ABSTRACT
Mental Workload (MWL) can be measured as the amount of mental strength necessary to complete a work. Mental workload measurement can help in the reduction of mental stress, tension, anxiety, strain, and worry, in daily life or job-specific tasks. This might have a significant impact on tasks like studies/learning and driving etc. In this paper, the classification of mental workload levels through deep learning (one-dimensional convolutional neural networks (1DCNN))has been done. STEW: Simultaneous Task EEG Workload Dataset is used in this study. Electroencephalogram (EEG) signals are captured during the mental task. Based on the subject's rating after completing the mental task, the workload is categorized as low mental workload or high mental workload. To balance and increase thedataset size Synthetic Minority Oversampling Technique (SMOTE) has been used. Different classification measures are used to evaluate the performance of the deep learning model used. Finally, the mental workload classification accuracy of 97.77 was achieved.
- W. L. Lim, O. Sourina and L. P. Wang, "STEW: Simultaneous Task EEG Workload Data Set," in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 26, no. 11, pp. 2106-2114, Nov. 2018, doi: 10.1109/TNSRE.2018.2872924.Google ScholarCross Ref
- P. Zhang, X. Wang, J. Chen, W. You and W. Zhang, "Spectral and Temporal Feature Learning With Two-Stream Neural Networks for Mental Workload Assessment," in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 27, no. 6, pp. 1149-1159, June 2019, doi: 10.1109/TNSRE.2019.2913400.Google ScholarCross Ref
- J. Song, D. Zhuang, G. Song and X. Wanyan, "Pilot mental workload measurement and evaluation under dual task," 2011 4th International Conference on Biomedical Engineering and Informatics (BMEI), 2011, pp. 809-812, doi: 10.1109/BMEI.2011.6098376.Google ScholarCross Ref
- K. Kitamura , "A ship Navigator's mental workload using salivary NO3− compared with R-R interval: Simulator-based experiment," 2014 World Automation Congress (WAC), 2014, pp. 98-102, doi: 10.1109/WAC.2014.6935693.Google ScholarCross Ref
- L. G. Lim , "A Unified Analytical Framework With Multiple fNIRS Features for Mental Workload Assessment in the Prefrontal Cortex," in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 28, no. 11, pp. 2367-2376, Nov. 2020, doi: 10.1109/TNSRE.2020.3026991.Google ScholarCross Ref
- P. Zarjam, J. Epps and N. H. Lovell, "Beyond Subjective Self-Rating: EEG Signal Classification of Cognitive Workload," in IEEE Transactions on Autonomous Mental Development, vol. 7, no. 4, pp. 301-310, Dec. 2015, doi: 10.1109/TAMD.2015.2441960.Google ScholarDigital Library
- S. B. Shafiei, A. S. Elsayed, A. A. Hussein, U. Iqbal and K. A. Guru, "Evaluating the Mental Workload During Robot-Assisted Surgery Utilizing Network Flexibility of Human Brain," in IEEE Access, vol. 8, pp. 204012-204019, 2020, doi: 10.1109/ACCESS.2020.3036751.Google ScholarCross Ref
- A. Henelius, K. Hirvonen, A. Holm, J. Korpela and K. Muller, "Mental workload classification using heart rate metrics," 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2009, pp. 1836-1839, doi: 10.1109/IEMBS.2009.5332602.Google ScholarCross Ref
- F. Larradet, G. Barresi and L. S. Mattos, "Effects of galvanic skin response feedback on user experience in gaze-controlled gaming: A pilot study," 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2017, pp. 2458-2461, doi: 10.1109/EMBC.2017.8037354.Google ScholarCross Ref
- Saundra G. Hart, Lowell E. Staveland, “ Development of NASA-TLX (NASA Load Index): Result of Empirical and Theoretical Research” Advance in Psychology, April 2008, vol. 52, pp. 139-183.Google Scholar
- X. Hou, Y. Liu, O. Sourina and W. Mueller-Wittig, "CogniMeter: EEG-based Emotion, Mental Workload and Stress Visual Monitoring," 2015 International Conference on Cyberworlds (CW), 2015, pp. 153-160, doi: 10.1109/CW.2015.58.Google ScholarDigital Library
