Zihinsel İş Yükü Seviyelerinin EEG Alt Bantlarına Dayalı Sınıflandırılması

Year 2025, Volume: 1 Issue: 1, 22 - 29, 30.07.2025

Müge Dolu , Şerife Gengeç Benli

Abstract

EEG sinyalleri kullanılarak beyinde farklı durumlara verilen farklı yanıtlar ölçülerek analiz edilebilir. Bu çalışmada, MATB-II görev tabanlı çalışmasına ait açık erişimli bir veri seti kullanılarak 3 oturuma ait 3 farklı zorluk seviyesi (kolay,orta,zor) incelenmiştir. Öncelikle veriler 0.5 Hz ile 45 Hz aralığına filtrelenmiş ve faz kayması giderilmiştir. Sonrasında verilere 4. dereceden ayrık dalgacık dönüşümü uygulanmış ve elde edilen katsayıların her birinden zaman, frekans ve entropi tabanlı 26 özellik olmak üzere toplam 130 özellik çıkarılmıştır. Ardışık ileri seçim yöntemi kullanılarak özellik çıkarımına gidilmiştir. Yapay sinir ağları, k en yakın komşu ve rastgele orman algoritmaları ile kolay, orta ve zor seviyeleri için sınıflandırmalar yapılmış ve en yüksek başarım oranları k en yakın komşu algoritmasından elde edilmiştir

Keywords

makine öğrenmesi , zihinsel iş yükü , EEG analizi

Classification of Mental Workload Levels Based on EEG Sub-Bands

Abstract

Using EEG signals, different brain responses to varying conditions can be measured and analyzed. In this study, an open-access dataset from a MATB-II task-based experiment was used to examine three difficulty levels (easy, medium, difficult) across three sessions. First, the data were band-pass filtered between 0.5 Hz and 45 Hz, and phase distortion was eliminated. Next, a fourth-order discrete wavelet transform was applied, and from each of the resulting coefficients, 26 time-, frequency,- and entropy-based features were extracted 130 features in total. Feature extraction was then refined using the sequential forward selection method. Finally, classification at the easy, medium, and difficult levels was performed using artificial neural networks, k-nearest neighbors, and random forest algorithms, with the k-nearest neighbors classifier achieving the highest accuracy.

