Research Reports

Permanent URI for this collectionhttp://dl.cerist.dz/handle/CERIST/34

Browse

Author: search.filters.author.Nouali-Taboudjemat, Nadia

Search Results

Now showing 1 - 10 of 21
  • Thumbnail Image
    Item
    New GPU-based Swarm Intelligence Approach For Reducing Big Association Rules Space
    (CERIST, 2017-06-14) Djenouri, Youcef; Bendjoudi, Ahcène; Djenouri, Djamel; Belhadi, Asma; Nouali-Taboudjemat, Nadia
    This paper deals with exploration and mining of association rules in big data, with the big challenge of increasing computation time. We propose a new approach based on meta-rules discovery that gives to the user the summary of the rules’ space through a meta-rules representation. This allows the user to decide about the rules to take and prune. We also adapt a pruning strategy of our previous work to keep only the representatives rules. As the meta-rules space is much larger than the rules space, two approaches are proposed for efficient exploitation. The first one uses a bees swarm optimization method in the meta-rules discovery process, which is extended using GPU-based parallel programming to form the second one. The sequential version has been first tested using medium rules set, and the results show clear improvement in terms of the number of returned meta-rules. The two versions have then been compared on large scale rules sets, and the results illustrate the acceleration on the summarization process by the parallel approach without reducing the quality of resulted meta-rules. Further experiments on Webdocs big data instances reveal that the proposed method of pruning rules by summarizing meta-rules considerably reduces the association rules space compared to state-of-the-art association rules mining-based approaches.
  • Thumbnail Image
    Item
    Installation et configuration d’une solution de détection d’intrusions sans fil (Kismet)
    (CERIST, 2011-06) Lounis, Karim; Babakhouya, Abdelaziz; Nouali-Taboudjemat, Nadia
    Les réseaux sans fil (Wi-Fi, norme 802.11) offrent plusieurs avantages ; notamment en terme de mobilité, coût, débit et facilité de déploiement. Cependant, ils sont par nature plus sensibles aux problèmes de sécurité. Les mécanismes de sécurité (WEP, WPA, WPA2) ne permettent pas de se prévenir contre tous les problèmes de sécurité. En effet, les bornes Wi-Fi restent toujours vulnérables aux intrusions : attaque de déni de service, rogue AP, attaque de dé-authentification. Dans cette optique, il est conseillé de surveiller régulièrement l'activité du point d'accès sans fil afin de détecter les activités anormales sur le réseau et de les signaler sous forme d’ALERTES. Ce rapport présent les détails techniques d’installation et de configuration d’une solution de détection d’intrusion pour un réseau Wi-Fi. Cette solution se base sur des logiciels open source (Linux, Kismet, OPENWRT, DD-WRT, SWATCH) et une série de matériels sans fil (routeur Linksys WRT54GL et carte réseau sans fil).
  • Thumbnail Image
    Item
    Locating Emergency Responders using Mobile Wireless Sensor Networks
    (CERIST, 2012-07) Benkhelifa, Imane; Nouali-Taboudjemat, Nadia
    L'intervention d'urgence dans la gestion des catastrophes en utilisant les réseaux de capteurs sans fils est devenue récemment un intérêt de nombreux chercheurs du monde entier. Cet intérêt provient du nombre croissant de catastrophes et de crises (naturelles ou humaines) qui touchent des millions de vies ainsi que l'utilisation facile des nouvelles technologies pas cher. Ce document arrive avec un algorithme pour localiser les intervenants d'urgence et les secouristes en utilisant capteurs attachés aux secouristes. La solution proposée est très efficace et rapidement déployable et ne nécessite aucune infrastructure préinstallé. La solution est basée sur la prédiction des déplacements des secouristes en se basant sur des estimations de position précédentes. L'évaluation de notre solution montre que notre technique prend avantage de la prédiction d'une manière plus efficace que les solutions précédentes.
  • Thumbnail Image
    Item
    Infrastructure de communication sans fil avec qualité de service pour la gestion de crises et catastrophes
    (CERIST, 2016-11) Kabou, Abdelbasset; Nouali-Taboudjemat, Nadia; Nouali, Omar
    La Qualité de service (Quality of Service ou QoS) est un terme largement utilisé dans le domaine des technologies de communication. Dans les recommandations E.800, le CCITT (United Nations Consultative Committee for International Telephony and Telegraphy) défini la qualité de service comme : “Ensemble des effets portant sur les performances d’un service de communication et qui détermine le degré de satisfaction d’un utilisateur de ce même service”. Un intérêt particulier est porté dans ce rapport à la problématique du maintien de la QoS pour les applications multimédia. Ce type d'applications est très sensible aux variations des conditions régissant le réseau. Des métriques comme la bande passante, le taux de perte des paquets, la latence, la gigue ou des mécanismes tels le contrôle d’admission, les protocoles de signalisation, etc., sont de très grande importance pour ces applications et plus particulièrement durant une situation d'urgence. Ce rapport donne un aperçu de nos travaux sur la QoS des réseaux déployés en situation d'urgence.
  • Thumbnail Image
    Item
    Data reordering for minimizing threads divergence in GPU-based evaluating association rules
    (CERIST, 2015-03-26) Djenouri, Youcef; Bendjoudi, Ahcène; Mehdi, Malika; Habbas, Zineb; Nouali-Taboudjemat, Nadia
