Research on electroencephalogram emotion recognition based on the feature fusion algorithm of auto regressive model and wavelet packet entropy_Journal of Biomedical Engineering

Authors：

 LI Xin ^1,2 , SUN Xiaoqi ^1,2 , WANG Xin ^1,2 , SHI Chunyan ^1,2 , KANG Jiannan ³ , HOU Yongjie ⁴

1. Institute of Biomedical Engineering, Yanshan University, Qinhuangdao, Hebei 066004, P.R.China;
2. Measurement Technology and Instrumentation Key Lab of Hebei Province, Qinhuangdao, Hebei 066004, P.R.China;
3. College of Electronic & Information Engineering, Heibei University, Baoding, Hebei 071002, P.R.China;
4. HRA Medical Systems Co., Ltd,, Qinhuangdao, Hebei 066004, P.R.China;

Corresponding author：

LI Xin, Email: yddylixin@ysu.edu.cn

Keywords：

emotion recognition; electroencephalogram; wavelet packet entropy; auto-regressive; kernel principal component analysis; support vector machine

DOI：

10.7507/1001-5515.201610047

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Focused on the world-wide issue of improving the accuracy of emotion recognition, this paper proposes an electroencephalogram (EEG) signal feature extraction algorithm based on wavelet packet energy entropy and auto-regressive (AR) model. The auto-regressive process can be approached to EEG signal as much as possible, and provide a wealth of spectral information with few parameters. The wavelet packet entropy reflects the spectral energy distribution of the signal in each frequency band. Combination of them gives a better reflect of the energy characteristics of EEG signals. Feature extraction and fusion are implemented based on kernel principal component analysis. Six emotional states from a public multimodal database for emotion analysis using physiological signals (DEAP) are recognized. The results show that the recognition accuracy of the proposed algorithm is more than 90%, and the highest recognition accuracy is 99.33%. It indicates that this algorithm can extract the feature of EEG emotion well, and it is a kind of effective emotion feature extraction algorithm, providing support to emotion recognition.

Citation： LI Xin, SUN Xiaoqi, WANG Xin, SHI Chunyan, KANG Jiannan, HOU Yongjie. Research on electroencephalogram emotion recognition based on the feature fusion algorithm of auto regressive model and wavelet packet entropy. Journal of Biomedical Engineering, 2017, 34(6): 831-836. doi: 10.7507/1001-5515.201610047 Copy

1.	聂聃, 王晓韡, 段若男, 等. 基于脑电的情绪识别研究综述. 中国生物医学工程学报, 2012, 31(4): 595-606.
2.	Petrantonakis P C, Hadjileontiadis L J. EEG-based emotion recognition using hybrid filtering and higher order crossings//3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, Amsterdam, Netherlands, 2009: 1-6.
3.	Khosrowabadi R, Quek H C, Wahab A, et al. EEG-Based emotion recognition using Self-Organizing map for boundary detection//International Conference on Pattern Recognition. Istanbul, Turkey, 2010: 4242-4245.
4.	Hosseini S A, Naghibi-Sistani M B. Emotion recognition method using entropy analysis of EEG signals. International Journal of Image, Graphics and Signal Processing (IJIGSP), 2011, 3(5): 30-36.
5.	Yuen C T, San W S, Rizon M, et al. Classification of human emotions from EEG signals using statistical features and neural network. International Journal of Integrated Engineering, 2009, 1(3): 71-79.
6.	Zhang Yong, Ji Xiaomin, Liu Bo, et al. Combined feature extraction method for classification of EEG signals. Neural Comput & Applic, 2017, 28: 3153-3161.
7.	Pham T D, Tran D, MA W, et al. Neural information processing. Cham: Springer International Publishing, 2015: 95-102.
8.	Hatamikia S, Maghooli K, Nasrabadi A M. The emotion recognition system based on autoregressive model and sequential forward feature selection of electroencephalogram signals. J Med Signals Sens, 2014, 4(3): 194-201.
9.	程波, 刘光远. 基于表面肌电信号小波包熵的情感识别. 计算机工程与应用, 2008, 44(26): 214-216.
10.	He L, Margaret L, Zhang J, et al. Study of wavelet packet energy entropy for emotion classification in speech and glottal//International Conference on Digital Image Processing. Beijing, China, 2013: 8878.
11.	Murugappan M. Human emotion classification using wavelet transform and KNN//International Conference on Pattern Analysis and Intelligent Robotics, Putrajaya, Malaysia, 2011: 148-153.
12.	Mohammadi Z, Frounchi J, Amiri M. Wavelet-based emotion recognition system using EEG signal. Neural Computing and Applications, 2017, 28(8): 1985-1990.
13.	杨鹏圆. 基于小波包和 Hilbert-Huang 变换的情感脑电识别研究. 太原: 太原理工大学, 2014.
14.	Koelstra S, Muhl C, Soleymani M, et al. DEAP: A database for emotion analysis using physiological signals. IEEE Transactions on Affective Computing, 2012, 3(1): 18-31.
15.	赵龙莲, 粱作清, 伍文清, 等. 生物反馈训练后癫痫患者脑电相关维数变化的分析. 中国生物医学工程学报, 2010, 29(1): 71-76.
16.	李颖洁, 石菁, 朱春妍, 等. 心算任务下脑电信息传输. 上海大学学报:自然科学版, 2007, 13(4): 439-443.
17.	Stoica P, Moses R L. Introduction to spectral analysis. USA: Prentice Hall, 1997.
18.	Farah C, Zied L. Speech emotion recognition in acted and spontaneous context//International Conference on Intelligent Human Computer Interaction. Evry, France, 2014(39): 139-145.
19.	Burrus C S, Gopinath R A, GUO H. Introduction to wavelets and wavelet transforms:a primer. Houston: Prentice Hall Upper Saddle River, 1998.
20.	Military specification: US NAVY, MIL-S-901D, Shock tests high impact shipboard machinery equipment and systems requirement, 1989.
21.	Zhao W F, Qu J F, Chai Y, et al. Proceedings of the 2015 Chinese intelligent systems conference, 2. Berlin, Heidelberg: Springer International Publishing, 2015, 2: 201-207.
22.	韦振中. 基于核主成分分析的特征提取方法. 广西工学院学报, 2006, 17(4): 27-31.

