Time filter

Source Type

Dehache I.,Ecole Normale Superieure de Constantine | Souici-Meslati L.,Annaba University
Proceedings of 2012 International Conference on Complex Systems, ICCS 2012 | Year: 2012

Nowadays, biometrics is a research field in full expansion, several identification and verification systems are now developed, however their performances remain unsatisfactory facing to the growing security needs. Generally, the use of only one biometric decreases the reliability of these systems; thus, we have to combine several modalities. In this paper, we propose a multibiometric fusion approach for identity verification using two modalities: the fingerprints and the signature. Combinations of neural multi-layer perceptrons (MLP) are used for the unimodal classification. Our multimodal integration approach is based on the use of Support Vector Machines (SVM). The final identity verification decision is made according to the scores generated by the SVM classifier. The experimental results of the proposed multibiometric system are encouraging. © 2012 IEEE. Source

Hebboul A.,Ecole Normale Superieure de Constantine | Hachouf F.,University of Mentouri Constantine | Boulemnadjel A.,University of Mentouri Constantine
Neurocomputing | Year: 2015

In this paper, an Incremental Neural Network for Classification and Clustering (INNCC) is proposed. The main advantages of this neural network are the linkage between data topology preservation and classes representation by using the cluster posterior probabilities of classes. It is a constructive model without prior conditions such as a suitable number of nodes. A new neuron is inserted when new data are not represented by existing neurons. In training step, both supervised and unsupervised learning are used. The training dataset contains few samples with class labels and several unlabeled ones. The Support Vector Machines (SVM) operates in the training step to assess the INNCC classification result. The proposed approach has been tested on synthetic and real datasets. Obtained results are very promising. © 2015 Elsevier B.V. Source

Zhu X.,University of Tennessee at Knoxville | Zhu X.,University of Chinese Academy of Sciences | Boushaba M.,University of Mentouri Constantine | Reghioua M.,Ecole Normale Superieure de Constantine
IEEE Transactions on Reliability | Year: 2015

The Joint Reliability Importance (JRI) of two components evaluates the interaction effect between the components on system reliability. This paper focuses on the JRI of components in a consecutive-K-out-of-n :F system, and an m-consecutive-k- out-of-n:F system, both with Markov-dependent components. We derive the closed-form formulas of the JRI of two components using probability generating functions, and extend the results to the JRI of three and more components. We further provide exact conditional distributions of random variables which are used in probability generating functions for determining the JRI of two components. Our numerical examples and tests demonstrate the use of derived formulas, and provide further insights about the JRI for Markov-dependent components. © 2015 IEEE. Source

Boulemnadjel A.,University of Mentouri Constantine | Hachouf F.,University of Mentouri Constantine | Hebboul A.,Ecole Normale Superieure de Constantine | Djemal K.,University of Evry Val dEssonne
Engineering Applications of Artificial Intelligence | Year: 2015

In this paper a new soft subspace clustering algorithm is proposed. It is an iterative algorithm based on the minimization of a new objective function. The classification approach is developed by acting at three essential points. The first one is related to an initialization step; we suggest to use a multi-class support vector machine (SVM) for improving the initial classification parameters. The second point is based on the new objective function. It is formed by a separation term and compactness ones. The density of clusters is introduced in the last term to yield different cluster shapes. The third and the most important point consists in an active learning with SVM incorporated in the classification process. It allows a good estimation of the centers and the membership degrees and a speed convergence of the proposed algorithm. The developed approach has been tested to classify different synthetic datasets and real images databases. Several indices of performance have been used to demonstrate the superiority of the proposed method. Experimental results have corroborated the effectiveness of the proposed method in terms of good quality and optimized runtime. © 2015 Elsevier Ltd. Source

Bellour A.,Ecole Normale Superieure de Constantine | Bousselsal M.,Laboratoire Dedp Non Lineaires Et Hm Ecole Normale Superieure Of Kouba
Mathematical Methods in the Applied Sciences | Year: 2014

This paper is concerned with the numerical solution of delay integro-differential equations. The main purpose of this work is to provide a new numerical approach based on the use of continuous collocation Taylor polynomials for the numerical solution of delay integro-differential equations. It is shown that this method is convergent. Numerical illustrations confirm our theoretical analysis. Copyright © 2013 John Wiley & Sons, Ltd. Source

Discover hidden collaborations