Cash amounts and interest rates are usually estimated by using educated guesses based on expected values or other statistical techniques to obtain them. Fuzzy numbers can capture the difficulties in estimating these parameters. Fuzzy present value, fuzzy equivalent uniform annual value, fuzzy future value, fuzzy benefit-cost ratio, and fuzzy payback period are the methods examined with numeric examples in the paper. The paper also gives the ranking methods of fuzzy numbers.
{"title":"Capital budgeting techniques under fuzzy information","authors":"C. Kahraman, E. Tolga","doi":"10.1109/TAI.1998.744850","DOIUrl":"https://doi.org/10.1109/TAI.1998.744850","url":null,"abstract":"Cash amounts and interest rates are usually estimated by using educated guesses based on expected values or other statistical techniques to obtain them. Fuzzy numbers can capture the difficulties in estimating these parameters. Fuzzy present value, fuzzy equivalent uniform annual value, fuzzy future value, fuzzy benefit-cost ratio, and fuzzy payback period are the methods examined with numeric examples in the paper. The paper also gives the ranking methods of fuzzy numbers.","PeriodicalId":424568,"journal":{"name":"Proceedings Tenth IEEE International Conference on Tools with Artificial Intelligence (Cat. No.98CH36294)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128189426","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}
This paper addresses the issues of intelligibility, classification speed, and required space in majority voting classifiers. Methods that classify unknown cases using multiple classifiers (e.g. bagging, boosting) have been actively studied in recent years. Since these methods classify a case by taking majority voting over the classifiers, the reasons behind the decision cannot be described in a logical form. Moreover, a large number of classifiers is needed to significantly improve the accuracy. This greatly increases the amount of time and space needed in classification. To solve these problems, a method for learning a single decision tree that approximates the majority voting classifiers is proposed in this paper. The proposed method generates if-then rules from each classifier, and then learns a single decision tree from these rules. Experimental results show that the decision trees by our method are considerably compact and have similar accuracy compared to bagging. Moreover, the proposed method is 8 to 24 times faster than bagging in classification.
{"title":"Turning majority voting classifiers into a single decision tree","authors":"Y. Akiba, S. Kaneda, H. Almuallim","doi":"10.1109/TAI.1998.744847","DOIUrl":"https://doi.org/10.1109/TAI.1998.744847","url":null,"abstract":"This paper addresses the issues of intelligibility, classification speed, and required space in majority voting classifiers. Methods that classify unknown cases using multiple classifiers (e.g. bagging, boosting) have been actively studied in recent years. Since these methods classify a case by taking majority voting over the classifiers, the reasons behind the decision cannot be described in a logical form. Moreover, a large number of classifiers is needed to significantly improve the accuracy. This greatly increases the amount of time and space needed in classification. To solve these problems, a method for learning a single decision tree that approximates the majority voting classifiers is proposed in this paper. The proposed method generates if-then rules from each classifier, and then learns a single decision tree from these rules. Experimental results show that the decision trees by our method are considerably compact and have similar accuracy compared to bagging. Moreover, the proposed method is 8 to 24 times faster than bagging in classification.","PeriodicalId":424568,"journal":{"name":"Proceedings Tenth IEEE International Conference on Tools with Artificial Intelligence (Cat. No.98CH36294)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123870554","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}
The utilization of spatial ontologies to representing and reasoning about real-world problems exhibits some advantages when compared with traditional approaches. Namely reification, flexibility, efficiency and process understanding are considerably improved. However, the search mechanism, which underlies the reasoning process, always has exponential complexity, mainly because real-world problems produce models with high branching factors and solution depths. Therefore, the study and implementation of control strategies and cooperation among them are essential to meet the challenge of search complexity reduction. In particular, improvements on two fundamental steps of the process-successor generation and state completion can reduce drastically the search effort. In this paper, some search strategies are introduced, such as the utilization factor and the use of several lists of open nodes. Some classical approaches as sub-goaling and heuristic search are applied to the problem of controlling the process of reasoning about spatial ontologies. The other aim of this paper is to discussing some kinds of cooperation among the previous search strategies to reaching a search complexity reduction. The proposed search strategies were incorporated in a reasoner implemented in Prolog, whose performance has shown drastical improvements.
