Indonesian Journal of Electrical Engineering and Computer Science Vol. 27, No. 1, July 2022, pp. 528~537 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v27.i1.pp528-537  528 Journal homepage: http://ijeecs.iaescore.com Neuromorphic solutions: digital implementation of bio-inspired spiking neural network for electrocardiogram classification Dze Rynn Chen, Yan Chiew Wong Centre for Telecommunication Research and Innovation (CeTRI), Faculty of Electronics and Computer Engineering (FKEKK), Universiti Teknikal Malaysia Melaka (UTeM), Melaka, Malaysia Article Info ABSTRACT Article history: Received Jan 18, 2022 Revised May 24, 2022 Accepted Jun 8, 2022 Conventional techniques of off-chip processing for wearable devices cause high hardware resource usage which leads to heat generation and increased 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 electrocardiogram (ECG) classification, enabling engineers to overcome the constraints of heat generation caused by hardware utilization. Thus, this work aims to investigate common building blocks in a spiking neural network (SNN), analyze the spike-based plasticity mechanism and implement ECG classification on a neuromorphic circuit. The MIT-BIH Arrhythmia database (MITDB) 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 state-of the-art performance of this work lies in providing a generic mechanism to adapt ECG classification into a neuromorphic solution, a non-Von Neumann architecture. 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. Keywords: Digital hardware Edge computing Electrocardiogram Field programmable gate array Field programmable gate arrays Neuromorphic Spiking neural network This is an open access article under the CC BY-SA license. Corresponding Author: Yan Chiew Wong Centre for Telecommunication Research and Innovation (CeTRI), Faculty of Electronics and Computer Engineering (FKEKK), Universiti Teknikal Malaysia Melaka Street of Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia Email: ycwong@utem.edu.my 1. INTRODUCTION Cardiac arrhythmias refer to the impairment of the electrical impulses coordinating human heartbeats and are used to identify the presence of cardiovascular diseases (CVDs). Due to the nature of arrhythmias that can reflect electrical activities in the heart, they can be detected by analyzing electrocardiogram (ECG) signals taken from the body [1]. To do this, the conventional way was for medical professionals to manually inspect results of an ECG test. However, arrhythmias occur intermittently, and thus are difficult to detect based solely on ECG tests. Therefore, continuous monitoring of ECGs is crucial in early detection of potential cardiovascular problems. In status quo, most wearable devices employ the mechanism of collecting data, then transmitting it to external servers which perform off-chip processing [2]. There are several problems with this. Firstly, conventional techniques of using remote servers and signal processing requires intensive computation and processing, causing higher hardware resource usage. Due to