Support Vector Regression for Improved Real-Time, Simultaneous Myoelectric Control

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 22; no. 6; pp. 1198 - 1209
• Main Authors: Ameri, Ali, Kamavuako, Ernest N., Scheme, Erik J., Englehart, Kevin B., Parker, Philip A.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2014; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adult; Amputee; Artificial neural networks; Biofeedback, Psychology - methods; Computer Systems; Control systems; Data Interpretation, Statistical; electromyogram (EMG); Electromyography; Electromyography - methods; Female; Fitts' Law; Forearm; Humans; Kidnapping; Law; Learning theory; Male; Mathematical analysis; Middle Aged; Movement; Muscle Contraction; Muscle, Skeletal - physiopathology; Myoelectric control; Myoelectricity; Neural networks; Pattern Recognition, Automated - methods; Prosthetics; Real time; Real-time systems; Regression Analysis; Reproducibility of Results; Sensitivity and Specificity; simultaneous control; Support Vector Machine; Support vector machines; Target acquisition; Wrist; Young Adult
• ISSN: 1534-4320; 1558-0210; 1558-0210
• DOI: 10.1109/TNSRE.2014.2323576

This study describes the first application of a support vector machine (SVM) based scheme for real-time simultaneous and proportional myoelectric control of multiple degrees of freedom (DOFs). Three DOFs including wrist flexion-extension, abduction-adduction and forearm pronation-supination were investigated with 10 able-bodied subjects and two individuals with transradial limb deficiency (LD). A Fitts' law test involving real-time target acquisition tasks was conducted to compare the usability of the SVM-based control system to that of an artificial neural network (ANN) based method. Performance was assessed using the Fitts' law throughput value as well as additional metrics including completion rate, path efficiency and overshoot. The SVM-based approach outperformed the ANN-based system in every performance measure for able-bodied subjects. The SVM outperformed the ANN in path efficiency and throughput with the first LD subject and in throughput with the second LD subject. The superior performance of the SVM-based system appears to be due to its higher estimation accuracy of all DOFs during inactive and low amplitude segments (these periods were frequent during real-time control). Another advantage of the SVM-based method was that it substantially reduced the processing time for both training and real time control.