Genetically optimized hybrid gait dynamics classifier

Variability in quantitative data arises from many potential sources including natural temporal dynamics of neuro motor control, pathologies of neurological or musculo skeletal system, aging effects, as well as variations in the external environment. Stride interval is one of the outputs of highly integrated and multilayered complex gait process. Stride interval fluctuates from one stride to another in a complex fashion. Analysis of variation of stride interval time series is called stride rate variability (SRV) analysis. Several linear and nonlinear techniques have been developed for SRV analysis. Recent studies in other areas of biomedical signal processing suggested that classification between physiological and pathological groups can be improved by combining different signal processing measures. In this paper, we have combined two SRV measures, threshold based acceleration change index (TACI) and symbolic entropy complexity measure normalized corrected Shannon entropy (NCSE) by using genetic algorithm (GA). It was found that combined classifier provide better classification