1.Numpy >= 1.13.3
2.Sklearn >= 0.18.1
The five codes: demo-user1.ipynb,demo-user-4.ipynb,demo-user-13.ipynb,demo-user-14.ipynb,demo-user-15.ipynb are used to train the model for 5 users. The data for the 5 users are present in Data-1,Data-4,Data-13,Data-14,Data-15 The Data folders should be in the same folder as the script and no arguments are required. And we check accuracies for user authentication on the data of other users.
Extractor.py is used to retrieve features from raw data using algorithm from paper Gamboa, H. and Fred, A.L., 2003, April. An Identity Authentication System Based On Human Computer Interaction Behaviour. In PRIS (pp. 46-55)
In the results folder, we have supplied the pdf- version of the notebooks of the training and testing for all the users for easy visualization.
To run the script, launch jupyter notebook from terminal.