Pub Date : 2011-09-19DOI: 10.1109/ICNC.2011.6022163
H. Ketout, J. Gu, G. Horne
In this paper, Universal Binary Neurons Cellular Neural Networks (UBN_CNN) endocardial edge detection is proposed. The echocardiographic image is preprocessed to enhance the contrast and smoothness by utilizing Multi Valued Neural Cellular Neural Networks (MVN_CNN) non linear filter. UBN_CNN is applied to the smoothed image to extract the heart boundaries. A non threshold Boolean function with nine variables is utilized to detect the edges corresponding to the upward and downward brightness overleaps. Some experimental results are given for different echocardiographic images. The combination of MVN_CNN and UBN_CNN approach showed better results for extracting the LV endocardial boundaries.
{"title":"MVN_CNN and UBN_CNN for endocardial edge detection","authors":"H. Ketout, J. Gu, G. Horne","doi":"10.1109/ICNC.2011.6022163","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022163","url":null,"abstract":"In this paper, Universal Binary Neurons Cellular Neural Networks (UBN_CNN) endocardial edge detection is proposed. The echocardiographic image is preprocessed to enhance the contrast and smoothness by utilizing Multi Valued Neural Cellular Neural Networks (MVN_CNN) non linear filter. UBN_CNN is applied to the smoothed image to extract the heart boundaries. A non threshold Boolean function with nine variables is utilized to detect the edges corresponding to the upward and downward brightness overleaps. Some experimental results are given for different echocardiographic images. The combination of MVN_CNN and UBN_CNN approach showed better results for extracting the LV endocardial boundaries.","PeriodicalId":299503,"journal":{"name":"2011 Seventh International Conference on Natural Computation","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124454824","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 : 2011-09-19DOI: 10.1109/ICNC.2011.6022513
Y. Saika, T. Aoki
We formulate the problem of inverse halftoning using multiple dithered images utilizing the Bayesian inference via the maximizer of the posterior marginal (MPM) estimate on the basis of statistical mechanics of the Q-Ising model. From the theoretical point of view, the Monte Carlo simulation for a set of snapshots of the Q-Ising model clarifies that the performance is improved introducing the prior information on original images into the MPM estimate and that the optimal performance is realized around the Bayes-optimal condition within statistical uncertainty. Then, these properties are qualitatively confirmed by the analytical estimate via the infinite-range model. Next, we try the Bethe approximation established in statistical mechanics for this problem. Numerical simulations clarify that the Bethe approximation works as well as the MPM estimate via the Monte Carlo simulation for 256-level standard images, if we set parameters of the model prior appropriately.
{"title":"Bethe approximation to inverse halftoning using multiple halftone images","authors":"Y. Saika, T. Aoki","doi":"10.1109/ICNC.2011.6022513","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022513","url":null,"abstract":"We formulate the problem of inverse halftoning using multiple dithered images utilizing the Bayesian inference via the maximizer of the posterior marginal (MPM) estimate on the basis of statistical mechanics of the Q-Ising model. From the theoretical point of view, the Monte Carlo simulation for a set of snapshots of the Q-Ising model clarifies that the performance is improved introducing the prior information on original images into the MPM estimate and that the optimal performance is realized around the Bayes-optimal condition within statistical uncertainty. Then, these properties are qualitatively confirmed by the analytical estimate via the infinite-range model. Next, we try the Bethe approximation established in statistical mechanics for this problem. Numerical simulations clarify that the Bethe approximation works as well as the MPM estimate via the Monte Carlo simulation for 256-level standard images, if we set parameters of the model prior appropriately.","PeriodicalId":299503,"journal":{"name":"2011 Seventh International Conference on Natural Computation","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123362527","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 : 2011-09-19DOI: 10.1109/ICNC.2011.6022377
Ling Wang, Chao Xing, Jie Yan
The problem of aircraft recognition in a single image is analyzed. A novel method combined Fourier series representation and nonparametric statistics is introduced to do pattern recognition for aircraft. Silhouettes obtained by image segmentation are described by Fourier series, after which empirical distribution function of curvature is computed. Fast matching is performed with coarse hypothesis test for partial classification. The re#ned hypothesis test is used to get detailed matching result. Experimental results show the effectiveness of the algorithm for shape recognition.
