EEG-Based Emotion Recognition via Knowledge-Integrated Interpretable Method
Despite achieving success in many domains, deep learning models remain mostly black boxes, especially in electroencephalogram (EEG)-related tasks. Meanwhile, understanding the reasons behind model predictions is quite crucial in assessing trust and performance promotion in EEG-related tasks. In this...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/6/1424 |
| _version_ | 1827748906610458624 |
|---|---|
| author | Ying Zhang Chen Cui Shenghua Zhong |
| author_facet | Ying Zhang Chen Cui Shenghua Zhong |
| author_sort | Ying Zhang |
| collection | DOAJ |
| description | Despite achieving success in many domains, deep learning models remain mostly black boxes, especially in electroencephalogram (EEG)-related tasks. Meanwhile, understanding the reasons behind model predictions is quite crucial in assessing trust and performance promotion in EEG-related tasks. In this work, we explore the use of representative interpretable models to analyze the learning behavior of convolutional neural networks (CNN) in EEG-based emotion recognition. According to the interpretable analysis, we find that similar features captured by our model and state-of-the-art model are consistent with previous brain science findings. Next, we propose a new model by integrating brain science knowledge with the interpretability analysis results in the learning process. Our knowledge-integrated model achieves better recognition accuracy on standard EEG-based recognition datasets. |
| first_indexed | 2024-03-11T06:13:32Z |
| format | Article |
| id | doaj.art-9a7c2947a1ba4d0d9ab8c2b9eb5fd21f |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-11T06:13:32Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-9a7c2947a1ba4d0d9ab8c2b9eb5fd21f2023-11-17T12:28:24ZengMDPI AGMathematics2227-73902023-03-01116142410.3390/math11061424EEG-Based Emotion Recognition via Knowledge-Integrated Interpretable MethodYing Zhang0Chen Cui1Shenghua Zhong2College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, ChinaDespite achieving success in many domains, deep learning models remain mostly black boxes, especially in electroencephalogram (EEG)-related tasks. Meanwhile, understanding the reasons behind model predictions is quite crucial in assessing trust and performance promotion in EEG-related tasks. In this work, we explore the use of representative interpretable models to analyze the learning behavior of convolutional neural networks (CNN) in EEG-based emotion recognition. According to the interpretable analysis, we find that similar features captured by our model and state-of-the-art model are consistent with previous brain science findings. Next, we propose a new model by integrating brain science knowledge with the interpretability analysis results in the learning process. Our knowledge-integrated model achieves better recognition accuracy on standard EEG-based recognition datasets.https://www.mdpi.com/2227-7390/11/6/1424interpretability analysisEEG-based emotion recognitionknowledge integration |
| spellingShingle | Ying Zhang Chen Cui Shenghua Zhong EEG-Based Emotion Recognition via Knowledge-Integrated Interpretable Method Mathematics interpretability analysis EEG-based emotion recognition knowledge integration |
| title | EEG-Based Emotion Recognition via Knowledge-Integrated Interpretable Method |
| title_full | EEG-Based Emotion Recognition via Knowledge-Integrated Interpretable Method |
| title_fullStr | EEG-Based Emotion Recognition via Knowledge-Integrated Interpretable Method |
| title_full_unstemmed | EEG-Based Emotion Recognition via Knowledge-Integrated Interpretable Method |
| title_short | EEG-Based Emotion Recognition via Knowledge-Integrated Interpretable Method |
| title_sort | eeg based emotion recognition via knowledge integrated interpretable method |
| topic | interpretability analysis EEG-based emotion recognition knowledge integration |
| url | https://www.mdpi.com/2227-7390/11/6/1424 |
| work_keys_str_mv | AT yingzhang eegbasedemotionrecognitionviaknowledgeintegratedinterpretablemethod AT chencui eegbasedemotionrecognitionviaknowledgeintegratedinterpretablemethod AT shenghuazhong eegbasedemotionrecognitionviaknowledgeintegratedinterpretablemethod |