Knowledge reduction is an important issue when dealing with huge amounts of data. And it has been proved that computing the minimal reduct of decision system is NP-complete. By introducing heuristic information into g...Knowledge reduction is an important issue when dealing with huge amounts of data. And it has been proved that computing the minimal reduct of decision system is NP-complete. By introducing heuristic information into genetic algorithm, we proposed a heuristic genetic algorithm. In the genetic algorithm, we constructed a new operator to maintaining the classification ability. The experiment shows that our algorithm is efficient and effective for minimal reduct, even for the special example that the simple heuristic algorithm can’t get the right result.展开更多
In this paper we present a new optimization algorithm, and the proposed algorithm operates in two phases. In the first one, multiobjective version of genetic algorithm is used as search engine in order to generate app...In this paper we present a new optimization algorithm, and the proposed algorithm operates in two phases. In the first one, multiobjective version of genetic algorithm is used as search engine in order to generate approximate true Pareto front. This algorithm is based on concept of co-evolution and repair algorithm for handling nonlinear constraints. Also it maintains a finite-sized archive of non-dominated solutions which gets iteratively updated in the presence of new solutions based on the concept e-dominance. Then, in the second stage, rough set theory is adopted as local search engine in order to improve the spread of the solutions found so far. The results, provided by the proposed algorithm for benchmark problems, are promising when compared with exiting well-known algorithms. Also, our results suggest that our algorithm is better applicable for solving real-world application problems.展开更多
Feature selection （FS） is a process to select features which are more informative. It is one of the important steps in knowledge discovery. The problem is that not all features are important. Some of the features ma...Feature selection （FS） is a process to select features which are more informative. It is one of the important steps in knowledge discovery. The problem is that not all features are important. Some of the features may be redundant, and others may be irrelevant and noisy. The conventional supervised FS methods evaluate various feature subsets using an evaluation function or metric to select only those features which are related to the decision classes of the data under consideration. However, for many data mining applications, decision class labels are often unknown or incomplete, thus indicating the significance of unsupervised feature selection. However, in unsupervised learning, decision class labels are not provided. In this paper, we propose a new unsupervised quick reduct （QR） algorithm using rough set theory. The quality of the reduced data is measured by the classification performance and it is evaluated using WEKA classifier tool. The method is compared with existing supervised methods and the result demonstrates the efficiency of the proposed algorithm.展开更多
In this paper,we propose a Rough Set assisted Meta-Learning method on how to select the most-suited machine-learning algorithms with minimal effort for a new given dataset. A k-Nearest Neighbor (k-NN) algorithm is use...In this paper,we propose a Rough Set assisted Meta-Learning method on how to select the most-suited machine-learning algorithms with minimal effort for a new given dataset. A k-Nearest Neighbor (k-NN) algorithm is used to recognize the most similar datasets that have been performed by all of the candidate algorithms.By matching the most similar datasets we found,the corresponding performance of the candidate algorithms is used to generate recommendation to the user.The performance derives from a multi-criteria evaluation measure-ARR,which contains both accuracy and time.Furthermore,after applying Rough Set theory,we can find the redundant properties of the dataset.Thus,we can speed up the ranking process and increase the accuracy by using the reduct of the meta attributes.展开更多
Rough set philosophy hinges on the granularity of data, which is used to build all its basic concepts, like approximations, dependencies, reduction etc. Genetic Algorithms provides a general frame to optimize problem ...Rough set philosophy hinges on the granularity of data, which is used to build all its basic concepts, like approximations, dependencies, reduction etc. Genetic Algorithms provides a general frame to optimize problem solution of complex system without depending on the domain of problem.It is robust to many kinds of problems.The paper combines Genetic Algorithms and rough sets theory to compute granular of knowledge through an example of information table. The combination enable us to compute granular of knowledge effectively.It is also useful for computer auto-computing and information processing.展开更多
In this paper, a hybrid method based on rough sets and genetic algorithms, is proposed to improve the speed of robot path planning. Decision rules are obtained using rough set theory. A series of available paths are p...In this paper, a hybrid method based on rough sets and genetic algorithms, is proposed to improve the speed of robot path planning. Decision rules are obtained using rough set theory. A series of available paths are produced by training obtained minimal decision rules. Path populations are optimised by using genetic algorithms until the best path is obtained. Experiment results show that this hybrid method is capable of improving robot path planning speed.展开更多
In rough communication, because each agent has a different language and cannot provide precise communication to each other, the concept translated among multi-agents will loss some information and this results in a le...In rough communication, because each agent has a different language and cannot provide precise communication to each other, the concept translated among multi-agents will loss some information and this results in a less or rougher concept. With different translation sequences, the problem of information loss is varied. To get the translation sequence, in which the jth agent taking part in rough communication gets maximum information, a simulated annealing algorithm is used. Analysis and simulation of this algorithm demonstrate its effectiveness.展开更多
