Authors : Oğuzhan Hasar; Muhammed Kürşad Uçar

Volume/Issue : Volume 10 - 2025, Issue 9 - September

Google Scholar : https://tinyurl.com/3ek3ektv

Scribd : https://tinyurl.com/mvpbw6s4

DOI : https://doi.org/10.38124/ijisrt/25sep1252

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

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Stress is a state that occurs when an individual's physical and mental resources are taxed in response to demands, becoming especially evident under heavy mental exertion. Mental workload is a significant psychophysiological metric that directly influences task performance and can also lead to mental diseases such as depression. Thus, the objective evaluation of stress levels using physiological data is crucial for enhancing work productivity and assuring safety. This work employed an integrated approach utilizing electrocardiography (ECG) and photoplethysmography (PPG) signals for stress detection. The data were sourced from the publically accessible MAUS dataset and gathered from 22 healthy participants utilizing wearable sensors during N-back activities. The signals were segmented into epochs, and a total of 50 features were extracted at both temporal and spectral levels. The features were examined utilizing diverse machine learning algorithms. The models' performance is assessed using accuracy, specificity, F-score, and AUC criteria, with the Bagged Trees method achieving the greatest accuracy of 98.6%. The results indicate that employing several biosignals and sophisticated signal processing techniques provides excellent precision in stress detection. The device provides a pragmatic option for real-time monitoring of individuals' stress levels in their daily lives, thanks to its portable design.

Keywords : Component; Photolethysmography(PPG), Electrocardiography(ECG), Stress Detection, Machine Learning, Biomedical Signal Processing, Artificial Intelligence.

References :

