Hybrid FOW—a novel whale optimized firefly feature selector for gait analysis

摘要: Human gait analysis is a well-defined technique for human identification and tracking at distance based on their walking style. It plays an important role in the video surveillance, medical, defense applications. A number of sensors such as MEMS accelerators, gyroscopes, pressure, position were deployed measuring different signals from body utilized behavior. To effectively reconcile these innovations medical profession, system required to identify most features which have impact accurate diagnosis classification. This study proposes novel method FOW intended choose best optimization strategy hybrid integration whale firefly algorithms. approach approximating performance classification benchmarks order efficient system. In fact, issue whole set terminated, it can be significantly pruned. Experimentation has been carried 35 individuals 16 recorded analyzed. Moreover, proposed methodology tested with learning algorithms integrating extreme machine produced nearly 98.5% accuracy also outperformed other existing selection methodologies accuracy, sensitivity, specificity platforms.