Academic & Scientific Articles
Permanent URI for this communityhttp://dl.cerist.dz/handle/CERIST/3
Browse
43 results
Search Results
Item Combining Tags and Reviews to Improve Social Book Search Performance(Springer, 2018-08-15) Chaa, Messaoud; Nouali, Omar; Bellot, PatriceThe emergence of Web 2.0 and social networks have provided important amounts of information that led researchers from different fields to exploit it. Social information retrieval is one of the areas that aim to use this social information to improve the information retrieval performance. This information can be textual, like tags or reviews, or non textual like ratings, number of likes, number of shares, etc. In this paper, we focus on the integration of social textual information in the research model. As it seems logical that integrating tags in the retrieval model should not be in the same way taken to integrate reviews, we will analyze the different influences of using tags and reviews on both the settings of retrieval parameters and the retrieval effectiveness. After several experiments, on the CLEF social book search collection, we concluded that combining the results obtained from two separate indexes and two models with specific parameters for tags and reviews gives good results compared to when using a single index and a single model.Item Minimum redundancy and maximum relevance for single and multi-document Arabic text summarization(Elsevier, 2014-12) Oufaida, Houda; Nouali, Omar; Blache, PhilippeAutomatic text summarization aims to produce summaries for one or more texts using machine techniques. In this paper, we propose a novel statistical summarization system for Arabic texts. Our system uses a clustering algorithm and an adapted discriminant analysis method: mRMR (minimum redundancy and maximum relevance) to score terms. Through mRMR analysis, terms are ranked according to their discriminant and coverage power. Second, we propose a novel sentence extraction algorithm which selects sentences with top ranked terms and maximum diversity. Our system uses minimal language-dependant processing: sentence splitting, tokenization and root extraction. Experimental results on EASC and TAC 2011 MultiLingual datasets showed that our proposed approach is competitive to the state of the art systems.Item Lifetime-Aware Backpressure : A New Delay-Enhanced Backpressure-Based Routing Protocol(IEEE, 2019-03) Kabou, Abdelbaset; Nouali-Taboudjemat, Nadia; Djahel, Soufiene; Yahiaoui, Saïd; Nouali, OmarDynamic backpressure is a highly desirable family of routing protocols known for their attractive mathematical properties. However, these protocols suffer from a high end-to-end delay making them inefficient for real-time traffic with strict end-to-end delay requirements. In this paper, we address this issue by proposing a new adjustable and fully distributed backpressure-based scheme with low queue management complexity, named Lifetime-Aware Backpressure (LTA-BP). The novelty in the proposed scheme consists in introducing the urgency level as a new metric for service differentiation among the competing traffic flows in the network. Our scheme not just significantly improves the quality of service provided for real-time traffic with stringent end-to-end delay constraints, but interestingly protects also the flows with softer delay requirements from being totally starved. The proposed scheme has been evaluated and compared against other state-of-the-art routing protocol, using computer simulation, and the obtained results show its superiority in terms of the achieved end-to-end delay and throughput.Item Using ABE for Medical Data Protection in Fog Computing(2019-05-03) Krinah, Abdelghani; Challal, Yacine; Omar, Mawloud; Nouali, OmarFog is an extension of the cloud computing paradigm, developed to fix the clouds latency, especially for applications requiring a very short response time, such as e-health applications. However, these applications also require a high level of data confidentiality, hence the need to apply appropriate encryption techniques, which can ensure security needs, while respecting the characteristics of the infrastructures devices. In this article, we will focus on ABE encryption, through the work done to study its applicability in the cloud and the Internet of things, as well as the improvements that can be made to adapt it to the fog computing environment.Item Secure Inverted Index Based Search over Encrypted Cloud Data with User Access Rights Management(Springer, 2019-01-18) Boucenna, Fateh; Nouali, Omar; Kechid, Samir; Kechadi, M. TaharCloud computing is a technology that provides users with a large storage space and an enormous computing power. However, the outsourced data are often sensitive and confidential, and hence must be encrypted before being outsourced. Consequently, classical search approaches have become obsolete and new approaches that are compatible with encrypted data have become a necessity. For privacy reasons, most of these approaches are based on the vector model which is a time consuming process since the entire index must be loaded and exploited during the search process given that the query vector must be compared with each document vector. To solve this problem, we propose a new method for constructing a secure inverted index using two key techniques, homomorphic encryption and the dummy documents technique. However, 1) homomorphic encryption generates very large ciphertexts which are thousands of times larger than their corresponding plaintexts, and 2) the dummy documents technique that enhances the index