10.57647/ijbbe.2026.0601.03

Real-Time Stress Detection Using Combined PPG and PCG Signals with Deep Learning

Show Details XML PDF
  • Sanaz Dalvandi1,
  • Atefeh Salimi Shahraki*2,
  • Farhad Azimifar3,
  • Mahdi Sajadieh1,
  1. Department of Electrical Engineering, Isf.C., Islamic Azad University, Isfahan, Iran
  2. Department of Electrical Engineering, Laser and Biophotonics in Biotechnologies Research Center, Isf.C., Islamic Azad University, Isfahan, Iran
  3. Department of Biomedical Engineering, Isf.C., Islamic Azad University, Isfahan, Iran

Received: 2025-12-29

Revised: 2026-06-05

Accepted: 2026-06-20

Published in Issue 2026-06-30

Copyright (c) 2026 Sanaz Dalvandi, Atefeh Salimi Shahraki, Farhad Azimifar, Seyed Mahdi Sajadieh (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Dalvandi, S., Salimi Shahraki, A., Azimifar, F., & Sajadieh, M. (2026). Real-Time Stress Detection Using Combined PPG and PCG Signals with Deep Learning. International Journal of Biophotonics and Biomedical Engineering (IJBBE), 6(1). https://doi.org/10.57647/ijbbe.2026.0601.03
Crossref
Scopus
Google Scholar
Europe PMC

PDF views: 55

Abstract

Given the serious risks psychological stress poses to both mental and cardiovascular health, there is a need for real-time and unobtrusive monitoring methods. We present a new deep learning framework that uses synchronized photoplethysmogram (PPG) and phonocardiogram (PCG) inputs to classify stress.  In contrast to current methods that use multimodal sensors or electrocardiography (ECG), our system uses only PCG and PPG, which are inexpensive, noninvasive, and wearable technology compatible.  The architecture incorporates a Bi-LSTM for sequential dependency modeling and a 1D U-Net encoder for multiscale temporal feature extraction.  A physiologically interpretable, self-supervised learning strategy is made possible by the automatic derivation of stress labels from PPG-based inter-beat intervals using RMSSD (root mean square of successive differences).  State-of-the-art accuracy (98.5%) and F1-scores (>0.97) are demonstrated via experimental results on a public dataset, together with real-time inference capabilities (<50 ms on CPU). Our approach opens the door for scalable wearable health monitoring devices by proving the feasibility of interpretable, end-to-end deep learning for stress detection using synchronized acoustic and optical cardiac inputs.

Keywords

  • Stress detection,
  • Deep learning,
  • PCG,
  • PPG,
  • Wearable devices
PDF

