Pub Date : 2012-05-29DOI: 10.1109/ICNC.2012.6234756
Adriana Takahashi, Adrião D. Dória Neto, B. Bedregal
In this work we propose a generalized real interval kernel method applied on Support Vector Machines. Since the real interval kernel method is constructed from the real kernel method, it is reasonable to extend it to intervals on any domain which has some algebraic structure. This extension is applied on Support Vector Machines classification of interval data.
{"title":"An introduction interval kernel-Based methods applied on Support Vector Machines","authors":"Adriana Takahashi, Adrião D. Dória Neto, B. Bedregal","doi":"10.1109/ICNC.2012.6234756","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234756","url":null,"abstract":"In this work we propose a generalized real interval kernel method applied on Support Vector Machines. Since the real interval kernel method is constructed from the real kernel method, it is reasonable to extend it to intervals on any domain which has some algebraic structure. This extension is applied on Support Vector Machines classification of interval data.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122438217","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234708
Yu-liang Qian, Hao Zhang, D. Peng, Cong-Hua Huang
PSO (Particle Swarm Optimization)-RBF is widely used in intelligent fault diagnosis for generator unit. Since PSO has slow convergence rate, low accuracy, and early-maturing problem which effect training speed and diagnosis accuracy of PSO-RBF, the operations of crossover and variation of genetic algorithm (GA) are introduced into PSO such that the performance of PSO can be improved. GA-PSO is employed to optimize the RBF neural network with concrete steps, then GA-PSO-RBF is applied in fault diagnosis for generator unit. Simulation results show that GA-PSO-RBF is superior to PSO-RBF in training speed, convergence accuracy, and diagnosis accuracy, thus, it is a new efficient diagnosis approach.
{"title":"Fault diagnosis for generator unit based on RBF neural network optimized by GA-PSO","authors":"Yu-liang Qian, Hao Zhang, D. Peng, Cong-Hua Huang","doi":"10.1109/ICNC.2012.6234708","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234708","url":null,"abstract":"PSO (Particle Swarm Optimization)-RBF is widely used in intelligent fault diagnosis for generator unit. Since PSO has slow convergence rate, low accuracy, and early-maturing problem which effect training speed and diagnosis accuracy of PSO-RBF, the operations of crossover and variation of genetic algorithm (GA) are introduced into PSO such that the performance of PSO can be improved. GA-PSO is employed to optimize the RBF neural network with concrete steps, then GA-PSO-RBF is applied in fault diagnosis for generator unit. Simulation results show that GA-PSO-RBF is superior to PSO-RBF in training speed, convergence accuracy, and diagnosis accuracy, thus, it is a new efficient diagnosis approach.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122471035","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234768
Yanfang Deng, Jianling Xiang, Z. Ou
Accurate forecast of traffic flow is crucial to effective and proactive traffic management systems in the context of intelligent transportation systems and dynamic traffic assignment. This paper presents an application of a supervised statistical learning technique called support vector regression (SVR) with hybrid chaotic genetic algorithm (CGAs) for urban short-term traffic flow forecasting. With the increase of complexity and the larger scale of traffic flow forecast demand, genetic algorithms (GAs) are often faced with the problems of premature convergence, slowly reaching the global optimal solution or trapping into a local optimum. The proposed algorithm is used to overcome premature local optimum in determining three parameters of the SVR model. The predictive performance is compared to other models and the results show the algorithm can not only overcome the premature of GA but also can increase its robustness, and at the same time reduce the error of traffic flow forecasting, raise the forecast precision.
