User Authentication Based on JPEG2000 Images

Carta, Massimiliano; Podda, Barbara; Perra, Cristian

doi:10.1007/11738695_27

Cited by 1 publication

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the use of evolutionary algorithms are almost non-present for this purpose. Some of the relevant work on user authentication system has been reported in [3], [9] and [8]. However only [10] has done some preliminary work using GA. To the best of our knowledge no previous study has used any of the genetic algorithms for user authentication on smart phones.…”

Section: Related Workmentioning

confidence: 99%

“…We set four objectives for our UGuard identification system: (1) correctly identify an imposter and the legitimate user, (2) user's identification within 8 calls, (3) if an imposter is detected, block the mobile phone to ensure information security, and (4) the system should be simple and efficient to facilitate its deployment on smart phones.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid GA-PSO fuzzy system for user identification on smart phones

Shahzad

Zahid

Farooq

2009

Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

The major contribution of this paper is a hybrid GA-PSO fuzzy user identification system, UGuard, for smart phones. Our system gets 3 phone usage features as input to identify a user or an imposter. We show that these phone usage features for different users are diffused; therefore, we justify the need of a front end fuzzy classifier for them. We further show that the fuzzy classifier must be optimized using a back end online dynamic optimizer. The dynamic optimizer is a hybrid of Particle Swarm Optimizer (PSO) and Genetic Algorithm (GA). We have collected phone usage data of 10 real users having Symbian smart phones for 8 days. We evaluate our UGuard system on this dataset. The results of our experiments show that UGuard provides on the average an error rate of 2% or less. We also compared our system with four classical classifiers -Naïve Bayes, Back Propagation Neural Networks, J48 Decision Tree, and Fuzzy System -and three evolutionary schemes -fuzzy system optimized by ACO, PSO, and GA. To the best of our knowledge, the current work is the first system that has achieved such a small error rate. Moreover, the system is simple and efficient; therefore, it can be deployed on real world smart phones.

show abstract