A rough set based fuzzy neural network algorithm is proposed to solve the problem of pattern recognition. The least square algorithm (LSA) is used in the learning process of fuzzy neural network to obtain the performa...A rough set based fuzzy neural network algorithm is proposed to solve the problem of pattern recognition. The least square algorithm (LSA) is used in the learning process of fuzzy neural network to obtain the performance of global convergence. In addition, the numbers of rules and the initial weights and structure of fuzzy neural networks are difficult to determine. Here rough sets are introduced to decide the numbers of rules and original weights. Finally, experiment results show the algorithm may get better effect than the BP algorithm.展开更多
As the first step of service restoration of distribution system,rapid fault diagnosis is a significant task for reducing power outage time,decreasing outage loss,and subsequently improving service reliability and safe...As the first step of service restoration of distribution system,rapid fault diagnosis is a significant task for reducing power outage time,decreasing outage loss,and subsequently improving service reliability and safety.This paper analyzes a fault diagnosis approach by using rough set theory in which how to reduce decision table of data set is a main calculation intensive task.Aiming at this reduction problem,a heuristic reduction algorithm based on attribution length and frequency is proposed.At the same time,the corresponding value reduction method is proposed in order to fulfill the reduction and diagnosis rules extraction.Meanwhile,a Euclid matching method is introduced to solve confliction problems among the extracted rules when some information is lacking.Principal of the whole algorithm is clear and diagnostic rules distilled from the reduction are concise.Moreover,it needs less calculation towards specific discernibility matrix,and thus avoids the corresponding NP hard problem.The whole process is realized by MATLAB programming.A simulation example shows that the method has a fast calculation speed,and the extracted rules can reflect the characteristic of fault with a concise form.The rule database,formed by different reduction of decision table,can diagnose single fault and multi-faults efficiently,and give satisfied results even when the existed information is incomplete.The proposed method has good error-tolerate capability and the potential for on-line fault diagnosis.展开更多
In rough communication, because each agent has a different language and can not provide precise communication to each other, the concept translated among multi-agents will loss some information, and this results in a ...In rough communication, because each agent has a different language and can not provide precise communication to each other, the concept translated among multi-agents will loss some information, and this results in a less or rougher concept. With different translation sequences the amount of the missed knowledge is varied. The λ-optimal translation sequence of rough communication, which concerns both every agent and the last agent taking part in rough communication to get information as much as he （or she） can, is given. In order to get the λ-optimal translation sequence, a genetic algorithm is used. Analysis and simulation of the algorithm demonstrate the effectiveness of the approach.展开更多
文摘Knowledge reduction is an important issue when dealing with huge amounts of data. And it has been proved that computing the minimal reduct of decision system is NP-complete. By introducing heuristic information into genetic algorithm, we proposed a heuristic genetic algorithm. In the genetic algorithm, we constructed a new operator to maintaining the classification ability. The experiment shows that our algorithm is efficient and effective for minimal reduct, even for the special example that the simple heuristic algorithm can’t get the right result.
文摘In this paper we present a new optimization algorithm, and the proposed algorithm operates in two phases. In the first one, multiobjective version of genetic algorithm is used as search engine in order to generate approximate true Pareto front. This algorithm is based on concept of co-evolution and repair algorithm for handling nonlinear constraints. Also it maintains a finite-sized archive of non-dominated solutions which gets iteratively updated in the presence of new solutions based on the concept e-dominance. Then, in the second stage, rough set theory is adopted as local search engine in order to improve the spread of the solutions found so far. The results, provided by the proposed algorithm for benchmark problems, are promising when compared with exiting well-known algorithms. Also, our results suggest that our algorithm is better applicable for solving real-world application problems.
基金supported by the UGC, SERO, Hyderabad under FDP during XI plan periodthe UGC, New Delhi for financial assistance under major research project Grant No. F-34-105/2008
文摘Feature selection （FS） is a process to select features which are more informative. It is one of the important steps in knowledge discovery. The problem is that not all features are important. Some of the features may be redundant, and others may be irrelevant and noisy. The conventional supervised FS methods evaluate various feature subsets using an evaluation function or metric to select only those features which are related to the decision classes of the data under consideration. However, for many data mining applications, decision class labels are often unknown or incomplete, thus indicating the significance of unsupervised feature selection. However, in unsupervised learning, decision class labels are not provided. In this paper, we propose a new unsupervised quick reduct （QR） algorithm using rough set theory. The quality of the reduced data is measured by the classification performance and it is evaluated using WEKA classifier tool. The method is compared with existing supervised methods and the result demonstrates the efficiency of the proposed algorithm.
