Key result
Quantized DNN pipeline paired with fixed-point hardware detects atrial fibrillation with ~94% accuracy.
Why the study?
To develop a low-power hardware module and quantized neural network for real-time cardiac fibrillation diagnosis targeting IoMT devices and ASIC implementations.
Does a fixed-point hardware module with a quantized neural network maintain AF detection accuracy while improving energy efficiency in ECG recordings?
Does a fixed-point hardware module with a quantized neural network maintain AF detection accuracy while improving energy efficiency in ECG recordings?
A co-designed fixed-point Hjorth hardware and quantized DNN achieves high diagnostic accuracy for atrial fibrillation while offering significant energy and area savings suitable for wearable IoMT devices.
This paper presents the hardware aspects of a Hjorth-parameter deep neural network (DNN)-based cardiac fibrillation diagnosis pipeline targeting low-power Internet of Medical Things (IoMT) devices and ASIC implementations. Building on earlier edge-to-cloud studies where Hjorth activity, mobility, and complexity were computed in software on microcontrollers and classified by a floating-point DNN, we introduce a fully synthesizable fixed-point hardware module that computes these parameters in real time, together with a quantized neural network (QNN) operating directly on the resulting fixed-point features. The Hjorth block includes derivative generation, accumulator banks, variance computation, and hardware divider and square-root units. Using the Shandong Provincial Hospital Database (SPHD) as in our previous work, we evaluate the impact of end-to-end fixed-point quantization on the AF-related arrhythmia detection performance for bit widths between 6 and 16 bits. For 10–12-bit configurations, the quantized pipeline achieves accuracy of approximately 93.7% and an area under the ROC curve (AUC) above 0.97, closely matching the floating-point baseline while significantly reducing the arithmetic complexity and memory footprint. ASIC synthesis in a 28 nm CMOS standard-cell library shows that the complete atrial detector core, integrating the Hjorth extractor and the hardware fully connected QNN, occupies on the order of 2×104μm2 and dissipates about 3 mW, with a critical-path delay of 7.08 ns. For the optimal 10–12-bit operating points, the synthesized core achieves per-inference energy in the range of 18.6–19.0 nJ (18,600–19,000 pJ) per classification, confirming its suitability for integration into wearable and IoMT ECG monitoring nodes. These results demonstrate that co-designed fixed-point Hjorth hardware and quantized DNNs can deliver a favorable trade-off between diagnostic performance, area, power, latency, and per-inference energy compared with existing MCU-, FPGA-, and ASIC-based ECG classifiers.
No takes yet. Share an insight, caveat, or question.
Kouretas et al. (2026) studied Atrial fibrillation. Fixed-point Hjorth hardware and quantized DNNs vs. Floating-point baseline was evaluated on AF-related arrhythmia detection accuracy. A co-designed fixed-point Hjorth hardware and quantized DNN pipeline achieved approximately 93.7% accuracy and an AUC above 0.97 for atrial fibrillation detection.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: