SciTePress - Affiliation Profile

CERIST Alger, Algeria

Context (please use complete words only)

Field

Sort by

7 Papers

Knowledge Discovery from Log Data Analysis in a Multi-source Search System based on Deep Cleaning

Topics: Web Information Filtering and Retrieval; User-Centric Systems; Data Web Mining; Applications, Research Projects and Web Intelligence

Authors: Fatma Zohra Lebib ¹ , Hakima Mellah ² and Abdelkrim Meziane ²

Affiliations: ¹ University of Science and Technology Houari Boumediene, USTHB, Algiers, Algeria, Research Center in Scientific and Technical Information, CERIST, Algiers and Algeria , ² Research Center in Scientific and Technical Information, CERIST, Algiers and Algeria

Digital Object Identifier: 10.5220/0008121102570264

Proceedings of WEBIST 2019, ISBN: 978-989-758-386-5

Quick Abstract

In 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.

Ontological Interaction Modeling and Semantic Rule-based Reasoning for User Interface Adaptation

Topics: User-Centric Systems; Human Computer Interaction; Ontology Discovering, Modelling, Retrieving and the Semantic Web; Context, Adaptability and Web Intelligence

Authors: Fatma-Zohra Lebib , Hakima Mellah and Linda Mohand-Oussaid

Affiliation: CERIST, Algeria

Digital Object Identifier: 10.5220/0005854303470354

Proceedings of SRIS 2016/WEBIST, ISBN: 978-989-758-186-1

Quick Abstract

The paper aims to show how reasoning on ontology can be helpful for user interface adaptation. From a set of user characteristics and interface parameters, it is possible to deduct the most suitable and adaptable interfaces for him/her. To do so, Semantic Web Rule Language (SWRL) rules are used to derive the appropriate interface for a specific user, considering different factors related to his/her abilities, preferences, skills, etc. A use case, in handicrafts domain, is presented; different input and output interaction modalities (writing, selection, text, speech, etc) are proposed to a handcraft woman according to her sensory perception and motor skills. The modalities are structured within what we called "interaction ontology".

Indexing Multimedia Content for Textual Querying: A Multimodal Approach

Authors: Abdesalam Amrane ¹ , Hakima Mellah ¹ , Youssef Amghar ² and Rachid Aliradi ¹

Affiliations: ¹ Research Center on Scientific and Technical Information (CERIST), Algeria , ² University of Lyon, CNRS, INSA-Lyon, LIRIS and UMR5205, France

Digital Object Identifier: 10.5220/0004576200030012

Proceedings of WEBI 2013/ICEIS, ISBN: 978-989-8565-63-1

Quick Abstract

Multimedia retrieval approaches are classified into three categories: those using textual information, and those using low-level information and those that combine different information extracted from multimedia. Each approach has its advantages and disadvantages as well to improving multimedia retrieval systems. The recent works are oriented towards multimodal approaches. It is in this context that we propose an approach that combines the surrounding text with the information extracted from the visual content of multimedia and represented in the same repository in order to allow querying multimedia content based on keywords or concepts. Each word contained in queries or in description of multimedia is disambiguated by using the WordNet in order to define its semantic concept.

User Interest Extraction based on Weighted Tags

Authors: Saida Kichou ¹ , Hakima Mellah ¹ , Imene Lasbeur ² and Imen Abdelouahid ²

Affiliations: ¹ Research Center on Scientific and Technical Information (CERIST) Benaknoun, Algeria , ² University of Boumerdes, Algeria

Digital Object Identifier: 10.5220/0004599300220031

Proceedings of WEBI 2013/ICEIS, ISBN: 978-989-8565-63-1

Quick Abstract

Collaborative tagging systems are based on assigning keywords freely chosen by users, which promotes ressources sharing and organization by the way and improves the information retrieval. The tags allocation by users is illustrated particularly in sites sharing photos or videos (Flickr, YouTube). As navigations and clicks, tags can be good indicators of the user's interests. In this paper, we examine the limitations of previous tag-based profile extraction. We believe that for a better result, tags of a resource must represent well its content. Existing systems consider ‘Popularity’ as the unique criterion to judge the tag effectiveness. But it does not always reflect its importance and representativeness to the resource. In this paper, we propose a novel approach based on tag strength to represent a user. In which we introduce weighted tags based on user expertise.

Matching Resources in Social Environment

Authors: Amel Benna ¹ , Hakima Mellah ² , Islam Choui ³ and Ali Oualid ³

Affiliations: ¹ CERIST and USTHB, Algeria , ² CERIST, Algeria , ³ ESI, Algeria

Digital Object Identifier: 10.5220/0004088800610070

Proceedings of WEBI 2012/ICEIS, ISBN: 978-989-8565-14-3

Quick Abstract

User comments on the web are becoming more and more important. We focus, in this paper, on the use of user-defined tags for annotating resources to identify links between them. These links are based on a social context of the resource, obtained by applying k-means classification method and a hierarchical classification of tags within a cluster. The resources are re-assigned to this classification to facilitate the search process. The ranking of results is performed according to their degree of relevance, by evaluating a similarity score between the tagged contents, in hierarchical clusters of tags, and the user request. The results of the evaluation, on the social bookmarking system del.icio.us, demonstrate significant improvements over traditional approaches.

Web Services based Approach for Integrating Multimedia Content

Authors: Fatma Zohra Lebib ¹ , Hakima Mellah ¹ and Youssef Amghar ²

Affiliations: ¹ Research Center in Scientific and Technical Information, Algeria , ² National Institute of Applied Sciences, France

Digital Object Identifier: 10.5220/0004087800510060

Proceedings of WEBI 2012/ICEIS, ISBN: 978-989-8565-14-3

Quick Abstract

Multimedia content is derived from various autonomous, distributed and heterogeneous content sources. 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.

WATERMARKING OF COMPRESSED VIDEO BASED ON DCT COEFFICIENTS AND WATERMARK PREPROCESSING

Topic: Image and Video Watermarking

Authors: Samira Bouchama ¹ , Latifa Hamami ² and Hassina Aliane ¹

Affiliations: ¹ Research Center on Scientific and Technical Information, Algeria , ² National Polytechnic School, Algeria

Digital Object Identifier: 10.5220/0003321601140119

Proceedings of IMAGAPP 2011/VISIGRAPP, ISBN: 978-989-8425-46-1

Quick Abstract

Considering the importance of watermarking of compressed video, several watermarking methods have been proposed for authentication, copyrights protection or simply for a secure data carrying through the Internet. Applied to the H.264/AVC video standard, in most of cases, these methods are based on the use of the quantized DCT coefficients often experimentally or randomly selected. In this paper, we introduce a watermarking method based on the DCT coefficients using two steps: the first one consists in a watermark pre-processing based on similarity measurement which can allow to adapt the best the watermark to the carrying coefficients of low frequencies. A second step takes advantage from the coefficients of high frequencies in order to maintain the video quality and reduce the bitrate. Results show that it is possible to achieve a very good compromise between video quality, embedding capacity and bitrate.

Related Ontology Subjects/Areas/Topics (3)

Computer Vision, Visualization and Computer Graphics

Image and Video Analysis

Image and Video Watermarking

Topic(s):

Title:
ISBN:
Year:
Acronym:
Subject:

Title:
Author:
Affiliation:
Subject:

Name:
Affiliation:
Country:
Conference:
Subject:

Name:
Country:
Subject:

Affiliation

Filter listed results, by