MAKİNE ÖĞRENMESİ VE DERİN ÖĞRENME İLE ÇOK BOYUTLU ÖZELLİKLER KULLANILARAK EEG SİNYALLERİNDEN KOGNİTİF İŞ YÜKÜNÜN SINIFLANDIRILMASI

Abstract

Bu çalışmada EEG sinyallerinden kognitif iş yükü seviyelerinin sınıflandırılması amaçlanmıştır. 48 deneğe ait dinlenme ve görev kognitif yük koşullarındaki EEG sinyalleri analiz edilmiştir. EEG verileri üzerinde 1-50 Hz bandında bant geçiren ve çentik filtreleme yöntemleri uygulanarak gürültü ve artefaktlar temizlenmiştir. Daha sonra, EEG verileri 256 ve 512 örnek boyutlarında pencereleme tekniğiyle segmente edilerek zaman, frekans ve karmaşıklık temelli toplam 309 öznitelik çıkarılmıştır. Elde edilen öznitelik seti kullanılarak, çok sınıflı sınıflandırma işlemi için lojistik regresyon, destek vektör makineleri, k-en yakın komşu, rastgele orman, XGBoost makine öğrenmesi algoritmaları ile derin sinir ağları (DNN), tek boyutlu konvolüsyonel sinir ağları (1D-CNN) ve uzun kısa süreli bellek (LSTM) gibi derin öğrenme yöntemleri uygulanmıştır. Deneysel sonuçlarda en yüksek başarı, 99.4% doğruluk oranı ve 0,990 kohen kappa değeri ile XGBoost modelinde, derin öğrenme yöntemlerinde ise 98.75% doğruluk oranı ve 0,981 kappa değeri ile LSTM modelinde elde edilmiştir. Bu çalışma, EEG sinyallerinden elde edilen çok boyutlu özelliklerin hem makine öğrenmesi algoritmaları hem de derin öğrenme modelleriyle entegrasyonunun kognitif iş yükü sınıflandırmasında yüksek doğruluk sağladığını ortaya koymaktadır.

Keywords

• EEG
• Kognitif İş Yükü
• Makine Öğrenmesi
• Derin Öğrenme
• Özellik Çıkarımı
• Biyomedikal.

CLASSIFICATION OF COGNITIVE WORKLOAD FROM EEG SIGNALS USING MULTIDIMENSIONAL FEATURES WITH MACHINE LEARNING AND DEEP LEARNING

Abstract

This study aims to classify cognitive workload levels from EEG signals. EEG signals from 48 subjects under resting and task cognitive load conditions were analyzed. Noise and artifacts were removed by applying band-pass and notch filtering methods in the 1-50 Hz band on the EEG data. Then, the EEG data were segmented with the windowing technique in 256 and 512 sample sizes, and a total of 309 features based on time, frequency, and complexity were extracted. Using the obtained feature set, logistic regression (LR), support vector machines (SVM), k-nearest neighbor (k-NN), random forest (RF), XGBoost machine learning (ML) algorithms and deep neural networks (DNN), one-dimensional convolutional neural networks (1D-CNN) and long short-term memory (LSTM) deep learning (DL) methods were applied for multi-class classification. In the experimental results, the highest success was obtained in the XGBoost model with a 99.4% accuracy rate and 0.990 Cohen’s kappa value, and in DL methods, a 98.75% accuracy rate and 0.981 Kappa value in the LSTM model. This study reveals that integrating multidimensional features obtained from EEG signals with both ML algorithms and DL models provides high accuracy in cognitive workload classification.

Keywords

• EEG
• Cognitive Workload
• Machine Learning
• Deep Learning
• Feature Extraction
• Biomedical.

