RABAH Mokhtari

Djemiat Farid

Conception et réalisation d’un Plateforme d’apprentissage (enseignement à distance)

Chetouana Nesrine , Ben mekhfi Asma

Site web pour un opticien-lunetier

Bakhti Smail , Boudjellal Hocine

La segmentation des images par la methode de classification Fuzzy C-means (FCM)

AMOUR Nasreddine

Une approche MDA pour la transformation des diagrammes de classe UML vers une base de données Basant sur l’outil EMF

Mehoues Ahmed

Compilateur des diagrammes de classe vers le langage java

Saadin Imadeddine

Une approche MDA pour la transformation et l analyse des diagramme de classe

Salah Khoums

Approche de transformation et vérification des architectures logicielle

Lounes Bilal

Integrated DM in CRM solution

Bearing fault diagnosis is critical for predictive maintenance in industrial machinery, yet many existing data-driven methods struggle to adapt to varying operational loads and often analyze entire vibration signals, which can dilute key fault indicators. To address this, we propose a novel peak-centric approach that focuses on diagnostically rich signal regions, combining the Progressive Moving Average Transform (PMAT) with a 2D Convolutional Neural Network (CNN) for enhanced classification. Our primary contribution is a novel methodology that leverages localized peak regions for fault diagnosis, integrating the recently developed PMAT signal transformation and validating its generalization to mechanical systems to create highly discriminative 2D image representations from 1D vibration data. The method involves three key steps: extracting fixed-length signal fragments containing significant peaks, converting these fragments into 120×120 pixel images using the Left PMAT transform, and classifying the images into one of four health states using a custom 2D-CNN architecture. The model was rigorously evaluated on the CWRU dataset under a leave-one-load-out cross-validation scheme across four distinct load scenarios. It achieved exceptional performance, with macro-average F1-scores exceeding 99.83% in three of the four scenarios, specifically under loaded conditions (1-3 HP), and a top accuracy of 99.96%. A comparative analysis demonstrated that our PMAT-based method consistently outperformed a Continuous Wavelet Transform (CWT) baseline and other recent state-of-the-art models under these loaded scenarios. In conclusion, the proposed PMAT and 2D-CNN framework provides a robust and highly accurate tool for bearing fault diagnosis, successfully demonstrating PMAT's cross-domain generalization capability while establishing a competitive benchmark for future research. Future work will explore a hybrid PMAT-CWT transformation to further improve performance under zero-load conditions.

Citation

Rabah Mokhtari , ABDELHAFID Benyounes , Imad Eddine Tibermacine, Abdelaziz Rabehi, Alfian Ma’arif, , (2025-12-07), A Peak-Centric Approach to Bearing Fault Diagnosis Using Progressive Moving Transform and 2D- Convolutional Neural Network, International Journal of Robotics and Control Systems, Vol:5, Issue:6, pages:15, Association for Scientific Computing Electronics and Engineering (ASCEE)

This paper presents the Progressive Moving Average Transform (PMAT), a novel signal transformation method for converting time-domain signals into 2D representations by progressively computing Moving Averages (MAs) with varying window sizes. The approach aims to enhance signal analysis and classification, particularly in the context of heartbeat classification. Our approach integrates PMAT with a 2D-Convolutional Neural Network (CNN) model for the classification of ECG heartbeat signals. The 2D-CNN model is employed to extract meaningful features from the transformed 2D representations and classify them efficiently. To assess the effectiveness of our approach, we conducted extensive simulations utilizing three widely-used databases: the MIT-BIH database and the INCART database, chosen to cover a wide range of heartbeats. Our experiments involved classifying more than 6 heartbeat types grouped into three main classes. Results indicate high accuracy and F1-scores, with 99.09% accuracy and 92.13% F1-score for MIT-BIH, and 98.37% accuracy and 79.37% F1-score for INCART. Notably, the method demonstrates robustness when trained on one database and tested on another, achieving accuracy rates exceeding 95% in both cases. Specifically, the method achieves 96% accuracy when trained on MIT-BIH and tested on the ST-T European database. These findings underscore the effectiveness and stability of the proposed approach in accurately classifying heartbeats across different datasets, suggesting its potential for practical implementation in medical diagnostics and healthcare systems.

Citation

Rabah Mokhtari , , (2025-02-04), ECG heartbeat classification using progressive moving average transform, Scientific Reports, Vol:15, Issue:1, pages:1-16, Nature Portfolio

The community structure is proving to have a very important role in the understanding of complex networks, but discovering them remains a very diÕcult problem despite the existence of several methods. In this article, we propose a novel algorithm for discovering communities in complex networks based on a modiÒed random walk (RW) and label propagation algorithm (LPA). First, we calculate the similarity between nodes based on the new formula of RW. Then, the labels are propagated by the obtained similarity of the Òrst step using LPA. Finally, the third step will be a new measure to Ònd the optimal partitioning of communities. Experimental results obtained on several real and synthetic networks reveal that our algorithm outperforms existing methods in Ònding communities.

Citation

Makhlouf Benazi , BILAL Lounnas , Rabah Mokhtari , , (2022), A complex network community detection algorithm based on random walk and label propagation, Transactions on Emerging Telecommunications Technologies., Vol:33, Issue:9, pages:73-91, Wiley

Creating an effective method for extracting disease information is one of the major challenges in the classification of gene expression data as long as there is (in the presence) a massive amount of redundant data and noise. Bio-inspired algorithms are among the most effective when used for solving gene selection. Several techniques or methods may help in detecting diseases and cancer. Moth Flame Optimization Algorithm (MFOA) is computationally less expensive and can converge faster than other methods.

Citation

Ali Dabba , Rabah Mokhtari , abdelkamel Tari, Samy Meftali, ,(2022), A New Gene Selection Method Based On Moth Flame Optimization,Second International Conference on artificial intelligence and its applications (AIAP'2022),EL OUED, Algeria

Several techniques or methods may help in detecting diseases and cancer. Creating an effective method for extracting disease information is one of the major challenges in the classification of gene expression data as long as there is (in the presence) a massive amount of redundant data and noise. Bio-inspired algorithms are among the most effective when used for solving gene selection. Moth Flame Optimization Algorithm (MFOA) is computationally less expensive and can converge faster than other methods. In this paper, we propose a new extension of the MFOA called the modified Moth Flame Algorithm (mMFA), the mMFA is combined with Mutual Information Maximization (MIM) to solve gene selection in microarray data classification. Our approach Called Mutual Information Maximization – modified Moth Flame Algorithm (MIM-mMFA), the MIM based pre-filtering technique is used to measure the relevance and the redundancy of the genes, and the mMFA is used to evolve gene subsets and evaluated by the fitness function, which uses a Support Vector Machine (SVM) with Leave One Out Cross Validation (LOOCV) classifier and the number of selected genes. In order to test the performance of the proposed MIM-mMFA algorithm, we compared the MIM-mMFA algorithm with other recently published algorithms in the literature. The experiment results which have been conducted on sixteen benchmark datasets either binary-class or multi-class, confirm that MIM-mMFA algorithm provides a greater classification accuracy.

Citation

Rabah Mokhtari , , (2020), Gene selection and classification of microarray data method based on mutual information and moth flame algorithm, Expert Systems with Applications, Vol:166, Issue:114012, pages:73-91, Elsevier

Unified Modeling Language (UML) and Object Constraint Language (OCL) are the most commonly used languages to model software systems. OCL is a formal language used to specify invariants as well as pre- and post-conditions on UML diagrams. However, there is no meaner to verify the satisfaction of the OCL constraints properties by the modeled system. This paper presents a formal approach to reason about UML Class Diagram (CD) and OCL “pre-” and “post-conditions” described on CD operations (or methods) using Observational Transition Systems in CafeOBJ (OTS/CafeOBJ) and proof scores of CafeOBJ. CafeOBJ is an executable formal algebraic specification language widely used to specify models for varieties of software and systems and verifying properties of them.

Citation

Rabah Mokhtari , ,(2020), Validation of UML Class Diagram and OCL pre-and post-conditions using OTS/CafeOBJ proof scores,2020 4th International Symposium on Informatics and its Applications (ISIA),M'sila, Algeria

The concept of reconfigurable and dynamic software architecture (DSA) occupies today an important place in the field of software engineering. As result, several architecture description languages (ADLs) and approaches have been proposed for describing DSA in the highest level of abstraction. However, most of these works present theoretical solutions without giving an idea on the execution of final systems at run time. In this paper, we propose a new DSA called coloured software architecture (CSA) based on two concepts coloured operation and coloured connector. Then, we propose a new ADL called coloured-ADL and implement a compiling, verification and simulation tool dedicated to CSA. The simulation of system instances, derived from a CSA, is mainly used to explain coloured-ADL and evaluate the reliability of the simulated system. On the other hand, the verification is focused on checking a new defined safety property called architectural stack overflow (ASO). A safe CSA should be free of ASO violation property. To check a CSA, the verification uses also finite state processes (FSP) and labelled transition state (LTS) to expect this kind of property. We illustrate our propositions through two case studies from the literature.

Citation

Rabah Mokhtari , a_chaoui2001@yahoo.com, , (2017), Compiling, verifying and simulating dynamic software architectures using ANTLR and coloured-ADL, International Journal of Communication Networks and Distributed Systems (IJCNDS), Vol:19, Issue:4, pages:27, inderscience

Le domaine des agents mobiles a tiré récemment une grande attention surtout après l’apparition des nouvelles technologies des réseaux de communication sans fil à base de dispositifs embarqués avec des ressources limitées comme les réseaux de capteurs sans fil (RCSF). Par conséquent, un ensemble de protocoles et d’outils de développement ont été réalisés pour permettre le développement et le déploiement d’applications à base d’agents mobiles sur les nœuds des réseaux d’infrastructures sans fil. Cependant, les travaux sur les approches du génie logiciel qui doivent accompagner les progressions techniques et technologiques de ce domaine sont limités et rares. Pour combler cette lacune, ce papier entre dans ce contexte et présente une approche MDE (Model Driven Architecture) pour une plate-forme spécifique dédiée aux RCSF dite MAPS (Mobile Agent Platform for Sun SPOTs). Notre approche utilise l’EMF pour définir un métamodèle décrivant les applications d’agents mobiles MAPS et implémente un outil de transformation permettant la génération automatique de code Java à partir des modèles d’applications MAPS

Citation

Rabah Mokhtari , a_chaoui2001@yahoo.com, ,(2016), Une approche MDE pour la modélisation et la transformation de modèle MAPS (Mobile Agent Platform for Sun SPOTs),CAL 2016,Besançon, France – Juin 7-8, 2016

We propose in this paper a complete MDA approach to manipulate Software Architecture in different abstract levels. Our approach is based on two tools one to defining and transforming Software Architectures (SAs) and the second to generate code in Specific Platforms. Our first tool is based on graph transformation and uses ATOM3 tool. To describe SAs we have proposed a meta-model, based on UML Component Diagrams, and a graph grammar that performs automatically the transformation of SAs to XML documents that represent in fact Platform Independent Models validated by an XML Schema. The second tool makes use of theses XML documents in order to generating codes in Specific Platforms.

Citation

Rabah Mokhtari , ,(2014), An MDA approach to transforming Software Architectures using Graph Grammar,ISIA 2014,M'sila, Algeria

Nous proposons dans cet article une approche et un outil pour la transformation desArchitectures Logicielles Dynamiques (ou Dynamic Software Architecture DSA) au momentde la conception (ou design time) en des documents XML. Nous avons utilisé lesdiagrammes de composants UML pour représenter les architectures logicielles. Notreapproche est basée sur la transformation de graphes et utilise l’outil ATOM3. Pour cetobjectif, nous avons proposé un méta-modèle pour les DSAs (Diagrammes de composantsUML) et une grammaire de graphes permettant d’exécuter automatiquement latransformation d’une DSA en un document XML correspondant. Afin qu’on puissemanipuler la dynamicité des architectures, notre outil permet à l’utilisateur de créer uneDSA, d’ajouter des composants et de supprimer des composants depuis une DSA, et detransformer par la suie, la nouvelle DSA au document XML correspondant. Pour valider les documents XML générés on a défini pour notre méta-modèle une DTD (Document Type Definition) correspondante

Citation

Rabah Mokhtari , a_chaoui2011@yahoo.com, ,(2011), Transformation des architectures logicielles dynamiques vers des documents XML en utilisant ATOM3,CAL 2011,Lille, France

In this paper we propose an approach and a tool for transforming Dynamic Software Architectures (DSA) to XML documents. We have used UML component diagrams to represent the software architectures. Our approach is based on graph transformation and uses ATOM3. To this end, we have proposed a meta-model for the DSA (UML component diagrams) and a graph grammar that performs automatically the transformation of a DSA to its corresponding XML document. In order to manipulate the dynamicity of software architectures our tool allows the user to create a DSA, to add components to a DSA, and remove components from a DSA during the design-time. Then, it allows the user to transform the new DSA to its corresponding XML document. To validate the generated XML documents we have defined for our meta-model the corresponding Document Type Definition (DTD).

Citation

Rabah Mokhtari , a_chaoui2001@yahoo.com, ,(2010), Mapping UML Components diagrams to XML using Graph Transformation.,CAINE 2010,Las Vegas, Nevada, USA

The technology of mobile agents obtained recently more importance not only because of its capacity of developing and building a distributed, heterogeneous, and interoperable systems, but also because of its robustness development of mobile and communication network as well. However, there are few works dealing with the methods and tools of analysis and design of the mobile agents systems. Furthermore, the mobile systems have introduced new concepts as: migration, cloning and the locations. We propose in this paper an extension of the most important UML 2.0 diagrams to model the mobile agents systems with the objective to face these three concepts. A case study illustrates the proposed approach.

Citation

Rabah Mokhtari , , (2009), Towards an extension of UML2.0 to model mobile agent-based systems, International Journal of Computer Science and Network Security, Vol:9, Issue:, pages:124-131, IJCSNS