Abstract
One control challenge in prosthetic legs is seamless transition from one gait mode to another. User intent recognition (UIR) is a high-level controller that tells a low-level controller to switch to the identified activity mode, depending on the user’s intent and environment. We propose a new framework to design an optimal UIR system with simultaneous maximum performance and minimum complexity for gait mode recognition. We use multi-objective optimization (MOO) to find an optimal feature subset that creates a trade-off between these two conflicting objectives. The main contribution of this paper is two-fold: (1) a new gradient-based multi-objective feature selection (GMOFS) method for optimal UIR design; and (2) the application of advanced evolutionary MOO methods for UIR. GMOFS is an embedded method that simultaneously performs feature selection and classification by incorporating an elastic net in multilayer perceptron neural network training. Experimental data are collected from six subjects, including three able-bodied subjects and three transfemoral amputees. We implement GMOFS and four variants of multi-objective biogeography-based optimization (MOBBO) for optimal feature subset selection, and we compare their performances using normalized hypervolume and relative coverage. GMOFS demonstrates competitive performance compared to the four MOBBO methods. We achieve a mean classification accuracy of and with the optimal selected subset for able-bodied and amputee subjects, respectively, while using only 23% of the available features. Results thus indicate the potential of advanced optimization methods to simultaneously achieve accurate, reliable, and compact UIR for locomotion mode detection of lower-limb amputees with prostheses.
Highlights
Prosthetic legs have significantly enhanced the lifestyle of individuals with a transfemoral amputation
We propose the application of multi-objective biogeography-based optimization (MOBBO) for feature selection of the user intent recognition (UIR) system
We investigate the influence of disjoint and overlapped windowing with different frame lengths on the classification accuracy of the UIR system
Summary
Prosthetic legs have significantly enhanced the lifestyle of individuals with a transfemoral amputation. Prostheses help lower-limb amputees regain their walking mobility for activities such as level walking, stair ascent and descent, incline walking, sitting and standing, etc. One active research area is the development of a functional control system for each walking task [1,2,3]. The main design objective is to enable amputees to achieve walking that is similar to that of able-bodied persons, while minimizing metabolic energy expenditure. Challenges include recognizing gait modes automatically, selecting the appropriate control system corresponding to the identified gait mode, and achieving a smooth transition in real time. Activity mode recognition must be achieved in parallel with control system development to address these problems. Activity mode recognition is referred to as high-level control, while control system design for each walking activity is referred to as low-level control [4]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