{"title":"Search strategies for reasoning about spatial ontologies","authors":"J. Pais, C. Pinto-Ferreira","doi":"10.1109/TAI.1998.744880","DOIUrl":"https://doi.org/10.1109/TAI.1998.744880","url":null,"abstract":"The utilization of spatial ontologies to representing and reasoning about real-world problems exhibits some advantages when compared with traditional approaches. Namely reification, flexibility, efficiency and process understanding are considerably improved. However, the search mechanism, which underlies the reasoning process, always has exponential complexity, mainly because real-world problems produce models with high branching factors and solution depths. Therefore, the study and implementation of control strategies and cooperation among them are essential to meet the challenge of search complexity reduction. In particular, improvements on two fundamental steps of the process-successor generation and state completion can reduce drastically the search effort. In this paper, some search strategies are introduced, such as the utilization factor and the use of several lists of open nodes. Some classical approaches as sub-goaling and heuristic search are applied to the problem of controlling the process of reasoning about spatial ontologies. The other aim of this paper is to discussing some kinds of cooperation among the previous search strategies to reaching a search complexity reduction. The proposed search strategies were incorporated in a reasoner implemented in Prolog, whose performance has shown drastical improvements.","PeriodicalId":424568,"journal":{"name":"Proceedings Tenth IEEE International Conference on Tools with Artificial Intelligence (Cat. No.98CH36294)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122772408","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}
We propose the use of two kinds of constraints in order to control the evaluation of ambiguous structures. The first ones concern the immediate context of the words. In case of ambiguity, these constraints form a network controlling an ambiguous area. The second kind of constraint relies on descriptions of the elementary trees that can be attached to the words. Such descriptions, called unary quasitrees, allow the representation of the dependency relations between the words. They form a proof net on which a filtering method can be applied in order to reduce the number of constraints. The elaboration of the constraint networks and its simplification rely on information available at the lexical level. So, the method presented here simplifies the control of the disambiguation without doing an actual parse and can be reused whatever the linguistic formalism.
{"title":"Proof nets for controlling ambiguity in natural language processing","authors":"P. Blache","doi":"10.1109/TAI.1998.744886","DOIUrl":"https://doi.org/10.1109/TAI.1998.744886","url":null,"abstract":"We propose the use of two kinds of constraints in order to control the evaluation of ambiguous structures. The first ones concern the immediate context of the words. In case of ambiguity, these constraints form a network controlling an ambiguous area. The second kind of constraint relies on descriptions of the elementary trees that can be attached to the words. Such descriptions, called unary quasitrees, allow the representation of the dependency relations between the words. They form a proof net on which a filtering method can be applied in order to reduce the number of constraints. The elaboration of the constraint networks and its simplification rely on information available at the lexical level. So, the method presented here simplifies the control of the disambiguation without doing an actual parse and can be reused whatever the linguistic formalism.","PeriodicalId":424568,"journal":{"name":"Proceedings Tenth IEEE International Conference on Tools with Artificial Intelligence (Cat. No.98CH36294)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125389112","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}
Kevin F. R. Liu, Jonathan Lee, W. Chiang, Stephen J. H. Yang
A framework of integrated expert systems based on fuzzy Petri net, called fuzzy Petri net based expert system (FPNES) are proposed for bridge damage assessment. Major features of FPNES include: reasoning for uncertain and imprecise information; knowledge representation through the use of hierarchical fuzzy Petri nets; reasoning mechanism based on fuzzy Petri nets; and explanation of reasoning process through the use of hierarchical fuzzy Petri nets. FPNES offer several important benefits: (1) providing reasoning mechanism for uncertain and fuzzy information, (2) improving the efficiency of rule based reasoning by constructing relationship of concurrency among rule activation, and (3) explaining how to reach conclusions through the movements of tokens in fuzzy Petri nets. An application to the damage assessment of the Da-Shi bridge in Taiwan is used as an illustrative example of FPNES.
