Touch-stroke dynamics authentication using temporal regression forest

Shih Yin Ooi, Andrew Beng Jin Teoh

Research output: Contribution to journalArticle

Abstract

Touch-stroke dynamics is a relatively recent behavioral biometrics. It authenticates an individual by observing his behavior when swiping a 'stroke' on a smartphone or tablet. Several studies have attempted to determine the optimum authentication accuracy of classifiers, but none of them has used time series or temporal machine learning techniques. We postulate that when a user performs a series of touch strokes in a continuous manner, it can be perceived as a temporal behavior characteristic of the person. In this letter, we propose the use of a temporal regression forest to unearth this hidden but vital temporal information. By incorporating this temporal information in the authentication process, the proposed model is able to achieve average equal error rates of ∼4.0% and ∼2.5% on the Serwadda dataset and Frank dataset, respectively.

Original languageEnglish
Article number8713391
Pages (from-to)1001-1005
Number of pages5
JournalIEEE Signal Processing Letters
Volume26
Issue number7
DOIs
Publication statusPublished - 2019 Jul

Fingerprint

Stroke
Authentication
Regression
Smartphones
Biometrics
Learning systems
Time series
Classifiers
Postulate
Error Rate
Machine Learning
Person
Classifier
Series
Model

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

@article{6f22c267682a4e608c45301e4e30bae7,
title = "Touch-stroke dynamics authentication using temporal regression forest",
abstract = "Touch-stroke dynamics is a relatively recent behavioral biometrics. It authenticates an individual by observing his behavior when swiping a 'stroke' on a smartphone or tablet. Several studies have attempted to determine the optimum authentication accuracy of classifiers, but none of them has used time series or temporal machine learning techniques. We postulate that when a user performs a series of touch strokes in a continuous manner, it can be perceived as a temporal behavior characteristic of the person. In this letter, we propose the use of a temporal regression forest to unearth this hidden but vital temporal information. By incorporating this temporal information in the authentication process, the proposed model is able to achieve average equal error rates of ∼4.0{\%} and ∼2.5{\%} on the Serwadda dataset and Frank dataset, respectively.",
author = "Ooi, {Shih Yin} and Teoh, {Andrew Beng Jin}",
year = "2019",
month = "7",
doi = "10.1109/LSP.2019.2916420",
language = "English",
volume = "26",
pages = "1001--1005",
journal = "IEEE Signal Processing Letters",
issn = "1070-9908",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "7",

}

Touch-stroke dynamics authentication using temporal regression forest. / Ooi, Shih Yin; Teoh, Andrew Beng Jin.

In: IEEE Signal Processing Letters, Vol. 26, No. 7, 8713391, 07.2019, p. 1001-1005.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Touch-stroke dynamics authentication using temporal regression forest

AU - Ooi, Shih Yin

AU - Teoh, Andrew Beng Jin

PY - 2019/7

Y1 - 2019/7

N2 - Touch-stroke dynamics is a relatively recent behavioral biometrics. It authenticates an individual by observing his behavior when swiping a 'stroke' on a smartphone or tablet. Several studies have attempted to determine the optimum authentication accuracy of classifiers, but none of them has used time series or temporal machine learning techniques. We postulate that when a user performs a series of touch strokes in a continuous manner, it can be perceived as a temporal behavior characteristic of the person. In this letter, we propose the use of a temporal regression forest to unearth this hidden but vital temporal information. By incorporating this temporal information in the authentication process, the proposed model is able to achieve average equal error rates of ∼4.0% and ∼2.5% on the Serwadda dataset and Frank dataset, respectively.

AB - Touch-stroke dynamics is a relatively recent behavioral biometrics. It authenticates an individual by observing his behavior when swiping a 'stroke' on a smartphone or tablet. Several studies have attempted to determine the optimum authentication accuracy of classifiers, but none of them has used time series or temporal machine learning techniques. We postulate that when a user performs a series of touch strokes in a continuous manner, it can be perceived as a temporal behavior characteristic of the person. In this letter, we propose the use of a temporal regression forest to unearth this hidden but vital temporal information. By incorporating this temporal information in the authentication process, the proposed model is able to achieve average equal error rates of ∼4.0% and ∼2.5% on the Serwadda dataset and Frank dataset, respectively.

UR - http://www.scopus.com/inward/record.url?scp=85066485307&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066485307&partnerID=8YFLogxK

U2 - 10.1109/LSP.2019.2916420

DO - 10.1109/LSP.2019.2916420

M3 - Article

AN - SCOPUS:85066485307

VL - 26

SP - 1001

EP - 1005

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

IS - 7

M1 - 8713391

ER -