A Comparative Study on Prominent Connectivity Features for Emotion Recognition From EEG
Classifying distinct human emotions, the fundamental purpose of brain-computer interface research, is essential for providing instant personalized services and assistance to individuals. With such emerging applications for individuals, several techniques have been proposed recently to explore intera...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10092746/ |
| _version_ | 1797842501721128960 |
|---|---|
| author | Mahfuza Akter Maria M. A. H. Akhand A. B. M. Aowlad Hossain Md. Abdus Samad Kamal Kou Yamada |
| author_facet | Mahfuza Akter Maria M. A. H. Akhand A. B. M. Aowlad Hossain Md. Abdus Samad Kamal Kou Yamada |
| author_sort | Mahfuza Akter Maria |
| collection | DOAJ |
| description | Classifying distinct human emotions, the fundamental purpose of brain-computer interface research, is essential for providing instant personalized services and assistance to individuals. With such emerging applications for individuals, several techniques have been proposed recently to explore interactions between brain regions, such as correlation, synchronization, and dependence. Notably, functional and effective connectivity methods are applied to assess the relationships between different brain areas. The primary objective of this study is to compare the frequently used functional and effective connectivity methods to recognize emotion using Electroencephalogram (EEG) signals. This paper uses a benchmark emotional EEG dataset consisting of 32 channels of EEG signals collected from 32 subjects while they were watching 40 emotional music videos. Specifically, correlation, phase synchronization, and mutual information are used to measure functional brain connectivity, and transfer entropy is used to acquire effective brain connectivity. After extracting the features, they are represented in a two-dimensional connectivity feature map (CFM). The CFMs are then used to classify emotions by a convolutional neural network model. The results of classified emotions are analyzed regarding compatible EEG bands, accuracy, and time. Notably, the Gamma band is found as the most compatible band. The comparative study has demonstrated that though the connectivity method named Pearson correlation coefficient requires less time, the normalized mutual information is the most accurate method with advantageous detecting capability of nonlinear dependencies. |
| first_indexed | 2024-04-09T16:48:57Z |
| format | Article |
| id | doaj.art-4db55b051ba54b149a291705300a8947 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-09T16:48:57Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4db55b051ba54b149a291705300a89472023-04-21T23:00:21ZengIEEEIEEE Access2169-35362023-01-0111378093783110.1109/ACCESS.2023.326484510092746A Comparative Study on Prominent Connectivity Features for Emotion Recognition From EEGMahfuza Akter Maria0https://orcid.org/0009-0004-3600-0237M. A. H. Akhand1https://orcid.org/0000-0001-5465-8519A. B. M. Aowlad Hossain2https://orcid.org/0000-0002-2559-2781Md. Abdus Samad Kamal3https://orcid.org/0000-0003-3150-0510Kou Yamada4https://orcid.org/0000-0001-5502-2264Department of Computer Science and Engineering, Khulna University of Engineering and Technology, Khulna, BangladeshDepartment of Electronics and Communication Engineering, Khulna University of Engineering and Technology, Khulna, BangladeshDepartment of Electronics and Communication Engineering, Khulna University of Engineering and Technology, Khulna, BangladeshGraduate School of Science and Technology, Gunma University, Kiryu, JapanGraduate School of Science and Technology, Gunma University, Kiryu, JapanClassifying distinct human emotions, the fundamental purpose of brain-computer interface research, is essential for providing instant personalized services and assistance to individuals. With such emerging applications for individuals, several techniques have been proposed recently to explore interactions between brain regions, such as correlation, synchronization, and dependence. Notably, functional and effective connectivity methods are applied to assess the relationships between different brain areas. The primary objective of this study is to compare the frequently used functional and effective connectivity methods to recognize emotion using Electroencephalogram (EEG) signals. This paper uses a benchmark emotional EEG dataset consisting of 32 channels of EEG signals collected from 32 subjects while they were watching 40 emotional music videos. Specifically, correlation, phase synchronization, and mutual information are used to measure functional brain connectivity, and transfer entropy is used to acquire effective brain connectivity. After extracting the features, they are represented in a two-dimensional connectivity feature map (CFM). The CFMs are then used to classify emotions by a convolutional neural network model. The results of classified emotions are analyzed regarding compatible EEG bands, accuracy, and time. Notably, the Gamma band is found as the most compatible band. The comparative study has demonstrated that though the connectivity method named Pearson correlation coefficient requires less time, the normalized mutual information is the most accurate method with advantageous detecting capability of nonlinear dependencies.https://ieeexplore.ieee.org/document/10092746/Connectivity featureconvolutional neural networkelectroencephalography (EEG)emotion recognitionfeature extraction |
| spellingShingle | Mahfuza Akter Maria M. A. H. Akhand A. B. M. Aowlad Hossain Md. Abdus Samad Kamal Kou Yamada A Comparative Study on Prominent Connectivity Features for Emotion Recognition From EEG IEEE Access Connectivity feature convolutional neural network electroencephalography (EEG) emotion recognition feature extraction |
| title | A Comparative Study on Prominent Connectivity Features for Emotion Recognition From EEG |
| title_full | A Comparative Study on Prominent Connectivity Features for Emotion Recognition From EEG |
| title_fullStr | A Comparative Study on Prominent Connectivity Features for Emotion Recognition From EEG |
| title_full_unstemmed | A Comparative Study on Prominent Connectivity Features for Emotion Recognition From EEG |
| title_short | A Comparative Study on Prominent Connectivity Features for Emotion Recognition From EEG |
| title_sort | comparative study on prominent connectivity features for emotion recognition from eeg |
| topic | Connectivity feature convolutional neural network electroencephalography (EEG) emotion recognition feature extraction |
| url | https://ieeexplore.ieee.org/document/10092746/ |
| work_keys_str_mv | AT mahfuzaaktermaria acomparativestudyonprominentconnectivityfeaturesforemotionrecognitionfromeeg AT mahakhand acomparativestudyonprominentconnectivityfeaturesforemotionrecognitionfromeeg AT abmaowladhossain acomparativestudyonprominentconnectivityfeaturesforemotionrecognitionfromeeg AT mdabdussamadkamal acomparativestudyonprominentconnectivityfeaturesforemotionrecognitionfromeeg AT kouyamada acomparativestudyonprominentconnectivityfeaturesforemotionrecognitionfromeeg AT mahfuzaaktermaria comparativestudyonprominentconnectivityfeaturesforemotionrecognitionfromeeg AT mahakhand comparativestudyonprominentconnectivityfeaturesforemotionrecognitionfromeeg AT abmaowladhossain comparativestudyonprominentconnectivityfeaturesforemotionrecognitionfromeeg AT mdabdussamadkamal comparativestudyonprominentconnectivityfeaturesforemotionrecognitionfromeeg AT kouyamada comparativestudyonprominentconnectivityfeaturesforemotionrecognitionfromeeg |