{"title":"SVR with hybrid chaotic genetic algorithm for short-term traffic flow forecasting","authors":"Yanfang Deng, Jianling Xiang, Z. Ou","doi":"10.1109/ICNC.2012.6234768","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234768","url":null,"abstract":"Accurate forecast of traffic flow is crucial to effective and proactive traffic management systems in the context of intelligent transportation systems and dynamic traffic assignment. This paper presents an application of a supervised statistical learning technique called support vector regression (SVR) with hybrid chaotic genetic algorithm (CGAs) for urban short-term traffic flow forecasting. With the increase of complexity and the larger scale of traffic flow forecast demand, genetic algorithms (GAs) are often faced with the problems of premature convergence, slowly reaching the global optimal solution or trapping into a local optimum. The proposed algorithm is used to overcome premature local optimum in determining three parameters of the SVR model. The predictive performance is compared to other models and the results show the algorithm can not only overcome the premature of GA but also can increase its robustness, and at the same time reduce the error of traffic flow forecasting, raise the forecast precision.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122165283","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234613
Dingcai Shen, Xuewen Xia
A new method for finding multiple solutions of multimodal optimization problems is proposed in this paper. To avoid the necessity of specifying a niche radius, the proposed method adopts hybrid of species conservation and hill-valley detection mechanism. The proposed method is compared with classical Species Conservation Genetic Algorithm (SCGA) on a number of standard benchmark problems. The experimental results show that the new approach performs better in finding all optima with no additional parameters introduced.
{"title":"An improved species conserving genetic algorithm for multimodal optimization","authors":"Dingcai Shen, Xuewen Xia","doi":"10.1109/ICNC.2012.6234613","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234613","url":null,"abstract":"A new method for finding multiple solutions of multimodal optimization problems is proposed in this paper. To avoid the necessity of specifying a niche radius, the proposed method adopts hybrid of species conservation and hill-valley detection mechanism. The proposed method is compared with classical Species Conservation Genetic Algorithm (SCGA) on a number of standard benchmark problems. The experimental results show that the new approach performs better in finding all optima with no additional parameters introduced.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"282 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123291043","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234573
Helyane Bronoski Borges, J. C. Nievola
Hierarchical classification is a problem with application in many areas. Therefore, it makes the development of algorithms able to induce hierarchical classification models. This paper presents an algorithm for hierarchical classification using the global approach, called Hierarchical Classification using a Competitive Neural Network (HC-CNN). It was tested on some datasets from the bioinformatics field and the results are promising.
{"title":"Hierarchical classification using a Competitive Neural Network","authors":"Helyane Bronoski Borges, J. C. Nievola","doi":"10.1109/ICNC.2012.6234573","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234573","url":null,"abstract":"Hierarchical classification is a problem with application in many areas. Therefore, it makes the development of algorithms able to induce hierarchical classification models. This paper presents an algorithm for hierarchical classification using the global approach, called Hierarchical Classification using a Competitive Neural Network (HC-CNN). It was tested on some datasets from the bioinformatics field and the results are promising.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128304384","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234628
Z. Tao, A. Cui, Xiwei Wang, X. Tao
To obtain source and regional parameters, which are adopted to describe the earthquake source and crustal medium in a region to estimate ground motion, an inversion strategy is presented in this paper. Since these parameters are inversed from seismographic records by micro-genetic algorithm to establish strong ground motion attenuation relations, it is important to choose parameters not related with the sizes of earthquakes. One source parameter, stress drop Δσ, and four regional ones, Q0, η, R1 and R2, are selected as the inversed parameters.
{"title":"Inversion strategy for seismic source and regional parameters","authors":"Z. Tao, A. Cui, Xiwei Wang, X. Tao","doi":"10.1109/ICNC.2012.6234628","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234628","url":null,"abstract":"To obtain source and regional parameters, which are adopted to describe the earthquake source and crustal medium in a region to estimate ground motion, an inversion strategy is presented in this paper. Since these parameters are inversed from seismographic records by micro-genetic algorithm to establish strong ground motion attenuation relations, it is important to choose parameters not related with the sizes of earthquakes. One source parameter, stress drop Δσ, and four regional ones, Q0, η, R1 and R2, are selected as the inversed parameters.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"298 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115022712","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234752
W. Yi, Jihong Song
This paper research the non-linear system VanDerPol-Duffing oscillator behavior under the excitation of weak signal and non-Gaussion bounded noise based on random Melnikov methods, we find out the non-Gaussion bounded noise has little effect on the chaotic system, as for the bigger wiener process parameters, the gate value of the chaotic movement will be more bigger with the strength of non-Gaussion bounded noise. This paper researches the chaotic movement character under the excitation of weak signal and non-Gaussion bounded noise.
