Categorization of functional impairments in human locomotion using the methods of the fusion of multiple sensors and computational intelligence

The main aim of this dissertation work was to develop an intelligent system to monitor, quantify and differentiate variances in human gait with high reliability and efficiency using the fusion of multiple sensor data and the methods of fuzzy inferential logic. Gait disorders are heterogeneous and produce disabilities that vary substantially from individual to individual. The recognition, quantification and analysis of gait dysfunction is complex and, requires the integration of large amounts of data across multiple domains (kinetic, kinematic and electromyographic). Current systems for gait analysis generally require space and complex imaging equipment, as well as prolonged processing time, rendering them unsuitable for real-time applications. Quantitative gait analysis has been used to elucidate characteristic features of neurological gait disturbances. Although a number of studies have compared single patient groups with controls, there are only a few studies comparing gait parameters between patients with different neurological disorders. This dissertation work is based on the hypothesis that functional rehabilitation can be most effectively achieved through the reduction of variances from normal patterns through training and other compensatory strategies, hence, efficient and reliable detection, quantification and differentiation of these variances is a critical link between diagnosis and optimal recovery. Current clinical methods of gait analysis are time and labor intensive and involve extensive posthoc data analysis. These limitations reduce access to gait analysis and exclude direct application of the patient’s gait data to rehabilitative interventions in real-time. The goal of the dissertation work was to develop a novel intelligent system to monitor, quantify and differentiate variances in human gait with high reliability and efficiency using the fusion of multiple sensor data and the methods of fuzzy inferential logic. Applications of this innovative technology will include improved recognition of complex patterns related to variable and combined pathophysiologic factors, and reliable quantitative monitoring of gait-related disability with recovery or therapeutic intervention over time