- W. L. Lim, O. Sourina, Y. Liu and L. Wang, "EEG-based mental workload recognition related to multitasking," 2015 10th International Conference on Information, Communications and Signal Processing (ICICS), 2015, pp. 1-4, doi: 10.1109/ICICS.2015.7459834.Google ScholarCross Ref
- Hsu B-W, Wang M-JJ, Chen C-Y, Chen F. Effective Indices for Monitoring Mental Workload While Performing Multiple Tasks. Perceptual and Motor Skills. 2015;121(1):94-117. doi:10.2466/22.PMS.121c12x5Google ScholarCross Ref
- J. N. Mak, R. H. M. Chan and S. W. H. Wong, "Evaluation of mental workload in visual-motor task: Spectral analysis of single-channel frontal EEG," IECON 2013 - 39th Annual Conference of the IEEE Industrial Electronics Society, 2013, pp. 8426-8430, doi: 10.1109/IECON.2013.6700546.Google ScholarCross Ref
- M. K. Johnson, J. A. Blanco, R. J. Gentili, K. J. Jaquess, H. Oh and B. D. Hatfield, "Probe-independent EEG assessment of mental workload in pilots," 2015 7th International IEEE/EMBS Conference on Neural Engineering (NER), 2015, pp. 581-584, doi: 10.1109/NER.2015.7146689.Google ScholarCross Ref
- Ahirwal, Mitul Kumar, Anil Kumar, and Girish Kumar Singh. "Prediction and Classification." Computational Intelligence and Biomedical Signal Processing. Springer, Cham, 2021. 83-111.Google Scholar
- Ahirwal M.K., Kumar A., Singh G.K. (2021) Biomedical Signals. In: Computational Intelligence and Biomedical Signal Processing. SpringerBriefs in Electrical and Computer Engineering. Springer, Cham. https://doi.org/10.1007/978-3-030-67098-6_1Google ScholarCross Ref
- Ahirwal M.K., Kose M.R. (2021) Development of Emotional Decision-Making Model Using EEG Signals. In: Bhateja V., Peng SL., Satapathy S.C., Zhang YD. (eds) Evolution in Computational Intelligence. Advances in Intelligent Systems and Computing, vol 1176.Google ScholarCross Ref
- Ahirwal, M. K., & Kose, M. R. (2020). Audio-visual stimulation based emotion classification by correlated EEG channels. Health and Technology, 10(1), 7-23.Google Scholar
- Jinjing Ke, Jing Du, Xiaowei Luo, “ The effect of noise content and level on cognitive performance measured by electroencephalography (EEG)” Automation in Construction, vol. 31, Oct. 2021, pp. 103836.Google ScholarCross Ref
- Mohamad Sawan, Muhamad T. Salam, Jerome Le Lan, Amal Kasab, “ Wireless Recording System: From noninvasive EEG-NIRS to Invasive EEG devices” IEEE Transaction on Biomedical Circuits and Systems, vol. 7, April 2013, pp. 186-195.Google ScholarCross Ref
- Jakko Malmivuo, Sari Ahokas, Toni Valkky, “High-resolution EEG recording system using smart electrodes “ IEEE 14th Biennial Baltic Electronic Conference, Oct. 2014.Google Scholar
- P. B. Colditz, “ Digital Signal Processing of EEG Signals” IEEE Engineering in Medicine and Biology Magazine, vol. 21, Sep./Oct. 2001.Google Scholar
- Ahirwal M.K. (2021) Analysis and Identification of EEG Features for Mental Stress. In: Bhateja V., Peng SL., Satapathy S.C., Zhang YD. (eds) Evolution in Computational Intelligence. Advances in Intelligent Systems and Computing, vol 1176.Google ScholarCross Ref
- H. Qu, Y. Liu, L. Pang and Y. Shan, "Mental workload classification based on visual and operational EEG signals," CSAA/IET International Conference on Aircraft Utility Systems (AUS 2020), 2020, pp. 831-836, doi: 10.1049/icp.2021.0170.Google ScholarCross Ref
- J. Song, D. Zhuang, G. Song and X. Wanyan, "Pilot mental workload measurement and evaluation under dual task," 2011 4th International Conference on Biomedical Engineering and Informatics (BMEI), 2011, pp. 809-812, doi: 10.1109/BMEI.2011.6098376.Google ScholarCross Ref
- I. Kakkos , "Mental Workload Drives Different Reorganizations of Functional Cortical Connectivity Between 2D and 3D Simulated Flight Experiments," in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 27, no. 9, pp. 1704-1713, Sept. 2019, doi: 10.1109/TNSRE.2019.2930082.Google ScholarCross Ref
