Research Reports
Permanent URI for this collectionhttp://dl.cerist.dz/handle/CERIST/34
Browse
16 results
Search Results
Item Knowledge Discovery from Log Data Analysis in a Multi-source Search System based on Deep Cleaning(CERIST, 2019-07) Lebib, Fatma Zohra; Mellah, Hakima; Meziane, AbdelkrimIn a multi-source search system, understanding users’ interests and behaviour is essential to improve the search and adapt the results according to each user profile. The interesting information characterizing the users can be hidden in large log files, whereas it must be discovered, extracted and analyzed to build an accurate user profile. This paper presents an approach which analyzes the log data of a multi-source search system using the web usage mining techniques. The aim is to capture, model and analyze the behavioural patterns and profiles of users interacting with this system. The proposed approach consists of two major steps, the first step “pre-processing” eliminates the unwanted data from log files based on predefined cleaning rules, and the second step “processing” extracts useful data on user’s previous queries. In addition to the conventional cleaning process that removes irrelevant data from the log file, such as access of multimedia files, error codes and accesses of Web robots, deep cleaning is proposed, which analyzes the queries structure of different sources to further eliminate unwanted data. This allows to accelerate the processing phase. The generated data can be used for personalizing user-system interaction, information filtering and recommending appropriate sources for the needs of each user.Item Ontological Interaction Modeling and Semantic Rule-Based Reasoning for User Interface Adaptation(CERIST, 2016) Lebib, Fatma-Zohra; Mellah, Hakima; Mohand Oussaïd, LindaDisabled users conducting their interactive tasks on their devices address challenges such as user interface adaptation. The paper provides a valuable knowledge for supporting adaptive user interfaces. In this work an interactive application development, in handicrafts’ domain is considered, with the aim to build ontology which models the available interaction modalities and resources to be used by craftswomen interacting with the system. The paper is more focused on the Semantic Web Rule Language (SWRL) rules allowing to derive the appropriate modalities for specific woman considering different factors related to its sensory perception and motor skills to one finality that is enriching interaction ontology.Item Selection of Information Sources using a Genetic Algorithm(CERIST, 2017-01-02) Lebib, Fatma Zohra; Drias, Habiba; Mellah, HakimaWe address the problem of information sources selection in a context of a large number of distributed sources. We formulate the sources selection problem as a combinatorial optimization problem in order to yield the best set of relevant information sources for a given query. We define a solution as a combination of sources among a huge predefined set of sources. We propose a genetic algorithm to tackle the issue by maximizing the similarity between a selection and the query. Extensive experiments were performed on databases of scientific research documents covering different domains such as computer science and medicine. The results based on the precision measure are very encouraging.Item Handicraft women Recommendation Approach based on User's Social Tagging Operations(CERIST, 2016-07-12) Kichou, Saida; Mellah, Hakima; Boussaid, Omar; Meziane, AbdelkrimRecommendation predicts which items the user might be interested in, and aims to help users finding the adequate element. Such as movies, music and commercial products, persons may be also recommended. In the case of handicraft women, we propose a recommendation approach based on extracted user’s interest using his/her social tagging operations to improve business activities of the handicrafts women, the approach is applied with preliminary tests.Item Data mining pour la construction de communautés d'utilisateurs(CERIST, 2016-05-10) Boulkrinat, Nour El Houda; Drias, Habiba; Mellah, Hakima; Khellouf, Hassina; Bouchabou, AidaLes communautés d’utilisateurs sont tenues ensemble par un intérêt commun dans un champ de savoir et sont conduites par un désir et un besoin de partager des idées, des expériences, des modèles, des outils et des meilleures pratiques. Dans ce travail nous présentons notre solution pour la construction de communautés d’utilisateurs en tenant compte des centres d’intérêts et en se basant sur la technologie du data mining. Les centres d’intérêts seront introduits à partir d’une ontologie dédie au domaine de l’informatique. Quant au data mining, il sera utilisé pour la segmentation des communautés via l’utilisation de l’algorithme K-means. Cette construction de communautés aidera le système de recherche d’information à l’acquisition implicite des nouveaux profils par la sélection ou l’adaptation d’un profil prédéfini, et à la reformulation des requêtes de l’utilisateur en fonction de nouvelles connaissances acquissent à partir de la communauté où il appartient.Item Enterprise information system, agility and complexity, what is the relationship?