{"title":"An Approach of Context Ontology for Robust Face Recognition Against Illumination Variations","authors":"M. RezaulBashar, Yan Li, P. Rhee","doi":"10.1109/ICICT.2007.375351","DOIUrl":"https://doi.org/10.1109/ICICT.2007.375351","url":null,"abstract":"This paper proposes a face recognition method that is robust against image variations due to arbitrary lighting condition. Though many researches have been carried out on face recognition system, however; there exist some limitations such as illumination, pose, alignment, occlusion, etc. This paper presents a context ontology model making a robust face recognition system on different illumination situations. Our proposed system works on two phases: environmental context ontology building (modelling) and recognition using context ontology. Context ontology is built using context acquisition, context learning and context categorization. The recognition approach is implemented on illumination variant face recognition that takes identified context as input and performs recognition with usual process such as preprocessing, feature extraction, learning, and recognition. We have tested the recognition performance of our proposed model with an international standard FERET face database (our produced synthesized FERET images) and we have achieved a success rate of more than 92%.","PeriodicalId":206443,"journal":{"name":"2007 International Conference on Information and Communication Technology","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115525821","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":"Current Research on Planar Graphs","authors":"M. Rahman","doi":"10.1109/ICICT.2007.375362","DOIUrl":"https://doi.org/10.1109/ICICT.2007.375362","url":null,"abstract":"A graph consists of a set of vertices and a set of edges, each joining two vertices. A graph is planar if it can be embedded in the plane so that no two edges intersect geometrically except at a vertex to which they are both incident. A plane graph is a planar graph with a fixed embedding. Planar graphs have attracted computer scientists' interest due to their enormous applications, and a lot of interesting algorithms and complexity results have been obtained for planar graphs. In this talk we survey the results on planar graphs.","PeriodicalId":206443,"journal":{"name":"2007 International Conference on Information and Communication Technology","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116203203","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}
K.N. Shiv Subramaniam, S. Raj Bharath, S. Ravinder
{"title":"Improved Authentication Mechanism Using Keystroke Analysis","authors":"K.N. Shiv Subramaniam, S. Raj Bharath, S. Ravinder","doi":"10.1109/ICICT.2007.375389","DOIUrl":"https://doi.org/10.1109/ICICT.2007.375389","url":null,"abstract":"In this paper, a new methodology has been proposed by which the keystroke analysis can be combined with the existing authentication mechanisms through keyboard to improve the security of delicate applications to a very high extent. It can be useful to ascertain the intruders and reject them from the system, provided that we are able to deal with the typing rhythms of the intruders. Unlike other techniques, keystroke sampling does not require any specific hardware or software tool but just the computer in which the user enters text. Our approach can rely on what is typed by people because of their normal job, preferably username and password, and show attractive accuracies. As a consequence, we argue that our method can be used as a complementary way for user authentication and as an aid to intrusion detection to improve computer security.","PeriodicalId":206443,"journal":{"name":"2007 International Conference on Information and Communication Technology","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121217400","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":"Modeling for Performamnce: SystemC Model of A Communication Bus in A Distributed Network","authors":"S.M. Mahfuzul, J. Tran","doi":"10.1109/ICICT.2007.375382","DOIUrl":"https://doi.org/10.1109/ICICT.2007.375382","url":null,"abstract":"The enormous complexity of today's electronics and communication systems warrants the use of efficient system-level modelling techniques. SystemC has recently emerged as an efficient system-level modelling language. This paper presents the suitability of SystemC for modelling a serial communication bus typically employed in a complex distributed network. The highest level of abstraction in SystemC, called the functional level, is used to develop and analyse a model of the bus. SystemC offers flexibility in modelling the communication bus at this level of abstraction using unique SystemC features while providing increased model efficiency. The data bus model has been validated for various payloads and system size.","PeriodicalId":206443,"journal":{"name":"2007 International Conference on Information and Communication Technology","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127825998","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}
M. T. Islam, Durgaprasad Bollina, Abhaya C. Nayak, Shoba Ranganathan
