Development of a Human Motion Analysis System Based on Sensorized Insoles and Machine Learning Algorithms for Gait Evaluation

Human gait analysis can provide an excellent source for identifying and predicting pathologies injuries. In this respect, sensorized insoles also have a great potential extracting information. This, combined with mathematical techniques based on machine learning (ML), potentialize biomechanical analyses. The present study proposes proof-of-concept of system vertical ground reaction force (vGRF) acquisition insole that uses ML algorithm to identify different patterns vGRF extract characteristics help during clinical evaluation. acquired data from the was clustered by immunological (IA) gait. These clusters underwent mining process using classification regression tree (CART), where main each group were extracted, some rules created. As result, proposed able collect behavior After application IA CART algorithms, six groups found. these extracted verified capability gait, offering verification points focus