security produces lots of false positives in the search results. The proposed approach exploits the advantages of these two techniques by proposing two methods called the compressed table of encrypted scores and the double score formula. Moreover, we exploit a second secure inverted index in order to manage the users’ access rights to the data. Finally, in order to validate our approach, we performed an experimental study using a data collection of one million documents. The experiments show that our approach is many times faster than any other approach based on the vector model.Item Toward a new Backpressure-based framework to Enhance Situational Awareness in Disaster Response(IEEE ICT-DM-2017, 2017-12-11) Kabou, Abdelbaset; Nouali-Taboudjemat, Nadia; Nouali, OmarCrises generate intense need to communication not just as a panic reaction to crisis, but also due the critical need for communication in order to better coordinate during response activities. In the afterward of a disaster, the lack of resources to handle this increase of data, due to the fragility of network infrastructures, leads to network congestion or overload. The results is that critical data are prevented from reaching decision makers, which has a direct impact on situational-awareness. To overcome this problem, we propose a new cross layer architecture for Wireless Mesh Network with a twofold objective: one, to include a filtering system able to identify the most critical data and two, to propose a routing layer with the capacity to prioritize these data while ensuring the stability and throughput optimality of the whole network. The proposed solution combines both by proposing an adjustable and fully distributed version of the high throughput efficient Backpressure routing protocol, with a geolocation and role-based filtering and prioritizing system. Both components collaborate in a way to identify and send most critical data, using a lower end-to-end delay, without however starving less critical data. Extensive experiments, using NS-3 simulator, are used to validate the proposal and confirm the high impact of the introduced ideasItem New Technique to Deal With Verbose Queries in Social Book Search(CERIST, 2017) Chaa, Messaoud; Nouali, Omar; Bellot, PatriceVerbose query reduction and query term weighting are automatic techniques to deal with verbose queries. The objective is either to assign an appropriate weight to query terms according to their importance in the topic, or outright remove unsuitable terms from the query and keep only the suitable terms to the topic and user’s need. These techniques improve performance and provide good results for ad hoc information retrieval. In this paper we propose a new approach to deal with long verbose queries in Social Information Re-trieval (SIR) by taking Social Book Search as an example. In this approach, a new statistical measure was introduced to reduce and weight terms of verbose queries. Next, we expand he query by exploiting the similar books mentioned by users in their queries. We find that the proposed approach improves significantly the results.Item Accelerated Search over Encrypted Cloud Data(IEEE, 2017-02-13) Boucenna, Fateh; Nouali, Omar; Dabah, Adel; Kechid, SamirCompanies and other organizations such as hospitals seek more and more to enjoy the benefits of cloud computingin terms of storage space and computing power. However, outsourced data must be encrypted in order to be protected againstpossible attacks. Therefore, traditional information retrieval systems (IRS) are no longer effective and must be adapted in order towork over encrypted cloud data. In addition, in order to providethe ability to search over an encrypted index, we use the vectormodel to represent documents and queries which is the most usedin the literature. During the search process, the query vectormust be compared with each document vector which is a time consuming process since the data collection is generally huge.Consequently, the search performance is degraded and the searchprocess is too slow. To overcome this drawback, we proposethe use of High Performance Computing (HPC) architecturesto accelerate the search over encrypted cloud data. Indeed,we propose several techniques that take benefit from Graphics Processing Unit (GPU) and computer cluster architectures by distributing the work between different threads. In addition,in order to get the best performance, we design our solutionsso that they can process several queries simultaneously. Theexperimental study using 400.000 documents demonstrates theefficiency of our proposals by reaching a speed-up around 46x.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, OmarLa 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.Item Verbose Query Reduction by Learning to Rank for Social Book Search Track(CERIST, 2016-07) Chaa, Messaoud; Nouali, Omar; Bellot, PatriceIn this paper, we describe our participation in the INEX 2016 Social Book Search Suggestion Track (SBS). We have exploited machine learning techniques to rank query terms and assign an appropriate weight to each one before applying a probabilistic information retrieval model (BM15). Thereafter, only the top-k terms are used in the matching model. Several features are used to describe each term, such as statistical features, syntactic features and others features like whether the term is present in similar books and in the profile of the topic starter. The model was learned using the 2014 and 2015 topics and tested with the 2016 topics. Our experiments show that our approach improves the search results.