TY - GEN
T1 - EEG Data Analytics to Distinguish Happy and Sad Emotions Based on Statistical Features
AU - Pamungkas, Yuri
AU - Wibawa, Adhi Dharma
AU - Purnomo, Mauridhi Hery
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Affective computing is part of the important study of Human-Computer Interaction. Currently, EEG-based affective computing (emotion recognition) has become an interesting issue to be studied further. Emotions are not only closely related to aspects of HCI but also affect human health. Meanwhile, EEG is also considered a transparent tool in objectively revealing human emotions because the brain naturally produces EEG signals. This study focuses on comparing and classifying human emotions (happy and sad) based on EEG data. The channels used for recording EEG data are F7, F8, FP1, and FP2. Data preprocessing such as signal filtering, Independent Component Analysis, and Band Decomposition aims to clean the raw signal from artifacts and separate the signals according to specific frequency bands (Alpha, Beta, and Gamma). Then, statistical feature extraction is performed in the time domain to obtain the Mean values, Mean Absolute Value (MAV), and Standard Deviation values for further data analysis. The results show that emotion of happy has a higher feature value compared to emotion of sad. In the classification of happy and sad emotions using several algorithms, Random Forest signifies the highest classification accuracy (88.90%), compared to other algorithms such as SVM (86.70%), K-NN (88.87%), and Naive Bayes (86.63%).
AB - Affective computing is part of the important study of Human-Computer Interaction. Currently, EEG-based affective computing (emotion recognition) has become an interesting issue to be studied further. Emotions are not only closely related to aspects of HCI but also affect human health. Meanwhile, EEG is also considered a transparent tool in objectively revealing human emotions because the brain naturally produces EEG signals. This study focuses on comparing and classifying human emotions (happy and sad) based on EEG data. The channels used for recording EEG data are F7, F8, FP1, and FP2. Data preprocessing such as signal filtering, Independent Component Analysis, and Band Decomposition aims to clean the raw signal from artifacts and separate the signals according to specific frequency bands (Alpha, Beta, and Gamma). Then, statistical feature extraction is performed in the time domain to obtain the Mean values, Mean Absolute Value (MAV), and Standard Deviation values for further data analysis. The results show that emotion of happy has a higher feature value compared to emotion of sad. In the classification of happy and sad emotions using several algorithms, Random Forest signifies the highest classification accuracy (88.90%), compared to other algorithms such as SVM (86.70%), K-NN (88.87%), and Naive Bayes (86.63%).
KW - EEG-based affective computing
KW - KNN
KW - SVM
KW - emotion recognition
KW - random forest
UR - http://www.scopus.com/inward/record.url?scp=85126653626&partnerID=8YFLogxK
U2 - 10.1109/ISRITI54043.2021.9702766
DO - 10.1109/ISRITI54043.2021.9702766
M3 - Conference contribution
AN - SCOPUS:85126653626
T3 - 2021 4th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2021
SP - 345
EP - 350
BT - 2021 4th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2021
Y2 - 16 December 2021
ER -
