Apparatus and method for classifying gait pattern based on multi modal sensor using deep learning ensemble

摘要

The present invention collects gait information using a sensor of a shoe insole and uses a combination of CNN (Convolutional Neural Network) and RNN (Recurrent Neural Network) to accurately identify gait patterns. Multimodal using a deep learning ensemble A device and method for sensor-based gait pattern classification, comprising: a data collection unit that collects gait data from a smart insole; defines a section of a unit step in information about gait, and adjusts the size of all unit steps to a standard length A data generator that generates a data set; Each is independently trained using the data set generated by the data generator, and applies an average ensemble model to provide one final prediction by performing CNN learning classification and RNN learning classification, respectively. A CNN learning classification unit and an RNN learning classification unit; a gait classification result output unit for determining and outputting the type of gait using the values output from the fully connected network through the CNN learning classification unit and the RNN learning classification unit;