Publication

Abstract : Recent advances in low-cost wearable sensors with methodologies, have opened up a promising future for gait analysis. By providing patient analysis with gait disorders from clinics to common people the analysis requires some form of précised user input. The purpose of this study was to develop a computationally low-cost methodology that could evaluate the performance of different sensor configurations and to study the effect of locomotion mode for swing and stance using kinematic data from hip, knee and ankle extracted using mobile phone accelerometers. The method involved features translated as sum vectors and then using a simple neural network where gait data was normalized and classified the swing or stance. Sum-vector neural network-based method allowed a significantly higher test accuracy compared to the other machine learning algorithms. As an extended gait analysis model focusing predictive applications and implementations that need faster computations, the method could classify the gait kinetic and kinematics of human lower limb more optimally.