A real time performance assessment of simultaneous pattern recognition control for multi-functional upper limb prostheses

Abstract

A natural and intuitive operation of multifunctional upper limb prostheses involves the concurrent activation of multiple degrees of freedom in a proportional way. Several approaches to simultaneous and proportional control strategies have been investigated; provided outcome measures however were offline accuracy or error rates and lacked the functional component of a preclinical assessment. This study evaluated a simultaneous proportional pattern recognition control strategy with two parallel classifiers in a two-dimensional Fitts' law style test and compared it to a sequential pattern recognition approach. The proposed test allowed for a complete evaluation through different performance metrics such as throughput (TP, bits/sec), path efficiency (PE, %), completion rate (%), overshoot (%) and reaction time (sec). We found that the simultaneous approach presented with numerous advantages with respect to the sequential alternative through significantly higher TP and PE for combined-motion targets (p<;0.001) and significantly less overshooting in both combined and discrete targets (p<;0.01). For discrete motions, the TP was significantly lower for the simultaneous approach (p<;0.001) but PE was similar. There was no difference in either completion rate or reaction time. These results support the potential of simultaneous pattern recognition for the control of multifunctional prostheses and underline the usefulness of a simple functional test in a preclinical framework.