{"title":"Aircraft recognition based on nonparametrical statistics","authors":"Ling Wang, Chao Xing, Jie Yan","doi":"10.1109/ICNC.2011.6022377","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022377","url":null,"abstract":"The problem of aircraft recognition in a single image is analyzed. A novel method combined Fourier series representation and nonparametric statistics is introduced to do pattern recognition for aircraft. Silhouettes obtained by image segmentation are described by Fourier series, after which empirical distribution function of curvature is computed. Fast matching is performed with coarse hypothesis test for partial classification. The re#ned hypothesis test is used to get detailed matching result. Experimental results show the effectiveness of the algorithm for shape recognition.","PeriodicalId":299503,"journal":{"name":"2011 Seventh International Conference on Natural Computation","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130196617","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 : 2011-09-19DOI: 10.1109/ICNC.2011.6022536
Takanori Komatsu, A. Namatame
Many real-world networks increase interdependencies and this creates challenges for handling network risks like cascading failure. In this paper, we propose an evolutionary approach for designing optimal networks to mitigate network risks. In general there is usually a trade-off between risk contagion and risk sharing, and optimizing a network requires the selection of a proper fitness function. We use the maximum eigenvalue of the adjacency matrix of a network to control risk contagion. The evolutionary optimized networks are characterized as homogeneous networks where all nodes have, roughly speaking, the same degree. We also show that maximum eigenvalue can be used as the index of robustness against cascading failure. The network with smaller maximum eigenvalue has better robustness against cascading failure.
{"title":"An evolutionary optimal network design to mitigate risk contagion","authors":"Takanori Komatsu, A. Namatame","doi":"10.1109/ICNC.2011.6022536","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022536","url":null,"abstract":"Many real-world networks increase interdependencies and this creates challenges for handling network risks like cascading failure. In this paper, we propose an evolutionary approach for designing optimal networks to mitigate network risks. In general there is usually a trade-off between risk contagion and risk sharing, and optimizing a network requires the selection of a proper fitness function. We use the maximum eigenvalue of the adjacency matrix of a network to control risk contagion. The evolutionary optimized networks are characterized as homogeneous networks where all nodes have, roughly speaking, the same degree. We also show that maximum eigenvalue can be used as the index of robustness against cascading failure. The network with smaller maximum eigenvalue has better robustness against cascading failure.","PeriodicalId":299503,"journal":{"name":"2011 Seventh International Conference on Natural Computation","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132062037","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 : 2011-09-19DOI: 10.1109/ICNC.2011.6022195
Wenpan Liu, Jinhua Zheng, Mulin Wu, Juan Zou
Prematurity and slow convergence are two difficult problems in genetic algorithm, a new crossover is proposed, named hybrid crossover operator based on pattern, to gain a better convergence to the optimal solution. To retain the diversity of population, the approach of pattern is used, together with the behavior of antitone. The new method can be used for those application problems which are wanted to reach their best value quickly. More experiments show that the new crossover can find the global optimal solution and improve convergence ratio obviously.
{"title":"Hybrid crossover operator based on pattern","authors":"Wenpan Liu, Jinhua Zheng, Mulin Wu, Juan Zou","doi":"10.1109/ICNC.2011.6022195","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022195","url":null,"abstract":"Prematurity and slow convergence are two difficult problems in genetic algorithm, a new crossover is proposed, named hybrid crossover operator based on pattern, to gain a better convergence to the optimal solution. To retain the diversity of population, the approach of pattern is used, together with the behavior of antitone. The new method can be used for those application problems which are wanted to reach their best value quickly. More experiments show that the new crossover can find the global optimal solution and improve convergence ratio obviously.","PeriodicalId":299503,"journal":{"name":"2011 Seventh International Conference on Natural Computation","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123517623","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 : 2011-09-19DOI: 10.1109/ICNC.2011.6022277
Ze Zhang, Tuopeng Tong, Kai Song
In this paper, a novel regression algorithm, the Generalized Partial Least Squares Gaussian Process (GPLS-GP), is developed to improve the prediction performance of regression model. Profiting from the latent variables extraction power of PLS, noise, co-linearity between independent variables and other difficult problems could be overcome successfully. More importantly, by designing generalizing variables rationally and by taking advantages of the nonlinear regression superiority of GP (Gaussian process) to calculate the inner model, the nonlinear relationship of the process could be modeled to the most extreme. The theoretical findings are fully supported by the application performed on the prediction of the mean temperature of Izmir of Turkey. It is shown, in comparison to conventional approaches (GPLS, PLS and GP), the model of GPLS-GP yields superior performance while the Root-Mean-Square-Error (RMSE) of calibration and prediction are both improved notably.
