Pub Date : 2007-03-05DOI: 10.1109/RIVF.2007.369161
S. Bonnevay, Jérôme Champavère, M. Lamure
Game theory is a mathematical formalism dealing with problem of competition between players. In cooperative games, players can negotiate and form coalitions to optimize their own gains. The theory gives some mathematical solutions, but not explains how coalitions will be formed. This paper describes a negotiation platform used to test various dynamics in a cooperative game theory setting. We focus our attention on dynamic of coalition formation between players. Players are described by three features: attraction for gain, risk aversion and strength of character. These features are used to define rationalities of players for negotiations. Simulations are performed and described with different combinations of players' behaviors. Some first results of coalitions gains distribution are displayed versus mathematical game theory solutions.
{"title":"Negotiation platform based on game theory","authors":"S. Bonnevay, Jérôme Champavère, M. Lamure","doi":"10.1109/RIVF.2007.369161","DOIUrl":"https://doi.org/10.1109/RIVF.2007.369161","url":null,"abstract":"Game theory is a mathematical formalism dealing with problem of competition between players. In cooperative games, players can negotiate and form coalitions to optimize their own gains. The theory gives some mathematical solutions, but not explains how coalitions will be formed. This paper describes a negotiation platform used to test various dynamics in a cooperative game theory setting. We focus our attention on dynamic of coalition formation between players. Players are described by three features: attraction for gain, risk aversion and strength of character. These features are used to define rationalities of players for negotiations. Simulations are performed and described with different combinations of players' behaviors. Some first results of coalitions gains distribution are displayed versus mathematical game theory solutions.","PeriodicalId":158887,"journal":{"name":"2007 IEEE International Conference on Research, Innovation and Vision for the Future","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126690397","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}
Pub Date : 2007-03-05DOI: 10.1109/RIVF.2007.369170
N. Nhan
The XML medical knowledge representation (XMKR) is not a coding system, rather it is a medical knowledge system that tags the different manifestations of codified medical knowledge as they appear in text documents and models different medical systems appearing in text documents. The XMKR tagged documents can be viewed in different styles according to the needs of users.
{"title":"A natural language oriented XML knowledge representation for medical documents","authors":"N. Nhan","doi":"10.1109/RIVF.2007.369170","DOIUrl":"https://doi.org/10.1109/RIVF.2007.369170","url":null,"abstract":"The XML medical knowledge representation (XMKR) is not a coding system, rather it is a medical knowledge system that tags the different manifestations of codified medical knowledge as they appear in text documents and models different medical systems appearing in text documents. The XMKR tagged documents can be viewed in different styles according to the needs of users.","PeriodicalId":158887,"journal":{"name":"2007 IEEE International Conference on Research, Innovation and Vision for the Future","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123182972","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}
Pub Date : 2007-03-05DOI: 10.1109/RIVF.2007.369167
Cong Duy Vu Hoang, Dinh Dien, N. Nguyen, H. Ngo
Text classification concerns the problem of automatically assigning given text passages (or documents) into predefined categories (or topics). Whereas a wide range of methods have been applied to English text classification, relatively few studies have been done on Vietnamese text classification. Based on a Vietnamese news corpus, we present two different approaches for the Vietnamese text classification problem. By using the Bag Of Words - BOW and Statistical N-Gram Language Modeling - N-Gram approaches we were able to evaluate these two widely used classification approaches for our task and showed that these approaches could achieve an average of >95% accuracy with an average 79 minutes classifying time for about 14,000 documents (3 docs/sec). Additionally, we also analyze the advantages and disadvantages of each approach to find out the best method in specific circumstances.