1. Y. Liu and S. Du, “Psychological stress level detection based on electrodermal activity,” Biol. Psychol., vol. 169, pp. 1–7, 2022, doi: 10.1016/j.biopsycho.2022.108382.
2. H. Kurniawan, A. V. Maslov, and M. Pechenizkiy, “Stress detection from speech and galvanic skin response signals,” unpublished, Dept. of Computer Science, Eindhoven Univ. of Technology, Netherlands, 2023.
3. S. B. Dasari, C. T. Mallareddy, S. Annavarapu, and T. T. Garike, “Detection of mental stress levels using electroencephalogram signals (EEG),” unpublished, VR Siddhartha Engineering College, India.
4. [7] P. Samal and R. Singla, “EEG based stress level detection during gameplay,” unpublished, Dept. of ICE, Dr. B. R. Ambedkar NIT Jalandhar, India.
5. J. Guo and K. G. Smitha, “EEG based stress level identification,” unpublished, School of Computer Science and Engineering, Nanyang Technological University, Singapore.
6. T. Y. Wen and S. A. M. Aris, “Hybrid approach of EEG stress level classification using K-means clustering and support vector machine,” unpublished, Universiti Teknologi Malaysia.
7. G. Giannakakis, K. Marias, and M. Tsiknakis, “A stress recognition system using HRV parameters and machine learning techniques,” in Proc. 2019 8th Int. Conf. Affective Comput. Intell. Interact. Workshops and Demos (ACIIW), 2019, pp. 269–272, doi: 10.1109/ACIIW.2019.8925027.
8. S. Quoy, D. Istrate, M. Benchekroun, and V. Zalc, “HRV based stress detection using convolutional neural networks (CNNs),” in Proc. 2024 Int. Conf. Content-Based Multimedia Indexing (CBMI), 2024, pp. 20–24, doi: 10.1109/CBMI62980.2024.10859222.
9. Y. Hasanpoor, B. Tarvirdizadeh, and K. Alipour, “Stress assessment with convolutional neural network using PPG signals,” in Proc. IEEE India Council Int. Conf. (INDICON), 2022, pp. 197–202, doi: 10.1109/INDICON.2023.10440913.
10. J. Přibil, A. Přibilová, and I. Frollo, “Stress detection and classification from PPG signals recorded in different conditions – pilot study,” unpublished, Dept. of Imaging Methods, Institute of Measurement Science, Slovak Academy of Sciences, Bratislava, Slovakia, 2022.
11. J. Zhai and A. Barreto, “Stress detection in computer users based on digital signal processing of noninvasive physiological variables,” in Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC), 2006, pp. 1355–1358, doi: 10.1109/IEMBS.2006.259421.
12. M. Gjoreski, M. Luštrek, M. Gams, and H. Gjoreski, “Monitoring stress with a wrist device using context,” Sensors, vol. 22, no. 4, p. 1443, 2022, doi: 10.3390/s22041443.
13. P. Kasnesis, C. Chatzigeorgiou, M. Feidakis, Á. Gutiérrez, and C. Z. Patrikakis, “TranSenseFusers: A temporal CNN-Transformer neural network family for explainable PPG-based stress detection,” Comput. Biol. Med., vol. 165, p. 107537, 2023, doi: 10.1016/j.compbiomed.2023.107537.
14. P. Nagy and A. Jobbágy, “Sensor fusion for the accurate non-invasive measurement of blood pressure,” Med. Eng. Phys., vol. 105, p. 103927, 2022, doi: 10.1016/j.medengphy.2022.103927.
15. J. Wijsman, B. Grundlehner, H. Liu, H. Hermens, and J. Penders, “Towards mental stress detection using wearable physiological sensors,” unpublished, 2023.
16. N. Keshan, P. V. Parimi, and I. Bichindaritz, “Machine learning for stress detection from ECG signals in automobile drivers,” unpublished, State Univ. of New York at Oswego, USA.
17. R. K. Nath, H. Thapliyal, A. Caban-Holt, and S. P. Mohanty, “Machine learning based solutions for real-time stress monitoring,” unpublished, Univ. of Kentucky and Wake Forest School of Medicine, 2023.
18. S. Campanella, A. Altaleb, A. Belli, P. Pierleoni, and L. Palma, “PPG and EDA dataset collected with Empatica E4 for stress assessment,” unpublished, Università Politecnica delle Marche, Italy, 2022.
19. D. Chatterjee, R. Gavas, and S. K. Saha, “Detection of mental stress using novel spatio-temporal distribution of brain activations,” J. Biomed. Inform., vol. 137, p. 104324, 2023, doi: 10.1016/j.jbi.2022.104324.
20. M. K. Uçar, M. R. Bozkurt, C. Bilgin, and K. Polat, “Automaticdetection of respiratory arrests in OSA patients using PPGand machine learning techniques,” Neural Computing andApplications, vol. 28, no. 10, 2017.
21. D. M. W. Powers, “Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation,” arXiv preprint arXiv:2010.16061, 2020.
22. N. Kim, S. Lee, J. Kim, S. Y. Choi, and S.-M. Park, “Shuffled ECA-Net for stress detection from multimodal wearable sensor data,” Comput. Biol. Med., vol. 183, p. 109217, 2024, doi: 10.1016/j.compbiomed.2024.109217.
23. J. Beh, L. Chen, C. Zhang, L. Guo, and J. Liu, “MAUS: A Dataset for Mental Workload Assessment on N-back Task Using Wearable Sensor,” IEEE Dataport, 2021. [Online]. Available: https://ieee-dataport.org/open-access/maus-dataset-mental-workload-assessment-n-back-task-using-wearable-sensor