{"title":"A novel GPLS-GP algorithm and its application to air temperature prediction","authors":"Ze Zhang, Tuopeng Tong, Kai Song","doi":"10.1109/ICNC.2011.6022277","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022277","url":null,"abstract":"In this paper, a novel regression algorithm, the Generalized Partial Least Squares Gaussian Process (GPLS-GP), is developed to improve the prediction performance of regression model. Profiting from the latent variables extraction power of PLS, noise, co-linearity between independent variables and other difficult problems could be overcome successfully. More importantly, by designing generalizing variables rationally and by taking advantages of the nonlinear regression superiority of GP (Gaussian process) to calculate the inner model, the nonlinear relationship of the process could be modeled to the most extreme. The theoretical findings are fully supported by the application performed on the prediction of the mean temperature of Izmir of Turkey. It is shown, in comparison to conventional approaches (GPLS, PLS and GP), the model of GPLS-GP yields superior performance while the Root-Mean-Square-Error (RMSE) of calibration and prediction are both improved notably.","PeriodicalId":299503,"journal":{"name":"2011 Seventh International Conference on Natural Computation","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126134995","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 : 2011-09-19DOI: 10.1109/ICNC.2011.6022178
Y. Zhiqiang, Zhang Baoan, Zhang Jimin, W. Chenhui
For the model of semi-active suspension system of high-speed railway vehicle which has nonlinear features, the mathematical model of a quarter of vehicle has been established, and in the semi-active suspension system, a PID controller and a PID controller based on BP neural network have been established, respectively, and simulations of high-speed vehicle are carried out under the condition of passive suspension and semi-active suspension employing PID control algorithm based on BP neural network, then to compare the stabilities of high-speed railway vehicle in the above two cases. The simulation results will show that: high-speed railway vehicle of semi-active suspension by adopting PID control method based on BP neural network can effectively improve the stability of high-speed railway vehicle.
{"title":"Notice of RetractionResearch on semi-active control of high-speed railway vehicle based on neural network-PID control","authors":"Y. Zhiqiang, Zhang Baoan, Zhang Jimin, W. Chenhui","doi":"10.1109/ICNC.2011.6022178","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022178","url":null,"abstract":"For the model of semi-active suspension system of high-speed railway vehicle which has nonlinear features, the mathematical model of a quarter of vehicle has been established, and in the semi-active suspension system, a PID controller and a PID controller based on BP neural network have been established, respectively, and simulations of high-speed vehicle are carried out under the condition of passive suspension and semi-active suspension employing PID control algorithm based on BP neural network, then to compare the stabilities of high-speed railway vehicle in the above two cases. The simulation results will show that: high-speed railway vehicle of semi-active suspension by adopting PID control method based on BP neural network can effectively improve the stability of high-speed railway vehicle.","PeriodicalId":299503,"journal":{"name":"2011 Seventh International Conference on Natural Computation","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114376427","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 : 2011-07-26DOI: 10.1109/ICNC.2011.6022114
Yang Ke-ming, Xu Zhao-hui, Li Hong-wei, Cui Li, Ran Ying-ying, Zhang Yong-jie
A SOM (Self-organizing Feature Maps) model was introduced to cluster and analysis on the disease severity of wheat stripe rust based on PHI (Pushbroom hyperspectral imager) data. By means of acquiring the spectral index data (SID) and spectral angle data (SAD) of the samples, combining with the samples' spectral average reflectance data (ARD), three two-dimensional data matrixes were obtained as the inputs of SOM model. After iterative learning and self-organized clustering, the models' outputs farthest approached to the reality in 3-dimensional severity space of wheat stripe rust. Then, with the net-trained, all data of the trial plot were simulated. The simulating results demonstrate that the division of wheat stripe rust severity is obviously. The whole trial spot was derived into four grades and the results are satisfactory.
