Authors

Mme Chafika Ramdane & Prof. Mohamed-Khireddine Kholladi

Titer

Improvements to the quantum evolutionary clustering

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university, Skikda university and El Oued university

Abstract

In previous work, a novel approach to data clustering based on quantum evolutionary algorithm has been proposed. In a comparison to other evolutionary clustering algorithms, the approach showed a high performance in terms of effectiveness and quality of found clusters. Although the approach is sound, it tends to be trapped in local minima, which slows the convergence. The approach is based on degrees of belonging having a fixed relationship with the distance between the data points and the clusters. The fixed relationship ignores completely the dataset distribution. In this paper, we modify the approach to improve its convergence. We also modify the function calculating the degrees of belonging by taking inspiration from possibilistic clustering. Comparison has been done with approaches based on degrees of belonging like fuzzy, possibilistic, hybrid fuzzy possibilistic clustering and other quantum evolutionary algorithm. Results on both real and synthetic datasets show that the modifications brought to the approach enable a more efficient exploration of the search space which improves the convergence speed and quality.

Key Words

Data clustering, Quantum evolutionary clustering, Convergence,Degree of belonging, Fuzzy clustering and Possibilistic clustering

Journal

IJDATS: International Journal of Data Analysis Techniques and Strategies

Publisher

Inderscience Publishers

ISSN

1755-8050 (Print) and 1755-8069 (Online)

Subject

Applied and computational mathematics, Business administration, Computing science, Applications and software, Electronic systems, Control and artificial intelligence, Operational management, and Marketing and services.

Issue

Volume 5, Number 2 / January 2013

Category

Decision Sciences and Decision Making

Pages

pp. 175-197

DOI

10.1504/IJDATS.2013.053680

Subject Group

Computer and Mathematics

Online Date

Monday, May 06, 2013

File

Authors

Mme Chafika Ramdane, Dr Souham Meshoul, Prof. Mohamed-Chaouki Batouche & Prof. Mohamed-Khireddine Kholladi

Titer

A quantum evolutionary algorithm for data clustering

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university, Skikda university and El Oued university

Abstract

The emerging field of quantum computing has recently created much interest in the computer science community due to the new concepts it suggests to store and process data. In this paper, we explore some of these concepts to cope with the data clustering problem. Data clustering is a key task for most fields like data mining and pattern recognition. It aims to discover cohesive groups in large datasets. In our work, we cast this problem as an optimization process and we describe a novel framework, which relies on a quantum representation to encode the search space and a quantum evolutionary search strategy to optimize a quality measure in quest of a good partitioning of the dataset. Results on both synthetic and real data are very promising and show the ability of the method to identify valid clusters and also its effectiveness comparing to other evolutionary algorithms.

Keywords

Data clustering, Evolutionary algorithms, Quantum computing, Quantum representation, Optimization, Data mining and Data set partitioning.

Journal

IJDMMM: International Journal of Data Mining, Modeling and Management

Publisher

Inderscience Publishers

ISSN

ISSN online: 1759-1171 and ISSN print: 1759-1163

Subject

Issue

Volume 2, Number 4/2010

Category

Data Mining, Modeling and Management

Pages

pp. 369-387

DOI

10.1504/IJDMMM.2010.035564

Subject Group

Online Date

File

Authors

Mme Baha Fergani, Miss Khadidja Laoubi & Prof. Mohamed-Khireddine Kholladi

Titer

A Discrete Particle Swarm Algorithm for Geometric Image Inpainting

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

Reconstructing image structure can be accomplished using a geometric image inpainting algorithm. This is done following three main steps: the first step consists of locating the damaged region. In the second step, the structure of the corrupted contours is reconstructed by matching each damaged contour with its corresponding one in a way to obtain a visually plausible image. In the third step, the found couples are joined using a curve fitting technique. The search space of candidate solutions dramatically increases as the number of contours increases, which makes the search of the optimal solution by a traditional deterministic method infeasible. A good choice to solve this problem is the use of meta heuristics is used. In this paper, a Discrete Particle Swarm Optimization (DPSO) is used to find the best correspondence between contours using their curvature values as a quality metric. Additional information is used, which is the mean ordinate of each contour. It adds spatial information of the location of damaged contours. The experimental results and comparisons with the genetic algorithm show the efficiency of the DPSO for geometric image inpainting.

Keywords

Image inpainting, Geometric inpainting, Damaged contours, Contour matching and Discrete PSO algorithm.

Journal

IJIEI:International Journal of Intelligent Engineering Informatics

Publisher

Inderscience Publishers

ISSN

ISSN online: 1758-8723 and ISSN print: 1758-8715

Subject

Intelligent Engineering Informatics

Issue

Category

Intelligent Engineering Informatics

Pages

6 pages

DOI

Subject Group

Intelligent Engineering Informatics

Online Date

File

Authors

Miss Zahia Brahimi, Prof. Mohamed-Khireddine Kholladi, Dr Hamid Bessalah, Miss Amina Tarabet & Miss Fadila Mostefai

Titer

An efficient technique for secure transmission of the region of interest in medical images

Laboratory

MISC Laboratory of Constantine

Universities

Ministère de la Poste et des Technologies de l'Information et de la Communication, Algiers, CDTA  Center of Algiers, Constantine 2 university and El Oued university

Abstract

In this paper, we propose three ROI (Region of Interest) selective encryption schemes to achieve secure access for medical images. The security in the region of interest is ensured by using inversion or/and permutation function as cryptographic tools. The three schemes are performed during compression. Only few selected MSBs (Most Significant Bit-Planes) of the ROI's codeblocks are concerned by the encryption. The first permutation scheme incurs a little loss on compression efficiency. The second scheme, inverts a set of important bit-planes of each ROI codeblock with no compression overhead. The third scheme combines the two schemes performing inversion and permutation of the selected ROI's MSBs. The size of encrypted bitstream is not changed. Moreover, the JPEG 2000 codestream resulting from the encryption process remains compliant with the JPEG 2000 format. Decryption is provided of course by our decoder which requires the same function to recover the original medical image.

Keywords

Cryptography, Encryption schemes, Secure transmission, JPEG 2000 compression, Selective encryption, Permutation, Inversion, Medical images, MSBs, Bitplanes, Transmission security and Region of interest.

Journal

IJSISE: International Journal of Signal and Imaging Systems Engineering

Publisher

Inderscience Publishers

ISSN

1748-0698 (Print)1748-0701 (Online)

Subject

Electronic Systems, Control and Artificial Intelligence and Systems Engineering

Issue

Volume 7, Number 2 / 2014

Category

Control and Artificial Intelligence and Systems Engineering

Pages

pp. 116-125

DOI

10.1504/IJSISE.2014.060062

Subject Group

Science, Engineering and Technology

Online Date

Monday, March 31, 2014

File

Authors

Mme Baha Fergani & Prof. Mohamed-Khireddine Kholladi

Titer

On the analysis of parameters' effect in PDE-based image inpainting

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

Image Inpainting is an important task in the field of image processing, with many applications in the fields of image and vision analysis. It aims at restoring damaged or missed regions in images in the case of undetectable forms. The basic idea in image inpainting, according to the Bertalmio’s approach, is to smoothly propagate information from the boundaries of the missed region toward the inside of the gap in the direction of isophotes. The purpose of this paper is to analyze the effects of different parameters in Bertalmio’s approach on the quality of the resulting inpainted image. The parameters dealt with in the paper are the rate of improvement, the number of iterations, the number of isotropic diffusion and the number of anisotropic diffusion.

