Abstract With the internet growing at an exponential rate the web is increasingly hosting web pages in different languages. Hence it becomes essential for the search engines to be able to search information stored in a specific language. The native users also tend to look for any information on web nowadays. This leads to the need of effective search mechanisms to... With the internet growing at an exponential rate the web is increasingly hosting web pages in different languages. Hence it becomes essential for the search engines to be able to search information stored in a specific language. The native users also tend to look for any information on web nowadays. This leads to the need of effective search mechanisms to fulfill native user’s needs and provide them information in their native languages. The most preferred language for web information access is English Language but the growth and popularity of internet in countries like China, India, Russia Middle East and south Asia has lead to the importance of IR in Languages other than English. There has been a great increase in Indian content particularly Hindi on the Internet but retrieval of Hindi information is a complex task because of the various reasons such as Phonetic nature of Hindi language, morphology, word synonyms, ambiguous words etc. Influence of regional and foreign languages especially English on Hindi has been observed as a major factor hindering the performance of IR in Hindi language. The objective of the paper and present research is to study the effect of English on Hindi IR. This paper covers the comprehensive analysis of the influence of English Language on Hindi IR and its effect on performance of search engines supporting HindiLanguage. Read More Read Less

Abstract This paper proposes an innovative approach to improve the classification performance of Persian texts. Theproposed method uses a thesaurus as a helpful knowledge to obtain more representative word-frequencies in the corpus. Twotypes of word relationships are considered in our used thesaurus. This is the first attempt to use a Persian thesaurus in thefield of Persian information retrieval. Experimental results indicate... This paper proposes an innovative approach to improve the classification performance of Persian texts. Theproposed method uses a thesaurus as a helpful knowledge to obtain more representative word-frequencies in the corpus. Twotypes of word relationships are considered in our used thesaurus. This is the first attempt to use a Persian thesaurus in thefield of Persian information retrieval. Experimental results indicate the performance of text classification improves significantlyin the case of employing Persian thesaurus rather the case of ignoring Persian thesaurus. Read More Read Less

Abstract The maintenance of industrial systems is crucial for productivity, products quality and supplied services. Numerouscomputer systems are therefore developed for the task and must, in most cases, collaborate with each other. In the light of thisstatement, our work aims at realizing a system which consists in gathering the knowledge and the know-how in the field of faultdiagnosis for steam turbines,... The maintenance of industrial systems is crucial for productivity, products quality and supplied services. Numerouscomputer systems are therefore developed for the task and must, in most cases, collaborate with each other. In the light of thisstatement, our work aims at realizing a system which consists in gathering the knowledge and the know-how in the field of faultdiagnosis for steam turbines, by the construction of domain ontology. In order to better exploit the ontology and reason usingits classes, sub-classes and instances a Case Based Reasoning (CBR) paradigm is chosen, as it offers an ideal solution fordiagnostic of real application systems. The paper, therefore, presents a current work which has for objective to develop a CBRapplication for fault diagnosis based on ontology, by using the API JColibri. Read More Read Less

Abstract We propose a new modeling approach in Automatic Speaker Verification A.S.V based on Gaussians Mixtures Models and Maximum a posteriori adaptation MAP. We propose clustering algorithm for intra and inter speaker’s variability in voice module and contribute for Universal Speaker Model design. We compare the traditional approach which uses one specific customer model with the second called Universal speaker model... We propose a new modeling approach in Automatic Speaker Verification A.S.V based on Gaussians Mixtures Models and Maximum a posteriori adaptation MAP. We propose clustering algorithm for intra and inter speaker’s variability in voice module and contribute for Universal Speaker Model design. We compare the traditional approach which uses one specific customer model with the second called Universal speaker model USM (customers families). Voice module is applied for characterizing customers only; Universal Speaker Model is applied when speaker model is weak and designed for computing a reliable score. Read More Read Less