Development of a Machine Learning Model for the Classification of Healthy and Diabetic Subjects using Electromyography Signal - read

Aug 5, 2026

Diabetes can lead to complications like Diabetic Peripheral Neuropathy (DPN), which impairs muscle and nerve function. Electromyography (EMG) is a standard diagnostic tool, yet its complex signals slow analysis and delay detection and treatment. This study develops and compares machine learning models to classify healthy versus diabetic subjects using EMG recorded during dorsiflexion. Time-domain features (RMS, MAV, SD, VAR) are extracted, and KNN, SVM, and ANN are optimized with PSO. ANN achieves the best accuracy at 94.44%.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Introduction

Diabetes and DPN impact

EMG signals and analysis challenges

Role of machine learning classification

Related Works

Characteristics and complexity of EMG signals

Development of a Machine Learning Model for the Classification of Healthy and Diabetic Subjects using Electromyography Signal Muhammad Fathi Yakan Zulkifli1, Noorhamizah Mohamed Nasir1*, Muhammad Amin Ab Ghani2, Andi Andriansyah3, Mohammad Suhaimi Selomah1, Tay Gaik Tay1, Danial Md Nor1 1Department of Electronic Engineering, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Malaysia. 2Faculty of Technical and Vocational Education, Universiti Tun Hussein Onn (UTHM) , Malaysia 3Electrical Engineering Department, Faculty of Engineering, Universitas Mercu Buana , Indonesia | Abstract
Diabetes can lead to complications like Diabetic Peripheral Neuropathy (DPN), which impacts muscle and nerve function. Electromyography (EMG) is a standard diagnostic tool for detecting DPN, but its complex signals make analysis time-consuming, delaying detection and treatment. This study aims to develop and compare machine learning models for classifying healthy and diabetic individuals using EMG data collected during dorsiflexion movement. The Muscle Sensor V3 recorded EMG signals, which were then transformed into time-domain features—Root Mean Square (RMS), Mean Absolute Value (MAV), Standard Deviation (SD), and Variance (VAR)—for classification purposes. Machine learning models, including K-Nearest Neighbour (KNN), Support Vector Machine (SVM), and Artificial Neural Network (ANN), were optimized using Particle Swarm Optimization (PSO). The analysis revealed that healthy individuals exhibited higher EMG amplitudes than those with diabetes. Among the models, ANN achieved the highest classification accuracy (94.44%) compared to SVM (88.89%) and KNN (77. 78%). These results demonstrate the effectiveness of ANN as a reliable classifier for distinguishing between healthy and diabetic individuals, offering a more efficient and accurate approach to EMG data analysis for potential clinical applications.
This is an open access article under the CC BY-SA license
| Keywords:
Artificial Neural Network (ANN); Diabetes;
Electromyography (EMG); K-Nearest Neighbour (KNN); Particle Swarm Optimisation (PSO);
Support Vector Machine (SVM);
Article History:
Received: November 5, 2024
Revised: December 16, 2024
Accepted: January 9, 2025
Published: September 2, 2025
Corresponding Author:
Noorhamizah Mohamed Nasir Department of Electronic Engineering, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia (UTHM) Email:
[hamizahn@uthm.edu.my](hamizahn@uthm.edu.my) | | --- | --- | | | | INTRODUCTION Diabetes is one of the most chronic diseases, and its prevalence grows yearly [1] . It leads to serious problems, such as Diabetic Peripheral Neuropathy (DPN), which affects as many as half of those who have diabetes [2] . DPN can damage nerves and blood vessels in the lower legs, resulting in plantar foot ulcers [3] . These ulcers, if infected, can progress and potentially spread to the bone or surrounding tissues, leading to severe complications. Furthermore, DPN can disrupt the essential dorsiflexion movement, which involves lifting the foot upward at the ankle joint during walking. This can lead to gait abnormalities and significantly increase the risk of falls and injuries [4] . Therefore, the early detection of DPNis crucial for individuals with diabetes to maintain a high quality of life. This can be achieved by adopting a healthy lifestyle, which includes eating a healthy diet and exercising regularly [5] . Electromyography (EMG) has emerged asthe industry standard for detecting nerve damage in muscles [6] . By measuring and recording the electrical activity of skeletal muscles, EMG provides valuable insights into muscle conditions, including strength and weakness [7] . However, analysis of EMG data can be complex and timeconsuming, especially when dealing with large and intricate datasets [8] . These factors cause delays in detecting and treat

FAQs

Why is early detection of diabetic peripheral neuropathy (DPN) important?

DPN can damage nerves and blood vessels in the lower legs, leading to foot ulcers and severe complications. It can also affect dorsiflexion during walking, increasing gait abnormalities and fall risk.

What EMG data and features are used for classification?

EMG signals are recorded during dorsiflexion movement using a Muscle Sensor V3. The signals are converted into time-domain features including RMS, MAV, SD, and VAR for model input.

Which machine learning model performs best, and what accuracy is achieved?

Among KNN, SVM, and ANN, the artificial neural network (ANN) achieves the highest classification accuracy of 94.44%, outperforming SVM (88.89%) and KNN (77.78%).

Aug 5, 2026

Upload by Genevieve