- M. Bueno, E. Dogan, F. Hadj Selem, E. Monacelli, S. Boverie, A. Guillaume, “ How different mental workload levels affect the take-over after automated driving” IEEE 19th Conference of intelligent Transportation System (2016).Google ScholarDigital Library
- J. Zhang, Z. Yin and R. Wang, "Recognition of Mental Workload Levels Under Complex Human–Machine Collaboration by Using Physiological Features and Adaptive Support Vector Machines," in IEEE Transactions on Human-Machine Systems, vol. 45, no. 2, pp. 200-214, April 2015, doi: 10.1109/THMS.2014.2366914.Google ScholarCross Ref
- Chawla, Nitesh V., "SMOTE: synthetic minority over-sampling technique." Journal of artificial intelligence research 16 (2002): 321-357.Google ScholarDigital Library
- U. Singh and M. K. Ahirwal, "Mental Workload Classification for Multitasking Test using Electroencephalogram Signal," 2021 IEEE International Conference on Technology, Research, and Innovation for Betterment of Society (TRIBES), 2021, pp. 1-6, doi: 10.1109/TRIBES52498.2021.9751676.Google ScholarCross Ref
- Vishal Panday, Dhirendra Kumar Choudhary, Vinita Verma, Greeshma Sharma, Ram Singh, Sushil Chandra, “Mental Workload Estimation Using EEG”, 2020 Fifth International Conference on Research in Computional Intelligence and Communicaton Network (ICRCICN).Google Scholar
- Chakladar, Debashis Das, "EEG-based mental workload estimation using deep BLSTM-LSTM network and evolutionary algorithm." Biomedical Signal Processing and Control 60 (2020): 101989.Google ScholarCross Ref
- Zhang, J., Cui, X., Li, J. Imbalanced classification of mental workload using a cost-sensitive majority weighted minority oversampling strategy. Cogn Tech Work 19, 633–653 (2017). https://doi.org/10.1007/s10111-017-0447-x.Google ScholarDigital Library
- G. Zhu, F. Zong, H. Zhang, B. Wei and F. Liu, "Cognitive Load During Multitasking Can Be Accurately Assessed Based on Single Channel Electroencephalography Using Graph Methods," in IEEE Access, vol. 9, pp. 33102-33109, 2021, doi: 10.1109/ACCESS.2021.3058271.Google ScholarCross Ref
- V. Pandey, D. K. Choudhary, V. Verma, G. Sharma, R. Singh and S. Chandra, "Mental Workload Estimation Using EEG," 2020 Fifth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN), 2020, pp. 83-86, doi: 10.1109/ICRCICN50933.2020.9296150.Google ScholarCross Ref
- P. Huynh, G. Warner and H. Lin, "Effects of EMD and Feature Extraction on EEG Analysis," Journal of Advances in Information Technology, Vol. 11, No. 1, pp. 26-34, February 2020. doi: 10.12720/jait.11.1.26-34Google ScholarCross Ref
Index Terms
- Improved Classification of Mental Workload Using One Dimensional Convolutional Neural Network and SMOTE Technique
Recommendations
Imbalanced classification of mental workload using a cost-sensitive majority weighted minority oversampling strategy
Identifying the temporal variations in mental workload level (MWL) is crucial for enhancing the safety of human---machine system operations, especially when there is cognitive overload or inattention of human operator. This paper proposed a cost-...
On Ensemble Learning for Mental Workload Classification
Machine Learning, Optimization, and Data ScienceAbstractThe ability to determine a subject’s Mental Work Load (MWL) has a wide range of significant applications within modern working environments. In recent years, techniques such as Electroencephalography (EEG) have come to the forefront of MWL ...
The Effect of Mental Workload towards Mental Fatigue on Customer Care Agent Using Electroencephalogram
ICIBE '19: Proceedings of the 5th International Conference on Industrial and Business EngineeringHigh mental workload can lead to fatigue and further result in decreased concentration and work performance. This study is conducted to see the effects of mental workload towards mental fatigue. Mental fatigue measurement was conducted at the first and ...
Comments