Abstract
Control of active prosthetic hands using surface electromyography (sEMG) signals is an active research area; despite the advances in sEMG pattern recognition and classification techniques, none of the commercially available prosthetic hands provide the user with an intuitive control. One of the major reasons for this disparity between academia and industry is the variation of sEMG signals in a dynamic environment as opposed to the controlled laboratory conditions. This research investigated the effects of sEMG signal variation on the performance of a hand motion classifier due to arm position variation and also explored the effect of static position and dynamic movement strategies for classifier training. A wearable system is used to measure the electrical activity of the muscles and the position of the forearm while performing six classes of hand motions. The system is made position aware (POS) using inertial measurement units (IMUs) for different arm movement gestures. The hand gestures are decoded under both static and dynamic forearm movements. Four time domain (TD) features are extracted from the sEMG signals along with IMU-based arm position information. The features are trained and tested using linear discriminant analysis (LDA) and support vector machine (SVM) for both TD and TD-POS features. The results for the SVM show a significant difference between the static and dynamic approaches, while the TD-POS features show enhanced classification performance in comparison to the TD-based classification. Results have shown the effectiveness of the dynamic training approach and sensor fusion techniques to improve the performance of existing stand-alone sEMG-based prosthetic control systems.
Highlights
The control of a dexterous upper limb using surface electromyography is an active research area since the 1960s
The left-most column of Figure 5B, which corresponds to the CY class, indicates that 94.6% of the test samples were correctly classified as CY, 1.3% were misclassified as LA, 0.4% as OP, 1.5% as PI, 0.1% as RE, and 2.2% as SP
The linear discriminant analysis (LDA) and support vector machine (SVM) classifiers trained with the combined time domain (TD) features and discrete position data showed average classification accuracies of 84.3 ± 3.0 and 97.5 ± 0.5%, respectively, averaged across all subjects and classes
Summary
The control of a dexterous upper limb using surface electromyography (sEMG) is an active research area since the 1960s. The researchers have focused on the intuitive control of a multi-degree of freedom (DOF) prosthetic hand. Despite the advancements in the detection of the activity and the processing of the sEMG signals, most available commercial prostheses still utilize a pair of electrodes to control a single or multiple DOF of the prostheses (Parker and Scott, 1986). EMG-IMU Based Multi-Forearm Movement Decoding pre-defined hand gestures by generating a pre-trained sequence of pulses (Farina and Aszmann, 2014). Such non-intuitive control is one of the major reasons for amputees to abstain from achieving a complete control of the prosthetic device (Engdahl et al, 2015; Chadwell et al, 2016). A number of techniques including fuzzy systems (Lam et al, 2002), neural networks (Soares et al, 2003), spiking neural networks (Behrenbeck et al, 2019), fuzzy support vector machines (SVMs) (Xie et al, 2015), hidden Markov models (Chiang et al, 2008), and principal component analysis (PCA) (Naik et al, 2016) have shown high accuracy for hand movement decoding
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
