Pub Date : 2009-10-02DOI: 10.1109/FUZZY.2009.5277183
S. Miyamoto, Kenta Arai
Three approaches to extract clusters sequentially so that the specification of the number of clusters beforehand is unnecessary are introduced and four algorithms are developed. First is derived from possibilistic clustering while the second is a variation of the mountain clustering using medoids as cluster representatives. Moreover an algorithm based on the idea of noise clustering is developed. The last idea is applied to sequential extraction of regression models and we have the fourth algorithm. We compare these algorithms using numerical examples.
{"title":"Different sequential clustering algorithms and sequential regression models","authors":"S. Miyamoto, Kenta Arai","doi":"10.1109/FUZZY.2009.5277183","DOIUrl":"https://doi.org/10.1109/FUZZY.2009.5277183","url":null,"abstract":"Three approaches to extract clusters sequentially so that the specification of the number of clusters beforehand is unnecessary are introduced and four algorithms are developed. First is derived from possibilistic clustering while the second is a variation of the mountain clustering using medoids as cluster representatives. Moreover an algorithm based on the idea of noise clustering is developed. The last idea is applied to sequential extraction of regression models and we have the fourth algorithm. We compare these algorithms using numerical examples.","PeriodicalId":117895,"journal":{"name":"2009 IEEE International Conference on Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121958629","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 : 2009-10-02DOI: 10.1109/FUZZY.2009.5277187
Y. Fukusato, S. Sakurai, Siliang Wang, E. Sato-Shimokawara, Toru Yamaguchi
In this research, authors suggested one robot service in "Kukanchi". Therefore the authors developed the module which combined image recognition with voice recognition. By this module, the system recognizes movement and the utterance of the person. Furthermore, the system understands the intention of the person by using robot ontology in recognition contents. The service that understood the intention of the person by this system which authors developed is enabled. In this paper shows an example of the service that used the system.
{"title":"Domestic robot service based on ontology applying environmental information","authors":"Y. Fukusato, S. Sakurai, Siliang Wang, E. Sato-Shimokawara, Toru Yamaguchi","doi":"10.1109/FUZZY.2009.5277187","DOIUrl":"https://doi.org/10.1109/FUZZY.2009.5277187","url":null,"abstract":"In this research, authors suggested one robot service in \"Kukanchi\". Therefore the authors developed the module which combined image recognition with voice recognition. By this module, the system recognizes movement and the utterance of the person. Furthermore, the system understands the intention of the person by using robot ontology in recognition contents. The service that understood the intention of the person by this system which authors developed is enabled. In this paper shows an example of the service that used the system.","PeriodicalId":117895,"journal":{"name":"2009 IEEE International Conference on Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125293681","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 : 2009-10-02DOI: 10.1109/FUZZY.2009.5277188
M. Narita, Y. Murakawa, Chuzo Akiguchi, Y. Kato, Toru Yamaguchi
We, RSi (Robot Service Initiative) organization, have been developing a common network based robot service platform, named RSNP (Robot Service Network Protocol) since 2004. As spreading actual use of RSNP, strong requirements are raised on the push communication in limited conditions such as fewer operators and/or limited resources, and on the robot service integration with various devices supported by the other robot platform, such as RTM (Robot Technology Middleware), particularly. In this paper, we clarified these requirements and solved them by pseudo PUSH communication method, by introducing multimedia/sensor profile and by building RSi/RTM gateway. Moreover, we evaluate the effectiveness of the proposed scheme through the performance experiments. And also these results have been also reflected in RSNP 2.0, the latest specification.
