Please use this identifier to cite or link to this item:
Title: Analysis of feature selection on the performance of multimodal keystroke dynamics biometric systems
Authors: Mendes, Brenda Vasiljevic Souza
Keywords: keyboard keystroke dynamics;touch keystroke dynamics;biometrics;feature selection;classification accuracy
Issue Date: 2017
Publisher: Universidade Federal do Rio Grande do Norte
Citation: MENDES, Brenda Vasiljevic Souza. Analysis of feature selection on the performance of multimodal keystroke dynamics biometric systems. 2017. 54 f. TCC (Graduação) - Curso de Engenharia de Software, Departamento de Informática e Matemática Aplicada, Universidade Federal do Rio Grande do Norte, Natal, 2017.
Portuguese Abstract: New security systems, methods or techniques need to have their performance evaluated in conditions that closely resemble a real-life situation. Moreover, biometric systems need a realistic set of biometrics data to test their accuracy when classifying individuals between legitimate users or impostors. The use of similar modalities may influence the use of the same features, however, there is no indication that basic biometrics will perform well using the same set of features. This report aims to be the first to investigate the impact of feature selection in two similar yet different biometric modalities: keyboard keystroke dynamics and touchscreen keystroke dynamics. We have found that an efficient feature selection method, chosen to suit the needs of the classification algorithm employed by the system, can multiply accuracy rates while diminishing the number of features to be processed to a small subset - which also improves the system’s processing time and overall usability.
Other Identifiers: 2012939440
Appears in Collections:Engenharia de Software

Files in This Item:
File Description SizeFormat 
FeatureSelection_Mendes_2017.pdfMonografia538,27 kBAdobe PDFThumbnail

This item is licensed under a Creative Commons License Creative Commons