Cultural algorithms provide a useful framework to make evolutionary algorithms more efficient. However, there is still much for revision especially when they are applied in the constrained optimizations, where a mass of memory and computation cost is currently unavoidable. We propose a novel triple spaces cultural algorithm in which a new framework called anti-culture population consisting of individuals disobeying the guidance of culture is added to the traditional dual inheritance cultural algorithm. The effect that the individuals in the anti-culture population disobey culture's guidance is ensured by some mutation operations which make the individuals away from the Culture guided individual in a radiating way. The anti-culture population makes the evolution of both culture and the population faster and at the same time take a lower risk of the local optimization problem. Moreover, with the triple spaces structure and some novel rules to control the convergence process of the algorithm through awarding the most successful individuals and punishing the unsuccessful population, it is possible to deal with a constrained optimization problem with computation burden almost the same as that in solving unconstrained optimization problems. genetic algorithm is utilized as the basis of the population space due to its advantages in representing the structure of the space and convenience in computation. Comparisons with four reported algorithms show that our proposed approach has significant advantages while the cost of computation and storage is much lower.
{"title":"Constrained Optimization Using Triple Spaces Cultured Genetic Algorithm","authors":"Wanwan Tang, Yanda Li","doi":"10.1109/ICNC.2008.336","DOIUrl":"https://doi.org/10.1109/ICNC.2008.336","url":null,"abstract":"Cultural algorithms provide a useful framework to make evolutionary algorithms more efficient. However, there is still much for revision especially when they are applied in the constrained optimizations, where a mass of memory and computation cost is currently unavoidable. We propose a novel triple spaces cultural algorithm in which a new framework called anti-culture population consisting of individuals disobeying the guidance of culture is added to the traditional dual inheritance cultural algorithm. The effect that the individuals in the anti-culture population disobey culture's guidance is ensured by some mutation operations which make the individuals away from the Culture guided individual in a radiating way. The anti-culture population makes the evolution of both culture and the population faster and at the same time take a lower risk of the local optimization problem. Moreover, with the triple spaces structure and some novel rules to control the convergence process of the algorithm through awarding the most successful individuals and punishing the unsuccessful population, it is possible to deal with a constrained optimization problem with computation burden almost the same as that in solving unconstrained optimization problems. genetic algorithm is utilized as the basis of the population space due to its advantages in representing the structure of the space and convenience in computation. Comparisons with four reported algorithms show that our proposed approach has significant advantages while the cost of computation and storage is much lower.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"74 1","pages":"589-593"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80144760","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, a new optimization algorithm called Clone Immune Network Classification Algorithm (CINC), is proposed for fault diagnosis of power transformers. The algorithm has merged the merits of population-based immune algorithm and network-based immune algorithm. The characteristics of training fault samples are studied and extracted by memory antibody set. Consequently, CINC can be used to find a limited number of antibodies which can represent all training fault samples distributed structures and features, which helps to realize dynamic classification. Then the testing fault samples are classified with the k-nearest neighbor method (KNN). Compared with previous immune network model and immune algorithm, this one can prevent prematurity, keep variety and avoid local optimal. Many fault samples have been tested by CINC algorithm, and its results are compared with those obtained by IEC three-ratio method (TRM) and BP neural network (BPNN) respectively. Comparison results show that the proposed algorithm is feasible and practical. The algorithm is of fast convergence rate and high diagnosis correctness.