Keywords

Image, Damaged image, Inpainting and Partial Differential Equation (PDE).

Journal

JATIT: Journal of Theoretical and Applied Information Technology

Publisher

Little Lion Scientific Islamabad Pakistan.

ISSN

ISSN:1992-8645 and E-ISSN: 1817-3195

Subject

Theoretical and Applied Information Technology

Issue

Volume 47, Number 3 / 2013

Category

Theoretical and Applied Information Technology

Pages

pp. 926-935

DOI

Subject Group

Information Technology

Online Date

31, January 2013

File

Authors

Dr Chaker Mezioud & Prof. Mohamed-Khireddine Kholladi

Titer

From π-Calcul towards a Dynamic architecture for the resolution of the problems of optimization for mobile telephony operators

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

The operators of the mobile telephony are more and more demanding towards their applications. They wait for a big reliability, for a number ceaselessly increasing of services, the respect for the constraints of conviviality, for cost, etc. Therefore, the size and the complexity of the applications increase. The current techniques do not allow protecting us from problems of conception. That is why we need a high-level modeling, which will allow us to analyze the organization between the various elements of the system and the interactions between these elements. The interest of the systems multi agents ensues from collective behavior produced by the interactions of several autonomous and flexible entities called agents, whom these interactions turn around the cooperation, around the competition or of it. However techniques come from this domain, concentrate more on the expression of the relations inter-agents. The expression of the mobility from the point of view of the distributed systems is not described. A property acquired time, will allow processes to choose themselves to move on the sites of a network to work locally on the resources and be exchanged their interactions. Reason for which, we are going to propose in this paper a formalization which appeals to an algebra of process, which is p-calcul, to conceive systems automobile adaptive which can react to the shape of the problem.

Keywords

GSM, Cellular Networks, Multi Agents Systems, Process Algebra and Dynamic Optimization.

Journal

IJCSI: International Journal of Computer Science

Publisher

ISSN

ISSN (Online): 1694-0814  and ISSN (Online version): 1694-0784

Subject

Computer Science

Issue

Vol. 9, Issue 2, No 1, March 2012

Category

Computer Science

Pages

pp. 335-341

DOI

Subject Group

Computer science research

Online Date

March 2012

File

Authors

Miss Imene Bensalem & Prof. Mohamed-Khireddine Kholladi

Titer

Toponym disambiguation by arborescent relationships

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

Problem Statement: The way of referring to a place in the geographical space can be formal, based on the spatial coordinates, or informal, which we use in natural language by using toponyms (place names). A toponym can represent several geographical places. This ambiguity made problematic its conversion towards a unique formal representation. Toponym disambiguation in text is the task of assigning a unique location to an ambiguous place name in a given textual context. Approach: Several toponym disambiguation heuristics assume a geographical proximity between the toponyms of the same context. This proximity can be in terms of spatial distance or in terms of arborsecent relationships, i.e., proximity in the hierarchical tree of the world places. This study presents a new toponym disambiguation heuristic in text based on the quantification of the arborescent proximity between toponyms. This quantification is done by a new measure of geographical correlation that we call the Geographical Density. Results: Our method was compared to the state of the art methods using GeoSemCor corpus and it has outperformed them in term of recall (87.4%) and coverage (99.0%). The results show that the toponyms of the same context are much closer in terms of arborescent relationships than in terms of spatial relationships. Conclusion: We believe that the quantification of arborescent relationships between toponyms of the same textual context is a good way to improve the recall of TD task. However, all the arborescent relationships’ types must be considered and not only the meronymy, which is the relation the most exploited in the existing TD methods.

Keywords

Word Net, Disambiguation,Resolution and Toponym

Journal

JCS: Journal of Computer Science

Publisher

Science Publications

ISSN

ISSN Print : 1549-3636 and ISSN Online: 1552-6607

Subject

Computer Science

Issue

Volume 6 Number 6/2010

Category

Computer Science

Pages

pp. 653-659

DOI

10.3844/jcssp.2010.653.659

Subject Group

Computer Science

Online Date

June 2010

File

Authors

Titer

Fractal Structure of the urban objects

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

With regards to the big agglomerations and especially the cities, the constructed surface has often got an irregular shape, in spite of the efforts of the urbanists to promote more compact shapes. The internal spatial order of the big agglomerations is a matter of the fractal geometry. This article shows the interest of applying the fractal geometry in cities and in networks of communication of the urban zones. Thus, we are going to focus our attention especially on the coarse analysis of the constructions’ shape structure which concern the occupation of the soil surfaces (the fractal of surface such as the carpets of Sierpinski), and to scale permitting the analysis of the agglomerations and cities such like the city of Constantine, Algeria.

Keywords

Geographical information system, Fractal geometry, Urban object and Urban analysis.

Journal

IAJIT: The International Arab Journal of Information Technology

Publisher

Zarqa university

ISSN

ISSN: 1683-5198

Subject

Information Technology

Issue

Volume 1 Number 2/2004

Category

Information Technology

Pages

pp. 164-170

DOI

Subject Group

CCIS: College of Computing and Information  Societies

Online Date

Received May 18, 2003; accepted September 9, 2003, printed July 2004

File

Authors

Miss Samiha Brahimi & Prof. Mohamed-Khireddine Kholladi

Titer

Adapted Extremal Optimization For Materialized Views Selection

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

With the development of databases in general and data warehouses in particular, it is now of a great importance to reduce the administration tasks of data warehouses. The materialization of views is one of the most important optimization techniques. The construction of a configuration of views optimizing the data warehouse is an NP-hard problem. On the other hand, the algorithm called extremal optimization is used to solve complex problems. In this paper, we propose a new adapted extremal optimization (AEO) for the materialized views selection problem.

Keywords

Materialized views selection, Data warehouses, Extremal optimization and Query’s optimization

Journal

IJCA: International Journal of Computer Applications

Publisher

Foundation of Computer Science, New York, USA.

ISSN

ISSN 0975– 8887 and ISBN 978-93-80749-31-2

Subject

Data ware housing, algorithms, and optimization.

Issue

Volume 34 - Number 5/2011

Category

Computer Science

Pages

pp. 30-33

DOI

10.5120/4100-5932

Subject Group

Computer Sciences

Online Date

November 2011

File

Authors

Dr Hacene Belhadef, Mme Aicha Eutamene & Prof. Mohamed-Khireddine Kholladi

Titer

Character Recognition Approach Based on Ontology

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

In this paper, we present a general description of a new character recognition process based on ontology, semantically annotated by a domain expert. Such process is based essentially on a matching step between two ontologies, the first represents a domain ontology, containing the typographical description of different characters represent an alphabet of a well definite language (Latin for example), the second ontology, describes the document in question in the form of concepts where each concept represents a grapheme located in a -defined order in the document. In this work we consider that there is a robust extraction module of primitives that will serve us to instantiate our ontology, by the different graphemes and their spatial relationships that exist in the processed document.

Keywords

Character recognition, Grapheme, Matching, Ontology, Semantic annotation andTypographical features.

Journal

IJDIWC: International Journal of Digital Information and Wireless Communications

Publisher

The Society of Digital Information and Wireless Communications

ISSN

ISSN 2068-1038 and ISBN 978-1-.4244-7335-9.03.

