Pub Date : 2003-07-24DOI: 10.1109/NAFIPS.2003.1226817
M. Martinez, L. Longpré, V. Kreinovich, S. Starks, H. Nguyen
We show how quantum computing can speed up computations related to processing probabilistic, interval, and fuzzy uncertainty.
我们展示了量子计算如何加速与处理概率、区间和模糊不确定性相关的计算。
{"title":"Fast quantum algorithms for handling probabilistic, interval, and fuzzy uncertainty","authors":"M. Martinez, L. Longpré, V. Kreinovich, S. Starks, H. Nguyen","doi":"10.1109/NAFIPS.2003.1226817","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226817","url":null,"abstract":"We show how quantum computing can speed up computations related to processing probabilistic, interval, and fuzzy uncertainty.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"26 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":"130620507","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.2003.1226746
W. W. Melek, A. Goldenberg
In recent years several research groups have introduced the concept of modular and reconfigurable robotics (MRR) as a means for flexible automation. This concept allows for the execution of many complex tasks that cannot be performed by fixed configuration manipulators. Nevertheless, reconfigurable robots introduce a level of complexity to the problem of design of controllers that can handle a wide range of robot configurations with uniform and reliable performance. In parts A and B of this paper, we develop an intelligent control architecture that can be easily used in the presence of dynamic parameter uncertainty and unmodeled disturbances. The proposed architecture has several levels of hierarchy built on top of a conventional PID controller. Systematic design steps of the proposed intelligent control architecture are presented in Part A of this publication.
{"title":"Hierarchical intelligent control of modular manipulators Part A: neurofuzzy control design","authors":"W. W. Melek, A. Goldenberg","doi":"10.1109/NAFIPS.2003.1226746","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226746","url":null,"abstract":"In recent years several research groups have introduced the concept of modular and reconfigurable robotics (MRR) as a means for flexible automation. This concept allows for the execution of many complex tasks that cannot be performed by fixed configuration manipulators. Nevertheless, reconfigurable robots introduce a level of complexity to the problem of design of controllers that can handle a wide range of robot configurations with uniform and reliable performance. In parts A and B of this paper, we develop an intelligent control architecture that can be easily used in the presence of dynamic parameter uncertainty and unmodeled disturbances. The proposed architecture has several levels of hierarchy built on top of a conventional PID controller. Systematic design steps of the proposed intelligent control architecture are presented in Part A of this publication.","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":"134504365","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.2003.1226779
Chien-Chung Chan, Santhosh Sengottiyan
This paper introduces an algorithm for learning Bayes' rules from examples using rough sets. Induced rules are associated with properties of support, certainty, strength, and coverage factors as defined by Pawlak in his study of connections between rough set theory and Bayes' theorem. Differences between the two learning algorithms LEM2 and BLEM2 are presented. An idea of how to develop an optimized inference engine by taking advantage of induced rule properties is discussed.
{"title":"BLEM2: learning Bayes' rules from examples using rough sets","authors":"Chien-Chung Chan, Santhosh Sengottiyan","doi":"10.1109/NAFIPS.2003.1226779","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226779","url":null,"abstract":"This paper introduces an algorithm for learning Bayes' rules from examples using rough sets. Induced rules are associated with properties of support, certainty, strength, and coverage factors as defined by Pawlak in his study of connections between rough set theory and Bayes' theorem. Differences between the two learning algorithms LEM2 and BLEM2 are presented. An idea of how to develop an optimized inference engine by taking advantage of induced rule properties is discussed.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"29 14 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":"134553934","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.2003.1226782
T.Y. Lin
Dempster and Shafer introduced the belief function to measure someone's degree of beliefs or subjective probabilities. In IFSA'99 and NAFIPS'9, we presented two distinct proofs that a belief function is, in fact, an inner probability using the methods of functional analysis and measure theory respectively. In this paper, we continue the study and derive a new Dempster's rule of combination based on probability theory.
