Pub Date : 2012-08-11DOI: 10.1109/GrC.2012.6468652
T. Zhou, Huiling Lu, Lihua Liu, Longquan Yong, Shouheng Tuo
Aiming at the existing problems of support vector machine ensemble, such as strong randomicity, larger scale of training subsets size and high complexity of ensemble classifier, this paper put forward a novel SVM ensemble construction method based on clustering analysis. Firstly, the samples are clustered into several clusters according to their distribution with rival penalty competitive learning algorithm(RPCL). Then a small quantity of representative instances are chosen as training sets and training SVM that adopt self-perturbation in population convergence speed. Finally Ensemble improvement SVM is constructed by relative majority voting. Man-made data are used to test C_PSOSVM. Experiment result illustrate that the algorithm can improve ensemble SVM classification precision, reducing time-space complexity compared with Bagging, Adaboost.
{"title":"A new classification algorithm based on ensemble PSO_SVM and clustering analysis","authors":"T. Zhou, Huiling Lu, Lihua Liu, Longquan Yong, Shouheng Tuo","doi":"10.1109/GrC.2012.6468652","DOIUrl":"https://doi.org/10.1109/GrC.2012.6468652","url":null,"abstract":"Aiming at the existing problems of support vector machine ensemble, such as strong randomicity, larger scale of training subsets size and high complexity of ensemble classifier, this paper put forward a novel SVM ensemble construction method based on clustering analysis. Firstly, the samples are clustered into several clusters according to their distribution with rival penalty competitive learning algorithm(RPCL). Then a small quantity of representative instances are chosen as training sets and training SVM that adopt self-perturbation in population convergence speed. Finally Ensemble improvement SVM is constructed by relative majority voting. Man-made data are used to test C_PSOSVM. Experiment result illustrate that the algorithm can improve ensemble SVM classification precision, reducing time-space complexity compared with Bagging, Adaboost.","PeriodicalId":126161,"journal":{"name":"IEEE International Conference on Granular Computing","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114184410","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 : 2012-08-11DOI: 10.1109/GrC.2012.6468705
Jia-li Feng
It is shown that the abstracting of sensitivity feature is not only a conversion from quantity into quality, but also can be described by Qualitative Mapping, and wavelet transformation can be defined by qualitative mapping.
{"title":"Qualitative mapping defined wavelet transformation","authors":"Jia-li Feng","doi":"10.1109/GrC.2012.6468705","DOIUrl":"https://doi.org/10.1109/GrC.2012.6468705","url":null,"abstract":"It is shown that the abstracting of sensitivity feature is not only a conversion from quantity into quality, but also can be described by Qualitative Mapping, and wavelet transformation can be defined by qualitative mapping.","PeriodicalId":126161,"journal":{"name":"IEEE International Conference on Granular Computing","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122549620","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 : 2006-05-10DOI: 10.1109/GRC.2006.1635877
Wenming Cao, Tiancheng He, Shoujue Wang
We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.
{"title":"Text-continuous speech recognition based on ICA and geometrical learning","authors":"Wenming Cao, Tiancheng He, Shoujue Wang","doi":"10.1109/GRC.2006.1635877","DOIUrl":"https://doi.org/10.1109/GRC.2006.1635877","url":null,"abstract":"We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.","PeriodicalId":126161,"journal":{"name":"IEEE International Conference on Granular Computing","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116325021","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 : 2006-05-10DOI: 10.1109/GRC.2006.1635861
Haoran Zhang, Xiaodong Wang, Changjiang Zhang, G. Lv
This paper proposes a soft sensor technique based on support vector machine(SVM) technique, firstly gives an introduction to LSSVM, then designs a training algorithm for LSSVM, finally uses it to identify Absorption Stabilization System (ASS) process variable. Case studies are performed and indicate that the proposed method provides satisfactory performance with excellent approximation and generalization property, soft sensor technique based on LSSVM achieves superior performance to the conventional method based on neural networks. approaches. The formulation of the SVM embodies the Structural Risk Minimization (SRM) principle, which has been shown to be superior to the traditional Empirical Risk Minimization (ERM) principle, employed in conventional neural networks. It is this difference that equips SVM with a greater ability to generalize, hence a better generalization ability is guaranteed. As an interesting variant of the standard support vector machines, least squares support vector machines (LSSVM) have been proposed by Suykens and Vandewalle(5,6) for solving pattern recognition and nonlinear function estimation problems. Standard SVM formulation is modified in the sense of ridge regression and taking equality instead of inequality constraints in the problem formulation. As a result one solves a linear system instead of a QP problem, so LSSVM is easy to training. This paper discusses the basic principle of the LSSVM at first, and then uses it as a soft sensor tool to identify Absorption Stabilization System (ASS) process variable. The method can achieve higher identification precision at reasonably small size of training sample set and can overcome disadvantages of the artificial neural networks (ANNs). The experiments of the identification have been presented and discussed. The results indicate that the SVM method exhibits good generalization performance.
