Abdelkader Benyettou

• Professor
• Research Director at Centre Universitaire de Relizane

Big Data allows analysing and assessing all human production types with its 5Vs, which are Volume, Velocity, Variety, Veracity and Value. Big Data is useful to improve decision-making to adjust it better to market demand, specifically selection of supplier that is an important link to optimize the logistic chain of enterprises. In this case, leader...

Neural network is one of the pattern classification techniques, which has been widely used in many fields application. The multilayer perceptron in a training process has an accuracy impact. The selection of features is another factor that influences classification accuracy. The objective of this research is to optimize simultaneously parameters an...

Recent decades have seen increasing utilization of optimization packages, based on Operations Research and Mathematical Programming techniques, for effective management of the provision of goods and services in distribution systems. Large numbers of real-world applications have widely shown that the use of computerized procedures for distribution p...

Appel pour améliorer la prise en charge des patients atteints d'Hypertension Artérielle Pulmonaire en Algérie

Image segmentation plays a crucial role in many image processing and understanding applications. Despite the huge number of proposed image segmentation techniques, accurate segmentation remains a significant challenge in image analysis. This article investigates the viability of using echo state network (ESN), a biologically inspired recurrent neur...

This paper proposes a novel optimization algorithm called the Multi-Objective Volleyball Premier League (MOVPL) algorithm for solving global optimization problems with multiple objective functions. The algorithm is inspired by the teams competing in a volleyball premier league. The strong point of this study lies in extending the multi-objective ve...

Face detection is considered to be one of the principal techniques of biometrics. Several methods for face detection have been proposed and described in the literature, but the Viola and Jones method is one of the most prominent. This method is based on the principle of Haar filters. In this study, we propose a new type of Haar filter called a disp...

The historical document is a treasure. The frequent use of these documents requires having a numeric copy. The use of these numeric documents requires developing techniques to facilitate their use. The search by content, the word spotting, and handwriting recognition became important points of research in document analysis. For this purpose, in thi...

Spiking neural networks (SNNs) fall into the third generation of artificial neural network models, increasing the level of realism in a neural simulation. In this paper, a spiking neural network is presented for detecting and tracking of a moving object in video sequences with a static camera. The motion estimation of the object is carried out by m...

In this paper, we present a competent approach for dorsal hand vein features extraction from near infrared images and PCA matching. Which is the anisotropic diffusion filter; we present first a review about this filter most used for the image enhancement. The physiological features characterize the dorsal venous network of the hand. These networks...

https://www.praiseworthyprize.org/jsm/index.php journal=irecap&page=article&op=view&path%5B%5D=21771

The knowledge acquired during the learning of artificial neural networks (ANNs) is coded as values in synaptic weights, which makes their interpretations difficult, hence the name of the black box. The aim of this work is to provide a comprehensible interpretation of the ANN's decisions by extracting symbolic rules. We improve the performance of ou...

Rule extraction from neural networks is an important task. In practice, decision makers often settle for using less accurate, but comprehensible models, typically decision trees where the solutions are given in graphical form easily interpretable. The black-box rule extraction techniques, operating directly on the input-output relationship, are cle...

Cardiac activity is one of the most important determinants of a patient's condition. It results in the appearance of several waves during the Electrocardiography (ECG). The analysis of the ECG signal and the identification of its parameters constitute an essential step for diagnosis. However, a set of methods and algorithms are developed in view of...

Statistical language models are an important module in many areas of successful applications such as speech recognition and machine translation. And n-gram models are basically the state-of-the-art. However, due to sparsity of data, the modelled language cannot be completely represented in the n-gram language model. In fact, if new words appear in...

In this paper a cross-validation algorithm for training probabilistic neural networks (PNNs) is presented in order to be applied to automatic face identification. Actually, standard PNNs perform pretty well for small and medium sized databases but they suffer from serious problems when it comes to using them with large databases like those encounte...

Nowadays information technology and communication has evolve, computer networks became vulnerable faced to new forms of threats. In this article, a new model of intrusion detection based on multi-agents system and inspired from the biological immune system is presented. We begin through a presentation of the biological immune systems, followed by i...