{"title":"Interpreting belief functions as probabilities: a new combination rule","authors":"T.Y. Lin","doi":"10.1109/NAFIPS.2003.1226782","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226782","url":null,"abstract":"Dempster and Shafer introduced the belief function to measure someone's degree of beliefs or subjective probabilities. In IFSA'99 and NAFIPS'9, we presented two distinct proofs that a belief function is, in fact, an inner probability using the methods of functional analysis and measure theory respectively. In this paper, we continue the study and derive a new Dempster's rule of combination based on probability theory.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"7 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":"116230485","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.2003.1226833
J. Baldwin, S. B. Karale
Mass assignment based ID3 by Baldwin is an extension of ID3 algorithm by Quinlan for decision making and prediction problems. Mass assignment ID3 has been proved to be important while dealing with continuous variables. Use of entropy calculation to obtain better fuzzy partitions is introduced which results in asymmetric fuzzy sets. Use of asymmetric fuzzy sets, gives way to form decision trees, which increases the reliability and efficiency of the fuzzy ID3 algorithm in case of clustered databases or gives the competitive results. One attribute reduced database format is used to deal with the databases. Specific method of defuzzification is used to derive a point value from the probability distribution over the fuzzy sets of the target attribute, which becomes the prediction.
{"title":"New concepts for fuzzy partitioning, defuzzification and derivation of probabilistic fuzzy decision trees","authors":"J. Baldwin, S. B. Karale","doi":"10.1109/NAFIPS.2003.1226833","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226833","url":null,"abstract":"Mass assignment based ID3 by Baldwin is an extension of ID3 algorithm by Quinlan for decision making and prediction problems. Mass assignment ID3 has been proved to be important while dealing with continuous variables. Use of entropy calculation to obtain better fuzzy partitions is introduced which results in asymmetric fuzzy sets. Use of asymmetric fuzzy sets, gives way to form decision trees, which increases the reliability and efficiency of the fuzzy ID3 algorithm in case of clustered databases or gives the competitive results. One attribute reduced database format is used to deal with the databases. Specific method of defuzzification is used to derive a point value from the probability distribution over the fuzzy sets of the target attribute, which becomes the prediction.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"15 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":"121983055","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.2003.1226751
O. Uncu, I. Turksen
Fuzzy system modeling (FSM) is one of the most prominent tools in order to capture the hidden behavior of highly nonlinear systems with uncertainty. In this paper, a new type 2 FSM approach is proposed in order to increase the predictive power of traditional Takagi-Sugeno fuzzy system models. One of the biggest problems of type 2 fuzzy system models is computational complexity. In order to remedy this problem, the proposed inference mechanism performs type reduction as a first step. Then, the type 1 inference mechanisms are utilized to deduce a model output for a given crisp observation.
{"title":"A new two-step fuzzy inference approach based on Takagi-Sugeno inference using discrete type 2 fuzzy sets","authors":"O. Uncu, I. Turksen","doi":"10.1109/NAFIPS.2003.1226751","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226751","url":null,"abstract":"Fuzzy system modeling (FSM) is one of the most prominent tools in order to capture the hidden behavior of highly nonlinear systems with uncertainty. In this paper, a new type 2 FSM approach is proposed in order to increase the predictive power of traditional Takagi-Sugeno fuzzy system models. One of the biggest problems of type 2 fuzzy system models is computational complexity. In order to remedy this problem, the proposed inference mechanism performs type reduction as a first step. Then, the type 1 inference mechanisms are utilized to deduce a model output for a given crisp observation.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"11 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":"122361798","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.2003.1226780
A. Bargiela, W. Pedrycz
In this paper we discuss the issue of granular representation of time series. The critical concern is the ability to capture the essential features of the time series in the abstract granular representation of it. The discussion uses a set-theoretical framework of fuzzy sets and employs the Fuzzy C-means algorithm for the evaluation of the information granules obtained in various ways.
{"title":"Granulation of temporal data: a global view on time series","authors":"A. Bargiela, W. Pedrycz","doi":"10.1109/NAFIPS.2003.1226780","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226780","url":null,"abstract":"In this paper we discuss the issue of granular representation of time series. The critical concern is the ability to capture the essential features of the time series in the abstract granular representation of it. The discussion uses a set-theoretical framework of fuzzy sets and employs the Fuzzy C-means algorithm for the evaluation of the information granules obtained in various ways.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"113 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":"124731519","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.2003.1226806
K. Rahnamai, P. Arabshahi, A. Gray
The Cassini-Huygens mission to Saturn is the end of an era for NASA; sending one large spacecraft equipped to carry out a multitude of scientific experiments. Future NASA missions will deploy many smaller spacecrafts in highly controlled spatial configurations in what is referred to as "formation flying." Among the many challenges to this approach are: maintaining precise relative-positions, attitude relative to desired target, and communication for information sharing among all spacecraft in formation. In this paper we will investigate the advantages of using an intelligent fuzzy supervisory unit to modify the optimal regulator developed to maintain the relative position between spacecraft. The fuzzy agent modifies the optimal regulator based on information received from the navigation, communication, and control systems, and relative trajectory of the formation. This fuzzy agent seamlessly schedules and nonlinearly interpolates the optimal control gains.