References

1. Akman Aydın, E., 2021. EEG Sinyalleri Kullanılarak Zihinsel İş Yükü Seviyelerinin Sınıflandırılması. Politeknik Dergisi 24, 681–689. https://doi.org/10.2339/politeknik.794655
2. Amalakanti, S., Mulpuri, R.P., Avula, V.C.R., Reddy, A., Jillella, J.P., 2024. Impact of smartphone use on cognitive functions: A PRISMA-guided systematic review. Medicine India 0, 1–8. https://doi.org/10.25259/medindia_33_2023
3. Archila-Meléndez, M.E., Valente, G., Gommer, E.D., Correia, J.M., ten Oever, S., Peters, J.C., Reithler, J., Hendriks, M.P.H., Cornejo Ochoa, W., Schijns, O.E.M.G., Dings, J.T.A., Hilkman, D.M.W., Rouhl, R.P.W., Jansma, B.M., van Kranen-Mastenbroek, V.H.J.M., Roberts, M.J., 2020. Combining Gamma With Alpha and Beta Power Modulation for Enhanced Cortical Mapping in Patients With Focal Epilepsy. Front Hum Neurosci 14. https://doi.org/10.3389/fnhum.2020.555054
4. Borra, D., Fantozzi, S., Bisi, M.C., Magosso, E., 2023. Modulations of Cortical Power and Connectivity in Alpha and Beta Bands during the Preparation of Reaching Movements. Sensors 23. https://doi.org/10.3390/s23073530
5. Chen, Z., Xu, Xianfa, Zhang, J., Liu, Y., Xu, Xianggang, Li, L., Wang, W., Xu, H., Jiang, W., Wang, Y., 2016. Application of LC-MS-based global metabolomic profiling methods to human mental fatigue. Anal Chem 88, 11293–11296. https://doi.org/10.1021/acs.analchem.6b03421
6. Chikhi, S., Matton, N., Blanchet, S., 2022. EEG power spectral measures of cognitive workload: A meta-analysis. Psychophysiology. https://doi.org/10.1111/psyp.14009
7. Gupta, A., Siddhad, G., Pandey, V., Roy, P.P., Kim, B.G., 2021. Subject-specific cognitive workload classification using eeg-based functional connectivity and deep learning. Sensors 21. https://doi.org/10.3390/s21206710
8. Hamann, A., Carstengerdes, N., 2023. Assessing the development of mental fatigue during simulated flights with concurrent EEG-fNIRS measurement. Sci Rep 13. https://doi.org/10.1038/s41598-023-31264-w

