Authors : Anju L.; Menaka D.; S. Kalyani

Volume/Issue : Volume 11 - 2026, Issue 5 - May

Google Scholar : https://tinyurl.com/mrxzxv2v

Scribd : https://tinyurl.com/y53885nf

DOI : https://doi.org/10.38124/ijisrt/26May2024

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The rising demand for assistive technologies to improve quality of life for individuals with mobility impairments has accelerated the development of innovative bio-signal-driven solutions. Existing systems often restrict user independence due to limited interface adaptability and latency in command execution. This paper presents a comprehensive Electromyography (EMG)-based control framework that captures, processes, and classifies muscle activity signals to enable real-time, hands-free automation of smart environments. The proposed system employs surface EMG sensors interfaced with an Arduino microcontroller for signal acquisition. A multi-stage signal processing pipeline—comprising amplification, low-pass filtering, Min-Max normalization, and windowed time-domain feature extraction (Root Mean Square, Mean Absolute Value, and Zero Crossing Rate)—prepares the signals for classification. A Random Forest classifier, optimized via GridSearchCV hyperparameter tuning with 5-fold cross-validation, is trained on a benchmark MYO Thalmic dataset encompassing 36 subjects and seven distinct hand gestures.

Keywords : EMG Signal Processing; Random Forest Classification; Assistive Technology; Smart Home Automation; Hand Gesture Recognition; Surface EMG; Real-Time Control.

References :

1. M. Nguyen, T. N. Gia, and T. Westerlund, "EMG-based IoT system using hand gestures for remote control applications," in Proc. IEEE 7th World Forum on Internet of Things (WF-IoT), 2021.
2. Fukuda, T. Tsuji, A. Ohtsuka, and M. Kaneko, "EMG-based human-robot interface for rehabilitation aid," in Proc. IEEE Int. Conf. Robotics and Automation (ICRA), 1998.
3. B. Hudgins, P. Parker, and R. N. Scott, "A new strategy for multifunction myoelectric control," IEEE Trans. Biomed. Eng., vol. 40, no. 1, pp. 82–94, Jan. 1993.
4. E. Scheme and K. Englehart, "Electromyogram pattern recognition for control of powered upper-limb prostheses: State of the art and challenges for clinical use," J. Rehabil. Res. Dev., vol. 48, no. 6, pp. 643–660, 2011.
5. D. Xiong, D. Zhang, X. Zhao, and Y. Zhao, "Deep learning for EMG-based human-machine interaction: A review," IEEE/CAA J. Autom. Sinica, vol. 8, no. 3, pp. 512–533, 2021.
6. L. Breiman, "Random forests," Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001.
7. Hiraiwa, N. Uchida, and K. Shimohara, "EMG/EEG pattern recognition by neural networks," in Proc. 11th Eur. Meeting Cybernetics and Systems Research, 1992, pp. 1383–1390.
8. M. Atzori et al., "Electromyography data for non-invasive naturally-controlled robotic hand prostheses," Scientific Data, vol. 1, Art. no. 140053, 2014.
9. C. Sapsanis et al., "Improving EMG-based hand gesture recognition with principal component analysis," in Proc. 35th Annu. Int. Conf. IEEE EMBS, 2013, pp. 5448–5451.
10. Phinyomark, P. Phukpattaranont, and C. Limsakul, "Feature reduction and selection for EMG signal classification," Expert Syst. Appl., vol. 39, no. 8, pp. 7420–7431, 2012.