automatic terms. The next step is determining the feature vector using, for example, entropy calculation and its variations to generate a classification model. It is possible to use this approach to classify theoretical models such as the Circumplex model. This model proposes that emotions are distributed in a two-dimensional circular space. However, methods to determine the feature vector are highly susceptible to noise that may exist in the signal. In this article, a new method to adjust the classifier is proposed using metaheuristics based on the black hole algorithm. The method is aimed at obtaining results similar to those obtained with manual noise elimination methods. In order to evaluate the proposed method, the MAHNOB HCI Tagging Database was used. Results show that using the black hole algorithm to optimize the feature vector of the Support Vector Machine we obtained an accuracy of 92.56% over 30 executions.
AB - Emotions are a critical aspect of human behavior. One widely used technique for research in emotion measurement is based on the use of EEG signals. In general terms, the first step of signal processing is the elimination of noise, which can be done in manual or automatic terms. The next step is determining the feature vector using, for example, entropy calculation and its variations to generate a classification model. It is possible to use this approach to classify theoretical models such as the Circumplex model. This model proposes that emotions are distributed in a two-dimensional circular space. However, methods to determine the feature vector are highly susceptible to noise that may exist in the signal. In this article, a new method to adjust the classifier is proposed using metaheuristics based on the black hole algorithm. The method is aimed at obtaining results similar to those obtained with manual noise elimination methods. In order to evaluate the proposed method, the MAHNOB HCI Tagging Database was used. Results show that using the black hole algorithm to optimize the feature vector of the Support Vector Machine we obtained an accuracy of 92.56% over 30 executions.
UR - http://www.scopus.com/inward/record.url?scp=85049314093&partnerID=8YFLogxK
U2 - 10.1155/2018/3050214
DO - 10.1155/2018/3050214
M3 - Article
C2 - 29991942
AN - SCOPUS:85049314093
VL - 2018
JO - Computational Intelligence and Neuroscience
JF - Computational Intelligence and Neuroscience
SN - 1687-5265
M1 - 3050214
ER -