Digital implementation of bio-inspired spiking neural network for ECG classification

Chen, Dze Rynn (2022) Digital implementation of bio-inspired spiking neural network for ECG classification. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)

Preview

Text (Full Text) Digital implementation of bio-inspired spiking neural network for ECG classification.pdf - Submitted Version Download (5MB) | Preview

Abstract

Conventional techniques of off-chip processing for wearable devices cause higher hardware resource usage and power consumption. Hence, edge computing methods such as neuromorphic computing are considered the most promising modern technology to replace conventional processing. It is beneficial to employ neuromorphic processing in ECG classification, enabling engineers to overcome the constraints of hardware utilization. Thus, this work aims to investigate common building blocks in a spiking neural network (SNN), analyse the spike-based plasticity mechanism and implement ECG classification on a neuromorphic circuit. The MITBIH Arrhythmia database (MITDB) is used in this work, which is obtained from the Physionet website. The data is preprocessed in MATLAB, then used to train and test an SNN designed for field programmable gate arrays (FPGA), employing spike-based plasticity and Izhikevich neurons. The behaviour of spike timing dependent plasticity (STDP) in a neuromorphic circuit is also visualized in this work. The SNN classifies ECG data into two categories: normal and abnormal. The proposed digital design utilizes 1.058% of hardware resources on a Zedboard. Application-wise, this work provides a foundation for development of neuromorphic computing in wearable medical devices that perform continuous monitoring of ECG.

Actions (login required)

View Item