{"title":"Neural-linguistic classifier combination for large Arabic word vocabulary recognition","authors":"Imen Ben Cheikh, A. Kacem, A. Belaid","doi":"10.1109/ICMWI.2010.5648124","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5648124","url":null,"abstract":"A new system for large Arabic word vocabulary recognition is proposed. It is based on combination of three neural-linguistic classifiers that collaborate to improve the recognition results. Our work confirms not only “word superiority effect”, which is a concept in human reading process, but also proposes a new concept named “word derivation effect”. In fact, the proposed classifiers are based on transparent neural networks (TNNs) which use global features such as ascenders, descenders and loops. Thus, the system proceeds firstly by global structural primitives and then refines the vision by looking for local details, in cases of ambiguities. Inspired by previous works, dealing with the use of Arabic linguistic knowledge in writing recognition, we investigate the use of a linguistic based collaboration between TNNs to handle with a large Arabic word lexicon that involves decomposable words derived from healthy roots. Indeed, our neural classifiers, called TNN_R, TNN_S and TNN_C, are conceived to collaborate and respectively learn and recognize roots, schemes and conjugation elements of words. Comparisons between results of “classifier combination without collaboration”, results of “classifier collaboration” and results of “applying perceptive cycles” highlight the contribution of collaboration and perceptive cycles. The proposal system has been successfully demonstrated on a vocabulary of 2000 words and achieved satisfactory results compared to some related works, which either deal with large vocabulary and/or integrate linguistic knowledge in their system.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"3 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130043572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Semantic mapping of ADLs into MDA platforms using a meta-ontology","authors":"A. Adel, Boukerram Abbdellah","doi":"10.1109/ICMWI.2010.5648023","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5648023","url":null,"abstract":"In this article we contribute to the issue of the recent research work, in which software architecture is oriented more toward the OMG group. Thus, we try to map any ADL (Architecture Description Language) into MDA (Model Driven Architecture) platform. Our strategy is based on constructing a meta ontology that next can be used as a façade meta-model for semantic mapping of ADLs into MDA platforms. We show how this strategy can be used by mapping COSA architectural description concepts into CORBA. The goal of our work is to increase the high level of systems' concepts abstracting for wrapping and integrating heterogeneous software concepts into MDA platforms via a top-level ontology.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125300726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Toward a better automation of the distributed discovery mechanism for semantic web services","authors":"Hadj Madani Meghazi, Youcef Aklouf","doi":"10.1109/ICMWI.2010.5648060","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5648060","url":null,"abstract":"Semantic web services aim to automate the use of web services by adding some annotations to these services in order to improve semantic expression of their functionalities. With the evolution of organizations web services and their widespread use, searching for them based on a distributed context has become a real challenge. A functionality-based web service discovery mechanism is then necessary since the functionalities are the most important thing partners look for. In this paper, we present an automatic, a scalable, and a distributed discovery mechanism for web service execution environments. Our solution is based on P2P technologies that proved their efficiency and robustness as distributed systems.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127443429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Inverse kinematic using AIS","authors":"A. Serrat, M. Benyettou","doi":"10.1109/ICMWI.2010.5647979","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5647979","url":null,"abstract":"The kinematic problem of serial manipulators comprises the study of the relations between joint variables and Cartesian variables. We distinguish two problems, commonly referred to as the direct and kinematic problems. The former reduces matrix multiplications, and poses no major problem. The inverse kinematic problems, however, is more challenging, for it involves intensive variableelimination and nonlinear-equation solving. In this work, we have used the Clonal Selection to solve the inverse problem on a manipulator arm, to determine its various articulations. The results of simulation are presented to show the validity of the approach suggested above.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133096968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Towards a new approach for real time face detection and normalization","authors":"Hayet Mekami, Sidahmed Benabderrahmane","doi":"10.1109/ICMWI.2010.5647890","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5647890","url":null,"abstract":"Nowadays, face recognition algorithms, proposed in the literature, reached a correct performance level when the acquisitions conditions for the tested images are controlled (variability of the environment, illumination, poses, expressions and also the number of images in the database to identify people). These performances fall when these conditions are degraded. The controlled conditions of acquisition correspond to a good balance of illumination, as well as a high-resolution, a good pose of the face and a maximum sharpness of the face image. Although several methods have been proposed to resolve the problem of illumination variation, the problem of rotation and occlusion still an obstacle. In this paper, we propose a new method for face detection and normalization which consists to choose the best pose and the point of view of the detected face. This normalization conducts us to select the normalized images to be used as an input in the recognition process, in order to improve its performance. This approach was implemented and tested on a public database. The preliminary results seem very promising.