{"title":"Notice of RetractionClustering analysis on disease severity of wheat stripe rust based on SOM neural network","authors":"Yang Ke-ming, Xu Zhao-hui, Li Hong-wei, Cui Li, Ran Ying-ying, Zhang Yong-jie","doi":"10.1109/ICNC.2011.6022114","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022114","url":null,"abstract":"A SOM (Self-organizing Feature Maps) model was introduced to cluster and analysis on the disease severity of wheat stripe rust based on PHI (Pushbroom hyperspectral imager) data. By means of acquiring the spectral index data (SID) and spectral angle data (SAD) of the samples, combining with the samples' spectral average reflectance data (ARD), three two-dimensional data matrixes were obtained as the inputs of SOM model. After iterative learning and self-organized clustering, the models' outputs farthest approached to the reality in 3-dimensional severity space of wheat stripe rust. Then, with the net-trained, all data of the trial plot were simulated. The simulating results demonstrate that the division of wheat stripe rust severity is obviously. The whole trial spot was derived into four grades and the results are satisfactory.","PeriodicalId":299503,"journal":{"name":"2011 Seventh International Conference on Natural Computation","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115147985","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 : 2011-07-26DOI: 10.1109/ICNC.2011.6022378
Jian Sun, Yuting Wang, Jun-qing Li, K. Gao
Chemical Reaction Optimization (CRO) is a new heuristic optimization method mimicking the process of a chemical reaction where molecules interact with each other aiming to reach the minimum state of free energy. CRO has demonstrated its capability in solving NP-hard optimization problems. The Lin-Kernighan(LK) local search is known to be one of the most successful heuristics for the Traveling Salesman Problem (TSP). In this paper, we present a hybrid algorithm based on CRO and LK local search for TSP. The proposed algorithm consider the tradeoff between the exploration abilities of CRO and the exploitation abilities of LK local searcher. Experimental results show that the proposed algorithm is efficient.
{"title":"Hybrid algorithm based on Chemical Reaction Optimization and Lin-Kernighan local search for the Traveling Salesman Problem","authors":"Jian Sun, Yuting Wang, Jun-qing Li, K. Gao","doi":"10.1109/ICNC.2011.6022378","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022378","url":null,"abstract":"Chemical Reaction Optimization (CRO) is a new heuristic optimization method mimicking the process of a chemical reaction where molecules interact with each other aiming to reach the minimum state of free energy. CRO has demonstrated its capability in solving NP-hard optimization problems. The Lin-Kernighan(LK) local search is known to be one of the most successful heuristics for the Traveling Salesman Problem (TSP). In this paper, we present a hybrid algorithm based on CRO and LK local search for TSP. The proposed algorithm consider the tradeoff between the exploration abilities of CRO and the exploitation abilities of LK local searcher. Experimental results show that the proposed algorithm is efficient.","PeriodicalId":299503,"journal":{"name":"2011 Seventh International Conference on Natural Computation","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115162399","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}
How to generate a personalized 3D virtual body model conveniently and quickly is playing an increasingly important role in computer animation, virtual reality, entertainment, e-commerce and many other areas. Some related researchers just simply adjust human characteristic parameters to generate body model using existing 3D body model. In this article, in order to generate the personalized 3D virtual body model quickly, an approach based on Fuzzy Support Vector Machines (FSVM) is suggested. This constructs a classification model of the personalized body characteristic parameter. The one-versus-one (OVO) method based on the binary tree is used to handle a multiclass problem by breaking it into various two-class problems. Application of the method shows that the method of FSVM has the characteristics of less calculation and less error in the allowed range than the classical neural network.
{"title":"A method for customizing 3D virtual human body models based on Multi-class Support Vector Machine","authors":"Yongjian Sun, Renwang Li, Changjiang Wan, Xiumei Zhang","doi":"10.1109/ICNC.2011.6022036","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022036","url":null,"abstract":"How to generate a personalized 3D virtual body model conveniently and quickly is playing an increasingly important role in computer animation, virtual reality, entertainment, e-commerce and many other areas. Some related researchers just simply adjust human characteristic parameters to generate body model using existing 3D body model. In this article, in order to generate the personalized 3D virtual body model quickly, an approach based on Fuzzy Support Vector Machines (FSVM) is suggested. This constructs a classification model of the personalized body characteristic parameter. The one-versus-one (OVO) method based on the binary tree is used to handle a multiclass problem by breaking it into various two-class problems. Application of the method shows that the method of FSVM has the characteristics of less calculation and less error in the allowed range than the classical neural network.","PeriodicalId":299503,"journal":{"name":"2011 Seventh International Conference on Natural Computation","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115298446","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：