Conference Paper2024Cited by 8

Smartwatch-Based Human Stress Diagnosis Utilizing Physiological Signals and LSTM-Driven Machine Intelligence

Nabarun Halder, Jahanggir Hossain Setu, Ashraful Islam, M Ashraful Amin

2024 Advances in Science and Engineering Technology International Conferences (ASET)

IEEE, pp. 01-08

  • Good Health and Well-being — Relevance: 92%
DOI: 10.1109/aset60340.2024.10708730URL

Abstract

Stress responses, primarily the ‘fight-or-flight’ reactions, are fundamental to human survival but can become harmful when they persist for extended periods. Prolonged stress exposure has been linked to various health issues and accelerated aging. But this can be addressed or controlled if a person becomes aware of their stress condition early. Traditional methods of identifying human stress relied heavily on self-reported questionnaires, but with the advancements in machine intelligence utilizing Machine Learning (ML) and Deep Learning (DL) techniques, the use of smart wearables like smartwatches for diagnosing stress has gained prominence. These devices can collect real-time physiological data, e.g., heart rate, skin conductance, and movement patterns, which are crucial for detecting stress. In this study, we utilized the ‘Stress-Predict Dataset’ built from the Empatica E4 wearable smartwatch device. After processing raw signals collected from 35 participants and aligning them to a uniform frequency of 32 Hz, we developed a Long Short-Term Memory (LSTM) model for stress classification. Training and validation sets achieved accuracies of 93.67 % and 91.13 %, respectively. The test set achieved an accuracy of 91.78 %, indicating a strong ability to identify stress events. This includes correctly classifying 30.31 % of True Positive (TP) stress occurrences with a low rate of False Negatives (FN) (missed stress events) at 4.56%. There were also 61.47% of True Negative (TN) classifications, demonstrating the model's ability to correctly identify non-stressful states with a low rate of False Positives (FN) (incorrectly classified non-stress events) at 3.66%. This research contributes to the ongoing exploration of stress diagnosis using wearable smartwatch device data, underlining the potential for further advancements in physiological stress monitoring.

Keywords

  • skin conductance
  • stress detection
  • physiological signals
  • stress classification
  • Empatica E4
  • Heart rate
  • smartwatches
  • wearable sensors
  • physiological stress monitoring
  • LSTM

CCDS Authors

Nabarun Halder
Nabarun Halder

Nabarun Halder

  • Research Assistant, CCDS

Published at

UbiComp, IJCNN, HCII, IEEE Access

Research Interests

Machine Learning, Deep Learning, Natural Language Processing, Health Informatics, Human-Computer Interaction

Ashraful Islam, PhD
Ashraful Islam

Ashraful Islam, PhD

  • Center Director, CCDS
  • Director, HCI Wing

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh (IUB)

Published at

CHI, UIST, UbiComp, IJCNN, ICIP, HCII, ICDMW, BLP, IEEE Internet of Things Journal, JMIR, JMIR Human Factors, JMIR Formative Research, IEEE Access, Smart Agricultural Technology, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Human-Computer Interaction, AI for Social Good, AI for Public Health, AI for Impact

Prof. M Ashraful Amin, PhD
M Ashraful Amin, PhD

Prof. M Ashraful Amin, PhD

  • Founder Director, CCDS
  • Director, AI/ML, HCI & DS Wings

Professor

+1 more affiliation

Department of Information Sciences and Technology

George Mason University, USA

Published at

ACL, CHI, UbiComp, ECAI, WACV, PAKDD, IJCNN, ICPR, ICIP, HCII, CLEF, BLP, Scientific Reports, JMIR, IEEE Access, Smart Agricultural Technology, Frontiers in Computational Neuroscience, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Machine Learning, Cognitive & Vision Science, Cybernetics, Surveillance & Security, ICT in Education, Health, & Agriculture, Human-Computer Interaction, Internet of Things, Robotics

