In this paper we propose a clustering ensemble algorithm based on genetic algorithm. The most important feature of our method is ability to extract the number of clusters. Genetic algorithms have been known as methods with high ability to find the solution of optimization problems. One of these problems is clustering, a process that receives a dataset as input and divides its members into several subsets called cluster (partition or group). The members of each cluster would be alike while members of two different clusters would be as different as possible. One of the common ways to do this is combinational clustering. Combinational clustering will combine the results of different clustering methods or some executions of a clustering method to calculate final clusters. In this paper, an evolutionary combinational clustering method is proposed to find the number of clusters. The evaluation of this method on several common datasets shows the proper performance of proposed method to find final clusters as well as the exact number of clusters.
{"title":"An Evolutionary Approach to Clustering Ensemble","authors":"M. Mohammadi, Amin Nikanjam, A. Rahmani","doi":"10.1109/ICNC.2008.493","DOIUrl":"https://doi.org/10.1109/ICNC.2008.493","url":null,"abstract":"In this paper we propose a clustering ensemble algorithm based on genetic algorithm. The most important feature of our method is ability to extract the number of clusters. Genetic algorithms have been known as methods with high ability to find the solution of optimization problems. One of these problems is clustering, a process that receives a dataset as input and divides its members into several subsets called cluster (partition or group). The members of each cluster would be alike while members of two different clusters would be as different as possible. One of the common ways to do this is combinational clustering. Combinational clustering will combine the results of different clustering methods or some executions of a clustering method to calculate final clusters. In this paper, an evolutionary combinational clustering method is proposed to find the number of clusters. The evaluation of this method on several common datasets shows the proper performance of proposed method to find final clusters as well as the exact number of clusters.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"789 1","pages":"77-82"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76927128","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}
Modal Kleene algebras (MKA) formalize the behavior of regular programs. However, MKA is incapable of verifying regular programs with probabilistic information, which have richer and more powerful expressiveness than normal regular programs. We define an extension of MKA, called probabilistic modal Kleene algebra (PMKA) for verifying the regular programs with probability in a purely algebraic approach. We give relational semantics for the regular programs with probability. Then, we modify the existent probabilistic Hoare-style logic in some sort to a proof system named PHLnp for probabilistic regular programs without iteration, and prove the soundness of the modified system in terms of the relational semantics. At last, we show that PHLnp is subsumed by PMKA.
{"title":"Probabilistic Modal Kleene Algebra and Hoare-Style Logic","authors":"Rui Qiao, Jinzhao Wu, Xinyan Gao","doi":"10.1109/ICNC.2008.174","DOIUrl":"https://doi.org/10.1109/ICNC.2008.174","url":null,"abstract":"Modal Kleene algebras (MKA) formalize the behavior of regular programs. However, MKA is incapable of verifying regular programs with probabilistic information, which have richer and more powerful expressiveness than normal regular programs. We define an extension of MKA, called probabilistic modal Kleene algebra (PMKA) for verifying the regular programs with probability in a purely algebraic approach. We give relational semantics for the regular programs with probability. Then, we modify the existent probabilistic Hoare-style logic in some sort to a proof system named PHLnp for probabilistic regular programs without iteration, and prove the soundness of the modified system in terms of the relational semantics. At last, we show that PHLnp is subsumed by PMKA.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"100 1","pages":"652-661"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76993263","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}
In this paper, we present a novel particle swarm optimization (PSO) multiuser detection (MUD) approach for multiple-in-multiple-out (MIMO) systems with space-time block code (STBC). The proposed strategy consider the MUD problem with diversity reception from a multiobjective optimization (MO) viewpoint and develop a Pareto-optimal PSO-based (POPSO) algorithm. By taking advantage of the Pareto-optimal values, this approach effectively explores and exploits the channel fading information of received signals that are independent for each receive antenna, and accordingly improves the heuristic search ability to find the optimal solution. The proposed approach is shown to achieve superior bit-error-rate (BER) performance by simulations.
{"title":"Multiuser Detection in STBC-MIMO Systems Based on Pareto Optimality Particle Swarm Optimization Algorithm","authors":"Jianping An, Binbin Xu","doi":"10.1109/ICNC.2008.727","DOIUrl":"https://doi.org/10.1109/ICNC.2008.727","url":null,"abstract":"In this paper, we present a novel particle swarm optimization (PSO) multiuser detection (MUD) approach for multiple-in-multiple-out (MIMO) systems with space-time block code (STBC). The proposed strategy consider the MUD problem with diversity reception from a multiobjective optimization (MO) viewpoint and develop a Pareto-optimal PSO-based (POPSO) algorithm. By taking advantage of the Pareto-optimal values, this approach effectively explores and exploits the channel fading information of received signals that are independent for each receive antenna, and accordingly improves the heuristic search ability to find the optimal solution. The proposed approach is shown to achieve superior bit-error-rate (BER) performance by simulations.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"37 1","pages":"237-241"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80863999","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}
Finding communities in complex networks is not a trivial task. It not only can help to understand topological structure of large scale networks, but also is useful for data mining. In this paper, we propose a community detection technique based on the collective behavior of swarm aggregation, where all nodes are arranged on a circumference and each of them is assigned a angle at a random. The angles are gradually updated according to node's neighbors angle agreement. Finally, a stable state is reached and nodes belonging to the same community are aggregated together. By repeating this process, hierarchical community structure of input network can be obtained. The proposed technique is robust and efficient. Moreover, it is able to deal with both weighted and un-weighted networks.
