Wavelet based machine learning models for classification of human emotions using EEG signal
Humans have the ability to portray different expressions contrary to the emotional state of mind. Therefore, it is difficult to judge the human's real emotional state simply by judging the physical appearance. Although researchers are working on facial expressions analysis, voice recognition, g...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-12-01
|
| Series: | Measurement: Sensors |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266591742200188X |
| _version_ | 1797988755508822016 |
|---|---|
| author | Shashi Kumar G S Niranjana Sampathila Tanishq Tanmay |
| author_facet | Shashi Kumar G S Niranjana Sampathila Tanishq Tanmay |
| author_sort | Shashi Kumar G S |
| collection | DOAJ |
| description | Humans have the ability to portray different expressions contrary to the emotional state of mind. Therefore, it is difficult to judge the human's real emotional state simply by judging the physical appearance. Although researchers are working on facial expressions analysis, voice recognition, gesture recognition accuracy levels of such analysis are much less and the results are not reliable. Classifying the human emotions with machine learning models and extracting discrete wavelet features of Electroencephalogram (EEG) is proposed. The EEG data from Database for Emotion Analysis using Physiological signal (DEAP) online datasets is used for analysis and consists of peripheral biological signals as well as EEG recordings. EEG signal is collected from 32 subjects while watching 40 1-min-long music videos. Each video clip is rated by the participants in terms of the level of Valence, Arousal, Dominance. In the proposed work we have considered a significant band of EEG with a reduced frontal electrode (Fp1, F3, F4, Fp2) to get a comparable good result. The accuracy obtained from K- nearest neighbour (KNN), Fine KNN and Support Vector Machine (SVM) are 92.5%, 90% and 90% respectively for Valence, Arousal and Dominance. |
| first_indexed | 2024-04-11T08:07:56Z |
| format | Article |
| id | doaj.art-4069a7b2afc9454e9f1059b6fc0cdfb7 |
| institution | Directory Open Access Journal |
| issn | 2665-9174 |
| language | English |
| last_indexed | 2024-04-11T08:07:56Z |
| publishDate | 2022-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Measurement: Sensors |
| spelling | doaj.art-4069a7b2afc9454e9f1059b6fc0cdfb72022-12-22T04:35:27ZengElsevierMeasurement: Sensors2665-91742022-12-0124100554Wavelet based machine learning models for classification of human emotions using EEG signalShashi Kumar G S0Niranjana Sampathila1Tanishq Tanmay2Department of Electronics and Communication Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education (MAHE), Manipal, Karnataka, 576 104, IndiaDepartment of Biomedical Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education (MAHE), Manipal, Karnataka, 576 104, India; Corresponding author.Department of Electronics and Communication Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education (MAHE), Manipal, Karnataka, 576 104, IndiaHumans have the ability to portray different expressions contrary to the emotional state of mind. Therefore, it is difficult to judge the human's real emotional state simply by judging the physical appearance. Although researchers are working on facial expressions analysis, voice recognition, gesture recognition accuracy levels of such analysis are much less and the results are not reliable. Classifying the human emotions with machine learning models and extracting discrete wavelet features of Electroencephalogram (EEG) is proposed. The EEG data from Database for Emotion Analysis using Physiological signal (DEAP) online datasets is used for analysis and consists of peripheral biological signals as well as EEG recordings. EEG signal is collected from 32 subjects while watching 40 1-min-long music videos. Each video clip is rated by the participants in terms of the level of Valence, Arousal, Dominance. In the proposed work we have considered a significant band of EEG with a reduced frontal electrode (Fp1, F3, F4, Fp2) to get a comparable good result. The accuracy obtained from K- nearest neighbour (KNN), Fine KNN and Support Vector Machine (SVM) are 92.5%, 90% and 90% respectively for Valence, Arousal and Dominance.http://www.sciencedirect.com/science/article/pii/S266591742200188XElectroencephalogramDiscrete wavelet transformMachine learningConvolutional neural networkSupport vector machine |
| spellingShingle | Shashi Kumar G S Niranjana Sampathila Tanishq Tanmay Wavelet based machine learning models for classification of human emotions using EEG signal Measurement: Sensors Electroencephalogram Discrete wavelet transform Machine learning Convolutional neural network Support vector machine |
| title | Wavelet based machine learning models for classification of human emotions using EEG signal |
| title_full | Wavelet based machine learning models for classification of human emotions using EEG signal |
| title_fullStr | Wavelet based machine learning models for classification of human emotions using EEG signal |
| title_full_unstemmed | Wavelet based machine learning models for classification of human emotions using EEG signal |
| title_short | Wavelet based machine learning models for classification of human emotions using EEG signal |
| title_sort | wavelet based machine learning models for classification of human emotions using eeg signal |
| topic | Electroencephalogram Discrete wavelet transform Machine learning Convolutional neural network Support vector machine |
| url | http://www.sciencedirect.com/science/article/pii/S266591742200188X |
| work_keys_str_mv | AT shashikumargs waveletbasedmachinelearningmodelsforclassificationofhumanemotionsusingeegsignal AT niranjanasampathila waveletbasedmachinelearningmodelsforclassificationofhumanemotionsusingeegsignal AT tanishqtanmay waveletbasedmachinelearningmodelsforclassificationofhumanemotionsusingeegsignal |