{"title":"A Comparative Study on Vietnamese Text Classification Methods","authors":"Cong Duy Vu Hoang, Dinh Dien, N. Nguyen, H. Ngo","doi":"10.1109/RIVF.2007.369167","DOIUrl":"https://doi.org/10.1109/RIVF.2007.369167","url":null,"abstract":"Text classification concerns the problem of automatically assigning given text passages (or documents) into predefined categories (or topics). Whereas a wide range of methods have been applied to English text classification, relatively few studies have been done on Vietnamese text classification. Based on a Vietnamese news corpus, we present two different approaches for the Vietnamese text classification problem. By using the Bag Of Words - BOW and Statistical N-Gram Language Modeling - N-Gram approaches we were able to evaluate these two widely used classification approaches for our task and showed that these approaches could achieve an average of >95% accuracy with an average 79 minutes classifying time for about 14,000 documents (3 docs/sec). Additionally, we also analyze the advantages and disadvantages of each approach to find out the best method in specific circumstances.","PeriodicalId":158887,"journal":{"name":"2007 IEEE International Conference on Research, Innovation and Vision for the Future","volume":"125 38","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114046877","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}
Pub Date : 2007-03-05DOI: 10.1109/RIVF.2007.369169
A. Aussem, Sergio Rodrigues de Morais, M. Corbex
Learning the structure of a Bayesian network from a data set is NP-hard. In this paper, we discuss a novel heuristic called polynomial max-min skeleton (PMMS) developed by Tsamardinos et al. in 2005. PMMS was proved by extensive empirical simulations to be an excellent trade-off between time and quality of reconstruction compared to all constraint based algorithms, especially for the smaller sample sizes. Unfortunately, there are two main problems with PMMS : it is unable to deal with missing data nor with datasets containing functional dependencies between variables. In this paper, we propose a way to overcome these problems. The new version of PMMS is first applied on standard benchmarks to recover the original structure from data. The algorithm is then applied on the nasopharyngeal carcinoma (NPC) made up from only 1289 uncomplete records in order to shed some light into the statistical profile of the population under study.
{"title":"Analysis of Nasopharyngeal Carcinoma Data with a Novel Bayesian Network Learning Algorithm","authors":"A. Aussem, Sergio Rodrigues de Morais, M. Corbex","doi":"10.1109/RIVF.2007.369169","DOIUrl":"https://doi.org/10.1109/RIVF.2007.369169","url":null,"abstract":"Learning the structure of a Bayesian network from a data set is NP-hard. In this paper, we discuss a novel heuristic called polynomial max-min skeleton (PMMS) developed by Tsamardinos et al. in 2005. PMMS was proved by extensive empirical simulations to be an excellent trade-off between time and quality of reconstruction compared to all constraint based algorithms, especially for the smaller sample sizes. Unfortunately, there are two main problems with PMMS : it is unable to deal with missing data nor with datasets containing functional dependencies between variables. In this paper, we propose a way to overcome these problems. The new version of PMMS is first applied on standard benchmarks to recover the original structure from data. The algorithm is then applied on the nasopharyngeal carcinoma (NPC) made up from only 1289 uncomplete records in order to shed some light into the statistical profile of the population under study.","PeriodicalId":158887,"journal":{"name":"2007 IEEE International Conference on Research, Innovation and Vision for the Future","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123971815","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}
Pub Date : 2007-03-05DOI: 10.1109/RIVF.2007.369164
Do Phuc, Nguyen Thi My Phung
In this paper, we would like to present how to classify Vietnamese messages on the online forum. We use the naive Bayes model for building a classifier. Besides, we also utilize natural language processing (NLP) tools for word segmentation, POS tagging, noun phrase chunking, extracting the nouns and noun phrases in message. These nouns and noun phrases are used for representing the message. With the representation model based on nouns and noun phrases, we improve the accuracy of classification with the support of semantic relations between words.
{"title":"Using Naïve Bayes Model and Natural Language Processing for Classifying Messages on Online Forum","authors":"Do Phuc, Nguyen Thi My Phung","doi":"10.1109/RIVF.2007.369164","DOIUrl":"https://doi.org/10.1109/RIVF.2007.369164","url":null,"abstract":"In this paper, we would like to present how to classify Vietnamese messages on the online forum. We use the naive Bayes model for building a classifier. Besides, we also utilize natural language processing (NLP) tools for word segmentation, POS tagging, noun phrase chunking, extracting the nouns and noun phrases in message. These nouns and noun phrases are used for representing the message. With the representation model based on nouns and noun phrases, we improve the accuracy of classification with the support of semantic relations between words.","PeriodicalId":158887,"journal":{"name":"2007 IEEE International Conference on Research, Innovation and Vision for the Future","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117028405","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}
Pub Date : 2007-03-05DOI: 10.1109/RIVF.2007.369162
Nguyen Thanh Tri, Minh Le Nguyen, Akira Shimazu
Question classification is an important phase in question answering systems. In this paper, we propose to apply i) hierarchical classifiers, ii) hierarchical classifiers in combination with semi-supervised learning and iii) hierarchy expansion for question classification for improving the precision. When the number of classes is large, the performance of classification algorithms may be affected. In order to improve the performance by reducing the number of classes for each classifier, we propose to use hierarchical classifiers according to the question taxonomy, in which each internal node is attached a classifier. We try to use semi-supervised learning to consume unlabeled questions with expectation to improve the performance of classifiers in the hierarchy. We explored different applications of learning methods in for each classifier of the hierarchy: a) supervised learning for all classifiers at all levels; b) semi-supervised learning for the first-level classifier and supervised learning for other classifiers; c) semi-supervised learning for all classifiers. The experiments show that the first method (a) has better results than those of flat classification; the second method (b) produces better results than those of the first method while the effort to increase the performance of fine classifiers in the last method (c) is not so successful. As another effort, we propose to automatically group question classes by clustering in order to expand a node which has a large number of classes in the question taxonomy. The experiment also shows that the overall precision is improved.