文摘In this paper,we propose a Rough Set assisted Meta-Learning method on how to select the most-suited machine-learning algorithms with minimal effort for a new given dataset. A k-Nearest Neighbor (k-NN) algorithm is used to recognize the most similar datasets that have been performed by all of the candidate algorithms.By matching the most similar datasets we found,the corresponding performance of the candidate algorithms is used to generate recommendation to the user.The performance derives from a multi-criteria evaluation measure-ARR,which contains both accuracy and time.Furthermore,after applying Rough Set theory,we can find the redundant properties of the dataset.Thus,we can speed up the ranking process and increase the accuracy by using the reduct of the meta attributes.
文摘Rough set philosophy hinges on the granularity of data, which is used to build all its basic concepts, like approximations, dependencies, reduction etc. Genetic Algorithms provides a general frame to optimize problem solution of complex system without depending on the domain of problem.It is robust to many kinds of problems.The paper combines Genetic Algorithms and rough sets theory to compute granular of knowledge through an example of information table. The combination enable us to compute granular of knowledge effectively.It is also useful for computer auto-computing and information processing.
基金This project is partially supported by Science Research Funding from the Education Department of Liaoning Province, China (No.J9906065).
文摘In this paper, a hybrid method based on rough sets and genetic algorithms, is proposed to improve the speed of robot path planning. Decision rules are obtained using rough set theory. A series of available paths are produced by training obtained minimal decision rules. Path populations are optimised by using genetic algorithms until the best path is obtained. Experiment results show that this hybrid method is capable of improving robot path planning speed.
基金the Natural Science Foundation of Shandong Province (Y2006A12)the Scientific ResearchDevelopment Project of Shandong Provincial Education Department(J06P01)the Doctoral Foundation of University of Jinan(B0633).
文摘In rough communication, because each agent has a different language and cannot provide precise communication to each other, the concept translated among multi-agents will loss some information and this results in a less or rougher concept. With different translation sequences, the problem of information loss is varied. To get the translation sequence, in which the jth agent taking part in rough communication gets maximum information, a simulated annealing algorithm is used. Analysis and simulation of this algorithm demonstrate its effectiveness.
文摘A rough set based fuzzy neural network algorithm is proposed to solve the problem of pattern recognition. The least square algorithm (LSA) is used in the learning process of fuzzy neural network to obtain the performance of global convergence. In addition, the numbers of rules and the initial weights and structure of fuzzy neural networks are difficult to determine. Here rough sets are introduced to decide the numbers of rules and original weights. Finally, experiment results show the algorithm may get better effect than the BP algorithm.
基金Project Supported by National Natural Science Foundation of China （50607023）, Natural Science Femdation of CQ CSTC （2006BB2189）
文摘As the first step of service restoration of distribution system,rapid fault diagnosis is a significant task for reducing power outage time,decreasing outage loss,and subsequently improving service reliability and safety.This paper analyzes a fault diagnosis approach by using rough set theory in which how to reduce decision table of data set is a main calculation intensive task.Aiming at this reduction problem,a heuristic reduction algorithm based on attribution length and frequency is proposed.At the same time,the corresponding value reduction method is proposed in order to fulfill the reduction and diagnosis rules extraction.Meanwhile,a Euclid matching method is introduced to solve confliction problems among the extracted rules when some information is lacking.Principal of the whole algorithm is clear and diagnostic rules distilled from the reduction are concise.Moreover,it needs less calculation towards specific discernibility matrix,and thus avoids the corresponding NP hard problem.The whole process is realized by MATLAB programming.A simulation example shows that the method has a fast calculation speed,and the extracted rules can reflect the characteristic of fault with a concise form.The rule database,formed by different reduction of decision table,can diagnose single fault and multi-faults efficiently,and give satisfied results even when the existed information is incomplete.The proposed method has good error-tolerate capability and the potential for on-line fault diagnosis.
基金supported by the National Natural Science Foundation of China(61070241)the Natural Science Foundation of Shandong Province(ZR2010FM035)+1 种基金the Science and Technology Foundation of University of Jinan(XKY1031XKY0808)
文摘In rough communication, because each agent has a different language and can not provide precise communication to each other, the concept translated among multi-agents will loss some information, and this results in a less or rougher concept. With different translation sequences the amount of the missed knowledge is varied. The λ-optimal translation sequence of rough communication, which concerns both every agent and the last agent taking part in rough communication to get information as much as he （or she） can, is given. In order to get the λ-optimal translation sequence, a genetic algorithm is used. Analysis and simulation of the algorithm demonstrate the effectiveness of the approach.