{"title":"Push communication for network robot services and RSi/RTM interoperability","authors":"M. Narita, Y. Murakawa, Chuzo Akiguchi, Y. Kato, Toru Yamaguchi","doi":"10.1109/FUZZY.2009.5277188","DOIUrl":"https://doi.org/10.1109/FUZZY.2009.5277188","url":null,"abstract":"We, RSi (Robot Service Initiative) organization, have been developing a common network based robot service platform, named RSNP (Robot Service Network Protocol) since 2004. As spreading actual use of RSNP, strong requirements are raised on the push communication in limited conditions such as fewer operators and/or limited resources, and on the robot service integration with various devices supported by the other robot platform, such as RTM (Robot Technology Middleware), particularly. In this paper, we clarified these requirements and solved them by pseudo PUSH communication method, by introducing multimedia/sensor profile and by building RSi/RTM gateway. Moreover, we evaluate the effectiveness of the proposed scheme through the performance experiments. And also these results have been also reflected in RSNP 2.0, the latest specification.","PeriodicalId":117895,"journal":{"name":"2009 IEEE International Conference on Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130344875","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 : 2009-10-02DOI: 10.1109/FUZZY.2009.5277362
Yongming Li
In this paper, fuzzy Turing machines with membership degrees in distributive lattices, which are called lattice-valued fuzzy Turing machines, are studied. First several formulations of lattice-valued fuzzy Turing machines, including in particular deterministic and nondeterministic lattice-valued fuzzy Turing machines (l-DTMcs and l-NTMs), are given. It is shown that l-DTMcs and l-NTMs are not equivalent as the acceptors of fuzzy languages. This contrasts sharply with classical Turing machines. Second, it is shown that lattice-valued fuzzy Turing machines can recognize n-r.e. sets in the sense of Bedregal and Figueira, the super-computing power of fuzzy Turing machines is established in the lattice-setting. Third, it is demonstrated that the truth-valued lattice being finite is a necessary and sufficient condition for the existence of a universal lattice-valued fuzzy Turing machine. For an infinite distributive lattice with a compact metric, it is declared that a universal fuzzy Turing machine exists in an approximate sense. This means, for any prescribed accuracy, there is a universal machine that can simulate any lattice-valued fuzzy Turing machine on it with the given accuracy.
{"title":"Lattice-valued fuzzy turing machines and their computing power","authors":"Yongming Li","doi":"10.1109/FUZZY.2009.5277362","DOIUrl":"https://doi.org/10.1109/FUZZY.2009.5277362","url":null,"abstract":"In this paper, fuzzy Turing machines with membership degrees in distributive lattices, which are called lattice-valued fuzzy Turing machines, are studied. First several formulations of lattice-valued fuzzy Turing machines, including in particular deterministic and nondeterministic lattice-valued fuzzy Turing machines (l-DTMcs and l-NTMs), are given. It is shown that l-DTMcs and l-NTMs are not equivalent as the acceptors of fuzzy languages. This contrasts sharply with classical Turing machines. Second, it is shown that lattice-valued fuzzy Turing machines can recognize n-r.e. sets in the sense of Bedregal and Figueira, the super-computing power of fuzzy Turing machines is established in the lattice-setting. Third, it is demonstrated that the truth-valued lattice being finite is a necessary and sufficient condition for the existence of a universal lattice-valued fuzzy Turing machine. For an infinite distributive lattice with a compact metric, it is declared that a universal fuzzy Turing machine exists in an approximate sense. This means, for any prescribed accuracy, there is a universal machine that can simulate any lattice-valued fuzzy Turing machine on it with the given accuracy.","PeriodicalId":117895,"journal":{"name":"2009 IEEE International Conference on Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129938347","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 : 2009-10-02DOI: 10.1109/FUZZY.2009.5277380
H. Ishibuchi, Y. Kaisho, Y. Nojima
Recently fuzzy system design has been frequently formulated as multiobjective optimization problems with two conflicting goals: maximization of accuracy and interpretability. Whereas the formulation of accuracy maximization is usually straightforward in each application task, it is not easy to define the interpretability of fuzzy rule-based systems. As a result, interpretability maximization is often handled as complexity minimization. In this paper, we discuss whether the complexity minimization leads to the interpretability maximization in the design of fuzzy rule-based systems for pattern classification problems. Using very simple artificial test problems, we show that the complexity minimization does not always lead to the interpretability maximization. We also discuss the explanation capability of fuzzy rule-based systems to explain their reasoning results to human users in an understandable manner. We show that the interpretability maximization is closely related to but different from the explanation capability maximization.