{"title":"Improving the Accuracy of Question Classification with Machine Learning","authors":"Nguyen Thanh Tri, Minh Le Nguyen, Akira Shimazu","doi":"10.1109/RIVF.2007.369162","DOIUrl":"https://doi.org/10.1109/RIVF.2007.369162","url":null,"abstract":"Question classification is an important phase in question answering systems. In this paper, we propose to apply i) hierarchical classifiers, ii) hierarchical classifiers in combination with semi-supervised learning and iii) hierarchy expansion for question classification for improving the precision. When the number of classes is large, the performance of classification algorithms may be affected. In order to improve the performance by reducing the number of classes for each classifier, we propose to use hierarchical classifiers according to the question taxonomy, in which each internal node is attached a classifier. We try to use semi-supervised learning to consume unlabeled questions with expectation to improve the performance of classifiers in the hierarchy. We explored different applications of learning methods in for each classifier of the hierarchy: a) supervised learning for all classifiers at all levels; b) semi-supervised learning for the first-level classifier and supervised learning for other classifiers; c) semi-supervised learning for all classifiers. The experiments show that the first method (a) has better results than those of flat classification; the second method (b) produces better results than those of the first method while the effort to increase the performance of fine classifiers in the last method (c) is not so successful. As another effort, we propose to automatically group question classes by clustering in order to expand a node which has a large number of classes in the question taxonomy. The experiment also shows that the overall precision is improved.","PeriodicalId":158887,"journal":{"name":"2007 IEEE International Conference on Research, Innovation and Vision for the Future","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129397055","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}
Pub Date : 2007-03-05DOI: 10.1109/RIVF.2007.369140
Thuy Thi Nguyen, H. Grabner, B. Gruber, H. Bischof
In this paper, we present a new approach for automatic car detection from aerial images. The system exploits a robust machine learning method known as boosting for efficient car detection from high resolution aerial images. We propose to use on-line boosting with interactive training framework to efficiently train and improve the detector. We use integral images for fast computation of features. This also allows to perform exhaustive search for detection of cars after training. For post processing, we employ a mean shift clustering method, which improves the detection rate significantly. In contrast to related work, our framework does not rely on any priori knowledge of the image like a site-model or contextual information, but if necessary this information can be incorporated. An extensive set of experiments on high resolution aerial images using the new UltraCamD shows the superiority of our approach.
{"title":"On-line Boosting for Car Detection from Aerial Images","authors":"Thuy Thi Nguyen, H. Grabner, B. Gruber, H. Bischof","doi":"10.1109/RIVF.2007.369140","DOIUrl":"https://doi.org/10.1109/RIVF.2007.369140","url":null,"abstract":"In this paper, we present a new approach for automatic car detection from aerial images. The system exploits a robust machine learning method known as boosting for efficient car detection from high resolution aerial images. We propose to use on-line boosting with interactive training framework to efficiently train and improve the detector. We use integral images for fast computation of features. This also allows to perform exhaustive search for detection of cars after training. For post processing, we employ a mean shift clustering method, which improves the detection rate significantly. In contrast to related work, our framework does not rely on any priori knowledge of the image like a site-model or contextual information, but if necessary this information can be incorporated. An extensive set of experiments on high resolution aerial images using the new UltraCamD shows the superiority of our approach.","PeriodicalId":158887,"journal":{"name":"2007 IEEE International Conference on Research, Innovation and Vision for the Future","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125366521","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}
Pub Date : 2007-03-05DOI: 10.1109/RIVF.2007.369157
Son N. Nguyen, M. Orlowska
Sequential patterns mining has been explored for various data types, and its computational complexity is well understood. There are well-known methods to deal effectively with computational problems such as GSP [1] and PrefixSpan [2]. However, most methods show limited performance due to the exponential number of growing patterns. Moreover when the input data set is very large, it is unsolvable because of main memory limitation. This paper shows a partition-based approach to overcome this drawback, and to provide further performance enhancements of sequential patterns computation. Furthermore, the partition-based approach can be extended to the parallel paradigm of mining sequential patterns. We have made a series of observations that has led us to invent data pre-processing methods such that the final step of the partition-based algorithm, where a combination of all local candidate patterns must be processed, is executed on substantially smaller input data. This paper shows results from several experiments that confirmed our general and formally presented observations.