{"title":"Complex Network Community Detection Based on Swarm Aggregation","authors":"Tatyana B. S. de Oliveira, Liang Zhao","doi":"10.1109/ICNC.2008.324","DOIUrl":"https://doi.org/10.1109/ICNC.2008.324","url":null,"abstract":"Finding communities in complex networks is not a trivial task. It not only can help to understand topological structure of large scale networks, but also is useful for data mining. In this paper, we propose a community detection technique based on the collective behavior of swarm aggregation, where all nodes are arranged on a circumference and each of them is assigned a angle at a random. The angles are gradually updated according to node's neighbors angle agreement. Finally, a stable state is reached and nodes belonging to the same community are aggregated together. By repeating this process, hierarchical community structure of input network can be obtained. The proposed technique is robust and efficient. Moreover, it is able to deal with both weighted and un-weighted networks.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"18 1","pages":"604-608"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85446655","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}
Actually, the determination of medical scales items is feature weight problem in data-mining area. The framework of EC-based (Evolutionary computation) classification method for feature weight is presented contrasted with traditional statistical methods. And an improved EC-based k-NN algorithm for feature weight, GS-k-NN, is put forward and presented. Comparison between PSO and GA is made as well as among k-NN, GS-k-NN, C4.5, SVM in the paper. Results show that PSO-based GS-k-NN is more effective than other algorithms.
{"title":"Feature Weight and Its Application in Weight Determination of Medical Scale Items","authors":"Zhenhua Wang, Zhongsheng Hou, Ying Gao, Qiang Liu","doi":"10.1109/ICNC.2008.520","DOIUrl":"https://doi.org/10.1109/ICNC.2008.520","url":null,"abstract":"Actually, the determination of medical scales items is feature weight problem in data-mining area. The framework of EC-based (Evolutionary computation) classification method for feature weight is presented contrasted with traditional statistical methods. And an improved EC-based k-NN algorithm for feature weight, GS-k-NN, is put forward and presented. Comparison between PSO and GA is made as well as among k-NN, GS-k-NN, C4.5, SVM in the paper. Results show that PSO-based GS-k-NN is more effective than other algorithms.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"116 1","pages":"202-206"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85503807","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}
Stock exchange market, that has function of accommodating capital and optimizing resource allocation, is a part of capital markets. And it play important role of economy development. Research of relationship between stock exchange market and macroeconomic variables has realism significance. This paper, according to Shanghai stock exchange market index representing stock market, chooses 8 macroeconomic variables to research both long time balance and short time fluctuation relation between Shanghai stock exchange market index and macroeconomic variables using unit root testing, cointegration analysis and vector error correction model. The result of practical example indicates that there exist longtime stabilization relation between Shanghai stock exchange market index and macroeconomic variables. The development of stock exchange market has some promotional effect on economy. That shows that Chinese stock exchange market reflects the development level of macroeconomic.
{"title":"Analysis of Cointegration between Macroeconomic Variables and Stock Index","authors":"Yan-chun Liu, Liang-bin Sun","doi":"10.1109/ICNC.2008.689","DOIUrl":"https://doi.org/10.1109/ICNC.2008.689","url":null,"abstract":"Stock exchange market, that has function of accommodating capital and optimizing resource allocation, is a part of capital markets. And it play important role of economy development. Research of relationship between stock exchange market and macroeconomic variables has realism significance. This paper, according to Shanghai stock exchange market index representing stock market, chooses 8 macroeconomic variables to research both long time balance and short time fluctuation relation between Shanghai stock exchange market index and macroeconomic variables using unit root testing, cointegration analysis and vector error correction model. The result of practical example indicates that there exist longtime stabilization relation between Shanghai stock exchange market index and macroeconomic variables. The development of stock exchange market has some promotional effect on economy. That shows that Chinese stock exchange market reflects the development level of macroeconomic.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"24 1","pages":"318-322"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85528112","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}
For complex mechanical equipment containing N units the optimal model to preventive maintenance cycle policy is proposed to minimize the maintenance cost rate, the model is subject to the availability and the reliability. And optimal variable is preventive maintenance cycle. The recursion relationship of failure rate before and after imperfect preventive maintenance was built up concerning with the concept of age reduction factor. Finally, immunity particle swarm algorithm is used to solve the model; the result of an example proves the model valid and effective and the cost rate decreases 10.2% than single parts maintenance policy under identical restraint condition.
