A multiple layer fusion approach on keystroke dynamics

Pin Shen Teh, Andrew Beng Jin Teoh, Connie Tee, Thian Song Ong

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In this paper, we present a novel keystroke dynamic recognition system by means of a novel two-layer fusion approach. First, we extract four types of keystroke latency as the feature from our dataset. The keystroke latency will be transformed into similarity scores via Gaussian Probability Density Function (GPD). We also propose a new technique, known as Direction Similarity Measure (DSM), which measures the absolute difference between two sets of latency. Last, four fusion approaches coupled with six fusion rules are applied to improve the final result by combining the scores that are produced by GPD and DSM. Best result with equal error rate of 1.401% is obtained with our two-layer fusion approach.

Original languageEnglish
Pages (from-to)23-36
Number of pages14
JournalPattern Analysis and Applications
Volume14
Issue number1
DOIs
Publication statusPublished - 2011 Jan 1

Fingerprint

Fusion reactions
Probability density function

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Teh, Pin Shen ; Teoh, Andrew Beng Jin ; Tee, Connie ; Ong, Thian Song. / A multiple layer fusion approach on keystroke dynamics. In: Pattern Analysis and Applications. 2011 ; Vol. 14, No. 1. pp. 23-36.
@article{4654c924be7a44ad82bc39b7c8594777,
title = "A multiple layer fusion approach on keystroke dynamics",
abstract = "In this paper, we present a novel keystroke dynamic recognition system by means of a novel two-layer fusion approach. First, we extract four types of keystroke latency as the feature from our dataset. The keystroke latency will be transformed into similarity scores via Gaussian Probability Density Function (GPD). We also propose a new technique, known as Direction Similarity Measure (DSM), which measures the absolute difference between two sets of latency. Last, four fusion approaches coupled with six fusion rules are applied to improve the final result by combining the scores that are produced by GPD and DSM. Best result with equal error rate of 1.401{\%} is obtained with our two-layer fusion approach.",
author = "Teh, {Pin Shen} and Teoh, {Andrew Beng Jin} and Connie Tee and Ong, {Thian Song}",
year = "2011",
month = "1",
day = "1",
doi = "10.1007/s10044-009-0167-9",
language = "English",
volume = "14",
pages = "23--36",
journal = "Pattern Analysis and Applications",
issn = "1433-7541",
publisher = "Springer London",
number = "1",

}

A multiple layer fusion approach on keystroke dynamics. / Teh, Pin Shen; Teoh, Andrew Beng Jin; Tee, Connie; Ong, Thian Song.

In: Pattern Analysis and Applications, Vol. 14, No. 1, 01.01.2011, p. 23-36.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A multiple layer fusion approach on keystroke dynamics

AU - Teh, Pin Shen

AU - Teoh, Andrew Beng Jin

AU - Tee, Connie

AU - Ong, Thian Song

PY - 2011/1/1

Y1 - 2011/1/1

N2 - In this paper, we present a novel keystroke dynamic recognition system by means of a novel two-layer fusion approach. First, we extract four types of keystroke latency as the feature from our dataset. The keystroke latency will be transformed into similarity scores via Gaussian Probability Density Function (GPD). We also propose a new technique, known as Direction Similarity Measure (DSM), which measures the absolute difference between two sets of latency. Last, four fusion approaches coupled with six fusion rules are applied to improve the final result by combining the scores that are produced by GPD and DSM. Best result with equal error rate of 1.401% is obtained with our two-layer fusion approach.

AB - In this paper, we present a novel keystroke dynamic recognition system by means of a novel two-layer fusion approach. First, we extract four types of keystroke latency as the feature from our dataset. The keystroke latency will be transformed into similarity scores via Gaussian Probability Density Function (GPD). We also propose a new technique, known as Direction Similarity Measure (DSM), which measures the absolute difference between two sets of latency. Last, four fusion approaches coupled with six fusion rules are applied to improve the final result by combining the scores that are produced by GPD and DSM. Best result with equal error rate of 1.401% is obtained with our two-layer fusion approach.

UR - http://www.scopus.com/inward/record.url?scp=79251595640&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79251595640&partnerID=8YFLogxK

U2 - 10.1007/s10044-009-0167-9

DO - 10.1007/s10044-009-0167-9

M3 - Article

AN - SCOPUS:79251595640

VL - 14

SP - 23

EP - 36

JO - Pattern Analysis and Applications

JF - Pattern Analysis and Applications

SN - 1433-7541

IS - 1

ER -