Siddiqui et al. Res. Trends Int. J. Technol. Innov., April - June 2026, 1 (2) : 9-17
1Department of Biomedical Engineering, Manipal Institute of Technology, Manipal, India; 2Department of Electronics and Communication Engineering, International Institute of Information Technology Bangalore, India
Article History
Accepted : 19 May 2026
Published : 29 Jun 2026
Publication Issue
Volume 1, Issue 2
April - June 2026
Page Number9–17
Continuous ambulatory ECG monitoring can detect intermittent arrhythmias missed by short clinical recordings, but requires on-device classification to limit data transmission and battery drain. This paper presents a wearable single-lead ECG patch running a 1D convolutional neural network compressed to 82KB via quantisation, classifying five heartbeat types per the AAMI standard. Tested on the MIT-BIH Arrhythmia Database, the compressed model achieved 98.1 percent classification accuracy with a 6.7-day battery life on the prototype hardware.
Keywords - wearable ECG, arrhythmia classification, convolutional neural network, model quantization, edge AI
Paroxysmal arrhythmias are frequently missed by short-duration clinical ECGs, motivating wearable patches capable of continuous multi-day monitoring, which in turn requires that classification happen on-device to avoid the power cost of streaming raw waveform data.
A 1D CNN with three convolutional blocks was trained on the MIT-BIH Arrhythmia Database to classify heartbeats into five AAMI-defined superclasses, then compressed via post-training INT8 quantisation and deployed on an ARM Cortex-M4 microcontroller integrated into a single-lead adhesive ECG patch with a 100mAh battery.
The quantised model retained 98.1 percent classification accuracy on the MIT-BIH test partition, a 0.4 percentage point drop from the full-precision model, while reducing model size from 612KB to 82KB. Bench testing of the prototype patch showed continuous operation for 6.7 days between charges under typical duty cycling.
On-device quantised CNN classification enables multi-day wearable arrhythmia monitoring with clinically relevant accuracy. Future work includes a prospective clinical validation study against Holter monitor ground truth.
[1] Moody G. B. and Mark R. G., The MIT-BIH Arrhythmia Database, IEEE Engineering in Medicine and Biology, 2001. [2] Hannun A. Y. et al., Cardiologist-level arrhythmia detection with deep neural networks, Nature Medicine, 2019. [3] Jacob B. et al., Quantization and training of neural networks for efficient integer-arithmetic-only inference, CVPR, 2018.
© 2026 The Author(s). Published by IJEIA Editorial Office. This is an open access article under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
Ayesha Siddiqui, Rohit Bhatnagar (2026). Wearable ECG Monitoring System with Real-Time Arrhythmia Classification Using Lightweight CNN. IJEIA, 1(2), 9-17.
Fatima Zahra Khan, Rajat Bindal
Emerging Engineering TechnologiesNikhil Deshpande, Swathi Reddy