Pub Date : 2003-07-24DOI: 10.1109/NAFIPS.2003.1226759
H. Uesu, E. Tsuda, H. Yamashita
We often represent the inexact phenomena regarding mental process and cognition as fuzzy graphs. If we investigate the cluster and the order of the nodes in the fuzzy graph, we have a lot of interesting results. For this purpose we define the similarity Index and the connectivity Index. In this paper, we would discuss the definition of the indices and its properties.
{"title":"Mathematical analysis of similarity index and connectivity index in fuzzy graph","authors":"H. Uesu, E. Tsuda, H. Yamashita","doi":"10.1109/NAFIPS.2003.1226759","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226759","url":null,"abstract":"We often represent the inexact phenomena regarding mental process and cognition as fuzzy graphs. If we investigate the cluster and the order of the nodes in the fuzzy graph, we have a lot of interesting results. For this purpose we define the similarity Index and the connectivity Index. In this paper, we would discuss the definition of the indices and its properties.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123450046","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 : 2003-07-24DOI: 10.1109/NAFIPS.2003.1226829
M. Hanss
The transformation method has been proposed as a practical tool for the simulation and the analysis of systems with uncertain, fuzzy-valued model parameters using fuzzy arithmetic. Up to now, this method has been available in two forms: in a general form, which can be used for the simulation and the analysis of arbitrarily non-monotonic problems, and in a reduced form, which reduces the computational costs of the method to a large extent, requiring, instead, some additional conditions to be fulfilled. In this paper, the extended transformation method will be introduced as an advanced version of the previously presented formulations of the transformation method. This extended version includes the former versions as marginal cases and allows a pre-adjustment of the method, subject to the number of model parameters that are expected to cause non-monotonic behavior of the model output. Finally, to set up the method properly, a novel approach, again based on the transformation method, is presented to practically detect those parameters that are responsible for a non-monotonic behavior of the model output.
{"title":"Simulation and analysis of fuzzy-parameterized models with the extended transformation method","authors":"M. Hanss","doi":"10.1109/NAFIPS.2003.1226829","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226829","url":null,"abstract":"The transformation method has been proposed as a practical tool for the simulation and the analysis of systems with uncertain, fuzzy-valued model parameters using fuzzy arithmetic. Up to now, this method has been available in two forms: in a general form, which can be used for the simulation and the analysis of arbitrarily non-monotonic problems, and in a reduced form, which reduces the computational costs of the method to a large extent, requiring, instead, some additional conditions to be fulfilled. In this paper, the extended transformation method will be introduced as an advanced version of the previously presented formulations of the transformation method. This extended version includes the former versions as marginal cases and allows a pre-adjustment of the method, subject to the number of model parameters that are expected to cause non-monotonic behavior of the model output. Finally, to set up the method properly, a novel approach, again based on the transformation method, is presented to practically detect those parameters that are responsible for a non-monotonic behavior of the model output.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132971997","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 : 2003-07-24DOI: 10.1109/NAFIPS.2003.1226781
S. Coppock, L. Mazlack
Similarity is important in knowledge discovery. Cluster analysis, classification, and granulation each involve some notion or definition of similarity. The measurement of similarity is selected based on the domain and distribution of the data. Even within a specific domain, some similarity metrics may be considered more useful than others. There is an amount of uncertainty in quantitatively measuring the similarity between records of mixed data. The uncertainty develops from the lack of scale that both nominal and ordinal data have. Rough set theory is one tool developed for handling uncertainty. Rough sets can be used in dissimilarity analysis of qualitative data. It would seem that rough sets could be applied in measuring similarity between records containing both quantitative and qualitative data for the purpose of clustering the records.
{"title":"Rough sets used in the measurement of similarity of mixed mode data","authors":"S. Coppock, L. Mazlack","doi":"10.1109/NAFIPS.2003.1226781","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226781","url":null,"abstract":"Similarity is important in knowledge discovery. Cluster analysis, classification, and granulation each involve some notion or definition of similarity. The measurement of similarity is selected based on the domain and distribution of the data. Even within a specific domain, some similarity metrics may be considered more useful than others. There is an amount of uncertainty in quantitatively measuring the similarity between records of mixed data. The uncertainty develops from the lack of scale that both nominal and ordinal data have. Rough set theory is one tool developed for handling uncertainty. Rough sets can be used in dissimilarity analysis of qualitative data. It would seem that rough sets could be applied in measuring similarity between records containing both quantitative and qualitative data for the purpose of clustering the records.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127994897","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 : 2003-07-24DOI: 10.1109/NAFIPS.2003.1226777
T. Andreasen, H. Bulskov, R. Knappe
The main focus of this paper is how to measure similarity in a content-based information retrieval environment. In the first part we define the information base, which is a generative framework where an ontology in combination with a concept language defines a set of well-formed concepts. Well-formed concepts is assumed to be the basis for an indexing of the information base in the sense that these concepts appear in descriptions attached to objects in the base. Subsequent and last we introduce an approach for measuring similarity in this framework. The measuring problem is divided into to continuous parts where we first narrow what concepts have in common, and secondly use this fragment, a similarity graph, for calculating the similarity between concepts. The purpose of narrowing or restricting what concepts have in common is to manage the generative aspect of the ontology, and to retain the greatest possible number of shared attributes and characteristics of the concepts being compared. Taking the similarity graphs as input we discuss what properties a similarity function need to satisfy to measure the degree of similarity proportional to how close the concepts are or how much they share.
