Open Access

ARTICLE

Real Time Monitoring of Muscle Fatigue with IoT and Wearable Devices

by Anita Gehlot¹, Rajesh Singh¹, Sweety Siwach², Shaik Vaseem Akram¹, Khalid Alsubhi³, Aman Singh^4,*, Irene Delgado Noya^4,5, Sushabhan Choudhury²

1 School of Electronics & Electrical Engineering, Lovely Professional University, Punjab, 144411, India
2 Department of Electronics & Communication Engineering, University of Petroleum and Energy Studies, Dehradun, 248001, India
3 Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, 37848, Saudi Arabia
4 Higher Polytechnic School, Universidad Europea del Atlántico, C/Isabel Torres 21, 39011 Santander, Spain
5 Universidad Internacional Iberoamericana, Campeche, Mexico

* Corresponding Authors: Aman Singh. Email: ,

Computers, Materials & Continua 2022, 72(1), 999-1015. https://doi.org/10.32604/cmc.2022.023861

Received 24 September 2021; Accepted 27 December 2021; Issue published 24 February 2022

Abstract

Wearable monitoring devices are in demand in recent times for monitoring daily activities including exercise. Moreover, it is widely utilizing for preventing injuries of athletes during a practice session and in few cases, it leads to muscle fatigue. At present, emerging technology like the internet of things (IoT) and sensors is empowering to monitor and visualize the physical data from any remote location through internet connectivity. In this study, an IoT-enabled wearable device is proposing for monitoring and identifying the muscle fatigue condition using a surface electromyogram (sEMG) sensor. Normally, the EMG signal is utilized to display muscle activity. Arduino controller, Wi-Fi module, and EMG sensor are utilized in developing the wearable device. The Time-frequency domain spectrum technique is employed for classifying the three muscle fatigue conditions including mean RMS, mean frequency, etc. A real-time experiment is realized on six different individuals with developed wearable devices and the average RMS value assists to determine the average threshold of recorded data. The threshold level is analyzed by calculating the mean RMS value and concluded three fatigue conditions as >2 V: Extensive); 1–2 V: Moderate, and <1 V: relaxed. The warning alarm system was designed in LabVIEW with three color LEDs to indicate the different states of muscle fatigue. Moreover, the device is interfaced with the cloud through the internet provided with a Wi-Fi module embedded in wearable devices. The data available in the cloud server can be utilized for forecasting the frequency of an individual to muscle fatigue.

---

Keywords

---