This paper concerns with the online recognition of isolated hand writing Arabic characters, through, the interpretation of a script presented by a pen trajectory. This technique was generally used in the electronic organizers of Personal Digital Assistant type. First of all, we have built a data base with several scripters using a graphic tablet wh...

Multi-label classification is becoming increasingly widespread as a data mining technique. Its objective is to categorize models in several non-exclusive groups, and is applied in such areas as news categorization, image labeling and music classification, among others. Our contribution is to use the paradigm of active learning with the topological...

The dorsal hand vein biometric system developed has a main objective and specific targets; to get an electronic signature using a secure signature device. In this paper, we present our signature device with its different aims; respectively: The extraction of the dorsal veins from the images that were acquired through an infrared device. For each id...

Le développement récent des PDA, l’aspect de nouveaux types de dispositifs tels que les tablettes électroniques et les stylos et l’apparition du logiciel d‟encre électronique, augmentent le besoin de ce type de système. Le travail se situe dans le domaine de la reconnaissance de caractères arabes isolés en ligne, et la motivation est d’étudier le m...

In this paper, we propose a spiking neural network model for edge detection in images. The proposed model is biologically inspired by the mechanisms employed by natural vision systems, more specifically by the biologically fulfilled function of simple cells of the human primary visual cortex that are selective for orientation. Several aspects are s...

We propose a novel supervised technique for blood vessel segmentation in retinal images based on echo state networks. Retinal vessel segmentation is widely used for numerous clinical purposes such as the detection of various cardiovascular and ophthalmologic diseases. A large number of retinal vessel segmentation methods have been reported, yet ach...

In this paper, we propose a mimetic approach for simultaneous weighting and feature selection based on a combination between an evolutionary algorithm and Support Vector Machines to improve web documents categorization. However, textual representation generates high dimensionality matrix, which processed with a mimetic approach, may increase drasti...

Support vector machine (SVM) is a popular classification technique with many diverse applications. Parameter determination and feature selection significantly influences the classification accuracy rate and the SVM model quality. This paper proposes two novel approaches based on: Microcanonical Annealing (MA-SVM) and Threshold Accepting (TA-SVM) to...

DNA microarray is a very active area of research in the molecular diagnosis of cancer. Microarray data are composed of many thousands of features and from tens to hundreds of instances, which make the analysis and diagnosis of cancer very complex. In this case, gene/feature selection becomes an elemental and essential task in data classification. I...

In this paper, the authors describe and propose an efficient and effective method of speaker-independent continuous Arabic speech recognition method, based on a phonetically rich speech corpus. This speech corpus contains two datasets: (1) the Spoken Arabic Digits (SAD), recorded by 66 speakers (33 male and 33 female), holds 6600 digit words in whi...

Handwriting is considered to be one of the commonly used biometric modality to identify persons in forensic application. In this paper, we propose a new and efficient approach for off-line text-independent writer identification. Indeed, complete section of connected ink race (Connected-Component or CC), delimited only by where the writer has lifted...

Hyperspectral image classification has been an active field of research in recent years. The high dimensionality of spectral bands and the small number of training pixels cause the Hugh phenomenon and reduce significantly the classification results quality. In this paper, we introduce a new framework for hyperspectral images classification. The pro...

Brain computer interface provides communication opportunity between the brain and the environment around a person with severe motor disabilities. However, the implementation of such interfaces requires a good signal processing scheme, whose performances depend principally on the technique used to select the best features, and the classification tec...

Latent structure in the signals transmitted through dispersive channels (real or complex) was exploited to formulate the maximum a posteriori probability (MAP) equalization in closed form, which allowed robust integer processing and some benchmark results. Emphasis is mostly on the adaptive implementation of the equalizer on unknown channels, with...

This article is a study of the emphasis in modern classical Arabic MSA through the phenomenon of the emphasis where it was first carried out a review regarding the following aspects: articulation, phonetic, acoustic and also by experimental studies. Then we synthesized articulatory studies to see if the decline in the back of the tongue toward the...