{"title":"Research on Preventive Maintenance Cycle's Optimization of Complex System","authors":"D. Lv, H. Zuo, Jing Cai","doi":"10.1109/ICNC.2008.262","DOIUrl":"https://doi.org/10.1109/ICNC.2008.262","url":null,"abstract":"For complex mechanical equipment containing N units the optimal model to preventive maintenance cycle policy is proposed to minimize the maintenance cost rate, the model is subject to the availability and the reliability. And optimal variable is preventive maintenance cycle. The recursion relationship of failure rate before and after imperfect preventive maintenance was built up concerning with the concept of age reduction factor. Finally, immunity particle swarm algorithm is used to solve the model; the result of an example proves the model valid and effective and the cost rate decreases 10.2% than single parts maintenance policy under identical restraint condition.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"1 1","pages":"669-673"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85784596","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}
Speaker identity verification is an useful biometric recognition approach. Native speaker verification has achieved some better effects. But non-native speaker verification remains a challenging task because of wide varieties of non-native accents. Based on two speech corpus, one native speech corpus and one non-native corpus, by means of speaker adaptation. Combined with traditional speaker verification and connected digits continuous speech recognition techniques, non-native speaker identity verification experiments are performed. The combined judging strategy is proved to be more effective by the final experimental results.
{"title":"Non-Native Speaker Identity Verification Based on Speech","authors":"H. Wei, Jian Yang","doi":"10.1109/ICNC.2008.574","DOIUrl":"https://doi.org/10.1109/ICNC.2008.574","url":null,"abstract":"Speaker identity verification is an useful biometric recognition approach. Native speaker verification has achieved some better effects. But non-native speaker verification remains a challenging task because of wide varieties of non-native accents. Based on two speech corpus, one native speech corpus and one non-native corpus, by means of speaker adaptation. Combined with traditional speaker verification and connected digits continuous speech recognition techniques, non-native speaker identity verification experiments are performed. The combined judging strategy is proved to be more effective by the final experimental results.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"44 1","pages":"59-62"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84554395","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}
Yong-Zhi Li, Guangming He, Jing-yu Yang, Yu-Ping Wang
Based on manifold learning, a new feature extraction method is proposed for face recognition in the paper. The new method is called two-directional two-dimensional unsupervised discriminant projection ((2D)2UDP), which simultaneously works image matrix in the row direction and in the column direction for feature extraction. The experimental results on ORL face databases and AR face databases indicate that the proposed method has higher recognition rate and more stable.
{"title":"(2D)2UDP: A New Two-Directional Two-Dimensional Unsupervised Discriminant Projection for Face Recognition","authors":"Yong-Zhi Li, Guangming He, Jing-yu Yang, Yu-Ping Wang","doi":"10.1109/ICNC.2008.657","DOIUrl":"https://doi.org/10.1109/ICNC.2008.657","url":null,"abstract":"Based on manifold learning, a new feature extraction method is proposed for face recognition in the paper. The new method is called two-directional two-dimensional unsupervised discriminant projection ((2D)2UDP), which simultaneously works image matrix in the row direction and in the column direction for feature extraction. The experimental results on ORL face databases and AR face databases indicate that the proposed method has higher recognition rate and more stable.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"11 1","pages":"3-7"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78263585","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}
One key matter we meet when classical logic is used in analysis and information mining to massive knowledge system is the problem of Scott Law. Up to the present, the existent resolvents are far from our logical intuition. This paper gives a new strategy - to build an intuitive implication logic system, D, in which: (1) the property of implication should be in accordance with intuition; (2) the fundamental laws of classical logic should be reserved; (3) the properties of negation and conjunction should be not changed; (4) Scott Law should not generally hold Scott Law. Then, basing on the strict formal semantics, we demonstrate the soundness and consistency of system D.
{"title":"The Completeness and Decidability of Intuitive Implication Logic System","authors":"Guoping Du, Hongguang Wang, Na Li, Liang Xu","doi":"10.1109/ICNC.2008.499","DOIUrl":"https://doi.org/10.1109/ICNC.2008.499","url":null,"abstract":"One key matter we meet when classical logic is used in analysis and information mining to massive knowledge system is the problem of Scott Law. Up to the present, the existent resolvents are far from our logical intuition. This paper gives a new strategy - to build an intuitive implication logic system, D, in which: (1) the property of implication should be in accordance with intuition; (2) the fundamental laws of classical logic should be reserved; (3) the properties of negation and conjunction should be not changed; (4) Scott Law should not generally hold Scott Law. Then, basing on the strict formal semantics, we demonstrate the soundness and consistency of system D.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"465 1","pages":"573-577"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78319728","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：