Çok Seviyeli Dalgacık Dönüşümü ve Yerel İkili Örüntüler Tabanlı Otomatik EEG Duygu Tanıma Yöntemi

Elektroensefalogram (EEG) sinyallerinin çeşitli beyin ve nörolojik bozuklukları teşhis ettiği düşünülmektedir. Ayrıca beyin duruma göre karakteristik EEG sinyalleri üretir. Bu nedenle, duygusal durumu tespit etmek için EEG sinyalleri kullanılmış ve literatürde birçok EEG tabanlı otomatik duygu algılama modeli sunulmuştur. Bu çalışmada, çok düzeyli ayrık dalgacık dönüşümü, yerel ikili desen, komşuluk bileşen analizi ve k en yakın komşu sınıflandırıcı kullanılarak yeni bir otomatik EEG duygu algılama modeli sunulmuştur. Sunulan EEG sınıflandırma modelinin aşamaları; (i) kullanılan EEG sinyalleri beş eşit örtüşmeyen bölüme bölünmüştür, (ii) frekans katsayıları çok düzeyli ayrık dalgacık dönüşümü kullanılarak üretilmiştir, (iii) yerel ikili desen ham EEG bölümü ve frekans katsayılarından özellikler üretir, (iv) komşuluk bileşen analizi kullanarak özellik seçimi, (v) sınıflandırma ve (vi) katı çoğunluk oylaması. Yöntemimizi test etmek için GAMEEMO veri kümesini kullandık. Bu EEG duygu veriseti 14 kanal içerir ve kanal bazında sonuçlar hesaplanmıştır. Önerimiz, GAMEEMO veri kümesinde mükemmel sınıflandırma oranına (% 100.0) ulaştı. Bu sonuçlar, modelimizin duygu sınıflandırması için EEG sinyalleri üzerindeki yüksek sınıflandırma yeteneğini açıkça gösterdi.

Anahtar Kelimeler:

EEG duygu tanıma, Yerel ikili örüntü, Çoğunluk oylaması, Çok seviyeli dalgacık dönüşümü

Automatic EEG Emotion Recognition Method Based on Multi-Level Wavelet Transform and Local Binary Patterns

Electroencephalogram (EEG) signals have been considered to diagnose several brain and neurologic disorders. Moreover, the brain generated characteristic EEG signals according to the situation. Therefore, EEG signals have been used to detect emotional state and several EEG-based automated emotion detection models have been presented in the literature. In this work, a new automated EEG emotion detection model presented using multilevel discrete wavelet transform, local binary pattern, neighborhood component analysis, and k nearest neighbor classifier. The phases of the presented EEG classification model are; (i) the used EEG signals are divided into five equal non-overlapping segments, (ii) frequency coefficients are generated using multilevel discrete wavelet transform, (iii) local binary pattern generates features from raw EEG segment and frequency coefficients, (iv) feature selection using neighborhood component analysis, (v) classification and (vi) hard majority voting. We used the GAMEEMO dataset to test our proposal. This EEG emotion corpus contains 14 channels and channel-wise results were calculated. Our proposal reached perfect classification rate (100.0%) on the GAMEEMO dataset. These results clearly denoted the high classification ability of our model on the EEG signals for emotion classification.

Keywords:

EEG emotion recognition, Local binary pattern, Majority voting, Multilevel wavelet transform,