{"title":"Clone Immune Network Classification Algorithm for Fault Diagnosis of Power Transformer","authors":"Guizhi Xiao, Hui-xian Huang, Min Yang","doi":"10.1109/ICNC.2008.644","DOIUrl":"https://doi.org/10.1109/ICNC.2008.644","url":null,"abstract":"In this paper, a new optimization algorithm called Clone Immune Network Classification Algorithm (CINC), is proposed for fault diagnosis of power transformers. The algorithm has merged the merits of population-based immune algorithm and network-based immune algorithm. The characteristics of training fault samples are studied and extracted by memory antibody set. Consequently, CINC can be used to find a limited number of antibodies which can represent all training fault samples distributed structures and features, which helps to realize dynamic classification. Then the testing fault samples are classified with the k-nearest neighbor method (KNN). Compared with previous immune network model and immune algorithm, this one can prevent prematurity, keep variety and avoid local optimal. Many fault samples have been tested by CINC algorithm, and its results are compared with those obtained by IEC three-ratio method (TRM) and BP neural network (BPNN) respectively. Comparison results show that the proposed algorithm is feasible and practical. The algorithm is of fast convergence rate and high diagnosis correctness.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"30 4 1","pages":"638-643"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80407231","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}
Tabu search (TS) algorithm is a powerful local search method. It has been successfully used in many discrete optimization problems, such as TSP, JSP, and QAP, etc. Neighborhood structure and size are key factors for a local search algorithm to get good performance. If hill climbing strategy is used, the bigger the size of a neighborhood is, the better its performance is in the cost of more computing time. Using the basic inversion and inserting move for TSP problem, this paper constructs a kind of linked neighborhood structure which uses the information get from previous move. Experiments were taken on some of the TSP instances from TSPLIB to compare the performance of different neighborhood structures. The simulation results show that the linked neighborhood structure has better performance.
{"title":"The Study of Neighborhood Structure of Tabu Search Algorithm for Traveling Salesman Problem","authors":"Yiwen Zhong, Chao Wu, Lishan Li, Zhengyuan Ning","doi":"10.1109/ICNC.2008.749","DOIUrl":"https://doi.org/10.1109/ICNC.2008.749","url":null,"abstract":"Tabu search (TS) algorithm is a powerful local search method. It has been successfully used in many discrete optimization problems, such as TSP, JSP, and QAP, etc. Neighborhood structure and size are key factors for a local search algorithm to get good performance. If hill climbing strategy is used, the bigger the size of a neighborhood is, the better its performance is in the cost of more computing time. Using the basic inversion and inserting move for TSP problem, this paper constructs a kind of linked neighborhood structure which uses the information get from previous move. Experiments were taken on some of the TSP instances from TSPLIB to compare the performance of different neighborhood structures. The simulation results show that the linked neighborhood structure has better performance.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"94 1","pages":"491-495"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79029409","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}
Traffic incident detection based on a fusion of various available data sources has been an evolving research topic in ITS. This paper proposes a data fusion model for traffic incident detection using BP neural network. In this model, the cumulative sum (CUSUM) approach is used to develop incident detection algorithms using loop detector data and probe vehicle data respectively, while the BP neural network combines the outputs from both incident detection algorithms. The proposed algorithm is tested and evaluated with the data generated by the simulation model INTEGRATION. The result shows that the outputs using BP neural network improves the accuracy provided by each single source incident detection algorithm.
{"title":"Back-Propagation Neural Network for Traffic Incident Detection Based on Fusion of Loop Detector and Probe Vehicle Data","authors":"Liu Yu, Lei Yu, Jianquan Wang, Y. Qi, H. Wen","doi":"10.1109/ICNC.2008.54","DOIUrl":"https://doi.org/10.1109/ICNC.2008.54","url":null,"abstract":"Traffic incident detection based on a fusion of various available data sources has been an evolving research topic in ITS. This paper proposes a data fusion model for traffic incident detection using BP neural network. In this model, the cumulative sum (CUSUM) approach is used to develop incident detection algorithms using loop detector data and probe vehicle data respectively, while the BP neural network combines the outputs from both incident detection algorithms. The proposed algorithm is tested and evaluated with the data generated by the simulation model INTEGRATION. The result shows that the outputs using BP neural network improves the accuracy provided by each single source incident detection algorithm.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"32 1","pages":"116-120"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79068893","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}
Sheng Zhong, Baihai Zhang, Qiao Li, Jun Yu Li, Zhiwei Lin
This paper investigates an adaptive evolutionary genetic algorithm on combinatorial optimization problem, where the solution space can be organized in form of a subset tree. A kind of genetic gene uniform encode scheme and adaptive evolution idea are used before proceeding crossover operation, and crossover is achieved between the current and previous generations individual. The orthogonal table approach is utilized to produce initial population, which can satisfy the multiplicity of the initial population. Two examples are provided to illustrate the effectiveness of the proposed methods.