References

  1. Geetha R, et al. A Novel Deep Learning based Stress Analysis and Detection Scheme using Characteristic Data. In: 2023 Eighth International Conference on Science Technology Engineering and Mathematics (ICONSTEM). 2023.
  2. Durga CSLV, Manimaran J, Reddy MP. An Empirical Overview of Stress Detection Based on Photoplethysmography Signal Using Various Deep Learning Techniques. In: 2024 2nd International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT). 2024.
  3. Tarun M, et al. Stress Detection by Deep Learning Technique. In: 2024 Third International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS). 2024.
  4. Emadi M, Surani S. A New Method in Improving the Accuracy of Fetal Brain Health Diagnosis Based on Image Analysis of Constrictors Feature in Ultrasound Images. Int J Biophotonics Biomed Eng. 2025;5(1). DOI: https://doi.org/10.71498/ijbbe.2025.1195960
  5. Benchekroun M, et al. Comparison of Stress Detection through ECG and PPG signals using a Random Forest-based Algorithm. In: 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). 2022. DOI: https://doi.org/10.1109/EMBC48229.2022.9871906
  6. Eren E, Navruz TS. Stress Detection with Deep Learning Using BVP and EDA Signals. In: 2022 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA). 2022.
  7. Angalakuditi H, Bhowmik B. Stress Detection Using Deep Learning Algorithms. In: 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT). 2023.
  8. Rajabioun M. Identifying Autism from EEG Signals Using Features Derived from Active Brain Source Models. Int J Biophotonics Biomed Eng. 2025;5(1):55-68. DOI: https://doi.org/10.71498/ijbbe.2025.1204968
  9. Kyrou M, Kompatsiaris I, Petrantonakis PC. Deep Learning Approaches for Stress Detection: A Survey. IEEE Trans Affect Comput. 2025;16(2):499-517. DOI: https://doi.org/10.1109/TAFFC.2022.3188749
  10. Abdelfattah E, Joshi S, Tiwari S. Machine and Deep Learning Models for Stress Detection Using Multimodal Physiological Data. IEEE Access. 2025;13:4597-4608. DOI: https://doi.org/10.1109/ACCESS.2025.3141881
  11. Ghoshe DK, Munir NS, Debnath S. Mental Workload Assessment from ECG and PPG Signal Using Machine Learning Techniques. In: 2024 IEEE International Conference on Biomedical Engineering, Computer and Information Technology for Health (BECITHCON). 2024.
  12. Pashazadeh M, et al. A review of the antibacterial properties of zinc oxide nanoparticles: synthesis, mechanism of action, and medical applications. Int J Biophotonics Biomed Eng. 2025;5(1). DOI: https://doi.org/10.71498/ijbbe.2025.1202308
  13. Khanlari M, Dinparvar MJ. Design and Experimental Validation of a Portable Photometer for Non-Invasive Neonatal Jaundice Assessment. Int J Biophotonics Biomed Eng. 2025;5(1):69-78. DOI: https://doi.org/10.71498/ijbbe.2025.1211116
  14. Liu Z, et al. Mental Stress Detection Using PPG Signals Based on Transformer-LSTM Model. In: 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 2024.
  15. Gonzalez-Vazquez JJ, et al. A Deep Learning Approach to Estimate Multi-Level Mental Stress From EEG Using Serious Games. IEEE J Biomed Health Inform. 2024;28(7):3965-72. DOI: https://doi.org/10.1109/JBHI.2024.3378092
  16. Lazović A, Tadić P, Đorđević N, Atanasoski V, Tiosavljevic M, Ivanovic M, Hadzievski L, Ristic A, Vukcevic V, Petrovic J. SensSmartTech database of cardiovascular signals synchronously recorded by an electrocardiograph, phonocardiograph, photoplethysmograph and accelerometer (version 1.0.0). PhysioNet. 2024. DOI: https://doi.org/10.13026/fy9p-n277
  17. Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng CK, Stanley HE. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation. 2000;101(23):e215-e220. DOI: https://doi.org/10.1161/01.CIR.101.23.e215
  18. Andalibi Miandoab S, Ghasemzadeh N. Computational modeling of M1-BG-Th network firing rate and beta oscillation in brain neurological diseases for treatment with electrical or optogenetic stimulation. Int J Biophotonics Biomed Eng. 2025;5(1). DOI: https://doi.org/10.71498/ijbbe.2025.1191596
  19. Patel A, Nariani D, Rai A. Mental Stress Detection using EEG and Recurrent Deep Learning. In: 2023 IEEE Applied Sensing Conference (APSCON). 2023. DOI: https://doi.org/10.1109/APSCON56919.2023.10075003
  20. Aghamohammadian M, Vahedi A, Haghipour S. Optical biosensor for detection of hemoglobin using ternary photonic crystals. Int J Biophotonics Biomed Eng. 2025;5(1). DOI: https://doi.org/10.71498/ijbbe.2025.1193386
  21. HG T S, et al. Prediction of Cardiovascular Disease from Retinal Images using Deep Learning. In: 2024 4th International Conference on Artificial Intelligence and Signal Processing (AISP). 2024. DOI: https://doi.org/10.1109/AISP58276.2024.10564342