Keywords

Machine learning , mental workload , EEG analysis

References

• Burke R. E.,2007. Sir Charles Sherrington's the integrative action of the nervous system: a centenary appreciation. Brain : a journal of neurology, 130(Pt 4), 887–894. Doi:10.1093/brain/awm022
• Üngüren, E.,2016. Beynin nöroanatomik ve nörokimsayal yapısının kişilik ve davranış üzerindeki etkisi. Akdeniz Üniversitesi, Uluslararası Alanya İşletme Fakültesi Dergisi, 7(1).
• Choi, M. K., Lee, S. M., Ha, J. S., Seong, P. H., 2018. Development of an EEGbased workload measurement method in nuclear power plants. Annals of Nuclear Energy, 111, 595-607. Doi: 10.1016/j.anucene.2017.08.032
• Lim WL, Sourina O, Wang LP., 2018 STEW: Simultaneous Task EEG Workload Data Set. IEEE Trans Neural Syst Rehabil Eng. 26(11),2106-2114. Doi: 10.1109/TNSRE.2018.2872924
• Wang, S., Gwizdka, J., Chaovalitwongse, W. A., 2016. Using wireless EEG signals to assess memory workload in the n-back task. IEEE Transactions on HumanMachine Systems, 46(3): 424-435. Doi:10.1109/THMS.2015.2476818
• Bagheri, M., Power, S. D., 2022. Simultaneous classification of both mental workload and stress level suitable for an online passive brain-computer interface. Sensors (Basel), 22(2): 535. Doi: 10.3390/s22020535
• Jeon, J. H., Cai, H., 2022. Multi-class classification of construction hazards via cognitive states assessment using wearable EEG. Advanced Engineering Informatics, 53, 101646. Doi: 10.1016/j.aei.2022.101646
• Jebelli, H., Hwang, S., Lee, S. H., 2018. EEG-based workers' stress recognition at construction sites. Automation in Construction, 93: 315-324. Doi:10.1016/j.autcon.2018.05.027
• Dehais, F., Somon, B., Mullen, T., ve Callan, D. E., 2020. A neuroergonomics approach to measure pilot’s cognitive incapacitation in the real world with EEG. Applied Human Factors and Ergonomics, 111-117. Doi: 10.1007/978-3-030-51041-1_16
• Dolu M.,2024. Farklı uyaran türlerinin EEG sinyalleri üzerinden analizi. Yüksek lisans tezi, Erciyes Üniversitesi Fen Bilimleri Enstitüsü.
• Hinss, M. F., Jahanpour, E. S., Somon, B., et al., 2023. Open multi-session and multitask EEG cognitive dataset for passive brain-computer interface applications. Sci Data, 10, 85. Doi: 10.1038/s41597-022-01898-y
• Kang X., Handayani D., Yaacob H.,2021. Comparison between butterworth bandpass and stationary wavelet transform filter for electroencephalography signal. IOP Conference Series: Materials Science and Engineering. Doi:10.1088/1757-899X/1077/1/012024
• Guo T., Zhang T., Lim, E., Lopez Miguel., Ma F., Yu L., 2022. A Review of Wavelet Analysis and Its Applications: Challenges and Opportunities. IEEE Access, 10, 1-1. Doi:10.1109/ACCESS.2022.3179517
• Kumar, S. G. S., Sampathila, N., Tanmay, T., 2022.Wavelet based machine learning models for classification of human emotions using EEG signal. Measurement: Sensors, 24: 1-8. Doi:10.1016/j.measen.2022.100554
• Haşıloğlu, A., 2001. Dalgacık dönüşümü ve yapay sinir ağları ile döndürmeye duyarsız doku analizi ve sınıflandırma. Turkish Journal of Engineering and Environmental Sciences, 25: 405-413.
• Yu C., Wang M., 2022. Survey of emotion recognition methods using EEG information. Cognitive Robotics. 2. 132-146. Doi:10.1016/j.cogr.2022.06.001.
• Alakuş, TB, & Türkoğlu, İ. 2019. EEG Sinyallerine Dayalı Duygu Tahmininden Sıralı İleri Seçim Algoritması ile Özellik Seçimi. Sakarya Üniversitesi Fen Bilimleri Dergisi, 23(6), 1096-1105. Doi:10.16984/saufenbilder.501799
• Nurul, I., Amiza, A., Ilyas, M., Razalli, M., 2017. The performance analysis of k nearest neighbors (K-EYK) algorithm for motor imagery classification based on EEG signal. MATEC Web of Conferences, 147: 1-8. Doi:10.1051/matecconf/201714001024
• Gu, Y., Liang, Z., Hagihira, S., 2019. Use of multiple EEG features and artificial neural network to monitor the depth of anesthesia. Sensors (Basel), 19(15): 1- 11. Doi: 10.3390/s19112499
• Subasi A., Kiymik M., Alkan A., Koklukaya E.,2005. Neural network classification of EEG signals by using AR with MLE preprocessing for epileptic seizure detection, Mathematical and computational applications, vol. 10, no. 1, pp. 57-70. Doi: 10.3390/mca10010057
• Karimi M., Arab F., 2020. Machine Learning Based Framework for Estimation of Data Center Power Using Acoustic Side Channel. Doi: 10.48550/arXiv.2008.02481
• Priyama, A., Gupta, R., Ratheeb, A., Srivastava, S., 2013. Comparative analysis of decision tree classification algorithms. International Journal of Current Engineering and Technology, 3(2): 1710-1714. Doi:10.1155/2022/9449497
• Damodar E., Kunal M., Gauri D., Shubham D., 2018. Classification of EEG data for human mental state analysis using Random Forest Classifier. Procedia Computer Science. 132. 1523-1532. Doi:10.1016/j.procs.2018.05.116.
• Wang, T., Ke, Y., Huang, Y., He, F., Zhong, W., Liu, S., Ming, D., 2024. Using semi-supervised domain adaptation to enhance EEG-based cross-task mental workload classification performance, IEEE Journal of Biomedical and Health Informatics, 28(12):7032-7039. Doi:10.1109/JBHI.2024.3452410
• Albuquerque, R. O., Cassani, R., Gagnon, J. F., Tremblay, S., Falk, T. H., 2021. Adaptive filtering for improved EEG-based mental workload assessment of ambulant users. Frontiers in Neuroscience, 15: 611962. Doi:10.3389/fnins.2021.611962
• Chandra S., Verma K., Sharma G., Mittal A., Jha D., 2015. EEG based cognitive workload classification during NASA MATB-II multitasking. International Journal of Cognitive Research in Science, Engineering and Education. 3. 35-42. Doi:10.23947/2334-8496-2015-3-1-35-41
• Zhang Z., Zhao Z., Qu H., Liu C., Pang L..2023. A mental workload classification method based on GCN modified by squeeze-and-excitation residual. Mathematics 11, 1189. Doi:10.3390/math11051189