Subject

Digital Information and Wireless Communications

Issue

Volume 1, Number 2/2011

Category

Digital Information and Wireless Communications

Pages

pp. 629-638

DOI

Subject Group

Digital Information and Wireless Communications

Online Date

2011

File

Authors

Mme Aicha Eutamene, Prof. Mohamed Khireddine Kholladi & Dr Hacene Belhadef

Titer

Ontological model for character recognition based on spatial relations

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

In this paper, we present a set of spatial relations between concepts describing an ontological model for a new process of character recognition. Our main idea is based on the construction of the domain ontology modeling the Latin script. This ontology is composed by a set of concepts and a set of relations. The concepts represent the graphemes extracted by segmenting the manipulated document and the relations are of two types, is-a relations and spatial relations. In this paper we are interested by description of second type of relations and their implementation by java code

Keywords

Ontology, Grapheme, Character Recognition, Semantic Gap and Spatial Relations

Journal

SIPIJ: International Journal on Signal and Image Processing

Publisher

AIRCC Publishing Corporation

ISSN

ISSN: 0976-710X (Online) and ISSN : 2229-3922 (Print)

Subject

Signal and Image Processing

Issue

Volume4, Number.3/2013

Category

Signal and Image Processing

Pages

pp. 113-124

DOI

10.5121/sipij.2013.4310

Subject Group

Signal & Image Processing

Online Date

June 2013

File

Authors

Dr Khadoudja Ghanem, Dr Alice Caplier & Prof. Mohamed-Khireddine Kholladi

Titer

Contribution of facial transient features in facial expression analysis: classification & quantification

Laboratory

MISC Laboratory of Constantine and Gipsa Laboratory of Grenoble

Universities

Constantine 2 university, El Oued university and Grenoble

Abstract

The understanding of an image deals with the consideration of the most banal information conveyed by each pattern. A crucial anchor for facial expression analysis is to consider not only permanent features but transient ones too. In this work we are interested by all the outcomes of transient features in the analysis of facial expressions. Three processes based on transient features are proposed. The first process is proposed to classify a facial expression as one of the six universal expressions. The presence or absence of transient features on different facial regions is studied to associate each transient feature to a specific facial expression. The result is generally a doubt between two or more than two expressions. A post processing step is added to reduce doubt if exists between expressions. The second process is proposed to classify expressions into negative, positive or unknown classes. In this process, transient features are associated to negative or positive expressions. The angle formed by the naso labial furrows (if it exists) came to complete the classification of the considered expression in the two classes. Finally a process to quantify an expression with naso labial furrow comes to conclude the outcomes of transient features in facial expression analysis, where the angle formed by the naso labial furrow is calculated to deduce if the expression intensity is “High” or “medium”. Obtained results are given to prove the reliability of each process. 

Keywords

Facial expression, Facial Transient features, Expression Intensity, Quantification, Classification, Fusion data and Transferable belief model.

Journal

JATIT: Journal of Theoretical and Applied Information Technology

Publisher

Little Lion Scientific Islamabad Pakistan.

ISSN

ISSN 1992-8645 and E-ISSN 1817-3195

Subject

Theoretical and Applied Information Technology

Issue

Volume 15, Number 1/2010

Category

Theoretical and Applied Information Technology

Pages

pp. 69-78

DOI

Subject Group

Information Technology

Online Date

May 2010

File

Authors

Dr Chaker Mezioud & Prof. Mohamed-Khireddine Kholladi

Titer

Modeling and Optimization of Cellular Network: Towards an approach based on agent and ontology space

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

The current systems of communication know a considerable development thanks to the mobile communication and more particularly the cellular telephony. Reason for which the suppliers of service begin to find the big motivation, and make a commitment to have the means to be invested in enormous infrastructures of network. The conception of big cellular networks is a complex problem, which turns around a big impact: the quality of the service and the cost of the network. With the continuous and fast growth of the traffic of communication, the large-scale planning becomes harder and harder. The progress in this sector will lead certainly to the important improvements about the quality of service and the cost of deployment. The environment of the cellular networks is a fluctuating environment. The request in traffic varies in hour by hour and from a link to the other one. In this respect, solutions to problems of dynamic optimization are developed in a multi involving financial criteria (cost of network), technical criteria (insurance, availability) and the criteria for sale (quality of service). Problems with multi objectives, it becomes necessary to incorporate optimization methods in more general arrangements to develop more effective solutions, which can react to the shape of the problem. For these reasons we submit this article through a new approach based on multi-agent systems and spatial ontologies.

Keywords

GSM Network, Cellular Networks, Multi-Agents Systems, Geographic Information Systems, Spatial Ontologies,  Metrology and Dynamic Optimization.

Journal

IST Transactions of Control Engineering - Theory and Applications

Publisher

IST Press Transactions of Control Engineering (CETA)

ISSN

ISSN 1913-8784 and ISSN (CDROM) 1913-8792

Subject

Transactions of Control Engineering

Issue

Volume 1, Number 1/2010

Category

Transactions of Control Engineering

Pages

pp. 1-9

DOI

Subject Group

Transactions of Control Engineering

Online Date

January 23, 2010

File

Authors

Dr Abdelkrim Bouramoul, Prof. Mohamed-Khireddine Kholladi & Dr Bich-Lien Doan

Titer

PRESY: A Context Based Query Reformulation Tool for Information Retrieval on the Web

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university, El Oued university and SUPELEC France

Abstract

Problem statement: The huge number of information on the web as well as the growth of new inexperienced users creates new challenges for information retrieval. It has become increasingly difficult for these users to find relevant documents that satisfy their individual needs. Certainly the current search engines (such as Google, Bing and Yahoo) offer an efficient way to browse the web content. However, the result quality is highly based on uses queries which need to be more precise to find relevant documents. This task still complicated for the majority of inept users who cannot express their needs with significant words in the query. For that reason, we believe that a reformulation of the initial user’s query can be a good alternative to improve the information selectivity. This study proposed a novel approach and presents a prototype system called Profile-based Reformulation System (PRESY) for information retrieval on the web. Approach: It used an incremental approach to categorize users by constructing a contextual base. The latter was composed of two types of context (static and dynamic) obtained using the users’ profiles.  The architecture proposed was implemented using .Net environment to perform queries reformulating tests. Results: The experiments gave at the end of this article show that the precision of the returned content is effectively improved. The tests were performed with the most popular searching engine (i.e., Google, Bind and Yahoo) selected in particular for their high selectivity. Among the given results, we found that query reformulation improve the first three results by 10.7 and 11.7% of the next seven returned elements. So as we could see the reformulation of users’ initial queries improves the pertinence of returned content. Conclusion/Recommendations: Therefore, we believed that the exploitation of contextual data based on users’ profiles could be a very good way to reformulate user query. This complementary mechanism would be highly improve the quality of information retrieval on the web. In the other side, we believe that more the user’s profiles are properly constructed more the returned documents are relevant. Thus, the approach of constructing profiles needs to be deeply studied in order to have more representative elements. Additional data like historical searching and browsing activity of a user can be also combined to improve the query reformulation. This constitutes a part of our perspectives to improve PRESY.

Keywords

Information retrieval, Query reformulation, Dynamic context, Static context and User profiles

Journal

JCS: Journal of Computer Science

Publisher

Science Publications

ISSN

ISSN Print : 1549-3636 and ISSN Online: 1552-6607

Subject

Computer Science

Issue

Volume 6, Number 4/2010

Category

Computer Science

Pages

pp. 470-477

DOI

Subject Group

Computer Science

Online Date

2010

File

Authors

Mme Ouafek Naouel & Prof. Mohamed-Khireddine Kholladi

Titer

The Proposal of a New Image Inpainting Algorithm

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

In the domain of image inpainting or retouching, many recent works focus on combining methods of different fields of research in order to obtain more accurate results, and more original images. In this paper we propose a new algorithm that combines three different methods, each one represent a separate field. The first one for the use of artificial intelligence, the second one for the use of the partial differential equation (PDE) and the last one for the use of texture synthesis to reconstruct damages images.