{"title":"Fuzzy supervised optimal regulator for spacecraft formation flying","authors":"K. Rahnamai, P. Arabshahi, A. Gray","doi":"10.1109/NAFIPS.2003.1226806","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226806","url":null,"abstract":"The Cassini-Huygens mission to Saturn is the end of an era for NASA; sending one large spacecraft equipped to carry out a multitude of scientific experiments. Future NASA missions will deploy many smaller spacecrafts in highly controlled spatial configurations in what is referred to as \"formation flying.\" Among the many challenges to this approach are: maintaining precise relative-positions, attitude relative to desired target, and communication for information sharing among all spacecraft in formation. In this paper we will investigate the advantages of using an intelligent fuzzy supervisory unit to modify the optimal regulator developed to maintain the relative position between spacecraft. The fuzzy agent modifies the optimal regulator based on information received from the navigation, communication, and control systems, and relative trajectory of the formation. This fuzzy agent seamlessly schedules and nonlinearly interpolates the optimal control gains.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"22 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":"125032492","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.2003.1226766
A. Gaona, D. Olea, M. Melgarejo
This paper presents an approach for implementing center average defuzzifier by means of distributed arithmetic. This approach was applied in the design of two digital fuzzy processors, their architectures are described and compared in terms of system level organization. An automatic hardware code generation tool was used for specifying these fuzzy processors. Furthermore, they were implemented over a VirtexE/spl reg/ FPGA. Implementation results show that it is possible to obtain a processing speed up to 45 MFLIPS and reduced area cost for distributed arithmetic based parallel organized fuzzy inference systems.
{"title":"Distributed arithmetic in the design of high speed hardware fuzzy inference systems","authors":"A. Gaona, D. Olea, M. Melgarejo","doi":"10.1109/NAFIPS.2003.1226766","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226766","url":null,"abstract":"This paper presents an approach for implementing center average defuzzifier by means of distributed arithmetic. This approach was applied in the design of two digital fuzzy processors, their architectures are described and compared in terms of system level organization. An automatic hardware code generation tool was used for specifying these fuzzy processors. Furthermore, they were implemented over a VirtexE/spl reg/ FPGA. Implementation results show that it is possible to obtain a processing speed up to 45 MFLIPS and reduced area cost for distributed arithmetic based parallel organized fuzzy inference systems.","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":"130499937","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.2003.1226753
M. Makrehchi, M. Kamel
In this paper, we propose a framework for using real data to generate fuzzy membership functions which is one of the most challenging issues in the design of fuzzy systems. After modelling fuzzy membership functions by fuzzy partitions, an optimization technique based on a genetic algorithm is presented to find near optimal fuzzy partitions. The fitness function of the genetic algorithm is defined using Shannon entropy and mutual information measures to establish a mapping front real data to fuzzy variables. To generate fuzzy membership functions based on fuzzy partitions, some definitions and assumptions are also introduced. Numerical results are provided to demonstrate the effectiveness of the proposed approach.
{"title":"An information theoretic approach to generating membership functions from real data","authors":"M. Makrehchi, M. Kamel","doi":"10.1109/NAFIPS.2003.1226753","DOIUrl":"https://doi.org/10.1109/NAFIPS.2003.1226753","url":null,"abstract":"In this paper, we propose a framework for using real data to generate fuzzy membership functions which is one of the most challenging issues in the design of fuzzy systems. After modelling fuzzy membership functions by fuzzy partitions, an optimization technique based on a genetic algorithm is presented to find near optimal fuzzy partitions. The fitness function of the genetic algorithm is defined using Shannon entropy and mutual information measures to establish a mapping front real data to fuzzy variables. To generate fuzzy membership functions based on fuzzy partitions, some definitions and assumptions are also introduced. Numerical results are provided to demonstrate the effectiveness of the proposed approach.","PeriodicalId":153530,"journal":{"name":"22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003","volume":"77 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":"127599664","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：