Human_Activity_Recognition

A machine learning project to predict human activities in an android environment

Steps to Build

Download or clone the project and built with PyCharm

Android app can be built with android studio

• Input data text file is in the data folder
• Pickle saved files are in the checkpoint folder
• Report pdf file contains a complete tutorial

Note :

only need the data folder,checkpoint folder(empty) and the human_activity_recognition.py for a clean build

Used Technologies

• PyCharm (Community edition 2020.1)

• Android Studio

• Python 3.6

• Tensorflow 1.15.2

References

• http://www.cis.fordham.edu/wisdm/includes/files/sensorKDD-2010.pdf - Project based research paper

• http://www.cis.fordham.edu/wisdm/dataset.php - Dataset

• https://github.com/aqibsaeed/Human-Activity-Recognition-using-CNN/tree/master/ActivityRecognition - Android application feature extraction

• https://stackoverflow.com/questions/34343259/is-there-an-example-on-how-to-generate-protobuf-files-holding-trained-tensorflow - Tensorflow trained model freezing

• https://colah.github.io/posts/2015-08-Understanding-LSTMs/