PDF

___

[1] Alakus, T.B., M. Gonen, and I. Turkoglu, Database for an emotion recognition system based on eeg signals and various computer games–GAMEEMO. Biomedical Signal Processing and Control, 2020. 60: p. 101951.
[2] Er, M.B., H. Çiğ, and İ.B. Aydilek, A new approach to recognition of human emotions using brain signals and music stimuli. Applied Acoustics, 2021. 175: p. 107840.
[3] Hassouneh, A., A.M. Mutawa, and M. Murugappan, Development of a Real-Time Emotion Recognition System Using Facial Expressions and EEG based on machine learning and deep neural network methods. Informatics in Medicine Unlocked, 2020. 20: p. 100372.
[4] Nakisa, B., et al., Evolutionary Computation Algorithms for Feature Selection of EEG-based Emotion Recognition using Mobile Sensors. Expert Systems with Applications, 2017. 93.
[5] Zualkernan, I., et al., Emotion recognition using mobile phones. Computers & Electrical Engineering, 2017. 60: p. 1-13.
[6] Hossain, M.S. and G. Muhammad, An Emotion Recognition System for Mobile Applications. IEEE Access, 2017. 5: p. 2281-2287.
[7] Mehmood, R.M., R. Du, and H.J. Lee, Optimal Feature Selection and Deep Learning Ensembles Method for Emotion Recognition From Human Brain EEG Sensors. IEEE Access, 2017. 5: p. 14797-14806.
[8] Tivatansakul, S., et al. Emotional healthcare system: Emotion detection by facial expressions using Japanese database. in 2014 6th Computer Science and Electronic Engineering Conference (CEEC). 2014.
[9] Krithika, L.B. and G.G. Lakshmi Priya, Student Emotion Recognition System (SERS) for e-learning Improvement Based on Learner Concentration Metric. Procedia Computer Science, 2016. 85: p. 767-776.
[10] Hammoumi, O.E., et al. Emotion Recognition in E-learning Systems. in 2018 6th International Conference on Multimedia Computing and Systems (ICMCS). 2018.
[11] Chen, S., et al., Automatic Diagnosis of Epileptic Seizure in Electroencephalography Signals Using Nonlinear Dynamics Features. IEEE Access, 2019. 7: p. 61046-61056.
[12] Baykan B., A.E., Elmalı Ayşe Deniz. . ELEKTROENSEFALOGRAFİ. (Mart, 2021)]; Available from: http://www.itfnoroloji.org/semi2/eeg.htm.
[13] Li, X., et al., Exploring EEG features in cross-subject emotion recognition. Frontiers in neuroscience, 2018. 12: p. 162.
[14] Shawky, E., et al., EEG-Based Emotion Recognition using 3D Convolutional Neural Networks. International Journal of Advanced Computer Science and Applications, 2018. 9: p. 329.
[15] Pandey, P. and K.R. Seeja, Subject independent emotion recognition from EEG using VMD and deep learning. Journal of King Saud University - Computer and Information Sciences, 2019.
[16] Lan, Z., et al., Domain Adaptation Techniques for EEG-Based Emotion Recognition: A Comparative Study on Two Public Datasets. IEEE Transactions on Cognitive and Developmental Systems, 2019. 11(1): p. 85-94.
[17] Qing, C., et al., Interpretable Emotion Recognition Using EEG Signals. IEEE Access, 2019. 7: p. 94160-94170.
[18] Yin, Z., W. Zhang, and Z. Zheng. Locally Robust Feature Selection of EEG Signals for the Inter-subject Emotion Recognition. in 2020 39th Chinese Control Conference (CCC). 2020.
[19] Gao, Q., et al., EEG based emotion recognition using fusion feature extraction method. Multimedia Tools and Applications, 2020. 79(37): p. 27057-27074.
[20] Wei, C., et al., EEG-based emotion recognition using simple recurrent units network and ensemble learning. Biomedical Signal Processing and Control, 2020. 58: p. 101756.
[21] Naser, D.S. and G. Saha, Influence of music liking on EEG based emotion recognition. Biomedical Signal Processing and Control, 2021. 64: p. 102251.
[22] Tuncer, T., S. Dogan, and A. Subasi, A new fractal pattern feature generation function based emotion recognition method using EEG. Chaos, Solitons & Fractals, 2021. 144: p. 110671.
[23] Ghosh, L., S. Saha, and A. Konar, Decoding emotional changes of android-gamers using a fused Type-2 fuzzy deep neural network. Computers in Human Behavior, 2021. 116: p. 106640.
[24] Cheng, J., et al., Emotion Recognition From Multi-Channel EEG via Deep Forest. IEEE Journal of Biomedical and Health Informatics, 2021. 25(2): p. 453-464.
[25] Chatlani, N. and J.J. Soraghan. Local binary patterns for 1-D signal processing. in 2010 18th European Signal Processing Conference. 2010.
[26] Kaya, Y., et al., 1D-local binary pattern based feature extraction for classification of epileptic EEG signals. Applied Mathematics and Computation, 2014. 243: p. 209-219.
[27] Murugappan, M., N. Ramachandran, and Y. Sazali, Classification of human emotion from EEG using discrete wavelet transform. Journal of biomedical science and engineering, 2010. 3(04): p. 390.
[28] Zubair, M. and C. Yoon, EEG based classification of human emotions using discrete wavelet transform, in IT Convergence and Security 2017. 2018, Springer. p. 21-28.
[29] Goldberger, J., et al., Neighbourhood components analysis. Advances in neural information processing systems, 2004. 17: p. 513-520.
[30] Raghu, S. and N. Sriraam, Classification of focal and non-focal EEG signals using neighborhood component analysis and machine learning algorithms. Expert Systems with Applications, 2018. 113: p. 18-32.
[31] Aha, D.W., D. Kibler, and M.K. Albert, Instance-based learning algorithms. Machine learning, 1991. 6(1): p. 37-66.
[32] Mehmood, R.M. and H.J. Lee. Emotion classification of EEG brain signal using SVM and KNN. in 2015 IEEE international conference on multimedia & expo workshops (ICMEW). 2015. IEEE.