    This last decade, the success of Graphics Processor Units (GPUs) has led researchers to launch a lot of works on solving large complex problems by using these cheap and powerful architecture. Association Rules Mining (ARM) is one of these hard problems requiring a lot of computational resources. Due to the exponential increase of data bases size, existing algorithms for ARM problem become more and more inefficient. Thus, research has been focusing on parallelizing these algorithms. Recently, GPUs are starting to be used to this task. However, their major drawback is the threads divergence problem. To deal with this issue, we propose in this paper an intelligent strategy called Transactions- based Reordering "TR" allowing an efficient evaluation of association rules on GPU by minimizing threads divergence. This strategy is based on data base re-organization. To validate our proposition, theoretical and experimental studies have been carried out using well-known synthetic data sets. The results are very promising in terms of minimizing the number of threads divergence.
  • Thumbnail Image
    Item
    Association rules mining using evolutionary algorithms 
    (CERIST, 2014-10-16) Djenouri, Youcef; Bendjoudi, Ahcène; Nouali-Taboudjemat, Nadia
    This paper deals with association rules mining using evolutionary algorithms. All previous bio-inspired based association rules mining approaches generate non admissible rules which the end-user can not exploit them. In this paper, we propose two approaches permit to avoid non admissible rules by developing new strategy called delete and decomposition strategy. If an item is appeared in the antecedent and the consequent parts of given rule, this rule is composed on two admissible rules. Then, we delete such item to the antecedent part of the first rule and we delete the same item to the consequent part of the second rule. We also proposed two approaches (IARMGA and IARMMA), the first approach uses a classical genetic algorithm in the search process. However, the second one employs a mimetic algorithm to improve the quality of returned rules. To demonstrate the suggested approaches, several experiments have been carried out using both synthetic and reals instances. The results reveal that it has a compromise between the execution time and the quality of output rules. Indeed, IARMGA is faster than IARMMA whereas the last one outperforms IARMGA in terms of rules quality.
  • Thumbnail Image
    Item
    An Efficient Measure for Evaluating Association Rules
    (CERIST, 2014-06-24) Djenouri, Youcef; Gheraibai, Youcef; Mehdi, Malika; Bendjoudi, Ahcène; Nouali-Taboudjemat, Nadia
    Association rules mining (ARM) has attracted a lot of attention in the last decade. It aims to extract a set of relevant rules from a given database. In order to evaluate the quality of the resulting rules, existing measures, such as support and confidence, allow to evaluate the resulted rules of ARM process separately, missing the different dependencies between the rules. This paper addresses the problem of evaluating rules by taking into account two aspects : (1) The accuracy of the returned rules on the input data and (2) the distance between the returned rules. The rules set that covers the maximum of rules space is considered. To analyze the behavior of the proposed measure, it has been tested on two recent ARM algorithms BSO-ARM and HBSO-TS.
  • Thumbnail Image
    Item
    Parallel Association Rules Mining Using GPUs and Bees Behaviors
    (CERIST, 2014-06-24) Djenouri, Youcef; Bendjoudi, Ahcène; Mehdi, Malika; Nouali-Taboudjemat, Nadia; Habbas, Zineb
    This paper addresses the problem of association rules mining with large data sets using bees behaviors. The bees swarm optimization method have been successfully applied on small and medium data size. Nevertheless, when dealing Webdocs benchmark (the largest benchmark on the web), it is bluntly blocked after more than 15 days. Additionally, Graphic processor Units are massively threaded providing highly intensive computing and very usable by the optimization research community. The parallelization of such method on GPU architecture can be deal large data sets as the case of WebDocs in real time. In this paper, the evaluation process of the solutions is parallelized. Experimental results reveal that the suggested method outperforms the sequential version at the order of ×100 in most data sets, furthermore, the WebDocs benchmark is handled with less than ten hours.
  • Thumbnail Image
    Item
    Disaster Management Projects using Wireless Sensor Networks: An Overview
    (CERIST, 2014-02) Benkhelifa, Imane; Nouali-Taboudjemat, Nadia
    There are numerous projects dealing with disaster management and emergency response that use wireless sensor networks technologies. Indeed, WSNs offer a good alternative compared to traditional ad hoc networks. Air pollution monitoring, forest fire detection, landslide detection, natural disaster prevention, industrial sense and control applications, dangerous gas leakage, water level monitoring, vibration detection to prevent an earthquake, radiation monitoring are examples of the WSN applications related to disaster management. This paper presents an overview of the recent projects using WSN to collect data in disaster areas.
  • Thumbnail Image
    Item
    AdSIP: Decentralized SIP for Mobile Ad hoc Networks
    (CERIST, 2011-12) Nouali-Taboudjemat, Nadia; Belhoul, Yacine; Yahiaoui, Saïd
    SIP (Session Initiation Protocol) is an IETF signaling protocol designed to create, modify and terminate sessions between two or many users in multimedia applications. The implementation of SIP needs the use of proxy servers which are centralized entities to route SIP requests and responses to enable user endpoints to discover each other. However, the infrastructureless of ad hoc networks requires that the network nodes support the tasks of participants’ discovery and SIP routing messages. In this paper, we propose the AdSIP protocol which is a completely distributed architecture for SIP that implements the proxy servers in selected nodes. The proxy servers are selected using a distributed algorithm constructing a connected minimal global offensive alliance. AdSIP is implemented and compared under NS-2 with another protocol which uses a cluster based approach. The simulation results show the advantages of AdSIP and demonstrate that it is adapted to mobile ad hoc networks by giving low session establishment time, low control overhead and high service availability.