Iranian Journal of Biomedical Engineering (IJBME)
نشریه علمی مهندسی پزشکی زیستی

Sparsification of the PLS Regression Algorithm using L2-Norm of Weighted Coefficients: Application in Emotion Recognition

Document Type : Full Research Paper

Authors

Aref Einizade 1
Sepide Hajipour Sardouie 2

1 Ph.D. Student, Bioelectric Group, Department of Electrical Engineering, Sharif University of Technology, Tehran, Iran

2 Assistant Professor, Bioelectric Group, Department of Electrical Engineering, Sharif University of Technology, Tehran, Iran

https://doi.org/10.22041/ijbme.2020.124620.1589
Abstract
The brain electrical signal has been widely used in clinical and academic research, due to its ease of recording, non-invasiveness, and precision. One of the applications can be emotion recognition from the brain's electrical signal. Generally, two types of parameters (Valence and Arousal) are used to determine the type of emotion which in turn indicate "positive or negative" and "level of extroversion or excitement" for a specific emotion. The significance of emotion is determined by the effects of this phenomenon on daily tasks, especially in cases where the person is confronted with activities that require careful attention and concentration. In the emotion recognition problem, firstly, using proper emotion stimuli, different emotions are created for the subjects under study and the brain signals corresponding to each stimulus are recorded. The two main steps for solving the emotion recognition problem are extracting suitable features and using appropriate classification or regression methods. In previous studies, different visual and auditory have been used and various linear and nonlinear features and classifiers have been investigated. In this paper, the main goal was the improvement of linear regression algorithms to estimate the criteria for recognizing human emotions more efficiently. For this purpose we proposed a new algorithm that uses the sparseness of the mixing vector along with the linear regression cost function. The effectiveness of the proposed algorithm on simulated data has been investigated and its superiority to linear regression algorithms such as PLS, LASSO, SOPLS and Ridge was shown. Also, to apply the proposed algorithm on EEG data corresponding to emotion recognition, the DEAP dataset was used and the AR coefficients were extracted from the EEG signals. The results obtained from the proposed algorithm were compared with those of the other linear regression algorithms, which in total showed the relative superiority of the proposed method.

Keywords

EEG Signal
Emotion Recognition
Linear Regression
PLS Regression
Sparse Coefficients
Valence
Arousal
Subjects
[1]   عبدالصالحی، مهدی. "بررسی تغییرات کمیت­های غیر خطی سیگنال EEG در احساسات شادی، غم و خنثی" رساله دکتری مهندسی پزشکی بیوالکتریک، دانشگاه آزاد اسلامی واحد علوم تحقیقات، سال تحصیلی 93-1392.
[2]   Koelstra, S., Muhl, C., Soleymani, M., Lee, J. S., Yazdani, A., Ebrahimi, T., & Patras, I. (2012). Deap: A database for emotion analysis; using physiological signals. IEEE Transactions on Affective Computing, 3(1), 18-31.
[3]   Mehmood, R. M., Du, R., & Lee, H. J. (2017). Optimal feature selection and deep learning ensembles method for emotion recognition from human brain EEG sensors. Cities, 4, 5.
[4]   Zheng, W. (2017). Multichannel EEG-based emotion recognition via group sparse canonical correlation analysis. IEEE Transactions on Cognitive and Developmental Systems, 9(3), 281-290.
[5]   Zheng, W. L., Zhu, J. Y., & Lu, B. L. (2017). Identifying stable patterns over time for emotion recognition from EEG. IEEE Transactions on Affective Computing.
[6]   Katsigiannis, S., & Ramzan, N. (2018). DREAMER: a database for emotion recognition through EEG and ECG signals from wireless low-cost off-the-shelf devices. IEEE journal of biomedical and health informatics, 22(1), 98-107.
[7]   Subramanian, R., Wache, J., Abadi, M. K., Vieriu, R. L., Winkler, S., & Sebe, N. (2018). ASCERTAIN: Emotion and personality recognition using commercial sensors. IEEE Transactions on Affective Computing, (2), 147-160.
[8]   Hatamikia, S., Maghooli, K., & Nasrabadi, A. M. (2014). The emotion recognition system based on autoregressive model and sequential forward feature selection of electroencephalogram signals. Journal of medical signals and sensors, 4(3), 194.
[9]   Xie, O., Liu, Z. T., & Ding, X. W. (2018, July). Electroencephalogram Emotion Recognition Based on A Stacking Classification Model. In 2018 37th Chinese Control Conference (CCC) (pp. 5544-5548). IEEE.
[10]Piho, L., & Tjahjadi, T. (2018). A mutual information based adaptive windowing of informative EEG for emotion recognition. IEEE Transactions on Affective Computing.
[11]Zheng, W. L., Zhu, J. Y., & Lu, B. L. (2017). Identifying stable patterns over time for emotion recognition from EEG. IEEE Transactions on Affective Computing.
[12]Tripathi, S., Acharya, S., Sharma, R. D., Mittal, S., & Bhattacharya, S. (2017, February). Using Deep and Convolutional Neural Networks for Accurate Emotion Classification on DEAP Dataset. In AAAI (pp. 4746-4752).
[13]Chen, J., Hu, B., Xu, L., Moore, P., & Su, Y. (2015, November). Feature-level fusion of multimodal physiological signals for emotion recognition. In Bioinformatics and Biomedicine (BIBM), 2015 IEEE International Conference on (pp. 395-399). IEEE.
[14]Rozgić, V., Vitaladevuni, S. N., & Prasad, R. (2013, May). Robust EEG emotion classification using segment level decision fusion. In Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on (pp. 1286-1290). IEEE.
[15]Li, X., Song, D., Zhang, P., Yu, G., Hou, Y., & Hu, B. (2016, December). Emotion recognition from multi-channel EEG data through Convolutional Recurrent Neural Network. In Bioinformatics and Biomedicine (BIBM), 2016 IEEE International Conference on (pp. 352-359). IEEE.
[16]Zhao, Q., Caiafa, C. F., Mandic, D. P., Chao, Z. C., Nagasaka, Y., Fujii, N., ... & Cichocki, A. (2013). Higher order partial least squares (HOPLS): a generalized multilinear regression method. IEEE transactions on pattern analysis and machine intelligence, 35(7), 1660-1673.
[17]Rosipal, R., & Trejo, L. J. (2001). Kernel partial least squares regression in reproducing kernel hilbert space. Journal of machine learning research, 2(Dec), 97-123.
[18]Eliseyev, A., & Aksenova, T. (2016). Penalized multi-way partial least squares for smooth trajectory decoding from electrocorticographic (ECoG) recording. PloS one, 11(5), e0154878.
[19]Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B (Methodological), 58(1), 267-288.
[20]Van Gerven, M. A., Chao, Z. C., & Heskes, T. (2012). On the decoding of intracranial data using sparse orthonormalized partial least squares. Journal of neural engineering, 9(2), 026017.
[21]Shimoda, K., Nagasaka, Y., Chao, Z. C., & Fujii, N. (2012). Decoding continuous three-dimensional hand trajectories from epidural electrocorticographic signals in Japanese macaques. Journal of neural engineering, 9(3), 036015.
Iranian Journal of Biomedical Engineering (IJBME)
Volume 14, Issue 3
Autumn 2020
Pages 221-233

  • Receive Date 13 April 2020
  • Revise Date 03 August 2020
  • Accept Date 11 September 2020

Home

Contact Us