{"title":"Complexity, interpretability and explanation capability of fuzzy rule-based classifiers","authors":"H. Ishibuchi, Y. Kaisho, Y. Nojima","doi":"10.1109/FUZZY.2009.5277380","DOIUrl":"https://doi.org/10.1109/FUZZY.2009.5277380","url":null,"abstract":"Recently fuzzy system design has been frequently formulated as multiobjective optimization problems with two conflicting goals: maximization of accuracy and interpretability. Whereas the formulation of accuracy maximization is usually straightforward in each application task, it is not easy to define the interpretability of fuzzy rule-based systems. As a result, interpretability maximization is often handled as complexity minimization. In this paper, we discuss whether the complexity minimization leads to the interpretability maximization in the design of fuzzy rule-based systems for pattern classification problems. Using very simple artificial test problems, we show that the complexity minimization does not always lead to the interpretability maximization. We also discuss the explanation capability of fuzzy rule-based systems to explain their reasoning results to human users in an understandable manner. We show that the interpretability maximization is closely related to but different from the explanation capability maximization.","PeriodicalId":117895,"journal":{"name":"2009 IEEE International Conference on Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132437970","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 : 2009-10-02DOI: 10.1109/FUZZY.2009.5277281
J. Su, Ching-Shun Chen
In advanced semiconductor manufacturing, the in-process wafers need to be monitored periodically in order to obtain high stability and high yield rate. However, the actual measurement is usually obtained after all the work-pieces of the same lot have been processed. The parameter drift or shift of the production equipment could not be detected in real-time thereby increasing the production cost. We proposed a quality prediction system (QPS) based on support vector regression (SVR) and fuzzy learning mechanism (FLM) to overcome this problem. The SVR provided good generalization performance for prediction, and the embedded FLM implied a continuous improvement or at least non-degradation of the system performance in an ever changing environment. The effectiveness of the proposed QPS was validated by test on chemical vapor deposition (CVD) process in practical 12-inch wafer fabrication. The results show that the proposed QPS not only fulfills real-time quality measurement of each wafer, but also detects the performance degradation of the corresponding machines from the information of manufacturing process.
{"title":"Chemical vapor deposition quality prediction system based on support vector regression and fuzzy learning mechanism","authors":"J. Su, Ching-Shun Chen","doi":"10.1109/FUZZY.2009.5277281","DOIUrl":"https://doi.org/10.1109/FUZZY.2009.5277281","url":null,"abstract":"In advanced semiconductor manufacturing, the in-process wafers need to be monitored periodically in order to obtain high stability and high yield rate. However, the actual measurement is usually obtained after all the work-pieces of the same lot have been processed. The parameter drift or shift of the production equipment could not be detected in real-time thereby increasing the production cost. We proposed a quality prediction system (QPS) based on support vector regression (SVR) and fuzzy learning mechanism (FLM) to overcome this problem. The SVR provided good generalization performance for prediction, and the embedded FLM implied a continuous improvement or at least non-degradation of the system performance in an ever changing environment. The effectiveness of the proposed QPS was validated by test on chemical vapor deposition (CVD) process in practical 12-inch wafer fabrication. The results show that the proposed QPS not only fulfills real-time quality measurement of each wafer, but also detects the performance degradation of the corresponding machines from the information of manufacturing process.","PeriodicalId":117895,"journal":{"name":"2009 IEEE International Conference on Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134152514","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 : 2009-10-02DOI: 10.1109/FUZZY.2009.5277282
H. Ishibuchi, Hiroyuki Ohyanagi, Y. Nojima
The iterated prisoner's dilemma (IPD) game has been frequently used to examine the evolution of cooperative behavior among agents in the field of evolutionary computation. A number of factors are known to be related to the evolution of cooperative behavior. One well-known factor is spatial relations among agents. The IPD game is often played in a grid-world. Such a spatial IPD game has a neighborhood structure which is used for local opponent selection in the IPD game and local parent selection in genetic operations. Another important factor is the choice of a representation scheme to encode each strategy. Different representation schemes often lead to totally different results. Whereas the choice of a representation scheme is known to be important, a mixture of different representation schemes has not been examined for the spatial IPD game in the literature. This means that a population of homogeneous agents with the same representation scheme has been assumed. In this paper, we introduce a different situation to the spatial IPD game in order to examine the evolution of cooperative behavior under more general assumptions. The main novelty of our spatial IPD game is the use of a mixture of different representation schemes. This means that we use a population of inhomogeneous agents with different representation schemes. Another novelty is the use of two neighborhood structures, each of which is used for local opponent selection and local parent selection. Under these specifications, we show a number of interesting observations on the evolution of cooperative behavior.
