Energy-Efficient FPGA Accelerator With Fidelity-Controllable Sliding-Region Signal Processing Unit for Abnormal ECG Diagnosis on IoT Edge Devices

Abstract

Recently, with an increase in the number of healthcare devices, studies measuring and diagnosing electrocardiogram (ECG) signals in daily life are emerging. ECG signal analysis is an essential study area that can diagnose fatal heart abnormalities in humans at an early stage. Conventional signal detection uses one reference beat to diagnose ECG signals; thus, the detection rate is different for each person. In this study, we design a system that can learn a reference beat and diagnose ECG signals in real-time using hardware accelerators with the approximated template-based ECG diagnosis algorithm proposed in the previous study. The proposed algorithm can easily perform personalized learning, increasing the detection rate since it has faster learning time and consumes less memory than the existing algorithm. The learning data, which occupies a small memory space, enables real-time and simultaneous diagnosis of several people. We confirmed that the proposed ECG diagnosis algorithm is suitable for hardware acceleration by accelerating the ECG signal diagnosis and measuring the parallelized result using Alveo field-programmable gate array (FPGA). The ECG diagnosis algorithm, implemented at the FPGA in real-time, can flexibly determine reference beats that vary depending on the person and diagnose each person's signal. The experimental results showed that the time required to diagnose the ECG signals of five people containing 1987 beats takes 5.70 s with software and 0.572 s with hardware accelerators, which is 89.96% shorter than software execution time.

Real-Time Processing Stages of Electrocardiogram Signal: A Review

“…The PU array ran in a pipeline to generate efficient calculation results, which were then quantized using a Bit-width Converter. Lee et al (2021) introduced a system for real time ECG diagnosis using hardware accelerators and an approximated template-based algorithm. This personalized approach improves detection rates and reduces memory usage compared to existing methods.…”

FPGA-based Lightweight QDS-CNN System for sEMG Gesture and Force Level Recognition

“…Field Programmable Gate Array (FPGA) has become one of the most mainstream choices for accelerating CNN inference due to its excellent performance achieved on CNN inference tasks. In this work, Zynq architecture was adopted to construct an sEMG gesture and force level recognition system, by combining the advantages of high performance of the dedicated accelerator and flexibility of the general-purpose accelerator [18].The FPGA core of the Zynq architecture is programmable and can be upgraded and extended according to actual needs; meanwhile the ARM core can be used for signal pre-processing to reduce data transfer latency and enhance computational efficiency. FPGA can accelerate the computation of DL models through parallel computing and highly optimized hardware architecture, resulting in fast inference speed and low latency.…”

On-Cloud Linking Approach Using a Linkable Glue Layer for Metamorphic Edge Devices

“…Separating code based on the on-demand execution code enhances the independence of the edge and server code, enabling metamorphic program execution [16,17]. From a resource virtualization perspective, even if the code stored on the edge device remains unchanged, the behavior of the program executed at the edge can be changed if the code stored on the server is modified.…”