Gait rehabilitation monitor

This paper presents a simple wearable, non-intrusive affordable mobile framework that allows remote patient monitoring during gait rehabilitation by doctors and physiotherapists. The system includes a set of 2 Shimmer3 9DoF Inertial Measurement Units (IMUs), an Android smartphone and a developed app for collecting, primary processing of data and for persistence of data in a remote PostgreSQL database, which is available in a remote server and where further data processing is performed. This framework provides gait features classifier by invoking an implemented REST API available in the remote server. Low computational load algorithms based on Euler angles and filtered signals were developed and used for the classification and identification of several gait disturbances. These algorithms include the alignment of IMUs sensors data by means of a common temporal reference as well as heel strike and stride detection algorithms. After segmentation of the remotely collected signals for gait strides identification relevant features were extracted to feed, train and test a classifier for prediction of gait abnormalities using supervised machine learning type and Extremely Randomized Trees method.