Image segmentation refers to the process of dividing an image into multiple regions which represent meaningful areas. Image segmentation is an essential step for most image analysis tasks such as object recognition and tracking, pattern recognition, content-based image retrieval, etc. In recent years, a large number of image segmentation algorithms...

This study investigates the efficiency of the one-layered Spiking Neural Network (SNN) on the enhancing of the breast cancer diagnostic results. The proposed network is based on Spike Response Model (SRM) with multiple delays per connection. Beside its simplicity, this model allows to modeling the production of a biologically realistic response to...

In this paper, we present an competent approach for dorsal hand vein features extraction from near infrared images. The physiological features characterize the dorsal venous network of the hand. These networks are single to each individual and can be used as a biometric system for person identification/authentication. An active near infrared method...

Computational grids have the potential for solving large-scale scientific problems using heterogeneous and geographically distributed resources. At this scale, computer resources and network failures are no more exceptions, but belong to the normal system behavior. Therefore, one of the most valuable characteristics of grid tools, apart from the pe...

The support vector machines were originally created to classify binary problems. Their extension for multiclass problems was the subject of several researches. Usually, a multiclass classifier is obtained by combining several binary classifiers. During the last years, the attention is focused on four main models of Multi-class Support Vector Machin...

The support vector machines (SVM) are a powerful approach which has been applied in many difficult applications. However, they are principally designed for binary classification problems, and usually their extension for multiclass problems involves only bi-class SVM. In this study, a recently developed machine named the quadratic loss multi-class S...

In this work, a hybrid classification system based local database categorization is proposed for breast cancer classification. The proposed approach aims to improve the classification rate of the Artificial Immune System (AIS) and reduce its computational time. The principle of the hybrid classifier based AIS consists in categorizing the cells sets...

The language models (LM) are an important module in many areas of natural language processing, in particular speech recognition and machine translation. In this experimental work, we present the most popular smoothing methods and their effects on statistical language modelling. We compare the behavior of twelve smoothing algorithms that have been d...

In this paper, a Multi Layer Perceptron (MLP) based Artificial Immune System (AIS) is presented for breast cancer classification. The proposed algorithm integrates clonal selection principle of AIS in MLP learning to reduce its computational costs and accelerate its convergence to a Mean Squared Error Threshold (MSEth) set by the user. Applied on t...

This paper concentrates on the use of Echo State Networks (ESNs), an effective form of reservoir computing, to improve microscopic cellular image segmentation. An ESN is a sparsely connected recurrent neural network in which most of the weights are fixed a priori to randomly chosen values. The only trainable weights are those of links connected to...

Spectral band selection has been a very active and important field of research in hyperspectral image classification. The hyperspectral images contain redundant measurements and irrelevant information which reduce significantly the classification accuracy rate. In this paper, we propose a new framework for band selection problem based on Binary Cuc...

CONFERENCE EPOSTER

La réalisation d'emplois du temps annuels est un problème très fréquent pour beaucoup d'institutions éducatives. La plupart du temps ils sont réalisés de façon manuelle impliquant la simple modification d'emplois du temps des années passées. Dû au nombre important d'étudiants qui ne cesse de croitre, le nombre limité de salles de cours, assouplir l...

In this work, a new training algorithm for probabilistic neural networks (PNN) is presented. The proposed algorithm addresses one of the major drawbacks of probabilistic neural networks, which is the size of the hidden layer in the network. By using a cross-validation training algorithm, the number of hidden neurons is shrunk to a smaller number co...

Data compression is taking an important part in computer research on applications like tele-video-conferencing, remote sensing, document and medical imaging, and facsimile transmission; while our stocking disk and our passing bands are limited. This field regroups two families: Lossy compression, with acceptable loss of information, and lossless co...

Artificial Immune Systems (AIS) are adaptive systems inspired by the biological immune system, they are able of learning, memorize and perform pattern recognition. This work presents enhancements of CLONALG algorithm, one of the most popular algorithms in the AIS field, which are applied on DDSM for breast cancer classification.