{"title":"Evolution of cooperative behavior in a spatial iterated prisoner's dilemma game with different representation schemes of game strategies","authors":"H. Ishibuchi, Hiroyuki Ohyanagi, Y. Nojima","doi":"10.1109/FUZZY.2009.5277282","DOIUrl":"https://doi.org/10.1109/FUZZY.2009.5277282","url":null,"abstract":"The iterated prisoner's dilemma (IPD) game has been frequently used to examine the evolution of cooperative behavior among agents in the field of evolutionary computation. A number of factors are known to be related to the evolution of cooperative behavior. One well-known factor is spatial relations among agents. The IPD game is often played in a grid-world. Such a spatial IPD game has a neighborhood structure which is used for local opponent selection in the IPD game and local parent selection in genetic operations. Another important factor is the choice of a representation scheme to encode each strategy. Different representation schemes often lead to totally different results. Whereas the choice of a representation scheme is known to be important, a mixture of different representation schemes has not been examined for the spatial IPD game in the literature. This means that a population of homogeneous agents with the same representation scheme has been assumed. In this paper, we introduce a different situation to the spatial IPD game in order to examine the evolution of cooperative behavior under more general assumptions. The main novelty of our spatial IPD game is the use of a mixture of different representation schemes. This means that we use a population of inhomogeneous agents with different representation schemes. Another novelty is the use of two neighborhood structures, each of which is used for local opponent selection and local parent selection. Under these specifications, we show a number of interesting observations on the evolution of cooperative behavior.","PeriodicalId":117895,"journal":{"name":"2009 IEEE International Conference on Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132344418","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 : 2009-10-02DOI: 10.1109/FUZZY.2009.5277369
R. Alcalá, Y. Nojima, F. Herrera, H. Ishibuchi
Recently, multiobjective evolutionary algorithms have been applied to improve the difficult tradeoff between interpretability and accuracy of fuzzy rule-based systems. It is known that both requirements are usually contradictory, however, these kinds of algorithms can obtain a set of solutions with different trade-offs. The application of multiobjective evolutionary algorithms to fuzzy rule-based systems is often referred to as multiobjective genetic fuzzy systems. The first study on multiobjective genetic fuzzy systems was multiobjective genetic fuzzy rule selection in order to simultaneously achieve accuracy maximization and complexity minimization. This approach is based on the generation of a set of candidate fuzzy classification rules by considering a previously fixed granularity or multiple fuzzy partitions with different granularities for each attribute. Then, a multiobjective evolutionary optimization algorithm is applied to perform fuzzy rule selection. Although the multiple granularity approach is one of the most promising approaches, its interpretability loss has often been pointed out. In this work, we propose a mechanism to generate single granularity-based fuzzy classification rules for multiobjective genetic fuzzy rule selection. This mechanism is able to specify appropriate single granularities for fuzzy rule extraction before performing multiobjective genetic fuzzy rule selection. The results show that the performance of the obtained classifiers can be even improved by avoiding multiple granularities, which increases the linguistic interpretability of the obtained models.
{"title":"Generating single granularity-based fuzzy classification rules for multiobjective genetic fuzzy rule selection","authors":"R. Alcalá, Y. Nojima, F. Herrera, H. Ishibuchi","doi":"10.1109/FUZZY.2009.5277369","DOIUrl":"https://doi.org/10.1109/FUZZY.2009.5277369","url":null,"abstract":"Recently, multiobjective evolutionary algorithms have been applied to improve the difficult tradeoff between interpretability and accuracy of fuzzy rule-based systems. It is known that both requirements are usually contradictory, however, these kinds of algorithms can obtain a set of solutions with different trade-offs. The application of multiobjective evolutionary algorithms to fuzzy rule-based systems is often referred to as multiobjective genetic fuzzy systems. The first study on multiobjective genetic fuzzy systems was multiobjective genetic fuzzy rule selection in order to simultaneously achieve accuracy maximization and complexity minimization. This approach is based on the generation of a set of candidate fuzzy classification rules by considering a previously fixed granularity or multiple fuzzy partitions with different granularities for each attribute. Then, a multiobjective evolutionary optimization algorithm is applied to perform fuzzy rule selection. Although the multiple granularity approach is one of the most promising approaches, its interpretability loss has often been pointed out. In this work, we propose a mechanism to generate single granularity-based fuzzy classification rules for multiobjective genetic fuzzy rule selection. This mechanism is able to specify appropriate single granularities for fuzzy rule extraction before performing multiobjective genetic fuzzy rule selection. The results show that the performance of the obtained classifiers can be even improved by avoiding multiple granularities, which increases the linguistic interpretability of the obtained models.","PeriodicalId":117895,"journal":{"name":"2009 IEEE International Conference on Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132095975","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 : 2009-10-02DOI: 10.1109/FUZZY.2009.5277240
A. Thammano, Phongthep Ruxpakawong
This paper introduces a new concept of the connection weight to the standard recurrent neural networks – Elman and Jordan networks. The architecture of the modified networks is the same as that of the original recurrent neural networks. However, in the modified networks the weight of each connection is multi-valued, depending on the value of the input data involved. The backpropagation learning algorithm is also modified to suit the proposed concept. The modified networks have been benchmarked against their original counterparts. The results on eleven benchmark problems are very encouraging.
