Emotion recognition of multimodal physiological signals based on optimized LSTSVM
The least squares twin support vector machine(LSTSVM) is used for emotion recognition. The penalty coefficients，and kernel function parameter of LSTSVM model are difficult to determine, so the modified firefly algorithm(MFA) is used to select the best parameters of the LSTSVM to achieve optimal perf...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
National Computer System Engineering Research Institute of China
2018-03-01
|
| Series: | Dianzi Jishu Yingyong |
| Subjects: | |
| Online Access: | http://www.chinaaet.com/article/3000079532 |
| _version_ | 1819066668165365760 |
|---|---|
| author | Jin Chun Chen Guangyong |
| author_facet | Jin Chun Chen Guangyong |
| author_sort | Jin Chun |
| collection | DOAJ |
| description | The least squares twin support vector machine(LSTSVM) is used for emotion recognition. The penalty coefficients，and kernel function parameter of LSTSVM model are difficult to determine, so the modified firefly algorithm(MFA) is used to select the best parameters of the LSTSVM to achieve optimal performance. Based on four modal of physiological signals, which are EEG, skin electrical, electromyography and respiratory signal, the proposed algorithm is used for emotion recognition, and comparisons are made with standard LSTSVM and particle swarm optimization LSTSVM algorithm. Simulation results show that the proposed MFA-LSTSVM algorithm has higher accuracy and shorter training time. |
| first_indexed | 2024-12-21T16:06:01Z |
| format | Article |
| id | doaj.art-404d82cffa3c484b84b1c85823f14374 |
| institution | Directory Open Access Journal |
| issn | 0258-7998 |
| language | zho |
| last_indexed | 2024-12-21T16:06:01Z |
| publishDate | 2018-03-01 |
| publisher | National Computer System Engineering Research Institute of China |
| record_format | Article |
| series | Dianzi Jishu Yingyong |
| spelling | doaj.art-404d82cffa3c484b84b1c85823f143742022-12-21T18:57:53ZzhoNational Computer System Engineering Research Institute of ChinaDianzi Jishu Yingyong0258-79982018-03-0144311211610.16157/j.issn.0258-7998.1718393000079532Emotion recognition of multimodal physiological signals based on optimized LSTSVMJin Chun0Chen Guangyong1Key Lab of Wireless Mobile Communication Theory and Technology，Chongqing University of Post and Communications， Chongqing 400065，ChinaKey Lab of Wireless Mobile Communication Theory and Technology，Chongqing University of Post and Communications， Chongqing 400065，ChinaThe least squares twin support vector machine(LSTSVM) is used for emotion recognition. The penalty coefficients，and kernel function parameter of LSTSVM model are difficult to determine, so the modified firefly algorithm(MFA) is used to select the best parameters of the LSTSVM to achieve optimal performance. Based on four modal of physiological signals, which are EEG, skin electrical, electromyography and respiratory signal, the proposed algorithm is used for emotion recognition, and comparisons are made with standard LSTSVM and particle swarm optimization LSTSVM algorithm. Simulation results show that the proposed MFA-LSTSVM algorithm has higher accuracy and shorter training time.http://www.chinaaet.com/article/3000079532least squares twin support vector machinefirefly algorithmemotion recognitionmultimodal physiological signal |
| spellingShingle | Jin Chun Chen Guangyong Emotion recognition of multimodal physiological signals based on optimized LSTSVM Dianzi Jishu Yingyong least squares twin support vector machine firefly algorithm emotion recognition multimodal physiological signal |
| title | Emotion recognition of multimodal physiological signals based on optimized LSTSVM |
| title_full | Emotion recognition of multimodal physiological signals based on optimized LSTSVM |
| title_fullStr | Emotion recognition of multimodal physiological signals based on optimized LSTSVM |
| title_full_unstemmed | Emotion recognition of multimodal physiological signals based on optimized LSTSVM |
| title_short | Emotion recognition of multimodal physiological signals based on optimized LSTSVM |
| title_sort | emotion recognition of multimodal physiological signals based on optimized lstsvm |
| topic | least squares twin support vector machine firefly algorithm emotion recognition multimodal physiological signal |
| url | http://www.chinaaet.com/article/3000079532 |
| work_keys_str_mv | AT jinchun emotionrecognitionofmultimodalphysiologicalsignalsbasedonoptimizedlstsvm AT chenguangyong emotionrecognitionofmultimodalphysiologicalsignalsbasedonoptimizedlstsvm |