Exploiting FPGA Capabilities for Accelerated Biomedical Computing

TL;DR

This paper demonstrates how FPGA-based accelerators can enhance neural network performance for ECG analysis, providing a comprehensive guide for deploying deep learning models in biomedical applications.

Contribution

It introduces a custom FPGA accelerator and detailed methodology for optimizing neural networks on FPGAs for biomedical signal processing.

Findings

Achieved reduced latency and increased throughput in ECG classification

Validated robustness of models with added Gaussian noise

Provided a step-by-step FPGA deployment guide

Abstract

This study presents advanced neural network architectures including Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory Networks (LSTMs), and Deep Belief Networks (DBNs) for enhanced ECG signal analysis using Field Programmable Gate Arrays (FPGAs). We utilize the MIT-BIH Arrhythmia Database for training and validation, introducing Gaussian noise to improve algorithm robustness. The implemented models feature various layers for distinct processing and classification tasks and techniques like EarlyStopping callback and Dropout layer are used to mitigate overfitting. Our work also explores the development of a custom Tensor Compute Unit (TCU) accelerator for the PYNQ Z1 board, offering comprehensive steps for FPGA-based machine learning, including setting up the Tensil toolchain in Docker, selecting architecture, configuring PS-PL, and compiling and executing models. Performance metrics such as latency and throughput are calculated for practical insights, demonstrating the potential of FPGAs in high-performance biomedical computing. The study ultimately offers a guide for optimizing neural network performance on FPGAs for various applications.