— In this paper, feature selection and parameters determination in SVM are cast as an energy minimization procedure. The problem of feature selection and parameters determination is a very difficult problem where the number of feature is very large and where the features are highly correlated. We define the problem of feature selection and paramete...

Breast cancer ranks first in the causes of cancer deaths among women around the world. Early detection and diagnosis are the key for breast cancer control, it can increase the success of treatment, save lives and reduce cost. Mammography is one of the most frequently used diagnosis tools to detect and classify abnormalities of the breast. In this a...

Congrès sous l’égide de la Société Française de Génie Biologique et Médical (SFGBM).

The identification by the multimodal biometric consists in combining several biometric systems; it permits to reduce certain limitations of the system based on only one modality for improving their performances significantly. In this article, a multimodal system of identification is implemented by combining information resulting from two biometric...

Fuzzy modeling require two main steps which are structure identification and parameter optimization, the first one determines the numbers of membership functions and fuzzy if-then rules, while the second identifies a feasible set of parameters under the given structure. However, the increase of input dimension, rule numbers will have an exponential...

With the development growing of network technology, computer networks became increasingly wide and opened. This evolution gave birth to new techniques allowing accessibility of networks and information systems with an aim of facilitating the transactions. Consequently, these techniques gave also birth to new forms of threats. In this article, we pr...

Breast cancer ranks first in the causes of cancer deaths among women around the world. Early detection and diagnosis is the key for breast cancer control, and it can increase the success of treatment, save lives and reduce cost. Mammography is one of the most frequently used diagnosis tools to detect and classify abnormalities of the breast. In thi...

Service-oriented computing offers efficient solutions for executing complex applications in an acceptable amount of time. These solutions provide important computing and storage resources, but they are too difficult for individual users to handle. In fact, Service-oriented architectures are usually sophisticated in terms of design, specifications,...

This paper presents the application of Adaptive Network Based Fuzzy Inference System ANFIS on speech recognition. The primary tasks of fuzzy modeling are structure identification and parameter optimization, the former determines the numbers of membership functions and fuzzy if-then rules while the latter identifies a feasible set of parameters unde...

The probabilistic neural network (PNN) is a special type of radial basis neural network used mainly for classification problems. Due to the size of the network after training, this type of network is usually used for problems with a small-sized training dataset. In this paper, a new training algorithm is presented for use with large training databa...

Actually, hand vein biometrics is a recent technology that offers system for identification /authentication, it ranks among the best biometric modality by the results developed. Just like any recognition system this has four steps: the acquisition, enhancement, feature extraction and classification. This paper present the enhancement's step of the...

Work is in on line Arabic character recognition and the principal motivation is to study the Arab manuscript with on line technology. This system is a Markovian system, which one can see as like a Dynamic Bayesian Network (DBN). One of the major interests of these systems resides in the complete models training (topology and parameters) starting fr...

This paper presents a new approach to authenticate individuals using hand vein images. The proposed method is fully automated and employs palm dorsal hand vein images acquired from a low-cost, near infrared contactless imaging; the aim of our work. In order to evaluate the system performance, a prototype was designed and a dataset of 34 persons fro...

Grid reliability analysis and modeling are not easy tasks because of the complexity and large scale of the system. For some grid services which have large subtasks requiring time-consuming computation, the reliability of grid service could be rather low. To resolve this problem, RNFR and LNFR are proposed in literature. This paper describes the pro...

Data compression is taking an important part in computer research on applications like tele-video- conferencing, remote sensing, document and medical imaging, and facsimile transmission; while our stocking disk and our passing bands are limited. This field regroups two families: Lossy compression, with acceptable loss of information, and lossless c...

Many pattern recognition and machine learning methods have been used in cancer diagnosis. The Artificial Immune System (AIS) is a novel computational intelligence technique. Designed by the principles of the natural immune system, it is able of learning, memorize and perform pattern recognition. The AIS’s are used in various domains as intrusion de...

In this article, we propose the use an algorithm of artificial ants inspired from chemical recognition system of ants in a biometric checking system by iris recognition, in order to make a success of the impostures tests and acceptances tests of the legitimate users. We presented our motivations which brought us to such a proposal, as we compared s...