{"title":"Intelligent Agent System for Bio-medical Literature Mining","authors":"M. T. Islam, Durgaprasad Bollina, Abhaya C. Nayak, Shoba Ranganathan","doi":"10.1109/ICICT.2007.375342","DOIUrl":"https://doi.org/10.1109/ICICT.2007.375342","url":null,"abstract":"With the advances of World Wide Web technology and advanced research in bioinformatics and systems biology domain has highlighted the increasing need for automatic information extraction [IE] system to extract information from scientific literature databases. Extraction of scientific information in biomedical articles is a central task for supporting biomarker discovery efforts. In this paper, we propose an algorithm that is capable of extracting scientific information on biomarker like gene, genome, disease, allele, cell etc from the text by finding out the focal topic of the document and extracting the most relevant properties of that topic. The topic and its properties are represented as semantic networks and then stored in a database. This IE algorithm will extract the most important biological terms and relation by statistical and pattern matching NLP techniques. This IE tool expected to help the researchers to get the latest information on biomarker discovery and its other biomedical research advances. We show preliminary results, demonstrating that the method has a strong potential to biomarker discovery methods.","PeriodicalId":206443,"journal":{"name":"2007 International Conference on Information and Communication Technology","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123727903","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":"Lexical Semantics: A Newapproach to Analyze the Bangla Sentence with Semantic Features","authors":"MohammedMoshiul Hoque","doi":"10.1109/ICICT.2007.375348","DOIUrl":"https://doi.org/10.1109/ICICT.2007.375348","url":null,"abstract":"Semantics is concerned with the meaning of words and a word with semantic features is corresponding to their sense component. Associating words with semantic features is useful in the field of machine translation. This paper present a methodology for analysis the Bangla sentences in semantic manner. This paper also focuses on the several primitive semantic features of Bangla words that are necessary for semantic analysis. Semantic features are shown in a tabular fashion with values indicating whether the features or inverse features are applicable and also whatever the features are redundant. Context free grammar and top-down approach have been used for the purpose of generating annotated parse tree with distinct semantic features in this paper. Model is tested for simple sentence of Bangla and test results reflect the successful results for most of the test cases.","PeriodicalId":206443,"journal":{"name":"2007 International Conference on Information and Communication Technology","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128194892","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}
M. Akbar, Muhammad Khairul Ali Hassan, E. Manning, G. Shoja
{"title":"A Call Admission Protocol of Service Level Agreement in Enterprise Network","authors":"M. Akbar, Muhammad Khairul Ali Hassan, E. Manning, G. Shoja","doi":"10.1109/ICICT.2007.375403","DOIUrl":"https://doi.org/10.1109/ICICT.2007.375403","url":null,"abstract":"The admission of multimedia streams with a particular and guaranteed level of QoS (Quality of Service) from source to destination with the goal of increasing revenue is challenging in multimedia communications over IP (Internet Protocol) networks. In this paper, we present SLA (Service Level Agreement) as an agreement between users and network operators, for the transmission of a multimedia stream with several choices of QoS level. Control of the admission of SLAs, to achieve maximum revenue while fully respecting QoS guarantees, is called SLA admission control. We present a scalable algorithm for the admission of SLAs.","PeriodicalId":206443,"journal":{"name":"2007 International Conference on Information and Communication Technology","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133539626","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}
Y. Mansouri, M. Moallemi, A. Rasoulifard, H. Deldari
{"title":"A Broadcast Fault-Tolerant Hierarchical Token-Based Mutual Exclusion Algorithm","authors":"Y. Mansouri, M. Moallemi, A. Rasoulifard, H. Deldari","doi":"10.1109/ISCIT.2006.339910","DOIUrl":"https://doi.org/10.1109/ISCIT.2006.339910","url":null,"abstract":"Fault tolerance is a key feature for every grid based algorithm. In this paper we have proposed a fault tolerance technique for hierarchical mutual exclusion problem solver algorithm. This algorithm is based on Naimi-Trehel's token-based mutual exclusion algorithm. Our algorithm uses some intra cluster broadcasts to achieve this end and tolerate N-l permanent crashes of N nodes. We have also proposed a sketch of the proof for our algorithm and its integrity.","PeriodicalId":206443,"journal":{"name":"2007 International Conference on Information and Communication Technology","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115221377","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}