{"title":"Similarity from conceptual relations","authors":"T. Andreasen, H. Bulskov, R. Knappe","doi":"10.1109/NAFIPS.2003.1226777","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226777","url":null,"abstract":"The main focus of this paper is how to measure similarity in a content-based information retrieval environment. In the first part we define the information base, which is a generative framework where an ontology in combination with a concept language defines a set of well-formed concepts. Well-formed concepts is assumed to be the basis for an indexing of the information base in the sense that these concepts appear in descriptions attached to objects in the base. Subsequent and last we introduce an approach for measuring similarity in this framework. The measuring problem is divided into to continuous parts where we first narrow what concepts have in common, and secondly use this fragment, a similarity graph, for calculating the similarity between concepts. The purpose of narrowing or restricting what concepts have in common is to manage the generative aspect of the ontology, and to retain the greatest possible number of shared attributes and characteristics of the concepts being compared. Taking the similarity graphs as input we discuss what properties a similarity function need to satisfy to measure the degree of similarity proportional to how close the concepts are or how much they share.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125228974","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 : 2003-07-24DOI: 10.1109/NAFIPS.2003.1226754
Darius Makaitis
Fuzzy logic controllers have been proven to be an effective means of solving real world control issues. One of the difficulties in the construction of fuzzy controllers is the design of the rule base under which they operate. This paper investigates the application of evolutionary programming as an iterative learning process for the fuzzy rule base. This approach is applied to the problem of an elevator control system. The system is optimized for efficiency and smoothness by encouraging higher velocities with minimal changes in acceleration, and by discouraging violations of the design parameters for the system. The performance of the evolved system compares favorably to that of fuzzy controllers designed using traditional methods.
{"title":"Evolving fuzzy controllers through evolutionary programming","authors":"Darius Makaitis","doi":"10.1109/NAFIPS.2003.1226754","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226754","url":null,"abstract":"Fuzzy logic controllers have been proven to be an effective means of solving real world control issues. One of the difficulties in the construction of fuzzy controllers is the design of the rule base under which they operate. This paper investigates the application of evolutionary programming as an iterative learning process for the fuzzy rule base. This approach is applied to the problem of an elevator control system. The system is optimized for efficiency and smoothness by encouraging higher velocities with minimal changes in acceleration, and by discouraging violations of the design parameters for the system. The performance of the evolved system compares favorably to that of fuzzy controllers designed using traditional methods.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134081340","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 : 2003-07-24DOI: 10.1109/NAFIPS.2003.1226805
Dr. Ellen Applebaum
This article describes the creation of a robust fuzzy gain scheduler for flutter suppression in the open-loop response of a non-minimum phase aeroservoelastic UAV (unmanned aerial vehicle) model. Two sets of Takagi-Sugeno (TS) fuzzy rules were constructed for gain scheduling: one set for system identification of the approximate plant matrices and one for full state feedback control using interpolated gains. Interpolation takes place along the one-dimensional, slowly varying velocity envelope. Twenty-three working points, in a velocity range of 20 m/s through 95 m/s, were chosen for the construction of the nominal plant models. Nominal gain vectors were constructed using LQR optimization methods. To achieve stability over the entire velocity envelope, gain vectors were added to the scheduling table using pole placement techniques. The resultant gain scheduling table and fuzzy gain scheduling led to asymptotically stable regulated output responses with average settling times of 0.5 seconds.
{"title":"Fuzzy gain scheduling for flutter suppression in unmanned aerial vehicles","authors":"Dr. Ellen Applebaum","doi":"10.1109/NAFIPS.2003.1226805","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226805","url":null,"abstract":"This article describes the creation of a robust fuzzy gain scheduler for flutter suppression in the open-loop response of a non-minimum phase aeroservoelastic UAV (unmanned aerial vehicle) model. Two sets of Takagi-Sugeno (TS) fuzzy rules were constructed for gain scheduling: one set for system identification of the approximate plant matrices and one for full state feedback control using interpolated gains. Interpolation takes place along the one-dimensional, slowly varying velocity envelope. Twenty-three working points, in a velocity range of 20 m/s through 95 m/s, were chosen for the construction of the nominal plant models. Nominal gain vectors were constructed using LQR optimization methods. To achieve stability over the entire velocity envelope, gain vectors were added to the scheduling table using pole placement techniques. The resultant gain scheduling table and fuzzy gain scheduling led to asymptotically stable regulated output responses with average settling times of 0.5 seconds.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121216297","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 : 2003-07-24DOI: 10.1109/NAFIPS.2003.1226811
M. Zarandi, M. Esmaeilian
This paper presents a fuzzy expert system for Textile manufacturing system using fuzzy cluster analysis. The proposed approach consists of two phases. The first phase is developed with an unsupervised learning and involves a baseline design to effectively identify a prototype fuzzy system. At this phase, a cluster analysis approach is implemented. For the aim of determination of the optimal values of clustering parameters, i.e., weighting exponent (m), and the number of clusters (c), Genetic Algorithms are used. At the second phase, fine tuning process is done to adjust the parameters identified in the baseline design, subject to supervised learning. This phase is realized by using approximate reasoning module. Approximate reasoning parameters are also optimized, using GAs. Finally, the proposed approach is validated by applying it to scheduling system of a Textile industry and comparing the results with a Sugeno-type fuzzy system modeling that uses subtractive clustering in its structure identification stage. The results show that the proposed fuzzy system better represents the behaviour of the complex systems, such as Textile industries.