{"title":"Adaptive Evolutionary Genetic Algorithms on a Class of Combinatorial Optimization Problems","authors":"Sheng Zhong, Baihai Zhang, Qiao Li, Jun Yu Li, Zhiwei Lin","doi":"10.1109/ICNC.2008.547","DOIUrl":"https://doi.org/10.1109/ICNC.2008.547","url":null,"abstract":"This paper investigates an adaptive evolutionary genetic algorithm on combinatorial optimization problem, where the solution space can be organized in form of a subset tree. A kind of genetic gene uniform encode scheme and adaptive evolution idea are used before proceeding crossover operation, and crossover is achieved between the current and previous generations individual. The orthogonal table approach is utilized to produce initial population, which can satisfy the multiplicity of the initial population. Two examples are provided to illustrate the effectiveness of the proposed methods.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"7 1","pages":"166-170"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81800513","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}
Based on reviewing the research progress of evolving model for small-world network, the defects of present studies were pointed out. Taking a square grid as the basis, an evolving model for small-world network based on benefit choice was built. This model is different from other papers in which limitation of vector' degree was considered. Then, the author proposed a simulation scheme and compared the network generated by simulation with a same scale random network. The results show that this network has small-world characteristic. Finally, several directions were given.
{"title":"Evolving Model for Small-World Network Based on Benefit Choice","authors":"Shuang Chen, Yue-Ping Zhao","doi":"10.1109/ICNC.2008.700","DOIUrl":"https://doi.org/10.1109/ICNC.2008.700","url":null,"abstract":"Based on reviewing the research progress of evolving model for small-world network, the defects of present studies were pointed out. Taking a square grid as the basis, an evolving model for small-world network based on benefit choice was built. This model is different from other papers in which limitation of vector' degree was considered. Then, the author proposed a simulation scheme and compared the network generated by simulation with a same scale random network. The results show that this network has small-world characteristic. Finally, several directions were given.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"97 1","pages":"448-450"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85377726","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}
Map projection transformation is a basic operation for topographic and spatial data transformation in geographic information system. Existing methods need projection type and corresponding parameters, and manually select regression model. The transformation formulas are complex with operators based on cartology. This paper applies gene expression programming technique to projection transformation. The contributions include: (1)Formalizing the concepts of projection gene and generation gap, etc.; (2)Designing the fitness function with penalty; (3)Proposing a novel method of projection transformation-GEP based on multi-variable niches(MVN-GEP); The method automatically evolves the constants and constructs the easy formulas; proposing the algorithms of partitioning multi-variable niches(PMVN) and replacing individuals(RI); (4)Experiments show that new method is effective and the output formulas are easy. The average top fitness of geodetic abscissa is 97.1324 and that of geodetic ordinate is 97.7351; The average generation of geodetic abscissa is 238 and that of geodetic ordinate is 216.
{"title":"Mining Projection Transformation Based on Gene Expression Programming of Multi-Variable Niches","authors":"Yue Jiang, Changjie Tang, Haichun Zheng, Jiaoling Zheng, Chuan Li, Qian Luo, Jun Zhu","doi":"10.1109/ICNC.2008.53","DOIUrl":"https://doi.org/10.1109/ICNC.2008.53","url":null,"abstract":"Map projection transformation is a basic operation for topographic and spatial data transformation in geographic information system. Existing methods need projection type and corresponding parameters, and manually select regression model. The transformation formulas are complex with operators based on cartology. This paper applies gene expression programming technique to projection transformation. The contributions include: (1)Formalizing the concepts of projection gene and generation gap, etc.; (2)Designing the fitness function with penalty; (3)Proposing a novel method of projection transformation-GEP based on multi-variable niches(MVN-GEP); The method automatically evolves the constants and constructs the easy formulas; proposing the algorithms of partitioning multi-variable niches(PMVN) and replacing individuals(RI); (4)Experiments show that new method is effective and the output formulas are easy. The average top fitness of geodetic abscissa is 97.1324 and that of geodetic ordinate is 97.7351; The average generation of geodetic abscissa is 238 and that of geodetic ordinate is 216.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"46 1","pages":"288-292"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85617381","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}
With the increase of wind power installed capacities, the cost of integration is large due to the intermittent nature of wind energy. To accommodate wind farm power fluctuations, additional control measures are required. Accurate characterization of the fluctuations paves the way for optimal control design. In identifying localized characteristics of the signal, wavelet transform provides a suitable tool. Data gathered at a wind farm of New Mexico are studied with its daily output variations characterized using wavelet transform.