Keywords

Inpainting, Retouching, Isophotes, Texture synthesis, PDE and Digital image.

Journal

IJCES: International Journal of Computer Engineering Sciences

Publisher

IAET: International Association for Engineering and Technology

ISSN

ISSN : 2231-6590

Subject

Computer Engineering & Information Technology

Issue

Volume2, Issue 1/2012

Category

Computer Engineering & Information Technology

Pages

pp. 10-16

DOI

10.7323/ijces

Subject Group

Computer Engineering & Information Technology

Online Date

August 2012

File

Authors

Dr Esma Bendiab & Prof. Mohamed-Khireddine Kholladi

Titer

The Negative Selection Algorithm: a Supervised Learning Approach for Skin Detection and Classification.

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

Artificial immune systems (AIS) are relatively new class of meta-heuristics that mimics aspects of the human immune system to solve computational problems. They consist of three typical intelligent computational algorithms termed clonale selection algorithm, immune network theory and negative selection algorithm. The negative selection algorithm is a supervised learning algorithm based population. It has been successfully applied to change and anomaly detection. As AIS emerged, classification has been become an important application area of AIS. Classification systems that are based on AIS have attractive features inherited form biological immune system. On the other hand, skin color detection is used as a preliminary step in numerous computer vision applications like: face detection, hand gesture detection, person identification and others. Two main issues of the skin detection are: the selection of the best skin features space and the skin pixel classification algorithm. This paper describes initial framework of pixels skin color classification approach based on the negative selection algorithm from AIS.  We present a skin classification, for detecting skin pixels and non skin pixels in color images, using both color and texture features space and  the negative selection algorithm as a classifier. The proposed approach is able to detect skin regions from images taken from different imaging conditions. The results are promising and suggest a new approach for adapting human skin color using negative selection algorithm.

Keywords

Artificial Immune System, Negative Selection Algorithm, Classification, Supervised Learning and Skin Detection.

Journal

IJCSNS: International Journal of Computer Science and Network Security

Publisher

Dr. Sang H. Lee

ISSN

ISSN 1738-7906

Subject

Computer Science and Network Security

Issue

Volume 10 Number11/2010

Category

Computer Science and Network Security

Pages

pp. 86-92

DOI

Subject Group

Computer Science and Network Security

Online Date

Manuscript received November 5, 2010 Manuscript revised November 20, 2010

File

Authors

Prof. Mohamed Chaouki Batouche, Dr Rachid Benlamri & Prof. Mohamed-Khireddine Kholladi

Titer

A Computer Vision System for Diagnosing Scoliosis using moiré images

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

For young people, scoliosis deformities are an evolving process which must be detected and treated as early as possible. The moiré technique is simple, inexpensive, not aggressive and especially convenient for detecting spinal deformations. Doctors make their diagnosis by analyzing the symmetry of fringes obtained by such techniques. In this paper, we present a computer vision system for help diagnosing spinal deformations using noisy moiré images of the human back. The approach adopted in this paper consists in extracting fringe contours from moiré images, then localizing some anatomical features (the spinal column, lumbar hollow and shoulder-blades) which are crucial for 3D surface generation that is carried out using Mota's relaxation operator. Finally, rules furnished by doctors are used to derive the kind of the spinal deformation and to yield the diagnosis. The proposed system has been tested on a set of noisy moiré  images, and the experimental results have shown its robustness and reliability for the recognition of most scoliosis deformities.

Keywords

Vision system, Scoliosis, Moiré images, 3D surface generation, Medical diagnosis, Discrete relaxation and Image segmentation.

Journal

Computers in Biology and Medicine an International Journal

Publisher

Pergamon Press, Arizona, USA

ISSN

Subject

Computers in Biology and Medicine

Issue

Category

Computers in Biology and Medicine

Pages

pp. 339-353

DOI

Subject Group

Biology and Medicine

Online Date

1996

File

Authors

Dr. Kamel Houari, Dr Youssef Chahir & Prof. Mohamed-Khireddine Kholladi

Titer

Spectral Clustering and Dimensionality Reduction Applied to Content Based Image Retrieval with Hybrid Descriptors

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

The topic of research exposed in this paper concerns Content Based image retrieval in a heterogeneous high database. The increase of storage capacities and the evolution of compression techniques have generated an explosion of the digital information quantity. Their computerization opens a vast field of applications. In this setting we are interested more especially in the problem of the dimensionality reduction and spectral clustering of a heterogeneous database of images in order to image retrieval by the content. Our new gait described in this paper consists to: in first phase the description of the database images by a hybrid descriptor which are Interest SIFT points combined with texture descriptor given by the application of Wavelet transform. The descriptor is multi- dimensional, robust and invariant to changes and scales. In second phase the representation of the database images as a convex graph. In third phase the reduction of the space of representation by the application of an unsupervised spectral classification (The Spectral training uses information contained in the eigenvectors of the normalized matrix of transition to detect structures in data.) That will provide us classes of images that has shortcoming the Eigen-values calculated on the matrix of symmetry. As last phase, we use the Nyström theory that will permit us, not to recalculate the all Eigen-values, but only the lasts one.

Keywords

Image retrieval, Sift, Clustering, Texture and Nyström.

Journal

International Review on Computers and Software - November 2009

Publisher

IRECOS - Praise Worthy Prize

ISSN

ISSN 1828-6003 and CD ISSN 1828-6011

Subject

Computers and Software

Issue

Volume 4, Number 6/November 2009

Category

Computers and Software

Pages

pp. 633-639

DOI

Subject Group

Computers and Software

Online Date

November 2009

File

Authors

Kamel Houari, Youssef Chahir, Prof. Mohamed-Khireddine Kholladi & Prof. Mohammed Benmohamed

Titer

SIFT Points for Matching Aerial Images in Reduced Space

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

This paper we propose a novel approach for matching cartographic images over detecting interest points invariant to scale and affine transformations. Our scale and affine invariant detectors are based on the following recent results: Interest points extracted with the SIFT detector which is adapted to affine transformations and give repeatable results (geometrically stable). This provides a set of distinctive points which are invariant to scale, rotation and translation as well as robust to illumination changes and limited changes of viewpoint. The characteristic scale determines a scale invariant region for each point. The characteristic scale and the affine shape of neighborhood determine an affine invariant region for each point. We apply an unsupervised classification to reduce the space of sets of interest points by using weighted bipartite graph matching in solving the point correspondence. Diffusion map: projection of the bipartite graph in a reduce space on which we apply K-means to classify the representatives clusters. The performance of our approach detector is also confirmed by excellent matching results.

Keywords

Points, Local Features, Scale Invariance, Affine Invariance, Matching and Recognition.

Journal

International Review on Computers and Software

Publisher

IRECOS - Praise Worthy Prize

ISSN

ISSN 1828-6003 and CD ISSN 1828-6011

Subject

Computers and Software

Issue

Volume 5, Number 1/January  2010

Category

Computers and Software

Pages

pp. 14-21

DOI

Subject Group

Computers and Software

Online Date

January  2010

File

Authors

Dr Esma Bendiab & Prof. Mohamed-Khireddine Kholladi

Titer

The Negative Selection Algorithm: a Supervised Learning Approach for Skin Detection and Classification.