  22. Li M, et al. Stress Severity Detection in College Students Using Emotional Pulse Signals and Deep Learning. IEEE Trans Affect Comput. 2025:1-13. DOI: https://doi.org/10.1109/TAFFC.2023.3287146
  23. Wang W, Najafizadeh L. Ultra-Short Term Heart Rate Variability Estimation Using PPG and End-to-End Deep Learning. In: 2024 58th Asilomar Conference on Signals, Systems, and Computers. 2024. DOI: https://doi.org/10.1109 /IEEECONF57900.2024.1234567
  24. Kechris C, Delopoulos A. RMSSD Estimation From Photoplethysmography and Accelerometer Signals Using a Deep Convolutional Network. In: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). 2021. DOI: https://doi.org/10.1109/EMBC46164.2021.9630724
  25. Khomidov M, Lee JH. The Novel Estimation Algorithm of Heart Rate Variability and Stress Using Facial Video Analysis. In: 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2024.
  26. Mojtahed H, et al. A Deep Learning Approach for Heart Rate Variability Error Correction. In: 2024 IEEE 6th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS). 2024.
  27. Asjad M, et al. Federated Focal Modulated UNet for Cardiovascular Image Segmentation. In: 2024 IEEE International Conference on Big Data (BigData). 2024.
  28. Guru RP, et al. Enhanced Cardiovascular Disease Detection from Phonocardiogram Signals Using Deep Learning & Wavelet-Based Denoising. In: 2024 4th Asian Conference on Innovation in Technology (ASIANCON). 2024.
  29. Meghana ML, et al. Cardiovascular Disease Detection in ECG Images Using CNN-Bi-LSTM Model. In: 2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS). 2024.
  30. Sharma RK, et al. An Ensemble Convolutional Neural Network-Bidirectional Long Short-Term Memory-Attention Approach for Electrocardiogram-Based Heart Disease Diagnosis. In: 2025 International Conference on Microwave, Optical, and Communication Engineering (ICMOCE). 2025.
  31. Fayouka A, et al. Cardiac Segmentation: A Comparative Study Between 3D UNet and 2D UNet performances. In: 2024 IEEE/ACS 21st International Conference on Computer Systems and Applications (AICCSA). 2024.
  32. Novoselnik F, et al. 3D U-Net based method for fast segmentation of whole heart from CT images. In: 2022 International Symposium ELMAR. 2022.
  33. Sunilkumar G, Kumaresan P. Deep Learning and Transfer Learning in Cardiology: A Review of Cardiovascular Disease Prediction Models. IEEE Access. 2024;12:193365-86. DOI: https://doi.org/10.1109/ACCESS.2024.3352501
  34. Hasanpoor Y, et al. Stress Detection Using PPG Signal and Combined Deep CNN-MLP Network. In: 2022 29th National and 7th International Iranian Conference on Biomedical Engineering (ICBME). 2022.
  35. Roy TS, et al. Valvular Heart Disease Prediction Using CNNbased Residual Network. In: 2023 16th International Conference on Sensing Technology (ICST). 2023. Dalvandi et al., Int. J. Biophoton. Biomed. Eng., 6(1) 2026 35 10.57647/ijbbe.2026.0601.03
  36. Kannan A, et al. Detection of Valvular Heart Diseases From PCG Signals Using Machine and Deep Learning Models: A Review. IEEE Access. 2025;13:110344-64. DOI: https://doi.org/10.1109/ACCESS.2025.3350124
  37. Reshan MSA, et al. A Robust Heart Disease Prediction System Using Hybrid Deep Neural Networks. IEEE Access. 2023;11:121574-91. DOI: https://doi.org/10.1109/ACCESS.2023.3325193
  38. Kumar A, et al. Optimized Almond Damage Detection with UNet and Xception-based Segmentation and Classification. In: 2025 International Conference on Electronics and Renewable Systems (ICEARS). 2025.
  39. Kotipalli KD, et al. Machine Learning and Deep Learning Analysis of PCG Data. In: 2024 4th International Conference on Artificial Intelligence and Signal Processing (AISP). 2024. DOI: https://doi.org/10.1109/AISP58276.2024.10564351
  40. Nandan S, Mandal S, Ghosal P. Stress Detection and Monitoring: A Systematic Review. In: 2024 IEEE International Symposium on Smart Electronic Systems (iSES). 2024.
  41. Sanchez OD, et al. Real-Time Neural Classifiers for Sensor Faults in Three Phase Induction Motors. IEEE Access. 2023;11:19657-68. DOI: https://doi.org/10.1109/ACCESS.2023.3279745
  42. Sengar A, et al. Hybrid Approach for Heart Disease Detection using Classification Algorithms. In: 2023 IEEE International Conference on ICT in Business Industry & Government (ICTBIG). 2023.
  43. Shruthi K, Naidu RCA. Deep Learning for Cardiovascular Disease Detection: Comprehensive study on CNN and Random Forest based Hybrid Approach. In: 2025 International Conference on Knowledge Engineering and Communication Systems (ICKECS). 2025.