Low-Power FPGA-Based Quantized Neural Network Accelerator for Real-Time Arrhythmia Detection from Single-Lead ECG

Rahmani, Amir Hossein

doi:10.22075/mseee.2026.40918.1267

Low-Power FPGA-Based Quantized Neural Network Accelerator for Real-Time Arrhythmia Detection from Single-Lead ECG

Articles in Press

Document Type : Research Article

Author

Amir Hossein Rahmani

Department of Electrical Engineering, Sharif University of Technology, Tehran, Iran.

10.22075/mseee.2026.40918.1267

Abstract

Arrhythmia detection from long-term electrocardiogram (ECG) recordings is essential for early diagnosis of cardiovascular diseases in portable and wearable monitoring systems. This paper presents a low-power hardware accelerator for real-time beat-level arrhythmia classification using an 8-bit quantized 1D convolutional neural network (QNN) implemented on a Xilinx Artix‑7 FPGA. The network is trained and evaluated on the MIT-BIH Arrhythmia Database under an inter-patient scheme and classifies beats into three clinically relevant categories: normal (N), ventricular ectopic (V), and supraventricular ectopic (S). After quantization-aware training, the 8-bit fixed-point model achieves 98.4% overall accuracy, with 99.1% sensitivity and 98.7% positive predictive value (PPV) for N beats, and 96.6% sensitivity with 95.9% PPV for V beats on the held-out test set. The hardware accelerator exploits parallel multiply–accumulate units, on-chip BRAM reuse, and a streaming dataflow to process each 256-sample beat segment in 8.5 µs at 100 MHz, corresponding to a throughput of approximately 118 k beats/s while consuming 0.92 W power. Compared with a 32-bit floating-point implementation on an ARM Cortex-A9 processor, the proposed design provides about 9.3× speedup and 27× lower energy per beat, making it suitable for wearable and home monitoring systems.

Keywords

ECG

Arrhythmia Detection

Quantized Neural Network

FPGA Accelerator

Low Power Design

Subjects

Biomedical Engineering

[1] Y. Zhang, X. Chen, Y. Huang, and W. Wang, “A Real-Time FPGA-based Convolutional Neural Network for ECG Classification,” IEEE Access, vol. 7, pp. 184547–184555, 2019.

[2] H. Chen, S. Wang, and J. Xu, “Low-Power FPGA Implementation of Deep Convolutional Neural Network for ECG Arrhythmia Detection,” Biomedical Signal Processing and Control, vol. 62, 102101, 2020.

[3] P. Rajpurkar, A. Y. Hannun, M. Haghpanahi, C. Bourn, and A. Y. Ng, “Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks,” in Proc. AAAI, 2017.

[4] M. Zubair, J. Yoon, and S. S. Kim, “An Automated ECG Beat Classification System Using Deep Neural Networks,” IEEE Access, vol. 7, pp. 69215–69226, 2019.

[5] M. A. Al Rahhal et al., “Deep Learning Approach for Active Classification of Electrocardiogram Signals,” Information Sciences, vol. 345, pp. 340–354, 2016.

[6] H. Kiranyaz, T. Ince, and M. Gabbouj, “Real-Time Patient-Specific ECG Classification by 1‑D Convolutional Neural Networks,” IEEE Trans. Biomedical Engineering, vol. 63, no. 3, pp. 664–675, Mar. 2016.

[7] G. B. Moody and R. G. Mark, “The Impact of the MIT-BIH Arrhythmia Database,” IEEE Eng. Med. Biol. Mag., vol. 20, no. 3, pp. 45–50, 2001.

[8] A. L. Goldberger et al., “PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals,” Circulation, vol. 101, no. 23, pp. e215–e220, 2000.

[9] J. Pan and W. J. Tompkins, “A Real-Time QRS Detection Algorithm,” IEEE Trans. Biomedical Engineering, vol. BME‑32, no. 3, pp. 230–236, Mar. 1985.

[10] S. Han, H. Mao, and W. J. Dally, “Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding,” in Proc. ICLR, 2016.

[11] M. Rastegari, V. Ordonez, J. Redmon, and A. Farhadi, “XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks,” in Proc. ECCV, 2016.

[12] S. Yin, Z. Jiang, L. Liu, and S. Wei, “A High-Throughput and Energy-Efficient FPGA Accelerator for CNN-Based ECG Classification,” IEEE Trans. Circuits and Systems II: Express Briefs, vol. 68, no. 6, pp. 1950–1954, 2021.