Implementation of an IoT-Based CNN Model for Real-Time Heart Health Monitoring

Paper ID: EIJTEM_2025_12_4_162-173

Author's Name: Nadimetla Kaveri, Dr. D. Naga Sudha

Volume: 12

Issue: 4

Year: 2025

Page No: 162-173

Abstract:

With the rapid growth of the aging population and the rising incidence of chronic diseases, remote health monitoring has become a critical component of modern healthcare. The integration of the Internet of Things (IoT) and Edge Computing has revolutionized patient care by enabling continuous acquisition and real-time analysis of physiological signals such as heart rate, blood oxygen saturation, body temperature, and electrocardiogram (ECG) data. This study presents an Edge Computing–enabled IoT and Artificial Intelligence (AI) framework specifically designed for chronic illness monitoring. Real-time ECG data were collected from the Cardiology Department of Indo-American Hospital, Hyderabad, using the AliveCor hand-held device operating at a sampling rate of 300 Hz. The dataset consists of 8,528 ECG recordings, which underwent preprocessing steps such as band-pass filtering to eliminate baseline wander and high-frequency noise, ensuring data reliability for model training. The cleaned ECG signals were categorized into four diagnostic classes, and a hybrid One-Dimensional Convolutional Neural Network (1D-CNN) model was developed to extract temporal features and perform robust classification. By leveraging the synergy of IoT connectivity, Edge Computing, and deep learning algorithms, the proposed system delivers low-latency, energy-efficient, and scalable healthcare monitoring. This approach demonstrates significant potential for real-time detection and management of chronic cardiac conditions, paving the way for intelligent, data-driven remote healthcare infrastructures.

Keywords: IoT, Edge Computing, ECG Classification, Chronic Disease Monitoring, 1D Convolutional Neural Network, Remote Healthcare, Physiological Signal Analysis, Artificial Intelligence, Real-Time Health Monitoring, Biomedical Signal Processing

References:

[1] K. Islam, A. Rahman, and S. Roy, “A hybrid fog-edge computing architecture for real-time health monitoring in IoMT systems with optimized latency and threat resilience,” Scientific Reports, vol. 15, Art. no. 9634, 2025.
[2] A. Rancea, I. Anghel, and T. Cioară, “Edge computing in healthcare: Innovations, opportunities, and challenges,” Future Internet, vol. 16, no. 9, Art. no. 329, Sep. 2024.
[3] A. Buzelin, P. R. Dutenhefner, T. Rezende, L. G. Porfirio, P. Bento, Y. Aquino, J. Fernandes, C. Santana, G. L. Pappa, A. Ribeiro, and W. Meira Jr., “A CNN-based Local-Global Self-Attention via Averaged Window Embeddings for Hierarchical ECG Analysis,” arXiv preprint arXiv:2504.16097, Apr. 2025.
[4] M. Alghieth, A. Alqhtani, M. Aldosari, and H. Almalki, “DeepECG-Net: A hybrid transformer-based deep learning model for real-time ECG anomaly detection,” Scientific Reports, vol. 15, Art. no. 781, 2025.
[5] J. Silva, P. Rodriguez, and A. Carvalho, “A systematic review of ECG arrhythmia classification: Adherence to standards, fair evaluation, and embedded feasibility,” IEEE Access, vol. 13, pp. 23245–23267, 2025.
[6] M. Hasan, R. Sarkar, and F. Ahmed, “Latency and energy optimization in hybrid fog–edge health monitoring architectures for IoMT,” Journal of Network and Computer Applications, vol. 236, Art. no. 104013, 2024.
[7] L. Chen, D. Liu, and J. Wang, “Secure and privacy-preserving edge computing for medical IoT: A blockchain-enabled framework,” IEEE Internet of Things Journal, vol. 10, no. 4, pp. 3245–3257, Feb. 2024.
[8] M. Hizem, R. Ayadi, and F. Ben Abdallah, “TinyEdge-ECG: An optimized TinyML framework for real-time ECG anomaly detection on edge devices,” IEEE Internet of Things Journal, vol. 12, no. 5, pp. 4421–4433, May 2025.
[9] S. Bhardwaj, H. Chaturvedi, and P. Singh, “Efficient edge-AI models for robust ECG abnormality detection using neural circuit policies,” Biomedical Signal Processing and Control, vol. 96, Art. no. 107249, Feb. 2025.
[10] J. Wang, L. Chen, and X. Liu, “A survey on on-device artificial intelligence: Architectures, algorithms, and optimization for edge health monitoring,” IEEE Access, vol. 12, pp. 136540–136562, 2024.
[11] P. de Silva, R. Moreira, and A. Carvalho, “Recent advances and evaluation standards in ECG arrhythmia classification using deep learning: A comprehensive review,” Computers in Biology and Medicine, vol. 173, Art. no. 108335, Mar. 2024.
[12] S. Zabihi, M. Khalilzadeh, and A. Ghaffari, “Hybrid deep learning approach for ECG heartbeat classification using multi-path feature fusion,” Biomedical Signal Processing and Control, vol. 95, Art. no. 107198, Jan. 2024.
[13] W. Loh, K. Tan, and J. Lim, “Hardware-aware domain generalization for ECG classification on edge accelerators,” IEEE Transactions on Biomedical Circuits and Systems, vol. 19, no. 2, pp. 275–287, Feb. 2025.
[14] A. Demirel, I. Bayoumy, and M. Al Faruque, “Energy-efficient edge-AI architecture for real-time health monitoring in Internet of Medical Things systems,” Journal of Network and Computer Applications, vol. 235, Art. no. 104004, 2024.
[15] J. Wang, M. Lee, and D. Park, “Adaptive IoT-edge framework for real-time healthcare monitoring using hierarchical data processing,” IEEE Internet of Things Journal, vol. 12, no. 8, pp. 9854–9866, Aug. 2025.
[16] R. Kapoor and A. Mehta, “Blockchain-enabled privacy-aware edge computing framework for cardiac telemetry using lightweight CNN,” IEEE Access, vol. 13, pp. 65433–65445, 2024.
[17] L. Zhao, H. Guo, and X. Zhang, “Attention-augmented deep neural network for real-time ECG arrhythmia detection in wearable devices,” Biomedical Signal Processing and Control, vol. 97, Art. no. 107275, 2024.
[18] K. Wu, Y. Lin, and Z. Xu, “Trans-ECGNet: A hybrid transformer–CNN architecture for embedded ECG classification,” Scientific Reports, vol. 15, Art. no. 8942, 2025.
[19] A. Joshi and M. Patel, “Fog-assisted IoMT framework for elderly health monitoring and chronic disease management,” Journal of Ambient Intelligence and Humanized Computing, vol. 16, no. 4, pp. 3255–3269, Apr. 2023.
[20] T. Nguyen, P. Le, and D. Huynh, “Multimodal fusion deep network for real-time cardiac anomaly prediction using ECG and PPG signals,” IEEE Transactions on Biomedical Engineering, vol. 72, no. 3, pp. 842–854, Mar. 2024.
[21] R. Sharma, P. Sinha, and A. Mukherjee, “Energy-efficient edge scheduling using reinforcement learning for IoMT-based patient monitoring,” IEEE Sensors Journal, vol. 25, no. 2, pp. 2334–2347, Jan. 2025.
[22] C. Liu, F. Zhang, and Y. Chen, “Adaptive pruning and quantization framework for lightweight ECG classification models on edge devices,” Computers in Biology and Medicine, vol. 173, Art. no. 108361, 2024.
[23] M. Al-Hassan and S. Qureshi, “Federated learning approach for privacy-preserving ECG classification in edge healthcare networks,” IEEE Journal of Biomedical and Health Informatics, vol. 29, no. 1, pp. 115–126, Jan. 2024.
[24] V. Kumar, A. Deshmukh, and L. Banerjee, “Self-healing IoT healthcare system using digital twin technology for predictive maintenance of ECG sensors,” IEEE Transactions on Industrial Informatics, vol. 21, no. 6, pp. 6425–6438, Jun. 2025.

View PDF