24. MAUS Documentation, “MAUS Dataset Documentation,” 2021. [Online]. Available: https://ieee-dataport.org/open-access/maus-dataset-mental-workload-assessment-n-back-task-using-wearable-sensor
25. A. Dayal, S. Rajan, and L. Chen, “A Novel Approach to Cognitive Load Measurement in N-Back Tasks Using Wearable Sensors: Empirical Mode Decomposition with Machine Learning and Explainability,” Electronics, vol. 14, no. 2, pp. 238–252, 2025.
26. F. Ayar, E. Öğünç, E. C. Baykal, H. Bozkurt, and M. K. Uçar, “Artificial intelligence based 4 axis direction control with electroencephalography signal,” 2021 Medical Technologies Congress (TIPTEKNO), pp. 1–4, 2021, doi: 10.1109/TIPTEKNO53239.2021.9632988.
27. S. Quoy, D. Istrate, M. Benchekroun, and V. Zalc, “HRV based stress detection using convolutional neural networks,” Proc. IEEE Int. Conf. Content-Based Multimedia Indexing (CBMI), pp. 20–24, 2024.
28. A. Reiss, P. Schmidt, R. Dürichen, and K. Van Laerhoven, “Introducing WESAD, a multimodal dataset for wearable stress and affect detection,” Proc. 20th ACM Int. Conf. Multimodal Interaction, pp. 400–408, 2018.
29. A. Kuttala, R. Walambe, and K. Kotecha, “Multimodal hierarchical CNN feature fusion for stress detection,” Sensors, vol. 23, no. 6, p. 3223, 2023.
30. J. Beh, J. Liu, and L. Chen, “A robust PPG-based mental workload assessment system using wearable devices,” Biomed. Signal Process. Control, vol. 78, p. 103931, 2023.
31. M. Aydemir, H. M. Ertugrul, and M. F. Ozdemir, “Sequential forward mother wavelet selection for mental workload assessment using PPG signals,” Biomed. Signal Process. Control, vol. 68, p. 102726, 2021.
32. V. Markova and T. Ganchev, (2018), Three-step Attribute Selection for Stress Detection based on Physiological Signals. Proc. IEEE 27th International Scientific Conference Electronics (ET), Sozopol, Bulgaria, pp. 1–4. https://doi.org/10.1109/ET.2018.1234567
33. Beh, J., Liu, J., & Chen, L., (2023), A Robust PPG-Based Mental Workload Assessment System Using Wearable Devices. Biomedical Signal Processing and Control, 78, 103931. https://doi.org/10.1016/j.bspc.2022.103931
34. Rashid, N., Chen, L., Dautta, M., Jimenez, A., Tseng, P., & Al Faruque, M. A., (2021), Feature Augmented Hybrid CNN for Stress Recognition Using Wrist-based Photoplethysmography Sensor. 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 2374–2377. https://doi.org/10.1109/EMBC46164.2021.9630576
35. H. Zhang, Z. Wang, Y. Zhuang, S. Yin, Z. Chen, and Y. Liang, "Assessment of Mental Workload Level Based on PPG Signal Fusion Continuous Wavelet Transform and Cardiopulmonary Coupling Technology," Electronics, vol. 13, no. 7, p. 1238, Mar. 2024, doi: 10.3390/electronics13071238.
36. Radhika, K., & Oruganti, V. R. M., (2020), Transfer Learning for Subject-Independent Stress Detection using Physiological Signals. 2020 IEEE 17th India Council International Conference (INDICON), Bengaluru, India, pp. 1–6. https://doi.org/10.1109/INDICON49873.2020.9342505
37. V. Markova, T. Ganchev, and K. Kalinkov, “CLAS: A database for cognitive load, affect and stress recognition,” in Proc. Int. Conf. Biomedical Innovations and Applications (BIA), Varna, Bulgaria, Nov. 2019, pp. 1–4 .
38. Kumar, S., He, D., Qiao, G., & Donmez, B., (2022), Classification of Driver Cognitive Load based on Physiological Data: Exploring Recurrent Neural Networks. 2022 7th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM), Guilin, China, pp. 19–24. https://doi.org/10.1109/ICARM54641.2022.9959588
39. A. Aygun, T. Nguyen, Z. Haga, S. Aeron, and M. Scheutz, “Investigating methods for cognitive workload estimation for assistive robots,” Sensors, vol. 22, no. 18, p. 6834, 2022, doi: 10.3390/s22186834.
40. Radhika, K., & Oruganti, V. R. M., (2022), Cross Domain Features for Subject-Independent Stress Detection. 2022 IEEE Region 10 Symposium (TENSYMP), Mumbai, India, pp. 1–6. https://doi.org/10.1109/TENSYMP54529.2022.9864379
41. Nath, R. K., Thapliyal, H., & Caban-Holt, A., (2020), Validating Physiological Stress Detection Model Using Cortisol as Stress Bio Marker (Random Forest Classifier). 2020 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, USA, pp. 1–6. https://doi.org/10.1109/ICCE46568.2020.9043092
42. Sandulescu, V., Andrews, S., Ellis, D., Bellotto, N., & Martinez Mozos, O., (2015), Stress Detection Using Wearable Physiological Sensors. Lecture Notes in Computer Science, Springer, Cham, vol. 9196, pp. 295–302. https://doi.org/10.1007/978-3-319-18914-7_55
43. M. S. N. Sadoun, J. M. Vargas, M. M. Boularas, A. Boutin, F. Cottin, and T. M. Laleg-Kirati, “Cognitive Stress Detection during Physical Activity using Simultaneous, Mobile EEG and ECG signals,” IFAC PapersOnLine, vol. 58, no. 24, pp. 291–296, 2024, doi: 10.1016/j.ifacol.2024.11.052.
44. L. Breiman, “Bagging predictors,” Machine Learning, vol. 24, no. 2, pp. 123–140, 1996. doi:10.1007/BF00058655