Abstract
The determination of a subject’s mental workload (MWL) from an electroencephalogram (EEG) is a well-studied area in the brain-computer interface (BCI) field. A high MWL level can significantly contribute to mental fatigue, decreased performance, and long-term health problems. Inspired by the success of machine learning in various areas, researchers have investigated the use of deep learning models to classify subjects’ MWL levels. A common approach that is used to evaluate such classification models is the cross-validation (CV) technique. However, the CV technique used for such models does not take into account the time series nature of EEG signals. Therefore, in this paper we propose a modification of CV techniques, i.e. a blocked form of CV with rolling window and expanding window strategies, which are more suitable for EEG signals. Then, we investigate the effectiveness of the two strategies and also explore the effects of different block sizes for each strategy. We then apply these models to several state-of-the-art deep learning models used for MWL classification from EEG signals using a publicly available dataset, STEW. There were two classification tasks: Task 1- resting vs testing state, and Task 2- low vs moderate vs high MWL. Our results show that the model evaluated by the expanding window strategy, when it was trained using the 90% of data, provided a better performance than the rolling window strategy and that the BGRU-GRU model outperformed the other models for both tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahmadi, A., Bazregarzadeh, H., Kazemi, K.: Automated detection of driver fatigue from electroencephalography through wavelet-based connectivity. Biocybernetics Biomed. Eng. 41(1), 316–332 (2021)
Bergmeir, C., Benítez, J.M.: On the use of cross-validation for time series predictor evaluation. Inf. Sci. 191, 192–213 (2012)
Bergmeir, C., Costantini, M., Benítez, J.M.: On the usefulness of cross-validation for directional forecast evaluation. Comput. Stat. Data Anal. 76, 132–143 (2014)
Buscher, G., Dengel, A., Biedert, R., Elst, L.V.: Attentive documents: eye tracking as implicit feedback for information retrieval and beyond. ACM Trans. Interact. Intell. Syst. (TiiS) 1(2), 1–30 (2012)
Cao, Z., Yin, Z., Zhang, J.: Recognition of cognitive load with a stacking network ensemble of denoising autoencoders and abstracted neurophysiological features. Cogn. Neurodyn. 15(3), 425–437 (2021)
Cerqueira, V., Torgo, L., Mozetič, I.: Evaluating time series forecasting models: an empirical study on performance estimation methods. Mach. Learn. 109(11), 1997–2028 (2020)
Dorffner, G.: Neural networks for time series processing. In: Neural network world. Citeseer (1996)
Hernández, L.G., Mozos, O.M., Ferrández, J.M., Antelis, J.M.: EEG-based detection of braking intention under different car driving conditions. Front. Neuroinform. 12, 29 (2018)
Hoadley, B.: Asymptotic properties of maximum likelihood estimators for the independent not identically distributed case. Annals Math. Stat. 1977–1991 (1971)
Islam, M.K., Rastegarnia, A., Yang, Z.: Methods for artifact detection and removal from scalp EEG: a review. Neurophysiol. Clin. Clin. Neurophysiol. 46(4–5), 287–305 (2016)
Islam, M.R., Barua, S., Ahmed, M.U., Begum, S., Di Flumeri, G.: Deep learning for automatic EEG feature extraction: an application in drivers’ mental workload classification. In: Longo, L., Leva, M.C. (eds.) H-WORKLOAD 2019. CCIS, vol. 1107, pp. 121–135. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32423-0_8
Jeong, J.H., Yu, B.W., Lee, D.H., Lee, S.W.: Classification of drowsiness levels based on a deep spatio-temporal convolutional bidirectional LSTM network using electroencephalography signals. Brain Sci. 9(12), 348 (2019)
Kingphai, K., Moshfeghi, Y.: On EEG preprocessing role in deep learning effectiveness for mental workload classification. In: Longo, L., Leva, M.C. (eds.) H-WORKLOAD 2021. CCIS, vol. 1493, pp. 81–98. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-91408-0_6
Kingphai, K., Moshfeghi, Y.: On time series cross-validation for mental workload classification from EEG signals. In: Neuroergonomics Conference (2021)
Lee, D.H., Jeong, J.H., Kim, K., Yu, B.W., Lee, S.W.: Continuous EEG decoding of pilots’ mental states using multiple feature block-based convolutional neural network. IEEE Access 8, 121929–121941 (2020). https://doi.org/10.1109/ACCESS.2020.3006907
Lim, J., Wu, W.C., Wang, J., Detre, J.A., Dinges, D.F., Rao, H.: Imaging brain fatigue from sustained mental workload: an ASL perfusion study of the time-on-task effect. Neuroimage 49(4), 3426–3435 (2010)
Lim, W., Sourina, O., Wang, L.: Stew: simultaneous task EEG workload data set. IEEE Trans. Neural Syst. Rehabil. Eng. 26(11), 2106–2114 (2018)