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

In this paper, we propose a new approach of plant classification based on leaves recognition. The approach uses the dendritic cell algorithm, from the danger theory, as a classifier and the wavelet transform as a features space. The dendritic cell algorithm is a new immune inspired paradigm. It has demonstrates a potential proprieties as a classifier. As for the wavelet transform, it provides a powerful tool to capture localized and attractive features for texture classification. The experimental results about the data set leaf images show that the method is feasible and it gives an interesting recognition rate.

Keywords

Artificial Immune System (AIS), Danger Theory, Dendritic Cell Algorithm (DCA), Wavelet transform and Leaves recognition.

Journal

International Journal of Digital Information and Wireless Communication (IJDIWC)

Publisher

Published by the Society of Digital Information and Wireless Communication (SDIWC)

ISSN

ISSN 2068-1038, ISBN: 978-1-.4244-7335-9. 3.

Subject

Issue

Volume 1, Number 2

Category

Digital Information and Wireless Communications

Pages

pp. 317-325

DOI

Subject Group

Society of Digital Information and Wireless Communications

Online Date

File

Authors

Dr Chaker Mezioud & Prof. Mohamed-Khireddine Kholladi

Titer

Resolution of the problems of optimization for mobile phone operators: an approach based agents and ontologies space

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

The important success of the mobile systems of telecommunication motivates the suppliers of service to be reflected about enormous means of investments for infrastructures of network. The conception of big cellular networks is a complex problem, which turns around a big impact: the quality of the service and the cost of the network. With the continuous and fast growth of the traffic of communication, the large-scale planning becomes more and more difficult. This need is now more pointed with the evolution of phone networks (GSM), because of the biggest complexity of the system and the number of parameters which must be considered. In this subject, the solutions of the problems of dynamic optimization, Multi criteria associating the financial criteria (cost of the network), the technical criteria (insurance, availability) are developed in a context and the criteria of sale (quality of service). The interest of meta heuristics (methods of optimization) is based on their capacity to find the effective solutions in a reasonable time. But with objective multi-problems, the efficiency of meta heuristics can be compromised. Consequently, in this context it is necessary to integrate these methods into more general arrangements to develop more effective methods. For such reasons we are going to present an approach based on the Multi-Agents Systems (MAS) and the spatial ontologies, to conceive methods adaptive automobile which can react to the shape of the problem.

Keywords

GSM network, Cellular Networks, Multi-Agents Systems, Spatial Ontologies and Dynamic Optimization.

Journal

Journals of Complexity in Artificial and Natural System of Editura Universitatii “Petru Maior” targu Mures

Publisher

Editura Universitatii “Petru Maior” targu Mures

ISSN

ISBN: 978-973-7794-76-5.

Subject

Artificial and Natural System

Issue

2008

Category

Artificial and Natural System

Pages

pp. 76-81

DOI

Subject Group

Artificial and Natural System

Online Date

2008 Roumania

File

Authors

Dr Chaker Mezioud & Prof. Mohamed-Khireddine Kholladi

Titer

Research for Solving Optimization Problems of Planning and Allocation of Frequencies for Mobile Operators

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

The radio has been a large-scale development in recent years, with the advent of GSM (Global System for Mobile Communications) mobile phone. This growth is primarily due to the emergence of internationally accepted standards which facilitated the large-scale deployment, and also control technologies involving telecommunications, electronics and computers. Deploy these networks has been a great challenge for operators who have to master radio waves to completely new applications in relation to what was done since the beginning of the century. We went from broadcasting, personalized information and requirements for quality of service. On both issues, operators have made enormous progress in research on methods and planning tools that incorporate such models radio wave propagation, models for estimating quality of service and optimization algorithms on the setting.

Keywords

Mobile, Cellular networks, GSM, Ontologies, Optimization methods, Color graphs and Frequencies allocation

Journal

IJCST: International Journal of Computer Science and Telecommunications

Publisher

Scholarly Research Publishing

ISSN

ISSN 2047-3338

Subject

Computer Science and Telecommunications

Issue

Volume 3, Issue 5/2012

Category

Computer Science and Telecommunications

Pages

pp. 32-38

DOI

Subject Group

Computer Science and Telecommunications

Online Date

May 2012

File

Authors

Dr Chaker Mezioud & Prof. Mohamed-Khireddine Kholladi

Titer

Dynamic architecture for solving optimization problems of operators of mobile telephony

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

The operators of the mobile telephony are more and more demanding towards their applications. They wait for a big reliability, for a number ceaselessly increasing of services, the respect for the constraints of conviviality, for cost, etc. Therefore, the size and the complexity of the applications increase. The current techniques do not allow protecting us from problems of conception. That is why we need a high-level modeling, which will allow us to analyze the organization between the various elements of the system and the interactions between these elements. The interest of the systems multi agents ensues from collective behavior produced by the interactions of several autonomous and flexible entities called agents, whom these interactions turn around the cooperation, around the competition or of it. However techniques come from this domain, concentrate more on the expression of the relations inter-agents. The expression of the mobility from the point of view of the distributed systems is not described. A property acquired time, will allow processes to choose themselves to move on the sites of a network to work locally on the resources and be exchanged their interactions. Reason for which, we are going to propose in this paper a formalization which appeals to an algebra of process, which is π-calculus, to conceive systems automobile adaptive which can react to the shape of the problem.

Keywords

GSM, Cellular networks, Multi agents systems, Algebra of process and Dynamic optimization

Journal

IRECOS: International Review on Computers and Software

Publisher

IRECOS - Praise Worthy Prize

ISSN

ISSN: 1828-6003 and CD ISSN: 1828-6011

Subject

Computers and Software

Issue

Volume 2, Number 2/2009

Category

Computers and Software

Pages

4 Pages

DOI

Subject Group

Computers and Software

Online Date

June 2009

File

Authors

Dr Chaker Mezioud & Prof. Mohamed-Khireddine Kholladi

Titer

An Intelligent Agent for the Resolution of the Problems of Optimization for Mobile Phone Operators

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

The current systems of communication know a considerable development thanks to the mobile communication and more particularly the cellular telephony. Reason for which the suppliers of service begin to find the big motivation, and make a commitment to have the means to be invested in enormous infrastructures of network. The conception of big cellular networks is a complex problem, which turns around a big impact: the quality of the service and the cost of the network. With the continuous and fast growth of the traffic of communication, the large-scale planning becomes harder and harder. The progress in this sector will lead certainly to the important improvements about the quality of service and the cost of deployment. The environment of the cellular networks is a fluctuating environment. The request in traffic varies in hour by hour and from a link to the other one. The appeal to a process of design becomes indispensable, the objective of which is to supply networks capable of evolving and at a lower cost. The detailed and comprehensive analysis of the behavior of the traffic in the time and in the space is an indispensable process for the planning of the cellular network. In this subject, we propose the theme of the Multi Agents Systems as the foundation of our work, for purpose to propose an intelligent agent implanted at the level of every cell(zone of the territory lit by an antenna "BTS") and which serves to anticipate the modifications to be operated on the cellular network, to optimize the performances of the network during its evolution and to reduce the costs of its reorganization.