1. 聂聃, 王晓韡, 段若男, 等. 基于脑电的情绪识别研究综述. 中国生物医学工程学报, 2012, 31(4): 595-606.
2. Petrantonakis P C, Hadjileontiadis L J. EEG-based emotion recognition using hybrid filtering and higher order crossings//3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, Amsterdam, Netherlands, 2009: 1-6.
3. Khosrowabadi R, Quek H C, Wahab A, et al. EEG-Based emotion recognition using Self-Organizing map for boundary detection//International Conference on Pattern Recognition. Istanbul, Turkey, 2010: 4242-4245.
4. Hosseini S A, Naghibi-Sistani M B. Emotion recognition method using entropy analysis of EEG signals. International Journal of Image, Graphics and Signal Processing (IJIGSP), 2011, 3(5): 30-36.
5. Yuen C T, San W S, Rizon M, et al. Classification of human emotions from EEG signals using statistical features and neural network. International Journal of Integrated Engineering, 2009, 1(3): 71-79.
6. Zhang Yong, Ji Xiaomin, Liu Bo, et al. Combined feature extraction method for classification of EEG signals. Neural Comput & Applic, 2017, 28: 3153-3161.
7. Pham T D, Tran D, MA W, et al. Neural information processing. Cham: Springer International Publishing, 2015: 95-102.
8. Hatamikia S, Maghooli K, Nasrabadi A M. The emotion recognition system based on autoregressive model and sequential forward feature selection of electroencephalogram signals. J Med Signals Sens, 2014, 4(3): 194-201.
9. 程波, 刘光远. 基于表面肌电信号小波包熵的情感识别. 计算机工程与应用, 2008, 44(26): 214-216.
10. He L, Margaret L, Zhang J, et al. Study of wavelet packet energy entropy for emotion classification in speech and glottal//International Conference on Digital Image Processing. Beijing, China, 2013: 8878.
11. Murugappan M. Human emotion classification using wavelet transform and KNN//International Conference on Pattern Analysis and Intelligent Robotics, Putrajaya, Malaysia, 2011: 148-153.
12. Mohammadi Z, Frounchi J, Amiri M. Wavelet-based emotion recognition system using EEG signal. Neural Computing and Applications, 2017, 28(8): 1985-1990.
13. 杨鹏圆. 基于小波包和 Hilbert-Huang 变换的情感脑电识别研究. 太原: 太原理工大学, 2014.
14. Koelstra S, Muhl C, Soleymani M, et al. DEAP: A database for emotion analysis using physiological signals. IEEE Transactions on Affective Computing, 2012, 3(1): 18-31.
15. 赵龙莲, 粱作清, 伍文清, 等. 生物反馈训练后癫痫患者脑电相关维数变化的分析. 中国生物医学工程学报, 2010, 29(1): 71-76.
16. 李颖洁, 石菁, 朱春妍, 等. 心算任务下脑电信息传输. 上海大学学报:自然科学版, 2007, 13(4): 439-443.
17. Stoica P, Moses R L. Introduction to spectral analysis. USA: Prentice Hall, 1997.
18. Farah C, Zied L. Speech emotion recognition in acted and spontaneous context//International Conference on Intelligent Human Computer Interaction. Evry, France, 2014(39): 139-145.
19. Burrus C S, Gopinath R A, GUO H. Introduction to wavelets and wavelet transforms:a primer. Houston: Prentice Hall Upper Saddle River, 1998.
20. Military specification: US NAVY, MIL-S-901D, Shock tests high impact shipboard machinery equipment and systems requirement, 1989.
21. Zhao W F, Qu J F, Chai Y, et al. Proceedings of the 2015 Chinese intelligent systems conference, 2. Berlin, Heidelberg: Springer International Publishing, 2015, 2: 201-207.
22. 韦振中. 基于核主成分分析的特征提取方法. 广西工学院学报, 2006, 17(4): 27-31.

Previous Article
The analysis of event-related potentials in normal brain aging based on N-back cognitive tasks
Next Article
Degree centrality of the functional network in schizophrenia patients

Journal of Biomedical Engineering

Research on electroencephalogram emotion recognition based on the feature fusion algorithm of auto regressive model and wavelet packet entropy

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content