Human Activity Classification Using Deep Learning
Irfan Ayoub, Bhawna Sharma, Sheetal Gandotra, Manisha Manhas, Mehak Sharma, Umar Farooq · International Journal of Scientific Research in Computer Science Engineering and Information Technology · 2022
This paper describes a method to classify human activities using accelerometer data by training a deep learning model and using it in an android app which gathers real time accelerometer data while the device is with user and classifies his activity by assigning a probabilistic value with highest probability being the activity predicated. The dataset used in this paper is freely available which is provided by WISDM Lab and Google cloud-based instances running tensor flow library for python to code and train the model.