Feature extraction with wavelet transform for EEG signal based anxiety classification

Yıl 2023, , 726 - 732, 15.07.2023

Shams Qahtan Omar Omar , Cengiz Tepe

https://doi.org/10.28948/ngumuh.1230092

Öz

Anxiety affects productivity and quality of life as well as human abilities and behaviors. It can be considered the main cause of depression and suicide. Clinicians today use specific criteria to diagnose anxiety disorders. There is a need for reliable, non-invasive techniques that fulfil the complex task of detecting anxiety. This study aimed to classify binary and quadruple classes with fewer EEG channels and features by analyzing electroencephalography (EEG) signals. A DASPS database containing 14-channel EEG signals from 23 individuals was used. Using EEGLAB, 4 channels were selected from 14 channels. The wavelet transform is used for feature extraction. The MATLAB Classification learner toolbox contained eight methods for classification. The highest accuracy performances were obtained with the Decision trees method with an accuracy of 67.1% in binary classification, and with a support vector machine with an accuracy of 58.5% in quadruple classification.

Anahtar Kelimeler

Anxiety, Channel selection, Decision Tree, Support Vector Machine, EEG

EEG İşareti tabanlı anksiyete sınıflandırması için dalgacık dönüşümü ile öznitelik çıkarma

Öz

Anksiyete, üretkenliği ve yaşam kalitesini etkilediği kadar insan yeteneklerini ve davranışlarını da etkiler. Depresyon ve intiharın ana nedeni olarak kabul edilebilir. Günümüzde klinisyenler anksiyete bozukluklarını teşhis etmek için belirli kriterler kullanılmaktadır. Anksiyete tespitinin karmaşık görevini yerine getiren, invaziv olmayan güvenilir tekniklere ihtiyaç vardır. Bu çalışma, elektroensefalografi (EEG) sinyallerini analiz ederek ikili ve dörtlü sınıfları daha az EEG kanalı ve öznitelik sınıflandırmayı amaçlamıştır. 23 kişinin 14 kanallı EEG sinyalini içeren DASPS veri tabanı kullanılmıştır. EEGLAB kullanarak 14 kanaldan 4 kanal seçilmiştir. Öznitelik çıkarımı için dalgacık dönüşümü kullanılmıştır. MATLAB Classification learner toolbox’taki 8 yöntem ile sınıflandırma yapılmıştır. En yüksek doğrulukta başarımlar ikili sınıflandırmada %67.1 doğrulukta Karar ağaçları yönteminde, dörtlü sınıflandırmada %58.5 doğrulukta destek vektör makinesi ile elde edilmiştir

