A Fuzzy sequential locomotion mode recognition system for lower limb prosthesis control

Control of powered lower limb prostheses has a locomotion mode-dependent structure which demands a pattern recognizer that can classify the current locomotion mode and also detect transitions between them in an appropriate time. In order to achieve this goal, this paper presents a Fuzzy sequential locomotion mode recognition system to classify daily locomotion modes including level- walking, stair climbing, slope walking, standing and sitting using low-cost mechanical sensors. Since these signals have a quasi-periodic nature, using sequential pattern recognition tools, such as Hidden Markov Model(HMM) improves the recognition performance considering they use sequences of information to make a decision. On the other hand, simplicity of Fuzzy method, being a linguistic descriptor of patterns, makes training and classification procedures easier. Besides, the imprecise nature of Fuzzy modeling provides robustness to noisy signals from mechanical sensors which in turn, raises hopes to improving the recognition performance. The proposed Fuzzy sequential pattern recognizer models the daily locomotion modes with patterns consisting of some finite states and features of each state are described with a Fuzzy vector. Similar to HMMs, evaluation, assignment and training algorithms for such Fuzzy sequential tool are presented. Generating database for training the mentioned describing vectors and evaluating the performance of proposed system have been accomplished with the measured data from three IMUs and two FSRs mounted on the leg of four able-bodied subjects. Recognition performance has been evaluated for user-specific and user-independent classifications and the results have been compared with HMM. Overall accuracy of 95.8% for user-specific classification and 86.5% for user-independent classification has been achieved, which indicated higher recognition accuracy compared with HMM.