{"title":"A systematic fuzzy modeling for scheduling of textile manufacturing system","authors":"M. Zarandi, M. Esmaeilian","doi":"10.1109/NAFIPS.2003.1226811","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226811","url":null,"abstract":"This paper presents a fuzzy expert system for Textile manufacturing system using fuzzy cluster analysis. The proposed approach consists of two phases. The first phase is developed with an unsupervised learning and involves a baseline design to effectively identify a prototype fuzzy system. At this phase, a cluster analysis approach is implemented. For the aim of determination of the optimal values of clustering parameters, i.e., weighting exponent (m), and the number of clusters (c), Genetic Algorithms are used. At the second phase, fine tuning process is done to adjust the parameters identified in the baseline design, subject to supervised learning. This phase is realized by using approximate reasoning module. Approximate reasoning parameters are also optimized, using GAs. Finally, the proposed approach is validated by applying it to scheduling system of a Textile industry and comparing the results with a Sugeno-type fuzzy system modeling that uses subtractive clustering in its structure identification stage. The results show that the proposed fuzzy system better represents the behaviour of the complex systems, such as Textile industries.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128963657","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 : 2003-07-24DOI: 10.1109/NAFIPS.2003.1226794
S. Tsumoto
One of the most important problems with medical expert systems is that they cannot make a differential diagnosis with complicated cases. This paper reviews reasoning about complications from the viewpoint of information granulation and proposes an approach to extracting rules for diagnosis of complications from clinical datasets. The illustrative example show that rough set based granular computing gives a nice framework to detect the complications.
{"title":"Detecting possibility of complications of diseases using rough set based granulation","authors":"S. Tsumoto","doi":"10.1109/NAFIPS.2003.1226794","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226794","url":null,"abstract":"One of the most important problems with medical expert systems is that they cannot make a differential diagnosis with complicated cases. This paper reviews reasoning about complications from the viewpoint of information granulation and proposes an approach to extracting rules for diagnosis of complications from clinical datasets. The illustrative example show that rough set based granular computing gives a nice framework to detect the complications.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"265 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132187306","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 : 2003-07-24DOI: 10.1109/NAFIPS.2003.1226800
D. Ferrari, G. da Cruz
This paper proposes three approaches to classify substation single-line diagrams so it can be used in a power distribution network expansion. With these approaches the expertise shall confront different single-line diagrams, so he can choose the best solution to a given problem. This classification is based on reliability, operational flexibility and impact on the environment criteria of each electrical equipment that is part of a substation specification. Simulations were accomplished to establish the best way to stand for the classification criteria through the fuzzy logic use and the approach with the best outcomes in the classification.
{"title":"Classification of substation single-line diagrams based on fuzzy systems","authors":"D. Ferrari, G. da Cruz","doi":"10.1109/NAFIPS.2003.1226800","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226800","url":null,"abstract":"This paper proposes three approaches to classify substation single-line diagrams so it can be used in a power distribution network expansion. With these approaches the expertise shall confront different single-line diagrams, so he can choose the best solution to a given problem. This classification is based on reliability, operational flexibility and impact on the environment criteria of each electrical equipment that is part of a substation specification. Simulations were accomplished to establish the best way to stand for the classification criteria through the fuzzy logic use and the approach with the best outcomes in the classification.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127115592","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 : 2003-07-24DOI: 10.1109/NAFIPS.2003.1226769
Chongfu Huang
In this paper, we introduce a new fuzzy technique, information matrix, to compress images. With high compression speed, this fuzzy technique has compression ratio more than 50% for any original image and the reconstructed image quality is good, although not exactly as the same as the original image. In this paper we give two examples to show the compression ratio and the reconstructed image quality. One is a curve with 100 points. We compress this image with 20 rules. The compression ratio is 79%. Another is a colour picture with flowers. The compression ratio is 50%.
{"title":"Information matrix and image compression","authors":"Chongfu Huang","doi":"10.1109/NAFIPS.2003.1226769","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226769","url":null,"abstract":"In this paper, we introduce a new fuzzy technique, information matrix, to compress images. With high compression speed, this fuzzy technique has compression ratio more than 50% for any original image and the reconstructed image quality is good, although not exactly as the same as the original image. In this paper we give two examples to show the compression ratio and the reconstructed image quality. One is a curve with 100 points. We compress this image with 20 rules. The compression ratio is 79%. Another is a colour picture with flowers. The compression ratio is 50%.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127783475","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：