{"title":"FPNES: fuzzy Petri net based expert system for bridges damage assessment","authors":"Kevin F. R. Liu, Jonathan Lee, W. Chiang, Stephen J. H. Yang","doi":"10.1109/TAI.1998.744858","DOIUrl":"https://doi.org/10.1109/TAI.1998.744858","url":null,"abstract":"A framework of integrated expert systems based on fuzzy Petri net, called fuzzy Petri net based expert system (FPNES) are proposed for bridge damage assessment. Major features of FPNES include: reasoning for uncertain and imprecise information; knowledge representation through the use of hierarchical fuzzy Petri nets; reasoning mechanism based on fuzzy Petri nets; and explanation of reasoning process through the use of hierarchical fuzzy Petri nets. FPNES offer several important benefits: (1) providing reasoning mechanism for uncertain and fuzzy information, (2) improving the efficiency of rule based reasoning by constructing relationship of concurrency among rule activation, and (3) explaining how to reach conclusions through the movements of tokens in fuzzy Petri nets. An application to the damage assessment of the Da-Shi bridge in Taiwan is used as an illustrative example of FPNES.","PeriodicalId":424568,"journal":{"name":"Proceedings Tenth IEEE International Conference on Tools with Artificial Intelligence (Cat. No.98CH36294)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116369617","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}
A unified framework is presented for representation and reasoning over qualitative spatial relations. The approach builds on our earlier formalism for handling topological relations (B. El-Geresy, 1997; B. El-Geresy and A. Abdelmoty, 1997). It is shown how the formalism proposed is expressive enough to represent different types of relations in the orientation space, namely, extrinsic and intrinsic and to proximity relations. The approach proposed is applicable to objects of different types and can be used to reason over different space resolutions and granularities of relations. The main advantages of this work is that it offers a unified platform for handling different relations in the qualitative space which is a step towards developing general spatial reasoning engines for large spatial databases.
{"title":"Saving space: a unified approach for representing and reasoning over different qualitative spatial relations","authors":"B. El-Geresy, A. Abdelmoty","doi":"10.1109/TAI.1998.744884","DOIUrl":"https://doi.org/10.1109/TAI.1998.744884","url":null,"abstract":"A unified framework is presented for representation and reasoning over qualitative spatial relations. The approach builds on our earlier formalism for handling topological relations (B. El-Geresy, 1997; B. El-Geresy and A. Abdelmoty, 1997). It is shown how the formalism proposed is expressive enough to represent different types of relations in the orientation space, namely, extrinsic and intrinsic and to proximity relations. The approach proposed is applicable to objects of different types and can be used to reason over different space resolutions and granularities of relations. The main advantages of this work is that it offers a unified platform for handling different relations in the qualitative space which is a step towards developing general spatial reasoning engines for large spatial databases.","PeriodicalId":424568,"journal":{"name":"Proceedings Tenth IEEE International Conference on Tools with Artificial Intelligence (Cat. No.98CH36294)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116202999","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}
C. Lottaz, Djamila Sam-Haroud, B. Faltings, I. Smith
The paper presents SpaceSolver, a constraint satisfaction toolbox, providing access to constraint satisfaction techniques on continuous variables through an intuitive, Web based user interface. Moreover, we describe possible applications of such a platform to collaborative design and conclude that Internet based use of constraint satisfaction techniques has the potential of increasing productivity in several fields in engineering.
{"title":"Constraint techniques for collaborative design","authors":"C. Lottaz, Djamila Sam-Haroud, B. Faltings, I. Smith","doi":"10.1109/TAI.1998.744754","DOIUrl":"https://doi.org/10.1109/TAI.1998.744754","url":null,"abstract":"The paper presents SpaceSolver, a constraint satisfaction toolbox, providing access to constraint satisfaction techniques on continuous variables through an intuitive, Web based user interface. Moreover, we describe possible applications of such a platform to collaborative design and conclude that Internet based use of constraint satisfaction techniques has the potential of increasing productivity in several fields in engineering.","PeriodicalId":424568,"journal":{"name":"Proceedings Tenth IEEE International Conference on Tools with Artificial Intelligence (Cat. No.98CH36294)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125104292","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}
We present a fuzzy information retrieval method based on fuzzy-valued concept networks, where the relevant degree between any two concepts in a fuzzy-valued concept network is represented by arbitrary shapes of fuzzy numbers. There are two kinds of relevant relationships between any two concepts in a fuzzy-valued concept network (i.e., fuzzy positive association and fuzzy negative association). In order to reduce the time of fuzzy inference, the relevant matrices and the relationship matrices are used to model the fuzzy-valued concept networks. The elements of a relevant matrix represent the relevant degrees between concepts. The elements of a relationship matrix represent the relevant relationships between concepts. Furthermore, we also allow users' queries to be represented by arbitrary shapes of fuzzy numbers and to use the fuzzy positive association relationship and the fuzzy negative association relationship for formulating their queries in order to increase the flexibility of fuzzy information retrieval systems. We also present a fuzzy information retrieval method based on the network-type fuzzy-valued concept network architecture in the Internet environment.