Keywords

GSM, Cellular networks, Multi agents systems, Dynamic optimization

Journal

IJCA: International Journal of Computer Applications

Publisher

Published by Foundation of Computer Science, Edited by Japan

ISSN

ISBN: 978-93-80749-31-2 and ISSN: 0975-8887

Subject

Computer Science

Issue

Volume 18, Number 1

Category

Computer Science

Pages

pp. 37-42

DOI

Subject Group

Computer Science

Online Date

March 2011

File

Authors

Dr Esma Bendiab & Prof. Mohamed-Khireddine Kholladi

Titer

Recognition of Plant Leaves Using the Dendritic Cell Algorithm

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

In this paper, we propose a new approach of plant classification based on leaves recognition. The approach uses the dendritic cell algorithm, from the danger theory, as a classifier and the wavelet transform as a features space. The dendritic cell algorithm is a new immune inspired paradigm. It has demonstrates a potential proprieties as a classifier. As for the wavelet transform, it provides a powerful tool to capture localized and attractive features for texture classification. The experimental results about the data set leaf images show that the method is feasible and it gives an interesting recognition rate

Keywords

Artificial immune system (AIS), Danger theory, Dendritic cell algorithm (DCA), Wavelet transform and Leaves recognition.

Journal

IJDIWC: International Journal of Digital Information and Wireless Communications

Publisher

The Society of Digital Information and Wireless Communications

ISSN

ISSN 2225-658X

Subject

Digital Information and Wireless Communications

Issue

Volume 1, Number 1/2011

Category

Digital Information and Wireless Communications

Pages

pp. 284-292

DOI

Subject Group

The Society of Digital Information and Wireless Communications

Online Date

2011

File

Authors

Dr Abdelkrim Bouramoul, Prof. Mohamed-Khireddine Kholladi & Dr Bich-Lien Doan

Titer

Using context to improve the evaluation of information retrieval systems

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university, El Oued university and SUPELEC France

Abstract

The crucial role of the evaluation in the development of the information retrieval tools is useful evidence to improve the performance of these tools and the quality of results that they return. However, the classic evaluation approaches have limitations and shortcomings especially regarding to the user consideration, the measure of the adequacy between the query and the returned documents and the consideration of characteristics, specifications and behaviors of the search tool. Therefore, we believe that the exploitation of contextual elements could be a very good way to evaluate the search tools. So, this paper presents a new approach that takes into account the context during the evaluation process at three complementary levels. The experiments gives at the end of this article has shown the applicability of the proposed approach to real research tools. The tests were performed with the most popular searching engine (i.e. Google, Bing and Yahoo) selected in particular for their high selectivity. The obtained results revealed that the ability of these engines to rejecting dead links, redundant results and parasites pages depends strongly to how queries are formulated, and to the political of sites offering this information to present their content. The relevance evaluation of results provided by these engines, using the user's judgments, then using an automatic manner to take into account the query context has also shown a general decline in the perceived relevance according to the number of the considered results.

Keywords

Contextual evaluation, Evaluation campaigns, Relevance judgments, Information retrieval and Web search engine.

Journal

IJDMS: International Journal of Database Management Systems

Publisher

AIRCC-US

ISSN

ISSN 0975-5705 (On line) and 0975-5985 (Print) and ISBN 978-93-80749-31-2

Subject

Database Management Systems

Issue

Volume 3, Number.2/2011

Category

Database Management Systems

Pages

pp. 22-39

DOI

10.5121/ijdms.2011.3202

Subject Group

Computer Science

Online Date

May 2011

File

Authors

Miss Zahia Brahimi, Dr Hamid Bessalah, Miss Amina Tarabet & Prof. Mohamed-Khireddine Kholladi

Titer

Selective Encryption Techniques of JPEG2000 Code stream  for Medical Images Transmission

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

In this paper, novel selective encryption image schemes based on JPEG2000 are proposed. The first one encrypts only the code-blocks corresponding to some sensitive precincts. In order to improve the security level we introduce the permutation of code blocks contributing in the selected precincts.  The idea of combining permutation and selective encryption is used in order to minimize the amount of processed data encryption while ensuring the best possible degradation through the permutation. Many of proposals format compliant encryption schemes for JPEG2000 that have been made encrypt packet body data, but leave header packet in plaintext. The second approach, combines code-blocks data encryption to a cyclic permutation of all packets headers in the bit stream. Actually, in the JPEG2000 code stream, packet header information is specific to the visual content, and it is can be used as a fingerprint of the code stream.  Symmetric encryption AES with CFB mode is used to encrypt in the two schemes. The proposed schemes don’t introduce superfluous JPEG2000 markers in the protected code stream, i.e, its format is compliant to JPEG2000 code stream one. It keeps file format and compression ratio unchanged and doesn’t degrade the original error robustness. The proposed scheme works with any standard ciphers and introduces negligible computational cost.

Keywords

Communication system security, JPEG2000 Compression, Selective Encryption, Permutation, Medical images and Computer applications.

Journal

WSEAS TRANSACTIONS on CIRCUITS AND SYSTEMS

Publisher

WSEAS Transactions

ISSN

ISSN: 1109-2734

Subject

CIRCUITS AND SYSTEMS

Issue

Issue 7, Volume 7, July 2008

Category

Circuits and Systems

Pages

pp. 718-727

DOI

Subject Group

Circuits and Systems

Online Date

Manuscript received Feb 24, 2008; revised June 20, 2008

File

Authors

Prof. Djamel Fadel, Mme A. Laïfa, R. Djamaï & Prof. Mohamed-Khireddine Kholladi

Titer

Metrological data of some air pollutants in a town in north-eastern Algeria for use in epidemiological studies: case of respiratory

Laboratory

Laboratoire de Biologie Végétale et Environnement of Annaba and MISC Laboratory of Constantine

Universities

Annaba  university and El Oued university

Abstract

The public-health problem is environmental concern in our country. The awareness of the health authorities began to be felt by the management of this problem by encouraging epidemiological studies to determine the correlation between pollution levels and disease because of high concentrations of certain pollutants can be harmful. In this aim we have collected data measurement of air pollutants in the region of El Bouni from a monitoring network. Only those pollutants known for their toxicological effects on the respiratory system of humans were measured.

Keywords

Air pollution, Gaseous pollutants, Particulate matter, Toxicology, El Bouni and Algeria

Journal

PCN : Phys. Chem. News Journal

Publisher

Best Edition

ISSN

ISSN 1114-3800

Subject

Physics and Chemistry

Issue

Volume 36/2010

Category

Physics and Chemistry

Pages

pp. 135-140

DOI

Subject Group

Physics and Chemistry

Online Date

November 2010

File

Authors

Dr Hacene Belhadef & Prof. Mohamed-Khireddine Kholladi

Titer

Urban Ontology-Based Geographical Information System

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

The main objective aimed by this paper, is the construction of an urban ontology for a publicity panels management system implanted along roads and public way. This paper shows how the GIS domain can take advantage of new ontologies-based approaches of modeling and conceptualization. The Roads department of Constantine city (Algeria country) in which we were interested in our case study, gave us a clear idea on the problems concerning the decision making to critical situations as the accidents, the optimization of the road traffic, management of publicity panels and all underlying problems; the orientation and the good organization of the road also make a primordial preoccupation of this service. Our objective in this paper is, to assure a best use of the geographical information, by the good representation and interpretation of this information what also implies the understanding and the good decision making. The Department of Roads city of Constantine, uses an information system based on a classical conceptual model E / R (Entity Relationship) and a relational database, but the new system we have developed is based on a ontology obtained in two different ways the first is the manual application of the methodology of ontologies development, called METHONTOLOGY, and the second automatically uses the mapping  rules  between the model E/R and ontology, but in both cases the user has the impression that works in a classical system, by  against behind the interface There are only ontologies, this is the transparency that is ensured by our system to move (migrate) from one system to the an other without disturbing the users.

