A standalone computing system to classify human foot movements using machine learning techniques for ankle-foot prosthesis control
Authors:
- 6 December 2021
- journal article
- research article
- Published by Taylor & Francis in Computer Methods in Biomechanics and Biomedical Engineering
- Vol. 25 (12) , 1370-1380
Abstract
This paper presents different machine learning techniques to classify the following foot movements: (i) dorsiflexion, (ii) plantarflexion, (iii) inversion, (iv) eversion, (v) medial rotation, and (vi) lateral rotation. The purpose is to design a real-time standalone computing system to predict the foot movements in the sagittal plane, useful for ankle-foot prosthesis control. Electromyography (EMG) and forcemyography (FMG) signals were acquired from the leg's tibialis anterior, medial gastrocnemius, lateral gastrocnemius, and peroneus longus muscles. First, Raspberry Pi was used to acquire EMG/FMG signals and to classify foot movements in real-time using different machine learning techniques. Later, an Arduino Nano 33 BLE controller was employed to implement the TinyML algorithm to classify these foot movements in the Arduino environment. The results showed that Raspberry Pi-based classification provided more than 99.5% accuracy for the EMG signals using LDA, LR, KNN, and SVC classifiers for offline prediction. However, for the classification of real-time signals, the performance of LDA is exceptionally well in predicting all classes. For Arduino Nano 33 BLE controller, the TinyML algorithm performed the classification task in real-time (8.5msec) without any misclassification. Further, the classification accuracy using EMG signal is much better than FMG based classification. Finally, the TinyML algorithm is applied on a transtibial amputee, and it is found that all three classes were classified correctly. Our finding suggests that a TinyML based Arduino Nano 33 BLE microcontroller is comparatively faster to predict and control, and it is smaller in size, thus advantageous for real-time prosthetic leg control applications.Keywords
This publication has 23 references indexed in Scilit:
- Feature extraction and classification for EMG signals using linear discriminant analysis2016
- Assessment of a Wearable Force- and Electromyography Device and Comparison of the Related Signals for MyocontrolFrontiers in Neurorobotics, 2016
- Ankle positions classification using force myography: An exploratory investigation2016
- Classification of ankle joint movements based on surface electromyography signals for rehabilitation robot applicationsMedical & Biological Engineering & Computing, 2016
- Activity classification in users of ankle foot orthosesGait & Posture, 2014
- Assessment of the activation modalities of gastrocnemius lateralis and tibialis anterior during gait: A statistical analysisJournal of Electromyography and Kinesiology, 2013
- Control of a Powered Ankle–Foot Prosthesis Based on a Neuromuscular ModelIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2010
- Exoskeletons and orthoses: classification, design challenges and future directionsJournal of NeuroEngineering and Rehabilitation, 2009
- Myoelectric control systems—A surveyBiomedical Signal Processing and Control, 2007
- Development of recommendations for SEMG sensors and sensor placement proceduresJournal of Electromyography and Kinesiology, 2000