Stress Detection Using Hybrid Deep Learning Models with Attention Mechanisms: A Comparative Study of CNN-LSTM, CNN-GRU, and Ensemble Approaches


  • Gregorius Airlangga * Mail Atma Jaya Catholic University of Indonesia, Jakarta, Indonesia
  • (*) Corresponding Author
Keywords: Stress Detection; Hybrid Deep Learning; CNN-LSTM; Attention Mechanisms; Ensemble Model

Abstract

Accurate and reliable stress detection remains a critical challenge in health monitoring due to the multifaceted nature of stress and the difficulty in capturing its temporal and spatial characteristics from physiological data. Existing methods often lack the ability to effectively model these dependencies, leading to suboptimal performance and limited interpretability, which hinder their application in real-world scenarios such as wearable devices and mobile health systems. This study addresses these limitations by investigating hybrid deep learning models with attention mechanisms, specifically focusing on CNN-LSTM, CNN-GRU, and CNN-BiLSTM architectures and their ensemble. Leveraging the complementary strengths of convolutional and recurrent layers, these models aim to capture both spatial and temporal dependencies in stress-related data, while attention layers enhance interpretability by prioritizing relevant features. Experimental results reveal that the CNN-LSTM with Attention model achieved the best performance, with the lowest Mean Squared Error (MSE) and Mean Absolute Error (MAE), demonstrating its suitability for complex stress prediction tasks. The CNN-GRU model also performed well, offering a balance between computational efficiency and accuracy, while the CNN-BiLSTM model showed limitations, suggesting that additional model complexity may lead to overfitting. The ensemble model, combining predictions from all three architectures, delivered stable performance across metrics, underscoring the value of ensemble approaches in improving robustness and mitigating model-specific biases. These findings have significant implications for practical applications, such as wearable devices and mobile health systems, where accurate, interpretable, and reliable stress monitoring is essential for timely interventions. Future work should focus on optimizing these models for real-time deployment, exploring adaptive learning for personalized stress detection, and validating across diverse datasets to enhance generalizability. This research highlights the importance of hybrid architectures and attention mechanisms in addressing the challenges of stress detection, paving the way for responsive and user-centered health monitoring systems.

Downloads

Download data is not yet available.

References

D. Popovic et al., “Defining the importance of stress reduction in managing cardiovascular disease-the role of exercise,” Prog. Cardiovasc. Dis., vol. 70, pp. 84–93, 2022.

I. J. Vadakkiniath, “Prevalence and correlates of stress, anxiety, and depression in patients with chronic diseases: a cross-sectional study,” Middle East Curr. Psychiatry, vol. 30, no. 1, p. 66, 2023.

M. T. Osborne, L. M. Shin, N. N. Mehta, R. K. Pitman, Z. A. Fayad, and A. Tawakol, “Disentangling the links between psychosocial stress and cardiovascular disease,” Circ. Cardiovasc. Imaging, vol. 13, no. 8, p. e010931, 2020.

A. Zaree et al., “Cardiac rehabilitation in the modern era: optimizing recovery and reducing recurrence,” Cureus, vol. 15, no. 9, 2023.

R. Franco D’Souza, M. Mathew, V. Mishra, and K. M. Surapaneni, “Twelve tips for addressing ethical concerns in the implementation of artificial intelligence in medical education,” Med. Educ. Online, vol. 29, no. 1, p. 2330250, 2024.

P. E. Velmovitsky, “Use of Smart Technology Tools for Supporting Public Health Surveillance: From Development of a Mobile Health Platform to Application in Stress Prediction,” 2023.

B. A. Hickey et al., “Smart devices and wearable technologies to detect and monitor mental health conditions and stress: A systematic review,” Sensors, vol. 21, no. 10, p. 3461, 2021.

S. Sharma, G. Singh, and M. Sharma, “A comprehensive review and analysis of supervised-learning and soft computing techniques for stress diagnosis in humans,” Comput. Biol. Med., vol. 134, p. 104450, 2021.

C. V. Anikwe et al., “Mobile and wearable sensors for data-driven health monitoring system: State-of-the-art and future prospect,” Expert Syst. Appl., vol. 202, p. 117362, 2022.

K. Magtibay and K. Umapathy, “A Review of Tools and Methods for Detection, Analysis, and Prediction of Allostatic Load Due to Workplace Stress,” IEEE Trans. Affect. Comput., vol. 15, no. 1, pp. 357–375, 2023.

T. Joseph and B. TS, “Real-time Blood Pressure Prediction on Wearable Devices using Edge Based Deep Neural Networks: A Hardware-software Co-design Approach,” ACM Trans. Des. Autom. Electron. Syst., 2024.

A. Mahmoodzadeh et al., “Prediction of minimum horizontal stress in oil wells using recurrent neural networks,” Geoenergy Sci. Eng., vol. 223, p. 211560, 2023.

I. Salehin et al., “Real-Time Medical Image Classification with ML Framework and Dedicated CNN--LSTM Architecture,” J. Sensors, vol. 2023, no. 1, p. 3717035, 2023.

X. Zhu, “Attention-based Multi-task Deep Learning for Short-term Multi-energy Load Forecasting,” 2024.

K. Cao, T. Zhang, and J. Huang, “Advanced hybrid LSTM-transformer architecture for real-time multi-task prediction in engineering systems,” Sci. Rep., vol. 14, no. 1, p. 4890, 2024.

K. W. Ng, Y. F. Huang, C. H. Koo, K. L. Chong, A. El-Shafie, and A. N. Ahmed, “A review of hybrid deep learning applications for streamflow forecasting,” J. Hydrol., p. 130141, 2023.

A. A. Al-Atawi et al., “Stress Monitoring Using Machine Learning, IoT and Wearable Sensors,” Sensors, vol. 23, no. 21, p. 8875, 2023.

M. Bolpagni, S. Pardini, M. Dianti, and S. Gabrielli, “Personalized Stress Detection Using Biosignals from Wearables: A Scoping Review,” Sensors, vol. 24, no. 10, p. 3221, 2024.

N. Rane, S. Choudhary, and J. Rane, “Ensemble Deep Learning and Machine Learning: Applications, Opportunities, Challenges, and Future Directions,” Oppor. Challenges, Futur. Dir. (May 31, 2024), 2024.

Y. Zhang, J. Liu, and W. Shen, “A review of ensemble learning algorithms used in remote sensing applications,” Appl. Sci., vol. 12, no. 17, p. 8654, 2022.

Swadeshi, “Stress Detection Dataset.” Kaggle, 2023.


Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Stress Detection Using Hybrid Deep Learning Models with Attention Mechanisms: A Comparative Study of CNN-LSTM, CNN-GRU, and Ensemble Approaches

Dimensions Badge
Article History
Submitted: 2024-11-16
Published: 2024-11-30
Abstract View: 31 times
PDF Download: 19 times
Section
Articles