Keywords

GIS, Methontology, Mapping rules, Migration, Public roads network and Urban ontology.

Journal

JATIT: Journal of Theoretical and Applied Information Technology

Publisher

Little Lion Scientific Islamabad Pakistan.

ISSN

ISSN 1992-8645 and E-ISSN 1817-3195

Subject

Theoretical and Applied Information Technology

Issue

Volume 9, Number 2/2009

Category

Theoretical and Applied Information Technology

Pages

pp. 139-154

DOI

Subject Group

Information Technology

Online Date

2009

File

Authors

Dr Chaker Mezioud & Prof. Mohamed-Khireddine Kholladi

Titer

A new approach for the resolution of the problems of optimization for mobile telephony operators

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

The important success of the mobile systems of telecommunication motivates the suppliers of service to be reflected about enormous means of investments for infrastructures of network. The conception of big cellular networks is a complex problem, which turns around a big impact: the quality of the service and the cost of the network. With the continuous and fast growth of the traffic of communication, the large-scale planning becomes more and more difficult. This need is now more pointed with the evolution of phone networks (GSM), because of the biggest complexity of the system and the number of parameters which must be considered. In this subject, the solutions of the problems of dynamic optimization, Multi criteria associating the financial criteria (cost of the network), the technical criteria (insurance, availability) are developed in a context and the criteria of sale (quality of service). The interest of meta-heuristics (methods of optimization) is based on their capacity to find the effective solutions in a reasonable time. But with objective multi-problems, the efficiency of meta-heuristics can be compromised. Consequently, in this context it is necessary to integrate these methods into more general arrangements to develop more effective methods. For such reasons we are going to present an approach based on the multi-systems agents and the spatial ontologies, to conceive methods adaptive automobile which can react to the shape of the problem.

Keywords

GSM network, Cellular networks, Multi-agents systems, Spatial ontologies and Dynamic optimization.

Journal

JATIT: Journal of Theoretical and Applied Information Technology

Publisher

Little Lion Scientific Islamabad Pakistan.

ISSN

ISSN 1992-8645 and E-ISSN 1817-3195

Subject

Theoretical and Applied Information Technology

Issue

Volume 5, Number 3/2009

Category

Theoretical and Applied Information Technology

Pages

pp. 307-314

DOI

Subject Group

Information Technology

Online Date

2009

File

Authors

Dr Hacene Belhadef, Prof. Mohamed Khireddine Kholladi & Mme Aicha Eutamene

Titer

Ontology of graphemes for latin character recognition

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

In this paper, we present a general description of an ontology, describing the different character of Latin language, which is semantically annotated by a domain expert. This ontology represents the typographical description of the analyzed and processed document, by a set of concepts where each concept, represents a grapheme of character and must be designated by a unique number denoting its position or its localization in the document. The relationship between, two graphemes is of spatial type; it represents the connectivity between graphemes in the document to facilitate the recognizing process of characters. Our ontology is generic and can support other languages by enriching it by new specific spatial relationships.

Keywords

Character recognition, Grapheme, Ontology, Spatial relationship and Typographical features

Journal

International conference on advances in Engineering (ICAE’2011), will be published in international journal “Procedia Engineering”

Publisher

Sorpus and Ei Compendex, by Elsevier, 2011

ISSN

ISSN: 1877-7058

Subject

Computer science

Issue

Volume 24, Number 1/2011

Category

Computer science

Pages

pp. 589-584

DOI

10.1016/j.proeng.2011.11.2699

Subject Group

Computer science

Online Date

December 2011.

File

Authors

Prof. Djamel Fadel, A. Laifa, R. Djamai & Prof. Mohamed Khireddine Kholladi

Titer

Données métrologiques de certains polluants atmosphériques d’une ville du nord-est algérien en vue de leur utilisation dans les études épidémiologiques : cas des pathologies respiratoires

Laboratory

Annaba University and El Oued university

Universities

Constantine 2 university and El Oued university

Abstract

La problématique santé publique-environnement devient préoccupante dans notre pays. La prise de conscience des autorités sanitaires commence à se faire sentir par la prise en charge de cette problématique en encourageant des études épidémiologiques afin de déterminer la corrélation entre les niveaux de pollution et les maladies car des concentrations élevées de certains polluants peuvent être nocives. C'est dans cet objectif que nous avons recueilli des données métrologiques des polluants atmosphérique dans la région d'El Bouni à partir d'un réseau de surveillance. Seulement les polluants connus pour leur effet toxicologique sur l'appareil respiratoire de l'homme ont été mesuré.

Keywords

Pollution atmosphérique, Polluants gazeux, Particules en suspension, Toxicologie and El Bouni Algérie

Journal

Journal PCN : Physic Chem.

Publisher

Best Edition

ISSN

Subject

Physics and Chemistry

Issue

Volume 57, Number 57/2011

Category

Physics and Chemistry

Pages

pp. 135-140

DOI

Subject Group

Physics and Chemistry

Online Date

January 31, 2011

File

Authors

Prof.Djamel Fadel, R. Djamaî, Prof. Mohamed Khireddine Kholladi, A Laïfa, A. Acidi & M. A. Harkat.

Titer

Qualitative evaluation of the landscaped potentialities of a dam in the north-eastern of Algeria for its use for recreation and leisure

Laboratory

MISC Laboratory of Constantine

Universities

Annaba University, Constantine2 University and El Oued university

Abstract

The water of Zit Emba is an element having a dramatic impact ecological and landscape considerably. The environmental impacts can be assessed by specialists. From the point of landscaping view, the problem is quite complex. Given that all major water bodies are very attractive and still seduce the eye. This is explained by the fact that large bodies of water (dams, lakes, etc…) condense in several respects landscape by bringing together in one place the physical components of the territory namely natural terrain, water and various forms of vegetation. This is the case of Zit Emba dam near the town of Bekkouche Lakhdar in the wilaya of Skikda in northeastern Algeria. This stretch of water that appears in its complex structure makes the quantitative estimation very difficult. For this reason, we used a method of qualitative estimate based on a visual approach and landscape to assess the potential of the dam Zit Emba.

Keywords

Dam, Visual field, Landscape planning, Bekkouche Lakhdar, Algeria.

Journal

Journal of Scientific Research and Essays

Publisher

Academic Journals

ISSN

ISSN 1992-2248

Subject

Scientific Research and Essays

Issue

Volume 6, number 6/2011

Category

Scientific Research and Essays

Pages

8 pages

DOI

Subject Group

Scientific Research and Essays

Online Date

18 March, 2011

File

Authors

Dr. Abdelkrim Bouramoul, Prof. Mohamed-Khireddine Kholladi & Dr. Bich-Lien Doan

Titer

How Ontology Can be Used to Improve Semantic Information Retrieval: The AnimSe Finder Tool

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university, El Oued university and SUPELEC France

Abstract

In this paper, we propose a new approach for locating and retrieving documents; the search process is guided by the ‘AnimOnto’ domain ontology that we have constructed for this purpose. This ontology is used at two different stages: First, for the semantic indexing of documents, in this stage the representative concepts of each document are selected by a projection of the ontology on the document by attaching their terms to the ‘AnimOnto’ concepts. Then, during the semantics queries reformulation; in this stage we exploit the semantic links between concepts to expand the initial query. To validate these proposals, we have implemented the ‘AnimSe Finder’ tool (Animal Semantic Finder) which materializes the different phases of the proposed approach. The obtained scores show that the semantic indexing and the queries reformulation have generated a gain of 13.06 in terms of recall and 16.13 in terms of precision, which significantly reduces the documentary noise and silence.