{"title":"A Partition-Based Approach for Sequential Patterns Mining","authors":"Son N. Nguyen, M. Orlowska","doi":"10.1109/RIVF.2007.369157","DOIUrl":"https://doi.org/10.1109/RIVF.2007.369157","url":null,"abstract":"Sequential patterns mining has been explored for various data types, and its computational complexity is well understood. There are well-known methods to deal effectively with computational problems such as GSP [1] and PrefixSpan [2]. However, most methods show limited performance due to the exponential number of growing patterns. Moreover when the input data set is very large, it is unsolvable because of main memory limitation. This paper shows a partition-based approach to overcome this drawback, and to provide further performance enhancements of sequential patterns computation. Furthermore, the partition-based approach can be extended to the parallel paradigm of mining sequential patterns. We have made a series of observations that has led us to invent data pre-processing methods such that the final step of the partition-based algorithm, where a combination of all local candidate patterns must be processed, is executed on substantially smaller input data. This paper shows results from several experiments that confirmed our general and formally presented observations.","PeriodicalId":158887,"journal":{"name":"2007 IEEE International Conference on Research, Innovation and Vision for the Future","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129138726","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}
Pub Date : 2007-03-05DOI: 10.1109/RIVF.2007.369144
A. Bui, D. Sohier
This article presents the first algorithm to compute meeting times in a graph, and illustrates this computation by giving a full analysis of the Israeli and Jalfon random walk based distributed mutual exclusion algorithm. This allows comparisons between this algorithm and others self-stabilizing distributed mutual exclusion algorithm in terms of average times to access the critical resource and stabilization times, and also in terms of message complexity. This can give an objective criterion to the trade-off between time complexity and message complexity.
{"title":"Stabilization Time for Token Replications in Self-Stabilizing Random Walk Based Distributed Algorithms","authors":"A. Bui, D. Sohier","doi":"10.1109/RIVF.2007.369144","DOIUrl":"https://doi.org/10.1109/RIVF.2007.369144","url":null,"abstract":"This article presents the first algorithm to compute meeting times in a graph, and illustrates this computation by giving a full analysis of the Israeli and Jalfon random walk based distributed mutual exclusion algorithm. This allows comparisons between this algorithm and others self-stabilizing distributed mutual exclusion algorithm in terms of average times to access the critical resource and stabilization times, and also in terms of message complexity. This can give an objective criterion to the trade-off between time complexity and message complexity.","PeriodicalId":158887,"journal":{"name":"2007 IEEE International Conference on Research, Innovation and Vision for the Future","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116367966","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}
Pub Date : 2007-03-05DOI: 10.1109/RIVF.2007.369159
Saber Zrelli, T. Medeni, Y. Shinoda, I. T. Medeni
In this paper, we clarify the role of authentication systems as building blocks for Knowledge Technologies that constitutes the basis of an evolvable and trustworthy e-society. Such frameworks support the trustworthy cross-realm collaboration and user-friendly service provision through proper measures of authentication, privacy, integrity and secrecy of information. We define the requirements that such authentication systems must fulfill. Then, we present Kerberos as a candidate. We overview the basic operations and the cross-realm authentication model of Kerberos. Then we present the XKDCP extension as a solution for scalability and reliability issues in Kerberos cross-realm operations. With the proposed enhancements , we have achieved our goal on selecting an authentication system that matches the requirements for evolvable and verifiable e-society.
{"title":"Improving Kerberos Security System for Cross-Realm Collaborative Interactions: An Innovative Example of Knowledge Technology for Evolving & Verifiable E-Society","authors":"Saber Zrelli, T. Medeni, Y. Shinoda, I. T. Medeni","doi":"10.1109/RIVF.2007.369159","DOIUrl":"https://doi.org/10.1109/RIVF.2007.369159","url":null,"abstract":"In this paper, we clarify the role of authentication systems as building blocks for Knowledge Technologies that constitutes the basis of an evolvable and trustworthy e-society. Such frameworks support the trustworthy cross-realm collaboration and user-friendly service provision through proper measures of authentication, privacy, integrity and secrecy of information. We define the requirements that such authentication systems must fulfill. Then, we present Kerberos as a candidate. We overview the basic operations and the cross-realm authentication model of Kerberos. Then we present the XKDCP extension as a solution for scalability and reliability issues in Kerberos cross-realm operations. With the proposed enhancements , we have achieved our goal on selecting an authentication system that matches the requirements for evolvable and verifiable e-society.","PeriodicalId":158887,"journal":{"name":"2007 IEEE International Conference on Research, Innovation and Vision for the Future","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115472523","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：