Interpretation of Gait Supervising Mechanism Using Sensor Integrated Makeshift and Analysing Pattern by K-Means Clustering Algorithm

Abstract

Human mobility or walking pattern(gait) is described as the interpreter movements of the rotatory body to achieve extensive range of locomotion. Gait analysis is foremost widely used technique for identifying abnormalities in the lower extremities and gait characteristics essentially support HAT (Head, Arm & Trunk). The act of walking is unconscious when there are no dysfunctions, but for ambulated the continuous monitoring is required. The existing clinical analysis method couldn’t achieve the daily walking routine within the confinement of a room.The proposed method focuses on developing an ambulatory system on daily routines by incorporating feasible techniques for achieving the gait pattern which is not confined to a room atmosphere where all possibilities of walking pattern can’t be reached.This system has expounded an ideology, to interpret the gait parameters using an insole type shoe integrated sensor system. Here, a wearable gait system which is incorporated with force resistive sensors, piezo sensors, inertial sensors and IR sensors are interfaced to the ESP 32. The corresponding sensors extract the data of kinematic angles, kinetics, foot pressure, step count and foot stride investigations.The system proved to be efficient in finding the phases and orientation of the individual by interpreting values from the device. Acquired data can be clustered together to find the abnormal and normal values by applying K-Means clustering algorithm, later the values are utilized in biomechanics for rectifying posture or movement related problems.The device will have several applications in sports, rehabilitation medicine and post-surgery treatment.