Electromyogram (EMG) Signal Classification Based on Light-Weight Neural Network with FPGAs for Wearable Application

Abstract

Recently, the application of bio-signals in the fields of health management, human–computer interaction (HCI), and user authentication has increased. This is because of the development of artificial intelligence technology, which can analyze bio-signals in numerous fields. In the case of the analysis of bio-signals, the results tend to vary depending on the analyst, owing to a large amount of noise. However, when a neural network is used, feature extraction is possible, enabling a more accurate analysis. However, if the bio-signal time series is analyzed as is, the total neural network increases in size. In this study, to accomplish a light-weight neural network, a maximal overlap discrete wavelet transform (MODWT) and a smoothing technique are used for better feature extraction. Moreover, the learning efficiency is increased using an augmentation technique. In designing the neural network, a one-dimensional convolution layer is used to ensure that the neural network is simple and light-weight. Consequently, the light-weight attribute can be achieved, and neural networks can be implemented in edge devices such as the field programmable gate array (FPGA), yielding low power consumption, high security, fast response times, and high user convenience for wearable applications. The electromyogram (EMG) signal represents a typical bio-signal in this study.

Siamese Neural Network for User Authentication in Field-Programmable Gate Arrays (FPGAs) for Wearable Applications

“…While the CWT method involves substantial data and computation, the MODWT is a special form of DWT that maintains data size and enables straightforward calculation. In the hardware implementation, a finite impulse response (FIR) filter is utilized with digital logic [50]. By applying the MODWT method, time and frequency analysis are employed for classifying EMG signals, leading to high accuracy with fewer hardware resources.…”

“…By applying the MODWT method, time and frequency analysis are employed for classifying EMG signals, leading to high accuracy with fewer hardware resources. The algorithm for MODWT is based on a time series X with an arbitrary sample size N, where the jth level MODWT wavelet (W j *) and scaling (V j *) coefficients are computed [50].…”

“…HLS is a technique that automatically converts software code written in C/C++ into Verilog HDL, a language familiar to users. Writing large logic directly in Verilog HDL can be time-consuming, but HLS significantly reduces hardware development time and increases user convenience [50]. Additionally, HLS provides various #pragma-based methods for efficient hardware deployment, enabling hardware optimization.…”