{"title":"Analysis of VanDerPol oscillator under excitation of non-Gaussian bounded noise","authors":"W. Yi, Jihong Song","doi":"10.1109/ICNC.2012.6234752","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234752","url":null,"abstract":"This paper research the non-linear system VanDerPol-Duffing oscillator behavior under the excitation of weak signal and non-Gaussion bounded noise based on random Melnikov methods, we find out the non-Gaussion bounded noise has little effect on the chaotic system, as for the bigger wiener process parameters, the gate value of the chaotic movement will be more bigger with the strength of non-Gaussion bounded noise. This paper researches the chaotic movement character under the excitation of weak signal and non-Gaussion bounded noise.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131084886","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234705
Ying-ying Zhang, A. Vorontcov, Ji-chang Sun, Yan Liu, G. Hou
The research of the single water quality parameter prediction has important directive significance to the evaluation, planning, early warning and management of water environment. This paper proposed a neural network rolling predictive method for the single water quality parameter. It integrates the rolling predictive control idea into the nonlinear neural network parameter modeling. The trend and the rule of the water quality in the future day can be well known on some historical measured data. The tests in the specific water area showed that, this method can be used for the single water quality parameter prediction in a rolling way.
{"title":"Rolling prediction of single water quality parameter based on neural network","authors":"Ying-ying Zhang, A. Vorontcov, Ji-chang Sun, Yan Liu, G. Hou","doi":"10.1109/ICNC.2012.6234705","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234705","url":null,"abstract":"The research of the single water quality parameter prediction has important directive significance to the evaluation, planning, early warning and management of water environment. This paper proposed a neural network rolling predictive method for the single water quality parameter. It integrates the rolling predictive control idea into the nonlinear neural network parameter modeling. The trend and the rule of the water quality in the future day can be well known on some historical measured data. The tests in the specific water area showed that, this method can be used for the single water quality parameter prediction in a rolling way.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134041660","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234627
Chuanjun Wang, Xuefeng Bai, Tiejun Zhang, X. Niu
This paper presents a Fourier series based expression deformation model for 3D face recognition. Given a set of training 3D face scans with sufficient facial expressions, these face scans are first preprocessed and represented as a series of Fourier series coefficients. Then, the shape residues between the non-neutral and neutral face scans of the same subject are calculated. These residues are supposed to contain the expression deformation patterns and PCA is applied to learn these patterns. The eigenvector with top eigenvalue in the generated lower dimensional subspace of PCA is then used to build the expression deformation model. Experimental results show the feasibility and merits of the proposed expression deformation model in the recognition scenario.
{"title":"A Fourier series based expression deformation model for 3D face recognition","authors":"Chuanjun Wang, Xuefeng Bai, Tiejun Zhang, X. Niu","doi":"10.1109/ICNC.2012.6234627","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234627","url":null,"abstract":"This paper presents a Fourier series based expression deformation model for 3D face recognition. Given a set of training 3D face scans with sufficient facial expressions, these face scans are first preprocessed and represented as a series of Fourier series coefficients. Then, the shape residues between the non-neutral and neutral face scans of the same subject are calculated. These residues are supposed to contain the expression deformation patterns and PCA is applied to learn these patterns. The eigenvector with top eigenvalue in the generated lower dimensional subspace of PCA is then used to build the expression deformation model. Experimental results show the feasibility and merits of the proposed expression deformation model in the recognition scenario.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133483376","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234547
Liping Liu
This paper deals with an operator based on plant output tracking design problem of time-delays nonlinear systems by using a robust right coprime factorization approach. In details, operator based nonlinear control systems are designed, and sufficient conditions for the designed feedback control systems are obtained. Based on the conditions, robust stability of the nonlinear systems is ensured and output tracking performance is also realized. A simulation example is given to support the proposed design scheme.
{"title":"Robust output tracking control for nonlinear systems using right coprime factorization","authors":"Liping Liu","doi":"10.1109/ICNC.2012.6234547","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234547","url":null,"abstract":"This paper deals with an operator based on plant output tracking design problem of time-delays nonlinear systems by using a robust right coprime factorization approach. In details, operator based nonlinear control systems are designed, and sufficient conditions for the designed feedback control systems are obtained. Based on the conditions, robust stability of the nonlinear systems is ensured and output tracking performance is also realized. A simulation example is given to support the proposed design scheme.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"63 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133719309","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：