References

  1. 1.Charles R. Harris, K. Jarrod Millman, Stéfan J. van der Walt, Ralf Gommers, Pauli Virtanen, David Cournapeau, Eric Wieser, Julian Taylor, Sebastian Berg, Nathaniel J. Smith, Robert Kern, Matti Picus, Stephan Hoyer, Marten H. van Kerkwijk, Matthew Brett, Allan Haldane, Jaime Fernández del Río, Mark Wiebe, Pearu Peterson, Pierre Gérard-Marchant, Kevin Sheppard, Tyler Reddy, Warren Weckesser, Hameer Abbasi, Christoph Gohlke, Travis E. Oliphant. (2020). Array programming with NumPy. Nature, 585(7825), 357–362[10.1038/s41586-020-2649-2]
  2. 2.Wes McKinney. (2010). Data Structures for Statistical Computing in Python. Proceedings of the Python in Science Conferences, 56–61[10.25080/majora-92bf1922-00a]
  3. 3.Yong Yu, Xiaosheng Si, Changhua Hu, Jianxun Zhang. (2019). A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures. Neural Computation, 31(7), 1235–1270[10.1162/neco_a_01199]
  4. 4.Bruce S. McEwen. (2007). Physiology and Neurobiology of Stress and Adaptation: Central Role of the Brain. Physiological Reviews, 87(3), 873–904[10.1152/physrev.00041.2006]
  5. 5.Thomas Kluyver, Benjamin Ragan-Kelley, Pérez Fernando, Brian Granger, Matthias Bussonnier, Jonathan Frederic, Kyle Kelley, Jessica B. Hamrick, Jason Grout, Sylvain Corlay, Ivanov Paul, Avila Damián, Safia Abdalla, Carol Willing, Jupyter Development Team. (2016). Jupyter Notebooks – a publishing format for reproducible computational workflows. IOS Press eBooks[10.3233/978-1-61499-649-1-87]
  6. 6.Robert M. Sapolsky. (2005). The Influence of Social Hierarchy on Primate Health. Science, 308(5722), 648–652[10.1126/science.1106477]
  7. 7.Alex Graves, Navdeep Jaitly, Abdelrahman Mohamed. (2013). Hybrid speech recognition with Deep Bidirectional LSTM. , 273–278[10.1109/asru.2013.6707742]
  8. 8.Philip Schmidt, Attila Reiss, Robert Duerichen, Claus Marberger, Kristof Van Laerhoven. (2018). Introducing WESAD, a Multimodal Dataset for Wearable Stress and Affect Detection. , 400–408[10.1145/3242969.3242985]
  9. 9.Eleni Andreou, Evangelos C. Alexopoulos, Christos Lionis, Liza Varvogli, Charalambos Gnardellis, George P. Chrousos, Christina Darviri. (2011). Perceived Stress Scale: Reliability and Validity Study in Greece. International Journal of Environmental Research and Public Health, 8(8), 3287–3298[10.3390/ijerph8083287]
  10. 10.Zahra Karevan, Johan A. K. Suykens. (2020). Transductive LSTM for time-series prediction: An application to weather forecasting. Neural Networks, 125, 1–9[10.1016/j.neunet.2019.12.030]
  11. 11.Shruti Gedam, Sanchita Paul. (2021). A Review on Mental Stress Detection Using Wearable Sensors and Machine Learning Techniques. IEEE Access, 9, 84045–84066[10.1109/access.2021.3085502]
  12. 12.Blake Anthony Hickey, Taryn Chalmers, Phillip J. Newton, Chin‐Teng Lin, David Sibbritt, Craig S. McLachlan, Roderick Clifton‐Bligh, John W. Morley, Lal S. (2021). Smart Devices and Wearable Technologies to Detect and Monitor Mental Health Conditions and Stress: A Systematic Review. Sensors, 21(10), 3461[10.3390/s21103461]
  13. 13.Kayisan Mary Dalmeida, Giovanni Luca Masala. (2021). HRV Features as Viable Physiological Markers for Stress Detection Using Wearable Devices. Sensors, 21(8), 2873[10.3390/s21082873]
  14. 14.Talha Iqbal, Andrew J. Simpkin, Davood Roshan, Nicola Glynn, John Killilea, Jane Walsh, Gerard J. Molloy, Sandra Ganly, Hannah Ryman, Eileen Coen, Adnan Elahi, William Wijns, Atif Shahzad. (2022). Stress Monitoring Using Wearable Sensors: A Pilot Study and Stress-Predict Dataset. Sensors, 22(21), 8135[10.3390/s22218135]
  15. 15.Prerna Garg, Jayasankar Santhosh, Andreas Dengel, Shoya Ishimaru. (2021). Stress Detection by Machine Learning and Wearable Sensors. , 43–45[10.1145/3397482.3450732]
  16. 16.Daniel Soutner, Luděk Müller. (2013). Application of LSTM Neural Networks in Language Modelling. Lecture notes in computer science, 105–112[10.1007/978-3-642-40585-3_14]
  17. 17.Sayandeep Ghosh, SeongKi Kim, Muhammad Fazal Ijaz, Pawan Kumar Singh, Mufti Mahmud. (2022). Classification of Mental Stress from Wearable Physiological Sensors Using Image-Encoding-Based Deep Neural Network. Biosensors, 12(12), 1153[10.3390/bios12121153]
  18. 18.Gideon Vos, Kelly Trinh, Zóltan Sarnyai, Mostafa Rahimi Azghadi. (2023). Ensemble machine learning model trained on a new synthesized dataset generalizes well for stress prediction using wearable devices. Journal of Biomedical Informatics, 148, 104556[10.1016/j.jbi.2023.104556]
  19. 19.Ruixuan Dai, Chenyang Lu, Linda Yun, Eric J. Lenze, Michael S. Avidan, Thomas Kannampallil. (2021). Comparing stress prediction models using smartwatch physiological signals and participant self-reports. Computer Methods and Programs in Biomedicine, 208, 106207[10.1016/j.cmpb.2021.106207]
  20. 20.Michael Moser, Bernd Resch, Maximilian Ehrhart. (2023). An Individual-Oriented Algorithm for Stress Detection in Wearable Sensor Measurements. IEEE Sensors Journal, 23(19), 22845–22856[10.1109/jsen.2023.3304422]
  21. 21.Subhadeep Basu, Samiul Mamud. (2020). Comparative Study on the Effect of Order and Cut off Frequency of Butterworth Low Pass Filter for Removal of Noise in ECG Signal. , 156–160[10.1109/icce50343.2020.9290646]
  22. 22.Talha Iqbal, Adnan Elahi, William Wijns, Bilal Amin, Atif Shahzad. (2023). Improved Stress Classification Using Automatic Feature Selection from Heart Rate and Respiratory Rate Time Signals. Applied Sciences, 13(5), 2950[10.3390/app13052950]
  23. 23.Stanislav V. Kasl. (1984). Stress and Health. Annual Review of Public Health, 5(1), 319–341[10.1146/annurev.pu.05.050184.001535]
  24. 24.Muhammad Ali Fauzi, Bian Yang. (2021). Continuous Stress Detection of Hospital Staff Using Smartwatch Sensors and Classifier Ensemble. Studies in health technology and informatics, 285, 245–250[10.3233/shti210607]
  25. 25.Sheldon Cohen, Tom Kamarck, Robin Mermelstein. (1983). Perceived Stress Scale. PsycTESTS Dataset[10.1037/t02889-000]
  26. 26.Z. Fried, Sándor Szénási, Imre Felde. (2018). Reconstruction of a heat transfer coefficients by using FWA approach. EasyChair preprint[10.29007/l6qh]