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122209434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An MDP-based approach oriented optimal policy for path planning","authors":"N. Achour, Karim Braikia","doi":"10.1109/ICMWI.2010.5647970","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5647970","url":null,"abstract":"In this article we present an approach to improve the execution time of the Markov decision process (MDP) used in robotics for path planning. We've improved it for both value iteration algorithms (value iteration) and Policy Iteration (policy iteration). Unlike the conventional approach which initializes the algorithms with random values and explores all the accessible states at each iteration, our approach modifies the classical algorithms to improve their performance. These changes are reflected mainly in two points: non-random initialization of the algorithms, and a significant reduction of calculations at each iteration. The results are promising; they are presented at the end of the paper.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116142828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"On the integration of dispatching and covering for emergency vehicles management system","authors":"S. Ibri, M. Nourelfath, H. Drias","doi":"10.1109/ICMWI.2010.5647878","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5647878","url":null,"abstract":"In the vehicle management systems, two important issues have to be considered by managers: the dispatching problem with the aim of minimizing the response time for current emergency calls; and the covering problem with the objective of keeping proper coverage to satisfy future calls in best times. The purpose of this paper is to investigate the value, in term of service quality, of integrating the dispatching and covering problems in the same model. A heuristic algorithm, combining Ant optimization and Tabu search, is used as a solution approach. Several numerical examples are used to compare the integrated approach and the non-integrated one.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123709725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Dynamic threshold for replicas placement strategy","authors":"Mohamed Redha Djebbara, H. Belbachir","doi":"10.1109/ICMWI.2010.5647887","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5647887","url":null,"abstract":"The data replication is a very important technique for the availability of data in the grids. One of the challenges in data replication is the replicas placement. In this paper, we present our contribution by proposing a replicas placement strategy in a hierarchical grid. Our approach is based on a dynamic threshold, contrary to the other strategies of replicas placement which use a static threshold. In our strategy we show that the threshold depends on several factors such as the size of the data to be replicated, the consumed bandwidth which is explained by the level of the tree related to the grid.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124624386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Introduction of the website importance into the evaluation of the prior probability of relevance of web page","authors":"Arezki Hammache, R. Ahmed-Ouamer, M. Boughanem","doi":"10.1109/ICMWI.2010.5647831","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5647831","url":null,"abstract":"Usually, user accesses to information on the web using search engines. However, a significant factor, which is the quality of the restored documents, is underestimated by most of these engines. This is due to not taking into account all dimensions of a web document during the indexing and retrieval process. In recent years, language models have been proposed on Information Retrieval and increased in popularity, due to their simplicity, clear probabilistic meaning. In addition these models offer possibility of integrating a priori document information. Several features have been used to estimate the prior probability of a document such as: document length. However these features depend only on the document. A web page is part of website. The idea that we explore in this article is to use website features which contains the concerned page to estimate the page prior.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125190509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A comparative study of Neural networks architectures on Arabic text categorization using feature extraction","authors":"F. Harrag, A. Al-Salman, Mohammed Benmohammed","doi":"10.1109/ICMWI.2010.5648051","DOIUrl":"https://doi.org/10.1109/ICMWI.2010.5648051","url":null,"abstract":"In this paper, we present a model based on the Neural Network (NN) for classifying Arabic texts. We propose the use of Singular Value Decomposition (SVD) as a preprocessor of NN with the aim of further reducing data in terms of both size and dimensionality. Indeed, the use of SVD makes data more amenable to classification and the convergence training process faster. Specifically, the effectiveness of the Multilayer Perceptron (MLP) and the Radial Basis Function (RBF) classifiers are implemented. Experiments are conducted using an in-house corpus of Arabic texts. Precision, recall and F-measure are used to quantify categorization effectiveness. The results show that the proposed SVD-Supported MLP/RBF ANN classifier is able to achieve high effectiveness. Experimental results also show that the MLP classifier outperforms the RBF classifier and that the SVD-supported NN classifier is better than the basic NN, as far as Arabic text categorization is concerned.","PeriodicalId":404577,"journal":{"name":"2010 International Conference on Machine and Web Intelligence","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128436827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}