1 / 11

Refactoring a Keystroke Biometric System

Refactoring a Keystroke Biometric System. SeethaRam Janapala, Shiladitya Roy, Jackson John, Luca Columbu, Joseph Carrozza, Robert Zack, and Charles Tappert . Biometric Authentication System (BAS). Bio Feature Extractor. Biometric Authentication System (BAS). BAS Accuracy Calculator.

claudio
Télécharger la présentation

Refactoring a Keystroke Biometric System

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Refactoring a Keystroke Biometric System SeethaRam Janapala, Shiladitya Roy, Jackson John, Luca Columbu, Joseph Carrozza, Robert Zack, and Charles Tappert

  2. Biometric Authentication System (BAS)

  3. Bio Feature Extractor

  4. Biometric Authentication System (BAS)

  5. BAS Accuracy Calculator

  6. BAS Accuracy Calculator

  7. BAS Accuracy Calculator

  8. Refactoring Objectives • Fix errors and warnings in the code. • Remove deprecated elements and replace with supported ones. • Conform to coding standards. • Rewrite memory management components to support large data sets. • Improve system performance. • Enable applications to run standalone without an IDE.

  9. Completed Tasks • Modified code to efficiently use threads, collections, files, and buffering techniques to improve the system speed, manage the memory, and avoid OutOfMemory errors. • Now the system uses only 60MB-120MB memory and less CPU allowing the user to run the system in the background and continue his/her work.

  10. Completed Tasks • Preserve dichotomy data so subsequent runs did not need to re-dichotomize. • Changed BAS defaults to support odd valued NN’s. • Removed all unnecessary buttons to save dichotomy data as we are already storing the data by default.

  11. Completed Tasks • Parameterized the 'lowest N choices' for test results which can be used for larger nearest neighbor choice. • Converted Perl and Python scripts to Java. • Added error handling and improved logging. • Results saved in HTML format.

More Related