Cited By

  1. 1.Nikoletta-Anna Kapogianni, Angeliki Sideraki, Christos-Nikolaos Anagnostopoulos. (2025). Using Smartwatches in Stress Management, Mental Health, and Well-Being: A Systematic Review. Algorithms, 18(7), 419[10.3390/a18070419]
  2. 2.Frederic Andres. (2025). The Role of Emotional Intelligence in Self-Awareness and Well-Being. IGI Global eBooks, 1–46[10.4018/979-8-3373-0360-4.ch001]
  3. 3.Santiago Sosa, Adam K. Fontecchio, Evangelia G. Chrysikou, Jennifer S. Atchison. (2026). Beyond EDA: A Systematic Review of Multimodal Sympathetic Nervous System Arousal Classification for Stress Detection. Sensors, 26(5), 1584[10.3390/s26051584]
  4. 4.Matheus Correa Lindino, Luis Felipe Bortoletto, Bruno Sanches de Lima, Aurea Soriano-Vargas, Rickson C. Mesquita, Anderson Rocha. (2025). Distinguishing Stressor, Stress, and State Anxiety: Semantic and Physiological Insights With Machine Learning Approaches. IEEE Sensors Journal, 25(17), 34170–34186[10.1109/jsen.2025.3591761]
  5. 5.Maxine He, Abdulrahman Alkurdi, Jean L. Clore, Richard B. Sowers, Elizabeth T. Hsiao-Wecksler, Manuel E. Hernandez. (2025). Scoping Review of ML Approaches in Anxiety Detection from In-Lab to In-the-Wild. Applied Sciences, 15(18), 10099[10.3390/app151810099]
  6. 6.Shrivatsa Perur, Harish Kenchannavar, Rajeshwari Hegde, Anita Kenchannavar, Amruta Deshpande, Shanmugasundaram Hariharan. (2026). From brain to intervention: A framework for real-time stress detection using OpenBCI and machine learning. Neurocomputing, 705, 134880[10.1016/j.neucom.2026.134880]
  7. 7.Rajeswari Aleti, Monika Nijhawan, Mohammad Bakhatwar, Srinivas Baratam, Krishna Kishore Adireddy. (2026). PERSONALIZED CHRONOTHERAPY: BRIDGING PRECISION MEDICINE WITH CIRCADIAN THERAPEUTICS. INDIAN DRUGS, 63(03), 8–17[10.53879/id.63.03.15250]
  8. 8.Nabarun Halder, Armun Alam, Jahanggir Hossain Setu, Asif Mahmood, Ashraful Islam, M Ashraful Amin. (2025). Analyzing Machine Learning Models for Multiclass Classification of Human Stress Levels: Comparison Between Balanced and Imbalanced Data. International Conference on Knowledge and Smart Technology, 104–109[10.1109/kst65016.2025.11003364]
← All publications