(CERIST, 2016-02-05) Mellah, Hakima; Drias, HabibaComplexity term is present everywhere. Complexity surrounds information, information system, organization as well as computing systems. In this work we present some challenges that deal with complexity. Why enterprise organization can be seen as complex? From what, complexity can arise within enterprise information system? What is relationship between complexity and agility? What are factors that may evolve complexity within enterprise information system? How computing system led information system towards complexity? To response to all this challenges, several dimensions dealing with complexity are displayed such as dynamics in enterprise information system components, while interacting, that can be tolerated by components autonomy, intelligibility that causes knowledge evolving, and inter-connectivity that is necessary with distribution. All these factors influence each others, within in a three dimensional system. UML modeling of enterprise information system that includes complexity parameters is given.Item Recommendation Based on User’s Interest Case Study: Handicrafts women in emerging countries.(CERIST, 2015-10-29) Kichou, Saida; Mellah, Hakima; Boussaid, Omar; Meziane, AbdelkrimSocial tagging systems promote resources sharing, organization and improve information retrieval. In the area of handicraft women, social tagging improves collaboration between users, by recommending some users to others, providers and products to users, handicraft women to clients etc. The aim of this paper is to propose a recommendation approach based on user’s interest, extracted using his social tagging operations, to improve the handicrafts women business activities.Item Using tags Associated to Resources to Build Ontologies(CERIST, 2014-06-18) Keddari, Djalila; Mellah, Hakima; Benna, AmelSocial tagging has recently emerged in the collaborative web as a support shared resources organization allowing users to categorize these resources, that can be web pages, video, or images, by associating them with keywords, called tags. However, the use of uncontrolled tags poses several problems, namely ambiguity, writing variations where many tags denote the same concept, as well as tags volume. The latter has led to tags classification into several clusters using the K Means algorithm. The purpose of this work is that from tags clusters and their hierarchical classification, it would be important to build an ontology as these tags have a semantic aspect and are expressed by users who used the tagged resources. Building ontologies, based on resources tags, is a way to make automatic their building without requiring experts as usual. Reproducing these tags clusters into ontological form is a way to share its knowledge with other users. We aim through this paper to build an ontology based on tags. A technical approach to form ontological portions, starting from tags clusters is based on semantic distance existing between tags. As tags clusters have a semantic relationship, the semantic distance between clusters is used to merge ontological portions into a global ontology.Item Web services based approach for integrating multimedia content(CERIST, 2012-05) Lebib, Fatma-Zohra; Mellah, Hakima; Amghar, YoussefMultimedia content is derived from various autonomous, distributed and heterogeneous content sources (relational or object databases, multimedia applications, multimedia servers, etc...). To address problems posed by content sources heterogeneity, a service-oriented architecture is proposed to assure a dynamic integration of multimedia content. In this work we propose a model that we call MaaS (for Multimedia as a Service), through which multimedia content providers expose their content. Once the MaaS is discovered, its classification into category of concepts, based on domain ontology, is made. However, content access is done through a concept hierarchy. The sport domain is used to validate the proposed model.Item Recherche d'information personnalisée basée sur le profil utilisateur(CERIST, 2011-12) Boulkrinat, Nour El Houda; Mellah, HakimaL’objectif fondamental d’un système de recherche d’information basée sur le profil utilisateur est de retourner, à partir d’une collection de documents, les éléments qui sont pertinents à un besoin en information exprimé par l’utilisateur à travers une requête. La sélection des seuls documents intéressants un utilisateur se fait sur la base des données collecter sur l’utilisateur appelé profils et de la représentation des documents sous formes d’un index. La modélisation de ce profil est la clé de réussite de tout le processus de recherche dont la finalité est de satisfaire l’utilisateur en quête d’information en ne rapportant pour lui que les documents pertinents susceptibles de l’intéresser. Pour construire le profil utilisateur nous avons adopté, dans notre travail pour une représentation multidimensionnelle/sémantique à cet effet, la représentation multidimensionnelle concerne les déférents types d’information de l’utilisateur, et la sémantique (ensemble d’ontologies) pour représenter ces centres d’intérêts.