Dans ce travail, un nouvel algorithme d’apprentissage pour les réseaux de neurones probabilistes (PNN) est présenté. L'algorithme proposé met l’accent sur l'un des principaux inconvénients des PNNs qui est la taille de sa couche cachée. Le nouvel algorithme permet de réduire significativement le nombre de neurones dans la couche cachée ce qui est t...

In the last decade, several techniques of artificial intelligence proved their skills in the field of classification of cancer cells. We propose in this article a new idea of learning of the artificial immune systems (AIS) in the aim of improving CLONALG, one of the most popular algorithms in the field of the AIS. The principle of IMPROVED-CLONALG...

Developments in Arabic information retrieval did not follow the increasing use of the Arabic Web during the last decade. Semantic indexing in a language with high inflectional morphology, such as Arabic, is not a trivial task and requires a text analysis in the original language. Excepting cross-language retrieval methods or limited studies, the ma...

Cancer diagnosis is one of the most studied problems in the medical domain. Several researchers have focused in order to improve performance and achieve to obtain satisfactory results. Breast cancer is one of cancer killer in the world. The diagnosis of this cancer is a big problem in cancer diagnosis researches. In artificial intelligent, machine...

Artificial neural networks have been well developed so far. First two generations of neural networks have had a lot of successful applications. Spiking Neuron Networks (SNNs) are often referred to as the third generation of neural networks which have potential to solve problems related to biological stimuli. They derive their strength and interest...

We present in this paper an interesting approach to enhance the performance of multi-classification using Genetic Algorithm. Two systems for an instance selection and feature selection are respectively introduced. We combined Genetic Algorithm with multiclass Support Vector Machines in order to reduce the learning set. The goal is to simplify the l...

de reconnaissance biométrique multimodal basé sur la fusion: empreinte digitale, visage, géométrie de la main Houalef sara, Bendahmane Abderrahmane, Benyettou Abdelkader Département d'informatique SIMPA LAB USTO MB ALGERIE sara. RÉSUMÉ. Dans cet article un système de reconnaissance biométrique basé sur l'empreinte digitale, le visage et la géométri...

Among the different types of neural networks, probabilistic networks represent a class of networks widely used in classification problems. In this paper, a new training algorithm for 2 C A R I 2 0 1 2 C A R I 2 0 1 2 probabilistic neural network (PNN) is presented. The proposed algorithm focuses on one of the main disadvantages of probabilistic neu...

Le cancer du sein est devenu une parmi les causes majeures de moralité chez la gent féminine, le diagnostic correct de ce type de cancer reste un problème important dans le domaine médical. Il a été prouvé, dans la littérature, que différentes techniques de reconnaissance des formes ont été utilisées pour remédier à ce type de problème. Ces techniq...

Work is in on line Arabic character recognition and the principal motivation is to study the Arab manuscript with on line technology. This system is a Markovien system which one can see as like a Dynamic Bayesian Network (DBN). One of the major interests of these systems resides in the complete models training (topology and parameters) starting fro...

The increasing requirements of today’s applications pushes developers to propose sophisticate computing solutions in terms of design notations, specification languages and deployment tools. Service-oriented computing is a good example of these efficient technologies, but it is unfortunately too difficult to handle by individual users. The aim of ou...

This work consists to give a comparative study between two proposed methods of an extracted road network and its nodes from satellite images of Algeria sites. The proposed methods are founded on the information theory and the mathematical morphology. A model of integration of obtained results in a geographical information system GIS will be present...

Significant progress has been made in information retrieval covering text semantic indexing and multilingual analysis. However, developments in Arabic information retrieval did not follow the extraordinary growth of Arabic usage in the Web during the ten last years. In the tasks relating to semantic analysis, it is preferable to directly deal with...

Artificial neural networks have been well developed so far. First two generations of neural networks have had a lot of successful applications. Spiking Neuron Networks (SNNs) are often referred to as the third generation of neural networks which have potential to solve problems related to biological stimuli. They derive their strength and interest...