{"title":"New Soft Sensor Method Based on SVM","authors":"Haoran Zhang, Xiaodong Wang, Changjiang Zhang, G. Lv","doi":"10.1109/GRC.2006.1635861","DOIUrl":"https://doi.org/10.1109/GRC.2006.1635861","url":null,"abstract":"This paper proposes a soft sensor technique based on support vector machine(SVM) technique, firstly gives an introduction to LSSVM, then designs a training algorithm for LSSVM, finally uses it to identify Absorption Stabilization System (ASS) process variable. Case studies are performed and indicate that the proposed method provides satisfactory performance with excellent approximation and generalization property, soft sensor technique based on LSSVM achieves superior performance to the conventional method based on neural networks. approaches. The formulation of the SVM embodies the Structural Risk Minimization (SRM) principle, which has been shown to be superior to the traditional Empirical Risk Minimization (ERM) principle, employed in conventional neural networks. It is this difference that equips SVM with a greater ability to generalize, hence a better generalization ability is guaranteed. As an interesting variant of the standard support vector machines, least squares support vector machines (LSSVM) have been proposed by Suykens and Vandewalle(5,6) for solving pattern recognition and nonlinear function estimation problems. Standard SVM formulation is modified in the sense of ridge regression and taking equality instead of inequality constraints in the problem formulation. As a result one solves a linear system instead of a QP problem, so LSSVM is easy to training. This paper discusses the basic principle of the LSSVM at first, and then uses it as a soft sensor tool to identify Absorption Stabilization System (ASS) process variable. The method can achieve higher identification precision at reasonably small size of training sample set and can overcome disadvantages of the artificial neural networks (ANNs). The experiments of the identification have been presented and discussed. The results indicate that the SVM method exhibits good generalization performance.","PeriodicalId":126161,"journal":{"name":"IEEE International Conference on Granular Computing","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114479665","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 : 2005-07-25DOI: 10.1109/GRC.2005.1547227
L. Zadeh
It is a deep-seated tradition in science to view uncertainty as a province of probability theory. The generalized theory of uncertainty (GTU), which is outlined in this paper, breaks with this tradition and views uncertainty in a broader perspective. Uncertainty is an attribute of information. A fundamental premise of GTU is that information, whatever its form, may be represented as what is called a generalized constraint. The concept of a generalized constraint is the centerpiece of GTU.
{"title":"Toward a generalized theory of uncertainty (GTU) - an outline","authors":"L. Zadeh","doi":"10.1109/GRC.2005.1547227","DOIUrl":"https://doi.org/10.1109/GRC.2005.1547227","url":null,"abstract":"It is a deep-seated tradition in science to view uncertainty as a province of probability theory. The generalized theory of uncertainty (GTU), which is outlined in this paper, breaks with this tradition and views uncertainty in a broader perspective. Uncertainty is an attribute of information. A fundamental premise of GTU is that information, whatever its form, may be represented as what is called a generalized constraint. The concept of a generalized constraint is the centerpiece of GTU.","PeriodicalId":126161,"journal":{"name":"IEEE International Conference on Granular Computing","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122680677","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 : 2005-07-25DOI: 10.1109/GRC.2005.1547225
Yi Pan
Summary form only given. The understanding of protein structures is vital to determine the function of a protein and its interaction with DNA, RNA and enzyme. The information about its conformation can provide essential information for drug design and protein engineering. While there are over a million known protein sequences, only a limited number of protein structures are experimentally determined. Hence, prediction of protein structures from protein sequences using computer programs is an important step to unveil proteins' three dimensional conformation and functions. As a result, prediction of protein structures has profound theoretical and practical influence over biological study. In this talk, we would show how to use machine learning methods with various advanced encoding schemes and classifiers improve the accuracy of protein structure prediction. The explanation of how a decision is made is also important for improving protein structure prediction. The reasonable interpretation is not only useful to guide the "wet experiments", but also the extracted rules are helpful to integrate computational intelligence with symbolic AI systems for advanced deduction. Some preliminary results using SVM and decision tree for rule extraction and prediction interpretation would also be presented.
{"title":"Protein structure prediction and understanding using machine learning methods","authors":"Yi Pan","doi":"10.1109/GRC.2005.1547225","DOIUrl":"https://doi.org/10.1109/GRC.2005.1547225","url":null,"abstract":"Summary form only given. The understanding of protein structures is vital to determine the function of a protein and its interaction with DNA, RNA and enzyme. The information about its conformation can provide essential information for drug design and protein engineering. While there are over a million known protein sequences, only a limited number of protein structures are experimentally determined. Hence, prediction of protein structures from protein sequences using computer programs is an important step to unveil proteins' three dimensional conformation and functions. As a result, prediction of protein structures has profound theoretical and practical influence over biological study. In this talk, we would show how to use machine learning methods with various advanced encoding schemes and classifiers improve the accuracy of protein structure prediction. The explanation of how a decision is made is also important for improving protein structure prediction. The reasonable interpretation is not only useful to guide the \"wet experiments\", but also the extracted rules are helpful to integrate computational intelligence with symbolic AI systems for advanced deduction. Some preliminary results using SVM and decision tree for rule extraction and prediction interpretation would also be presented.","PeriodicalId":126161,"journal":{"name":"IEEE International Conference on Granular Computing","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125197032","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 : 2005-07-25DOI: 10.1109/GRC.2005.1547226
M. Shan
The business operations in century 21 are facing many new challenges. The role of IT supporting enterprise business operations has been also re-examined to cope with these new requirements. In this article, we highlight these new requirements and solutions to provide a modern business operation system.
