Fuzzy-Genetic Model for the Identification of Falls Risk Gait

This paper investigates the effectiveness of a hybrid genetic and fuzzy set algorithm for the recognition of gait patterns in falls risk patients. In a previous work, we have shown the usefulness of fuzzy set techniques for gait pattern identification. In this paper, we apply a genetic algorithm in conjunction with fuzzy logic rules to better select the optimal combination of pathological gait features for improved gait diagnostic capability. Gait features were calculated using minimum foot clearance data collected during continuous walking on a treadmill for 20 older adults. The subjects are composed of two groups, 10 individuals with normal gait, and 10 with a history of falls. Fuzzy rules were extracted from the gait dataset using subtractive clustering. The genetic algorithm was introduced in order to select the optimum combination of gait features. Using cross validation test data, the results indicated that the generalization performance, in terms of accuracy, for the hybrid system was 97.5%, compared to89.3% that was obtained using only the fuzzy system. The generalization performance of the gait classifier was also analyzed by determining the areas under the receiver operating characteristic plot. We observed that an improved gait classification performance became evident when the fuzzy system classifier used a small number of features that were selected by the genetic algorithm.