{"title":"Characterization of Daily Wind Farm Power Fluctuations Using Wavelet Transform","authors":"X. Chu, Wen Zhang, T. Nwachukwu, I. Hiskens","doi":"10.1109/ICNC.2008.133","DOIUrl":"https://doi.org/10.1109/ICNC.2008.133","url":null,"abstract":"With the increase of wind power installed capacities, the cost of integration is large due to the intermittent nature of wind energy. To accommodate wind farm power fluctuations, additional control measures are required. Accurate characterization of the fluctuations paves the way for optimal control design. In identifying localized characteristics of the signal, wavelet transform provides a suitable tool. Data gathered at a wind farm of New Mexico are studied with its daily output variations characterized using wavelet transform.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"30 1","pages":"481-485"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85955347","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}
Analyzing notor imagery electrocardiogram (ECoG) signal is very challenging for it is hard to set up a classifier based on the labeled ECoG obtained in the first session and apply it to the unlabeled test data obtained in the second session. Here we propose a new approach to analyze ECoG trails in the case of session-to-session transfer exists. In our approach, firstly, dimension reduction is performed with independent component analysis (ICA) decomposition. Secondly, ECoG trials are clustered by an unsupervised learning algorithm called affinity propagation. Primary experimental results show that the proposed approach gives the reasonable result than that using the classical K-means clustering algorithm.
{"title":"ECoG Analysis with Affinity Propagation Algorithm","authors":"Yuan Yuan, Anbang Xu, Ping Guo, Jia-cai Zhang","doi":"10.1109/ICNC.2008.495","DOIUrl":"https://doi.org/10.1109/ICNC.2008.495","url":null,"abstract":"Analyzing notor imagery electrocardiogram (ECoG) signal is very challenging for it is hard to set up a classifier based on the labeled ECoG obtained in the first session and apply it to the unlabeled test data obtained in the second session. Here we propose a new approach to analyze ECoG trails in the case of session-to-session transfer exists. In our approach, firstly, dimension reduction is performed with independent component analysis (ICA) decomposition. Secondly, ECoG trials are clustered by an unsupervised learning algorithm called affinity propagation. Primary experimental results show that the proposed approach gives the reasonable result than that using the classical K-means clustering algorithm.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"30 1","pages":"52-56"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85968385","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}
We present a new computational approach to measure the distance between two biological sequences. A biological sequence quantifies as a Markov Chain with 20 states. Stochastic state transition matrix is computed as the quantitative index of the biological sequence. The Kullback-Leibler discrimination information is used as a diversity indicator to measure the dissimilarity of each pair of the rows in the two state transition matrix. Distance between the two sequences is defined as the average value with the weight of the occurrence possibility of each amino acid. We illustrate its application in reconstructing a phylogeny of the Eutherian orders using concatenated H-stranded amino acid sequences. This phylogeny is consistent with the commonly accepted one for the Eutherians.
{"title":"A Novel Measurement of Sequence Dissimilarity and Its Application to Phylogeny","authors":"Xiao-hui Niu, Nana Li, Feng Shi, Xue-yan Li","doi":"10.1109/ICNC.2008.299","DOIUrl":"https://doi.org/10.1109/ICNC.2008.299","url":null,"abstract":"We present a new computational approach to measure the distance between two biological sequences. A biological sequence quantifies as a Markov Chain with 20 states. Stochastic state transition matrix is computed as the quantitative index of the biological sequence. The Kullback-Leibler discrimination information is used as a diversity indicator to measure the dissimilarity of each pair of the rows in the two state transition matrix. Distance between the two sequences is defined as the average value with the weight of the occurrence possibility of each amino acid. We illustrate its application in reconstructing a phylogeny of the Eutherian orders using concatenated H-stranded amino acid sequences. This phylogeny is consistent with the commonly accepted one for the Eutherians.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":"37 1","pages":"231-234"},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85974249","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：