Journal of Digital Convergence (디지털융복합연구)

The Society of Digital Policy and Management (한국디지털정책학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning Model for Mental Fatigue Discrimination System based on EEG

뇌파기반 정신적 피로 판별을 위한 딥러닝 모델

  • Seo, Ssang-Hee (School of Computer Science and Engineering, Kyungnam University)
  • 서쌍희 (경남대학교 컴퓨터공학부)
  • Received : 2021.08.18
  • Accepted : 2021.10.20
  • Published : 2021.10.28
Download PDF
⟨ Previous Next ⟩

Abstract

Individual mental fatigue not only reduces cognitive ability and work performance, but also becomes a major factor in large and small accidents occurring in daily life. In this paper, a CNN model for EEG-based mental fatigue discrimination was proposed. To this end, EEG in the resting state and task state were collected and applied to the proposed CNN model, and then the model performance was analyzed. All subjects who participated in the experiment were right-handed male students attending university, with and average age of 25.5 years. Spectral analysis was performed on the measured EEG in each state, and the performance of the CNN model was compared and analyzed using the raw EEG, absolute power, and relative power as input data of the CNN model. As a result, the relative power of the occipital lobe position in the alpha band showed the best performance. The model accuracy is 85.6% for training data, 78.5% for validation, and 95.7% for test data. The proposed model can be applied to the development of an automated system for mental fatigue detection.

개인의 정신적 피로는 인지능력 및 업무 수행능력을 감소시킬 뿐만 아니라 일상에서 발생하는 크고 작은 사고의 주요 요인이 된다. 본 논문에서는 EEG 기반의 정신적 피로 판별을 위한 CNN 모델을 제안하였다. 이를 위해 안정 상태와 작업 상태에서의 뇌파를 수집하여 제안한 CNN 모델에 적용한 후 모델 성능을 분석하였다. 실험에 참여한 피험자들은 모두 대학교에 재학 중인 오른손잡이 남학생들이며 평균 나이는 25.5세이다. 각 상태에서의 측정된 뇌파에 대해 스펙트럼분석을 수행하였으며, CNN 모델의 입력데이터로써 원시 EEG 신호, 절대파워, 상대파워를 사용하여 CNN모델의 성능을 비교 분석하였다. 그 결과, 알파대역 후두엽 위치의 상대파워가 가장 좋은 성능을 나타내었다. 모델정확도는 훈련데이터 85.6%, 검증데이터 78.5%, 시험데이터 95.7%이다. 제안한 모델은 정신적 피로 판별을 위한 자동화시스템 개발에 적용될 수 있다.

Keywords

Acknowledgement

This work was supported by Kyungnam University Foundation Grant in 2021.

References

  1. M. A. Boksem & M. Tops. (2008). Mental fatigue: costs and benefits. Brain Res Rev, 59(1), 125-139. DOI : 10.1016/j.brainresrev.2008.07.001
  2. A. Chaudhuri & P. O. Behan. (2004). Fatigue in neurological disorders. Lancet, 363(9413), 978-988. DOI : 10.1016/S0140-6736(04)1594-2
  3. M. Jagannath & V. Balasubramanian. (2014). Assessment of early onset of driver fatigue using multimodal fatigue measures in a static simulator. Applied Ergonomics, 45(4), 1140-1147. DOI : 10.1016/j.apergo.2014.02.001
  4. M. Fallahi, M. Motamedzade, R. Heidarimoghadam, R. R. Soltanian, & S. Miyake. (2016). Effects of mental workload on physiological and subjective responses during traffic density monitoring: A field study. Applied Ergonomics, 52, 95-103. DOI : 10.1016/j.apero.2015.07.009
  5. F. Laurent et al. (2013). Multimodal information improves the rapid detection of mental fatigue. Biomedical Signal Processing and Control, 8(4), 400-408. DOI : 10.1016/j.bspc.2013.01.007
  6. S. Y. Ccheng, H. Y. Lee, C. M. Shu, & H. T. Hsu. (2007). Electroencephalographic study of mental fatigue in visual display terminal tasks. Journal of Medical and Biological Engineering, 27(3), 124-131.
  7. A. Sahayadhas, K. Sundaraj, & M. Murugappan. (2012). Detecting driver drowsiness based onsensors: a review. Sensors, 12(12), 16937-16953. DOI : 10.3390/s121216937
  8. U. R. Acharya, S. V. Sree, G. Swapna, R. J. Martis, & J. S. suri. (2013). Automated EEG analysis of epilepsy: a review. Knowledge-Based Systems, 45, 147-165. DOI : 10.1016/j.knosys.2013.02.014
  9. C. Berka, et al. (2007). EEG correlates of task engagement and mental workload in vigilance, learning, and memory tasks. Aviat Space Environ Med, 78(5 Suppl), B231-244.
  10. A. Al-Nafjan, M. Hosny, Y. Al-Ohali, & A. Al-Wabil (2017). Review and classification of emotion recognition based on EEG brain-computer interface system research: a systematic review. Appl Sci, 7(12), 1239 DOI : 10.3390/app7121239
  11. N. Bigdely-Shamlo, T. Mullen, C. Kothe, K. M. Su, & K. A. Bobbins. (2015). The PREP pipeline: standardized preprocessing for large-scale EEG analysis. Frontiers in Neuroinformatics, 9, 16 DOI : 10.3389/fninf.2015.00016
  12. A. Gramfort, d. Strohmeier, J. Haueisen, M. S. Hamalainen, & M. Kowalski. (2013). Time-frequency mixed-norm estimates: sparse M/EEG imaging with non-stationsry source activations. NeuroImage, 70, 410-422 DOI : 10.1016/j.neuroimage.2012.12.051
  13. C. Clerc, L. Bougrain, & F. Lotte. (2016). Brain-Computer Interfaces 1: Foundations and Methods. New York: Wiley. DOI : 10.1002/9781119144977
  14. M. Alom, et al. (2019). A state-of-the-art survey on deep learning theory and architectures. Electronics, 8(3), 292. DOI : 10.3390/electronics8030292
  15. J. Jung, B. Yu, D. Lee, & S. Lee. (2018). Classification of drowsinesss levels based on a deep spatio-temporal convolutional bidirectional LSTM network using electroencephalography signals. Brain Sci, 9(12), 348. DOI : 10.3390/brainsci9120348
  16. H. Alaskar. (2018). Convolutional neural network application in biomedical signals. J Comput Sci Technol, 6(2), 45-59. DOI : 10.15640/jns.v6n2a5
  17. H. Zeng, et al. (2018). EEG classification of driver mental states by deep learning. Cogn Neurodyn, 12, 597-606. DOI : 10.1007/s11571-018-9496-y
  18. S. Chaabene, B. Bouaziz, A. Boudaya, A. Hokelmann, A. Ammar, & L. Chaari. (2021). Convolutional neural network for drowsiness detection using EEG signals. Sensors, 21(5), 1734. DOI : 10.3390/s21051734
  19. A. Craig, Y. Tran, N. Wijesuriva, & H. Nguyen. (2012). Regional brain wave activity changes associated with fatigue. Psychophysiology, 49(4), 574-582. DOI : 10.1111/j.1469-8986.2011.01329.x
  20. G. Li, et al. (2020). The impact of mental fatigue on brain activity: a comparative study both in resting state and task state using EEG. BMC Neuroscience, 21(20). DOI : 10.1186/s12868-020-00569-1