Title: Hardware-optimised CNN architecture for ECG biometric identification on embedded systems

Authors: Hatem Zehir; Toufik Hafs; Sara Daas

Addresses: Faculty of Technology, Electronics Department, Laboratory of Study and Research in Instrumentation and Communication of Annaba (LERICA), Badji Mokhtar-Annaba University, P.O. Box 12, 23000, Annaba, Algeria ' Faculty of Technology, Electronics Department, Laboratory of Study and Research in Instrumentation and Communication of Annaba (LERICA), Badji Mokhtar-Annaba University, P.O. Box 12, 23000, Annaba, Algeria ' Faculty of Technology, Electronics Department, Laboratory of Study and Research in Instrumentation and Communication of Annaba (LERICA), Badji Mokhtar-Annaba University, P.O. Box 12, 23000, Annaba, Algeria

Abstract: This paper presents an optimised convolutional neural network (CNN) for Electrocardiogram (ECG) biometrics, focusing on enhancing efficiency and performance using a quantised CNN model. The research evaluated the model on 10 subjects from the MIT-BIH database. ECG signals were filtered with a 4th-order Butterworth filter (1-40 Hz), and R-peaks were detected using the Pan-Tompkins++ algorithm. Segments around these peaks were windowed into 125 ms frames, and spectrograms were generated via short-time Fourier transform (STFT). These normalised spectrograms were fed into both standard and 8-bit quantised CNN models for biometric identification. The 8-bit quantised model, deployed on an ESP32, achieved 97.90% accuracy, outperforming the original model. It was 77% faster and 64% smaller in size, demonstrating significant improvements in efficiency and performance. The study suggests further exploration of quantised models in ECG biometrics.

Keywords: biometric identification; CNNs; convolutional neural networks; ESP32; quantisation; resource-efficient computing.

DOI: 10.1504/IJSISE.2025.150014

International Journal of Signal and Imaging Systems Engineering, 2025 Vol.14 No.1, pp.29 - 38

Received: 25 Jul 2024
Accepted: 10 Feb 2025
Published online: 21 Nov 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article