Mognon, A., Jovicich, J., Bruzzone, L., Buiatti, M.: Adjust: an automatic EEG artifact detector based on the joint use of spatial and temporal features. Psychophysiology 48(2), 229–240 (2011)
Murakami, H., Kumar, B.V.: Efficient calculation of primary images from a set of images. IEEE Trans. Pattern Anal. Mach. Intell. 5, 511–515 (1982)
Nagabushanam, P., Thomas George, S., Radha, S.: EEG signal classification using LSTM and improved neural network algorithms. Soft Comput. 24(13), 9981–10003 (2019). https://doi.org/10.1007/s00500-019-04515-0
Nussbaumer, H.J.: The fast fourier transform. In: Fast Fourier Transform and Convolution Algorithms, pp. 80–111. Springer, Berlin (1981). https://doi.org/10.1007/978-3-662-00551-4_4
Qayyum, A., Khan, M.A., Mazher, M., Suresh, M.: Classification of EEG learning and resting states using 1d-convolutional neural network for cognitive load assesment. In: 2018 IEEE Student Conference on Research and Development (SCOReD), pp. 1–5. IEEE (2018)
Qu, X., Liu, P., Li, Z., Hickey, T.: Multi-class time continuity voting for EEG classification. In: Frasson, C., Bamidis, P., Vlamos, P. (eds.) BFAL 2020. LNCS (LNAI), vol. 12462, pp. 24–33. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60735-7_3
Qu, X., Sun, Y., Sekuler, R., Hickey, T.: EEG markers of stem learning. In: 2018 IEEE Frontiers in Education Conference (FIE), pp. 1–9 (2018). https://doi.org/10.1109/FIE.2018.8659031
Saha, S., Baumert, M.: Intra-and inter-subject variability in EEG-based sensorimotor brain computer interface: a review. Front. Comput. Neurosci. 13, 87 (2020)
Schaffer, C.: Selecting a classification method by cross-validation. Mach. Learn. 13(1), 135–143 (1993)
Stone, M.: Cross-validatory choice and assessment of statistical predictions. J. Roy. Stat. Soc.: Ser. B (Methodol.) 36(2), 111–133 (1974)
Szalma, J.L., et al.: Effects of sensory modality and task duration on performance, workload, and stress in sustained attention. Hum. Factors 46(2), 219–233 (2004)
Tashman, L.J.: Out-of-sample tests of forecasting accuracy: an analysis and review. Int. J. Forecast. 16(4), 437–450 (2000)
Taylor, L.P.: Chapter 20 - independent assessor audit guide. In: Taylor, L.P. (ed.) FISMA Compliance Handbook, pp. 239–273. Syngress, Boston (2013). https://doi.org/10.1016/B978-0-12-405871-2.00020-8https://www.sciencedirect.com/science/article/pii/B9780124058712000208
Teplan, M., et al.: Fundamentals of EEG measurement. Meas. Sci. Rev. 2(2), 1–11 (2002)
Urigüen, J.A., Garcia-Zapirain, B.: EEG artifact removal—state-of-the-art and guidelines. J. Neural Eng. 12(3), 031001 (2015). https://doi.org/10.1088/1741-2560/12/3/031001,https://doi.org/10.1088%2F1741-2560%2F12%2F3%2F031001
Wang, S., Gwizdka, J., Chaovalitwongse, W.A.: Using wireless EEG signals to assess memory workload in the \( n \)-back task. IEEE Trans. Human-Mach. Syst. 46(3), 424–435 (2015)
Wylie, C., Shultz, T., Miller, J., Mitler, M., Mackie, R., et al.: Commercial motor vehicle driver fatigue and alertness study: Technical summary (1996)
Yang, S., Yin, Z., Wang, Y., Zhang, W., Wang, Y., Zhang, J.: Assessing cognitive mental workload via EEG signals and an ensemble deep learning classifier based on denoising autoencoders. Comput. Biol. Med. 109, 159–170 (2019)
Zeng, H., et al.: A lightgbm-based EEG analysis method for driver mental states classification. Comput. Intell. Neurosci. 2019 (2019)
Zhang, D., Cao, D., Chen, H.: Deep learning decoding of mental state in non-invasive brain computer interface. In: Proceedings of the International Conference on Artificial Intelligence, Information Processing and Cloud Computing, pp. 1–5 (2019)
Zhang, J., Li, S.: A deep learning scheme for mental workload classification based on restricted boltzmann machines. Cognit. Technol. Work 19(4), 607–631 (2017)
Zhang, Q., Yuan, Z., Chen, H., Li, X.: Identifying mental workload using EEG and deep learning. In: 2019 Chinese Automation Congress (CAC), pp. 1138–1142. IEEE (2019)
Zhang, Y., Liu, B., Ji, X., Huang, D.: Classification of EEG signals based on autoregressive model and wavelet packet decomposition. Neural Process. Lett. 45(2), 365–378 (2017)
Zhou, Y., Xu, T., Li, S., Shi, R.: Beyond engagement: an EEG-based methodology for assessing user’s confusion in an educational game. Univ. Access Inf. Soc. 18(3), 551–563 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kingphai, K., Moshfeghi, Y. (2023). On Time Series Cross-Validation for Deep Learning Classification Model of Mental Workload Levels Based on EEG Signals. In: Nicosia, G., et al. Machine Learning, Optimization, and Data Science. LOD 2022. Lecture Notes in Computer Science, vol 13811. Springer, Cham. https://doi.org/10.1007/978-3-031-25891-6_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-25891-6_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25890-9
Online ISBN: 978-3-031-25891-6
eBook Packages: Computer ScienceComputer Science (R0)