{"title":"Intelligent business operation management","authors":"M. Shan","doi":"10.1109/GRC.2005.1547226","DOIUrl":"https://doi.org/10.1109/GRC.2005.1547226","url":null,"abstract":"The business operations in century 21 are facing many new challenges. The role of IT supporting enterprise business operations has been also re-examined to cope with these new requirements. In this article, we highlight these new requirements and solutions to provide a modern business operation system.","PeriodicalId":126161,"journal":{"name":"IEEE International Conference on Granular Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128672012","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 : 2005-07-25DOI: 10.1109/GRC.2005.1547223
J. Kacprzyk
We consider multistage control of a fuzzy dynamic system under fuzzy constraints on controls and fuzzy goals on states. First, we present the standard solution by dynamic programming, indicate its limitations related to its inherent curse of dimensionality. We propose to use a granulation of the space of states and controls, and replace the source problem by its auxiliary counterpart with a small number of reference fuzzy states and reference fuzzy controls. After its solution by dynamic programming, we "adjust" the solution obtained by using Koczy and Hirota's interpolative reasoning technique.
{"title":"Optimal policies in multistage fuzzy control information granulation and interpolative reasoning","authors":"J. Kacprzyk","doi":"10.1109/GRC.2005.1547223","DOIUrl":"https://doi.org/10.1109/GRC.2005.1547223","url":null,"abstract":"We consider multistage control of a fuzzy dynamic system under fuzzy constraints on controls and fuzzy goals on states. First, we present the standard solution by dynamic programming, indicate its limitations related to its inherent curse of dimensionality. We propose to use a granulation of the space of states and controls, and replace the source problem by its auxiliary counterpart with a small number of reference fuzzy states and reference fuzzy controls. After its solution by dynamic programming, we \"adjust\" the solution obtained by using Koczy and Hirota's interpolative reasoning technique.","PeriodicalId":126161,"journal":{"name":"IEEE International Conference on Granular Computing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121223967","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 : 2005-07-25DOI: 10.1109/GRC.2005.1547228
Y. Zhong
Structuralism, functionalism as well as behaviorism are the major approaches to the artificial intelligence (AI) research in the history till the present time. All the three approaches have made great progress so far. On the other hand, however, all the three are separated from each other and also lack of mutual complementation. An attempt was thus made in the paper to propose a new approach to the AI research, the mechanism approach that tries to explore the mechanism of intelligence formation. As results, the three approaches are found to be happily unified based on the mechanism approach. A framework would be reported on the mechanism approach and the unification of the existed AI approaches.
{"title":"Mechanism approach to a unified theory of artificial intelligence","authors":"Y. Zhong","doi":"10.1109/GRC.2005.1547228","DOIUrl":"https://doi.org/10.1109/GRC.2005.1547228","url":null,"abstract":"Structuralism, functionalism as well as behaviorism are the major approaches to the artificial intelligence (AI) research in the history till the present time. All the three approaches have made great progress so far. On the other hand, however, all the three are separated from each other and also lack of mutual complementation. An attempt was thus made in the paper to propose a new approach to the AI research, the mechanism approach that tries to explore the mechanism of intelligence formation. As results, the three approaches are found to be happily unified based on the mechanism approach. A framework would be reported on the mechanism approach and the unification of the existed AI approaches.","PeriodicalId":126161,"journal":{"name":"IEEE International Conference on Granular Computing","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133113199","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 : 2005-07-25DOI: 10.1109/GRC.2005.1547224
S. Ohsuga
Many practical methods of data mining have been developed. But theoretical basis of data mining and discovery is not yet clear. This paper locates these software technologies in a global activity on information by human and tries to make the theoretical basis of the technologies clear.
{"title":"Difference between data mining and knowledge discovery - a view to discovery from knowledge-processing","authors":"S. Ohsuga","doi":"10.1109/GRC.2005.1547224","DOIUrl":"https://doi.org/10.1109/GRC.2005.1547224","url":null,"abstract":"Many practical methods of data mining have been developed. But theoretical basis of data mining and discovery is not yet clear. This paper locates these software technologies in a global activity on information by human and tries to make the theoretical basis of the technologies clear.","PeriodicalId":126161,"journal":{"name":"IEEE International Conference on Granular Computing","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132234713","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：