Keywords

Semantic web and Information retrieval.

Journal

IJCA: International Journal of Computer Applications

Publisher

Published by Foundation of Computer Science.

ISSN

ISSN 0975 – 8887, ISBN: 978-93-80749-31-2, FCS-US, 2011.

Subject

Computer science

Issue

Volume 21, Number 9/2011

Category

Computer science

Pages

pp. 48-54

DOI

10.5120/2536-3461

Subject Group

Computer science

Online Date

May 2011

File

Authors

Mme Aicha Eutamene,Dr Hacene Belhadef & Prof. Mohamed-Khireddine Kholladi

Titer

Ontology based New Approach for Character Recognition

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

The domain of pattern recognition and especially the character recognition is an area rich in term of scientific production, despite the abundance of work in this area but there are always anomalies. In this paper, we present a new approach for character recognition based on ontology, this last is carefully created with a domain expert, it contains a set of concepts and relationships, where each concept represents a grapheme, it is a feature extracted by an extraction module of a recognition system. Relationships between concepts are type spatial; describing the different possible relationships can be used between the graphemes, thus the characters in a document written in Latin alphabet. Our ontology is generic and can support other languages by enriching it by new specific spatial relationships.

Keywords

Characters recognition, Grapheme, Ontology, Spatial relation and Typographical features.

Journal

IJCA: International Journal of Computer Applications

Publisher

Foundation of Computer Science

ISSN

ISSN 0975 – 8887 and ISBN: 978-93-80749-31-2

Subject

Computer science

Issue

Volume 21, Number 10, Article 8/2011

Category

Computer science

Pages

pp. 40-44

DOI

10.5120/2623-3648.

Subject Group

Computer science

Online Date

May 2011

File

Authors

Dr Hacene Belhadef, Mme Aicha Eutamene & Prof. Mohamed-Khireddine Kholladi

Titer

Character Recognition Approach based on Ontology

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

In this paper, we present a general description of a new character recognition process based on ontology, semantically annotated by a domain expert. Such process is based essentially on a matching step between two ontologies, the first represents a domain ontology, containing the typographical description of different characters represent an alphabet of a well definite language (Latin for example), the second ontology, describes the document in question in the form of concepts where each concept represents a grapheme located in a defined order in the document. In this work we consider that there is a robust extraction module of primitives that will serve us to instantiate our ontology, by the different graphemes and their spatial relationships that exist in the processed document.

Keywords

Character recognition, Grapheme, Matching, Ontology, Semantic annotation and Typographical features. 

Journal

IJNCAA : International Journal of New Computer Architectures and their Applications

Publisher

The Society of Digital Information and Wireless Communications

ISSN

ISSN 2220-9085 (online)

Subject

Computer Architectures and their Applications

Issue

Volume 1, Number 2/2011

Category

Computer Architectures and their Applications

Pages

pp. 160-168.

DOI

Subject Group

Digital Information and Wireless Communications

Online Date

2011

File

Authors

Dr. Abdelkrim Bouramoul & Prof. Mohamed-Khireddine Kholladi

Titer

Improving Web search engines evaluation by the context consideration

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

Limitations and shortcomings of traditional approaches for evaluating information retrieval tools, particularly regarding to the consideration of the user, the manner in which these approaches measure the adequacy between the user’s query and the documents returned, and the  characteristics consideration of the search tool itself, have motivated our reflections for the exploitation of contextual elements around the user, the query and the search tool during the evaluation process. This paper presents a new approach  based on three complementary levels of context for evaluating information retrieval systems. The experiments gives at the end of this article has shown the applicability of the proposed approach to real research tools. The tests were performed with the most popular searching engine (i.e. Google, Bing and Yahoo) selected in particular for their high selectivity. The results have revealed that the evaluation of search engines at three different levels of context is a promising way to diagnose the performance, characteristics and behavior of these engines and the relevance of the results that they return.

Keywords

Information retrieval, Contextual evaluation, Relevance judgments and Web search engine

Journal

Journal of Information Organization

Publisher

ISSN

Subject

Information Organization

Issue

Volume 1 Number 1/2011

Category

Information Organization

Pages

pp. 6-16.

DOI

Subject Group

Information Organization

Online Date

17 October 2010, Revised 2 November 2010, Accepted 5 November 2010, Editing March 2011

File

Authors

Mme Baha Fergani, Prof. Mohamed-Khireddine Kholladi & Dr Mohamed Redha Bahri

Titer

Comparison of FCM and FISODATA

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

In fuzzy clustering, the fuzzy c-means (FCM) clustering algorithm is the best known and used method. An interesting extension of FCM is the fuzzy ISODATA (FISODATA) algorithm; it updates cluster number during the algorithm. That’s why we can have more or less clusters than the initialization step. It’s the power of the fuzzy ISODATA algorithm comparing to FCM. The aim of this paper is to compare FCM and FISODATA results.

Keywords

Machine intelligence and Fuzzy systems.

Journal

IJCA: International Journal of Computer Applications

Publisher

Foundation of Computer Science

ISSN

ISSN 0975 – 8887

Subject

Computer science

Issue

Volume 56, Number 8/2012

Category

Computer science

Pages

pp.35-39

DOI

Subject Group

Computer science

Online Date

Octobre 2012

File

Authors

Mme Aicha Eutamene, Prof. Mohamed-Khireddine Kholladi & Dr Hacene Belhadef

Titer

Architecture of a Character Recognition System Based on Ontology

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

The current revolution in the World Wide Web by using the notion of ontology has influenced in many domains of scientific research such that the domains that try bring a semantic to data and treatment; character recognition is one of these domains. In this paper we present new architecture of character recognition system that is characterized by using a domain ontology created by an expert; this ontology plays an intermediary role (bridge) between the low-level data and ones of high-level. The purpose behind this role is to bridge the semantic gap between these two types of data.

Keywords

Character recognition, Grapheme, Ontology and Semantic gap

Journal

IJCST: International Journal of Computer Science and Telecommunications

Publisher

Scholarly Research Publishing

ISSN

ISSN 2047-3338

Subject

Computer Science and Telecommunications

Issue

Volume 4, Issue 5/2013

Category

Computer Science and Telecommunications

Pages

pp. 49-55

DOI

Subject Group

Computer Science and Telecommunications

Online Date

May, 2013

File

Authors

Mme Baha Fergani & Prof. Mohamed-Khireddine Kholladi

Titer

Rebuilding Damaged Maps

Laboratory

MISC Laboratory of Constantine

Universities

Constantine 2 university and El Oued university

Abstract

The problem of reconstruction of damaged maps is a special case of the restoration of degraded document images where you take into account the spatial and factual geographical information. We propose in this paper the structure of our system of reconstituting damaged cards based on our classification of types of maps. The article is enriched by concepts important to understanding the system: maps (reference types), degradation (definition, sources, some solutions proposed in the literature).

Keywords

Maps, Damage, Image employed, Factual information and Spatial information.

Journal

IJGIS: International Journal of Geographical Information Science

Publisher

Taylor & Francis Group

ISSN

1365-8816 (Print), 1362-3087 (Online)

Subject

Geographical Information Science

Issue

Category

Geographical Information Science

Pages

6 pages

DOI

10.1080/13658816.2014.902950

Subject Group

Geographical Information Science

Online Date

File