Anahtar Kelimeler

EEG, Anksiyete, Kanal seçimi, Karar ağaçları, Destek Vektör Makinesi

Kaynakça

• Zhang, X. Wang, W. Tan, Q. Gao, D. J. J. o. m. Shin, and b. Engineering, EEG-based anxious states classification using affective BCI-based closed neurofeedback system. Journal of Medical and Biological Engineering, 41, 155–164, 2021. https:/ /doi.org/10.1007/s40846-020-0096-7.
• G. Giannakakis, M. Pediaditis, D. Manousos, E. Kazantzaki, F. Chiarugi, P. G. Simos, K. Marias, M. J. B. S. P. Tsiknakis, and Control, Stress and anxiety detection using facial cues from videos. 31, 89-101, 2017. https://doi.org/10.1016/j.bspc.2016.06.020.
• S. Mirzaei, P. J. B. S. P. Ghasemi, and Control, EEG motor imagery classification using dynamic connectivity patterns and convolutional autoencoder. 68, 102584, 2021. https://doi.org/10.1016/j.bspc.2021 .102584.
• R. G. de Magalhaes Júnior, F. T. Rocha, and C. E. J. I. L. A. T. Thomaz, Comparison Between Linear and Tensor Models of EEG Signals Representation. 19, 01, 132-137, 2021. https://doi.org/10.1109/TLA.2021.942 3856.
• M. Akmal, S. Zubair, and H. J. I. A. Alquhayz, Classification analysis of tensor-based recovered missing EEG data. 9, 41745-41756, 2021. https ://doi.org/10.1109/ACCESS.2021.3063382.
• S. Q. O. OMAR, and T. J. B. Ü. F. B. D. Cengiz, EEG Sinyallerini İşlemek İçin Makine Öğreniminin Kullanıldığı Konular Üzerine Bir İnceleme. 5, 1, 124-137,2022. https://doi.org/10.55117/bufbd.1099025.
• H. Sharma, R. Raj, and M. J. N. l. Juneja, EEG signal based classification before and after combined Yoga and Sudarshan Kriya. 707, 134300, 2019. https://do i.org/10.1016/j.neulet.2019.134300.
• A. R. Aslam, N. Hafeez, H. Heidari, and M. A. B. J. F. i. N. Altaf, Channels and Feature Identification with Large Scale Feature Extraction for Emotions and ASD Classification. 1094, 2022. https://doi.org/10.3389/fnin s.2022.844851.
• B. Penchina, A. Sundaresan, S. Cheong, and A. Martel, Deep LSTM recurrent neural network for anxiety classification from EEG in adolescents with autism. 227-238. https://doi.org/10.1007/978-3-030-59277-6 _21.
• A. Arsalan, M. J. J. o. A. I. Majid, and H. Computing, A study on multi-class anxiety detection using wearable EEG headband. 1-11, 2021. https://doi.org/ 10.1007/s12652-021-03249-y.
• A. Asif, M. Majid, S. M. J. C. i. b. Anwar, and medicine, Human stress classification using EEG signals in response to music tracks. 107, 182-196, 2019. https://doi.org/10.1016/j.compbiomed.2019.02.015.
• A. Baghdadi, Y. Aribi, R. Fourati, N. Halouani, P. Siarry, and A. M. J. a. p. a. Alimi, DASPS: A Database for Anxious States based on a Psychological Stimulation. 2019. https://doi.org/10.48550/arXiv.19 01.02942.
• M. Agrawal, M. A. Anwar, and D. Sethia, Stacked Sparse Autoencoder and Machine Learning Based Anxiety Classification Using EEG Signals. The First International Conference on AI-ML-Systems. Ekim 2021, pp. 1-7 https://doi.org/10.1145/3486001.348622 7.
• D. Maheshwari, S. K. Ghosh, R. Tripathy, M. Sharma, U. R. J. C. i. B. Acharya, and Medicine, Automated accurate emotion recognition system using rhythm-specific deep convolutional neural network technique with multi-channel EEG signals, Computers in Biology and Medicine, 134, 104428, 2021. https://doi.org/10 .1016/j.compbiomed.2021.104428.
• C. Brunner, A. Delorme, and S. J. B. E. B. T. Makeig, Eeglab–an open source matlab toolbox for electrophysiological research. 58, SI-1-Track-G, 000010151520134182, 2013. https://doi.org/10.1515 /bmt-2013-4182.
• A. Delorme, and S. J. J. o. n. m. Makeig, EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. 134, 1, 9-21, 2004. https://doi.org/10.1016/j.jneumeth. 2003.10.009.
• Ö. J. D. Ü. M. F. M. D. AYDEMİR, Ardışıl ileri yönlü öznitelik seçim algoritmasında etkin özniteliklerin belirlenmesi. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 8, 3, 495-501, 2017.
• M. L. A. Al-Zubaidi, and S. Aras, Investigation of Appropriate Classification Method for EOG Based Human Computer Interface. 2022 30th Signal Processing and Communications Applications Conference (SIU), Safranbolu, Turkey, 15-18 Mayıs 2022. https://doi.org/10.1109/SIU55565.2022.986495 3
• S.-W. Jang, and S.-H. J. S. Lee, Detection of epileptic seizures using wavelet transform, peak extraction and PSR from EEG signals, 12, 8, 1239, 2020. https://doi .org/10.3390/sym12081239.
• M. C. Guerrero, J. S. Parada, and H. E. Espitia, EEG signal analysis using classification techniques: Logistic regression, artificial neural networks, support vector machines, and convolutional neural networks. Heliyon, 7, 6, e07258, 2021/06/01/, 2021. https://doi.org/10.10 16/j.heliyon.2021.e07258.
• N. K. Al-Qazzaz, M. K. Sabir, S. H. M. Ali, S. A. Ahmad, K. Grammer, and Ieee, The Role of Spectral Power Ratio in Characterizing Emotional EEG for Gender Identification. IEEE EMBS Conference on Biomedical Engineering and Sciences. 334-338, 01-03 Mar, 2021.
• S. Aydin, S. Demirtaş, K. Ateş, and M. A. J. I. j. o. n. s. Tunga, Emotion recognition with eigen features of frequency band activities embedded in induced brain oscillations mediated by affective pictures. 26, 03, 1650013, 2016. https://doi.org/10.1142/S0129065716 500131.
• C. M. Raj, and A. Harsha, Study on wavelet spectral band based EEG compression. 2016 International Conference on Data Science and Engineering (ICDSE), Cochin, India, 23-25 Ağustos 2016. https://doi.org/ 10.1109/ICDSE.2016.7823955.
• G. Ekim, N. Ikizler, and A. Atasoy, The effects of different wavelet degrees on epileptic seizure detection from EEG signals. IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA), Gdynia, Poland, 03-05 Temmuz 2017. https://doi.org/10.1109/INISTA.2017.8001178.
• R. Sharma, EEG signal denoising based on wavelet transform. 758-761, 2017. https://doi.org/10.1109/ICE CA.2017.8203645.
• D. Chen, S. Wan, J. Xiang, and F. S. J. P. o. Bao, A high-performance seizure detection algorithm based on Discrete Wavelet Transform (DWT) and EEG. 12, 3, e0173138, 2017. https://doi.org/10.1371/journal.pone. 0173138.
• Z.-H. Zhou, Machine learning: Springer Nature, 2021.
• B. Charbuty, A. J. J. o. A. S. Abdulazeez, and T. Trends, Classification based on decision tree algorithm for machine learning. 2, 01, 20-28, 2021. https://doi .org/10.38094/jastt20165.
• Y. Ma, X. Ding, Q. She, Z. Luo, T. Potter, Y. J. C. Zhang, and m. m. i. medicine, Classification of motor imagery EEG signals with support vector machines and particle swarm optimization. 2016. https://doi.org/ 10.1155/2016/4941235.
• T. Nazir, X. Qi, and S. Silvestrov, Linear Classification of Data with Support Vector Machines and Generalized Support Vector Machines. Engineering Mathematics II, 355-375, 2016. https://doi.org/10.1063/1.4972718.
• L. J. I. J. o. B. Zhou, Recognition of depression patients with electroencephalogram. International Journal of Biometrics, 14, 3-4, 481-491, 2022. https://doi.org/ 10.1504/IJBM.2022.124684.
• K. Li, X. Zhang, and Y. Du, A SVM based classification of EEG for predicting the movement intent of human body. 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Jeju, Korea (South), 30 October 2013 - 02 November 2013.
• W. Zhao, J. Qu, Y. Chai, and J. Tang, Classification of Seizure in EEG Signals Based on KPCA and SVM. 201-207. https://doi.org/10.1007/978-3-662-48365-7_21.