Composite Human Activity Recognition(HAR) with Python and Keras.

In this work deep learning is applied to recognize human activities such as (Walking, Standing, Working on computer,Standing Up Walking and Going updownstairs,Going UpDown Stairs,Walking and Talking with someone,Talking while Standing). The CNN model classifies the activities into composite, for activities that include more than one component activities and non-composite for those with one unique activity. We use a standard human activity recognition dataset to train and test the model. The dataset was sourced from the Machine Learning Repository, UCI (https://archive.ics.uci.edu/ml/datasets/Activity+Recognition+from+Single+Chest-Mounted+Accelerometer)