Authors : Tanuj Kumar; Dr. Upendra Kumar Srivastava

Volume/Issue : Volume 11 - 2026, Issue 6 - June

Google Scholar : https://tinyurl.com/36ycvhbj

Scribd : https://tinyurl.com/4x7h3nv8

DOI : https://doi.org/10.38124/ijisrt/26jun1053

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Mental fatigue has emerged as one of the most pressing yet under-addressed challenges in higher education, particularly among engineering students who face relentless academic pressure, prolonged screen exposure, and an ever-growing cognitive workload. When left undetected, mental fatigue can significantly impair a student's ability to focus, reason, and retain new information. Despite the severity of this problem, most existing fatigue detection systems rely on single-modal physiological signals, such as Electroencephalogram (EEG) or Electrocardiogram (ECG), which provide only a limited view of an individual's fatigue state. Furthermore, these systems often lack behavioral and contextual inputs and are unable to adapt to individual differences. This paper presents a comprehensive, multimodal fuzzy logic-based mental fatigue detection system designed for engineering student populations. The proposed system integrates physiological signals, namely EEG, ECG- derived Heart Rate Variability (HRV), and Electromyography (EMG), together with behavioral indicators such as eye blink rate and Percentage of Eye Closure (PERCLOS), and contextual features including accumulated study duration and subjective workload intensity scores. Fuzzy logic is employed as the core decision-making mechanism because it reflects the inherently gradual and uncertain nature of mental fatigue. The system utilizes linguistic membership functions and a rule-based framework to infer fatigue levels from multimodal inputs. To further improve performance, an Adaptive Neuro-Fuzzy Inference System (ANFIS) is incorporated to optimize membership functions and rule weights using labeled training data. The proposed framework follows a seven-stage pipeline consisting of data acquisition, preprocessing, feature extraction, fuzzification, fuzzy inference, ANFIS-based optimization, and defuzzification. Experimental evaluation on a dataset of 120 engineering students achieved a peak classification accuracy of 98.2%, demonstrating the effectiveness of the proposed approach for real-time fatigue monitoring and management in academic environments.

Keywords : Mental Fatigue Detection, Fuzzy Logic, Adaptive Neuro-Fuzzy Inference System (ANFIS), Electroencephalogram (EEG), Electrocardiogram (ECG), Electromyography (EMG), Percentage of Eye Closure (PERCLOS), Multimodal Fusion, Engineering Students, Cognitive Load Assessment.

References :

1. Q. Wang, J. Yang, M. Ren, and Y. Zheng, "Driver fatigue detection: A survey," in Proc. 6th World Congress on Intelligent Control and Automation, vol. 2, pp. 8587–8591, 2011.
2. M. Imran, A. Khan, and F. Ali, "AI-Enhanced Cognitive Fatigue Monitoring Using ECG- Derived Heart Rate Variability," IEEE Sensors Journal, vol. 25, no. 3, pp. 4512–4525, 2025.
3. I. Eriņš, A. Ādamsons, and K. Pūks, "Fatigue Assessment in Occupational Expert Systems: A Rule-Based Approach," Applied Ergonomics, vol. 101, pp. 103691, 2022.
4. D. Snoun, M. Krir, and H. Khlaifi, "A Comprehensive Survey on Drowsiness and Alertness Monitoring System for Driver Vigilance," in Proc. 2017 IEEE/ACS 14th International Conference on Computer Systems and Applications (AICCSA), pp. 873–879, 2017.
5. R. S. Concepcion, E. P. Dadios, and A. A. Bandala, "ECG and EMG Based Fatigue Classification Using Artificial Neural Network," in Proc. 2018 IEEE Region 10 Conference (TENCON), pp. 1–6, 2018.
6. J.-S. R. Jang, "ANFIS: Adaptive-network- based fuzzy inference system," IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, no. 3, pp. 665–685, May/Jun. 1993.
7. L. A. Zadeh, "Fuzzy sets," Information and Control, vol. 8, no. 3, pp. 338–353, 1965.
8. M. B. I. Reaz, M. S. Hussain, and F. Mohd- Yasin, "Techniques of EMG signal analysis: Detection, processing, classification, and applications," Biological Procedures Online, vol. 8, no. 1, pp. 11–35, 2006.
9. S. H. Fairclough and L. Venables, "Prediction of subjective states from psychophysiology: A multivariate approach," Biological Psychology, vol. 71, no. 1, pp. 100–110, 2006.
10. S. G. Hart and L. E. Staveland, "Development of NASA-TLX (Task Load Index): Results of empirical and theoretical research," Advances in Psychology, vol. 52, pp. 139–183, 1988.