{"title":"A fuzzy information retrieval method using fuzzy-valued concept networks","authors":"Y. Horng, Shyi-Ming Chen, Chia-Hoang Lee","doi":"10.1109/TAI.1998.744797","DOIUrl":"https://doi.org/10.1109/TAI.1998.744797","url":null,"abstract":"We present a fuzzy information retrieval method based on fuzzy-valued concept networks, where the relevant degree between any two concepts in a fuzzy-valued concept network is represented by arbitrary shapes of fuzzy numbers. There are two kinds of relevant relationships between any two concepts in a fuzzy-valued concept network (i.e., fuzzy positive association and fuzzy negative association). In order to reduce the time of fuzzy inference, the relevant matrices and the relationship matrices are used to model the fuzzy-valued concept networks. The elements of a relevant matrix represent the relevant degrees between concepts. The elements of a relationship matrix represent the relevant relationships between concepts. Furthermore, we also allow users' queries to be represented by arbitrary shapes of fuzzy numbers and to use the fuzzy positive association relationship and the fuzzy negative association relationship for formulating their queries in order to increase the flexibility of fuzzy information retrieval systems. We also present a fuzzy information retrieval method based on the network-type fuzzy-valued concept network architecture in the Internet environment.","PeriodicalId":424568,"journal":{"name":"Proceedings Tenth IEEE International Conference on Tools with Artificial Intelligence (Cat. No.98CH36294)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131881731","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}
A two-level learning algorithm that decomposes multilayer neural networks into a set of sub-networks is presented. Many popular optimization methods, such as conjugate-gradient and quasi-Newton methods, can be utilized to train these sub-networks. In addition, if the activation functions are hard-limiting functions, the multilayer neural networks can be trained by the perceptron learning rule in this two-level learning algorithm. Two experimental problems are given as examples for this algorithm.
{"title":"Two-level learning algorithm for multilayer neural networks","authors":"Chin-Sung Liu, Ching-Huan Tseng","doi":"10.1109/TAI.1998.744795","DOIUrl":"https://doi.org/10.1109/TAI.1998.744795","url":null,"abstract":"A two-level learning algorithm that decomposes multilayer neural networks into a set of sub-networks is presented. Many popular optimization methods, such as conjugate-gradient and quasi-Newton methods, can be utilized to train these sub-networks. In addition, if the activation functions are hard-limiting functions, the multilayer neural networks can be trained by the perceptron learning rule in this two-level learning algorithm. Two experimental problems are given as examples for this algorithm.","PeriodicalId":424568,"journal":{"name":"Proceedings Tenth IEEE International Conference on Tools with Artificial Intelligence (Cat. No.98CH36294)","volume":"18 24","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133424445","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}
We propose a novel technique to learn concepts from a large set of objects by means of clustering techniques. Unlike conventional approaches, we utilize database scheme knowledge and specify what clusters mean by linking attribute-grouping to object clustering. We propose some sophisticated algorithms (and some extensions) and show how useful they are.
{"title":"Object clustering for scheme learning","authors":"I. Shioya, T. Miura","doi":"10.1109/TAI.1998.744739","DOIUrl":"https://doi.org/10.1109/TAI.1998.744739","url":null,"abstract":"We propose a novel technique to learn concepts from a large set of objects by means of clustering techniques. Unlike conventional approaches, we utilize database scheme knowledge and specify what clusters mean by linking attribute-grouping to object clustering. We propose some sophisticated algorithms (and some extensions) and show how useful they are.","PeriodicalId":424568,"journal":{"name":"Proceedings Tenth IEEE International Conference on Tools with Artificial Intelligence (Cat. No.98CH36294)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132420005","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：