9. Holding, B.C., Ingre, M., Petrovic, P., Sundelin, T., Axelsson, J., 2021. Quantifying Cognitive Impairment After Sleep Deprivation at Different Times of Day: A Proof of Concept Using Ultra-Short Smartphone-Based Tests. Front Behav Neurosci 15. https://doi.org/10.3389/fnbeh.2021.666146
10. Howells, F.M., Temmingh, H.S., Hsieh, J.H., Van Dijen, A. V., Baldwin, D.S., Stein, D.J., 2018. Electroencephalographic delta/alpha frequency activity differentiates psychotic disorders: A study of schizophrenia, bipolar disorder and methamphetamine-induced psychotic disorder. Transl Psychiatry. https://doi.org/10.1038/s41398-018-0105-y
11. Kamrud, A., Borghetti, B., Kabban, C.S., Miller, M., 2021. Generalized deep learning eeg models for cross-participant and cross-task detection of the vigilance decrement in sustained attention tasks. Sensors 21. https://doi.org/10.3390/s21165617
12. Karmakar, S., Kamilya, S., Koley, C., Pal, T., 2024. A Deep Learning Technique for Real Time Detection of Cognitive Load using Optimal Number of EEG Electrodes. IEEE Trans Instrum Meas. https://doi.org/10.1109/TIM.2024.3509604
13. Khan, M.A., Asadi, H., Zhang, L., Qazani, M.R.C., Oladazimi, S., Loo, C.K., Lim, C.P., Nahavandi, S., 2024. Application of artificial intelligence in cognitive load analysis using functional near-infrared spectroscopy: A systematic review. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2024.123717
14. Korkmaz, O.E., Korkmaz, S.G., Aydemir, O., 2024. Detection of multitask mental workload using gamma band power features. Neural Comput Appl 36, 10915–10926. https://doi.org/10.1007/s00521-024-09627-9
15. Kunasegaran, K., Ismail, A.M.H., Ramasamy, S., Gnanou, J.V., Caszo, B.A., Chen, P.L., 2023. Understanding mental fatigue and its detection: a comparative analysis of assessments and tools. PeerJ 11. https://doi.org/10.7717/peerj.15744
16. Li, P., Zhang, Y., Liu, S., Lin, L., Zhang, H., Tang, T., Gao, D., 2023. An EEG-based Brain Cognitive Dynamic Recognition Network for representations of brain fatigue. Appl Soft Comput 146. https://doi.org/10.1016/j.asoc.2023.110613
17. Li, Z., Tong, L., Zeng, Y., Gao, Y., Gong, D., Yang, K., Hu, Y., Yan, B., 2024. A novel method of cognitive overload assessment based on a fusion feature selection using EEG signals. J Neural Eng 21, 066047. https://doi.org/10.1088/1741-2552/ad9cc0
18. Lim, W.L., Sourina, O., Wang, L.P., 2018. STEW: Simultaneous task EEG workload data set. IEEE Transactions on Neural Systems and Rehabilitation Engineering 26, 2106–2114. https://doi.org/10.1109/TNSRE.2018.2872924
19. Lorist, M.M., Boksem, M.A.S., Ridderinkhof, K.R., 2005. Impaired cognitive control and reduced cingulate activity during mental fatigue. Cognitive Brain Research 24, 199–205. https://doi.org/10.1016/j.cogbrainres.2005.01.018
20. Mizuno, K., Tanaka, M., Yamaguti, K., Kajimoto, O., Kuratsune, H., Watanabe, Y., 2011. Mental fatigue caused by prolonged cognitive load associated with sympathetic hyperactivity. Behavioral and Brain Functions 7. https://doi.org/10.1186/1744-9081-7-17
21. Mundlos, P., Wulf, T., Mueller, F.A., 2024. Perceived task complexity in strategic decision situations: the role of cognitive integration and cognitive load. European Business Review. https://doi.org/10.1108/EBR-08-2024-0253
22. Ono, H., Sonoda, M., Sakakura, K., Kitazawa, Y., Mitsuhashi, T., Firestone, E., Jeong, J.W., Luat, A.F., Marupudi, N.I., Sood, S., Asano, E., 2023. Dynamic cortical and tractography atlases of proactive and reactive alpha and high-gamma activities. Brain Commun 5. https://doi.org/10.1093/braincomms/fcad111
23. Park, Y., Chung, W., 2020. A Novel EEG Correlation Coefficient Feature Extraction Approach Based on Demixing EEG Channel Pairs for Cognitive Task Classification. IEEE Access 8, 87422–87433. https://doi.org/10.1109/ACCESS.2020.2993318