{"title":"Dynamic system identification using recurrent neural network with multi-valued connection weight","authors":"A. Thammano, Phongthep Ruxpakawong","doi":"10.1109/FUZZY.2009.5277240","DOIUrl":"https://doi.org/10.1109/FUZZY.2009.5277240","url":null,"abstract":"This paper introduces a new concept of the connection weight to the standard recurrent neural networks – Elman and Jordan networks. The architecture of the modified networks is the same as that of the original recurrent neural networks. However, in the modified networks the weight of each connection is multi-valued, depending on the value of the input data involved. The backpropagation learning algorithm is also modified to suit the proposed concept. The modified networks have been benchmarked against their original counterparts. The results on eleven benchmark problems are very encouraging.","PeriodicalId":117895,"journal":{"name":"2009 IEEE International Conference on Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116197569","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 : 2009-10-02DOI: 10.1109/FUZZY.2009.5277400
Keeley A. Crockett, Z. Bandar, J. O'Shea
Fuzzy Decision Trees have been successfully applied to both classification and regression problems by allowing gradual transitions to exist between attribute values. Methodologies for fuzzification in fuzzy trees currently create such gradual transitions for continuous attributes. This is achieved by automatically creating fuzzy regions around tree nodes using an optimization algorithm or by using the knowledge of a human expert to create a series of fuzzy sets which are representative of the attributes domain. A problem occurs when trying to construct a fuzzy tree from real world data which comprises of only discrete or a mixture of discrete and continuous attributes. Discrete attribute values have no proximity to other values in the decision space, as there is no continuum between values. Consequently, within a fuzzy tree they are interpreted as crisp sets and contribute little towards the final outcome. This paper proposes a new approach for the fuzzification of discrete attributes in fuzzy decision trees. The approach ranks discrete values on the basis of their effect on the outcome rate and assigns a possibility of being a specific outcome. Experiments carried out on two real world financial datasets which contain a significant proportion of discrete attributes show improved classification accuracy compared with a crisp interpretation of such attributes within fuzzy trees.
{"title":"Fuzzification of discrete attributes from financial data in fuzzy classification trees","authors":"Keeley A. Crockett, Z. Bandar, J. O'Shea","doi":"10.1109/FUZZY.2009.5277400","DOIUrl":"https://doi.org/10.1109/FUZZY.2009.5277400","url":null,"abstract":"Fuzzy Decision Trees have been successfully applied to both classification and regression problems by allowing gradual transitions to exist between attribute values. Methodologies for fuzzification in fuzzy trees currently create such gradual transitions for continuous attributes. This is achieved by automatically creating fuzzy regions around tree nodes using an optimization algorithm or by using the knowledge of a human expert to create a series of fuzzy sets which are representative of the attributes domain. A problem occurs when trying to construct a fuzzy tree from real world data which comprises of only discrete or a mixture of discrete and continuous attributes. Discrete attribute values have no proximity to other values in the decision space, as there is no continuum between values. Consequently, within a fuzzy tree they are interpreted as crisp sets and contribute little towards the final outcome. This paper proposes a new approach for the fuzzification of discrete attributes in fuzzy decision trees. The approach ranks discrete values on the basis of their effect on the outcome rate and assigns a possibility of being a specific outcome. Experiments carried out on two real world financial datasets which contain a significant proportion of discrete attributes show improved classification accuracy compared with a crisp interpretation of such attributes within fuzzy trees.","PeriodicalId":117895,"journal":{"name":"2009 IEEE International Conference on Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134473851","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：