Skip to content
Pattern recognition techniques (Anomaly Detection, Classification etc) to measure the performance (far, frr, eer) of the continuous authentication service.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Continuous Authentication Experiments

How to use

All the experiments are called from file.

Load data

Firstly, you must specify from where to load the datasets. You can either load them from database (which it automatically will be saved to a json file for later use) or you can load them from a local file

  • If you want to load them from mongodb: python db (ask me for mlab db credentials)
  • If you want to load them from local: python local

Functions Experiments

The experiments can be set inside the file, instructions of use are specified within each function

  • For pure visualization of data: visualize.my_scatter(...)

  • To experiment with pure classification: classification.experiment(...)

  • To experiment with classification OvO & Majority Vote: classification_maj_vote.experiment(...)

  • To experiment with pure anomaly/novelty detection: anomaly.experiment(...)

You can’t perform that action at this time.