24. Roy, Y., Banville, H., Albuquerque, I., Gramfort, A., Falk, T.H., Faubert, J., 2019. Deep learning-based electroencephalography analysis: A systematic review. J Neural Eng. https://doi.org/10.1088/1741-2552/ab260c
25. Safari, M.R., Shalbaf, R., Bagherzadeh, S., Shalbaf, A., 2024. Classification of mental workload using brain connectivity and machine learning on electroencephalogram data. Sci Rep 14. https://doi.org/10.1038/s41598-024-59652-w
26. Shafiei, S.B., Shadpour, S., Mohler, J.L., 2024. An Integrated Electroencephalography and Eye-Tracking Analysis Using eXtreme Gradient Boosting for Mental Workload Evaluation in Surgery. Hum Factors. https://doi.org/10.1177/00187208241285513
27. Sheng, Q., 2025. Understanding the biomechanics of smartphone addiction: The physical and cognitive impacts of prolonged device use on college students. Molecular & Cellular Biomechanics 22, 650. https://doi.org/10.62617/mcb650
28. Skowronek, J., Seifert, A., Lindberg, S., 2023. The mere presence of a smartphone reduces basal attentional performance. Sci Rep 13. https://doi.org/10.1038/s41598-023-36256-4
29. Stancin, I., Cifrek, M., Jovic, A., 2021. A review of eeg signal features and their application in driver drowsiness detection systems. Sensors. https://doi.org/10.3390/s21113786
30. Subasi, A., 2007. EEG signal classification using wavelet feature extraction and a mixture of expert model. Expert Syst Appl 32, 1084–1093. https://doi.org/10.1016/j.eswa.2006.02.005
31. Sweller, J., 1988. Cognitive Load During Problem Solving: Effects on Learning. Cogn Sci 12, 257–285. https://doi.org/10.1207/s15516709cog1202_4
32. Sweller, J., van Merriënboer, J.J.G., Paas, F., 2019. Cognitive Architecture and Instructional Design: 20 Years Later. Educ Psychol Rev. https://doi.org/10.1007/s10648-019-09465-5
33. Taddeini, F., Avvenuti, G., Vergani, A.A., Carpaneto, J., Setti, F., Bergamo, D., Fiorini, L., Pietrini, P., Ricciardi, E., Bernardi, G., Mazzoni, A., 2025. Extended Cognitive Load Induces Fast Neural Responses Leading to Commission Errors. eNeuro 12. https://doi.org/10.1523/ENEURO.0354-24.2024
34. Wang, J., 2024. Research on the Speed of Information Transmission and User Cognition in the New Media Era. Communications in Humanities Research 40, 204–210. https://doi.org/10.54254/2753-7064/40/20242397
35. Wang, Y., Huang, Y., Gu, B., Cao, S., Fang, D., 2023. Identifying mental fatigue of construction workers using EEG and deep learning. Autom Constr 151. https://doi.org/10.1016/j.autcon.2023.104887
36. Weiler, H., Russell, S., Spielmann, J., Englert, C., 2025. Mental Fatigue: Is It Real? Journal of Applied Sport and Exercise Psychology 32, 14–26. https://doi.org/10.1026/2941-7597/a000033
37. Zadeh, M.Z., Babu, A.R., Lim, J.B., Kyrarini, M., Wylie, G., Makedon, F., 2020. Towards cognitive fatigue detection from functional magnetic resonance imaging data, in: Proceedings of the 13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA ’20. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3389189.3397648
38. Zafar, R., Dass, S.C., Malik, A.S., 2017. Electroencephalogram-based decoding cognitive states using convolutional neural network and likelihood ratio based score fusion. PLoS One 12. https://doi.org/10.1371/journal.pone.0178410
39. Zeng, H., Li, X., Borghini, G., Zhao, Y., Aricò, P., Di Flumeri, G., Sciaraffa, N., Zakaria, W., Kong, W., Babiloni, F., 2021. An eeg-based transfer learning method for cross-subject fatigue mental state prediction. Sensors 21. https://doi.org/10.3390/s21072369
40. Zhou, Y., Huang, S., Xu, Z., Wang, P., Wu, X., Zhang, D., 2022. Cognitive Workload Recognition Using EEG Signals and Machine Learning: A Review. IEEE Trans Cogn Dev Syst. https://doi.org/10.1109/TCDS.2021.3090217
41. Zhou, Y., Jiang, J., Wang, L., Liang, S., Liu, H., 2025. Enhanced Cognitive Load Detection in Air Traffic Control Operators Using EEG and a Hybrid Deep Learning Approach. IEEE Access. https://doi.org/10.1109/ACCESS.2025.3530091