Pub Date : 2012-05-29DOI: 10.1109/ICNC.2012.6234592
Yunong Zhang, Yanyan Shi, Lin Xiao, Bingguo Mu
For solving systems of time-varying nonlinear equations, this paper generalizes a special kind of recurrent neural network by using a design method proposed by Zhang et al. Such a recurrent neural network (termed Zhang neural network, ZNN) is designed based on an indefinite error-function instead of a norm-based energy function. Theoretical analysis and results of convergence and stability are presented to show the desirable properties (e.g., large-scale exponential convergence) of ZNN via two different activation-function arrays for solving systems of time-varying nonlinear equations. Computer-simulation results substantiate further the theoretical analysis and efficacy of ZNN for solving systems of time-varying nonlinear equations.
{"title":"Convergence and stability results of Zhang neural network solving systems of time-varying nonlinear equations","authors":"Yunong Zhang, Yanyan Shi, Lin Xiao, Bingguo Mu","doi":"10.1109/ICNC.2012.6234592","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234592","url":null,"abstract":"For solving systems of time-varying nonlinear equations, this paper generalizes a special kind of recurrent neural network by using a design method proposed by Zhang et al. Such a recurrent neural network (termed Zhang neural network, ZNN) is designed based on an indefinite error-function instead of a norm-based energy function. Theoretical analysis and results of convergence and stability are presented to show the desirable properties (e.g., large-scale exponential convergence) of ZNN via two different activation-function arrays for solving systems of time-varying nonlinear equations. Computer-simulation results substantiate further the theoretical analysis and efficacy of ZNN for solving systems of time-varying nonlinear equations.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"38 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":"131989197","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.2012.6234769
Geng Lin
The max-cut problem is a classical combinatorial optimization problem. This paper uses a Population Reinforced Optimization Based Exploration (PROBE) as a framework for developing metaheuristic algorithm for solving the max-cut problem. A solution is constructed by a greedy construction method, then a local search procedure, which is based on the Fiduccia and Mattheyses heuristic, is used to improve the solution. Experimental tests are done on some instances taken from the literature. The experiment results and comparisons show that the proposed algorithm is efficient for these tested benchmarks.
{"title":"A PROBE-based algorithm for the max-cut problem","authors":"Geng Lin","doi":"10.1109/ICNC.2012.6234769","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234769","url":null,"abstract":"The max-cut problem is a classical combinatorial optimization problem. This paper uses a Population Reinforced Optimization Based Exploration (PROBE) as a framework for developing metaheuristic algorithm for solving the max-cut problem. A solution is constructed by a greedy construction method, then a local search procedure, which is based on the Fiduccia and Mattheyses heuristic, is used to improve the solution. Experimental tests are done on some instances taken from the literature. The experiment results and comparisons show that the proposed algorithm is efficient for these tested benchmarks.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"70 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":"115102904","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.2012.6234568
Biao Yuan, Chaoyong Zhang, Kunlei Lian, X. Shao
Assembly sequence planning (ASP) refers to taking the related constraint factors such as assembly features, assembly tools and machines into consideration to generate a low-cost feasible sequence. In this paper, a mathematical model of assembly sequence planning problem based on connectors is constructed, and a hybrid honey-bees mating optimization (HBMO) algorithm is proposed for solving this ASP problem. The proposed algorithm has two main innovative features compared to the conventional HBMO algorithm. Firstly, a crossover operator, called Multipoint Precedence Crossover (MPX), is proposed, which can avoid the generation of infeasible solutions and preserve the meaningful characteristics of the queen and broods. Secondly, worker bees utilize the simulated annealing (SA) algorithm as a local search method to improve the broods, which makes the proposed algorithm achieve the right balance between intensification and diversification. The hybrid HBMO algorithm is tested on three practical instances and compared with other approaches, such as Guided-GAs, MAs (memetic algorithm) and AIS (artificial immune systems). The superior results on these practical instances validate the effectiveness of the proposed algorithm.
{"title":"A hybrid honey-bees mating optimization algorithm for assembly sequence planning problem","authors":"Biao Yuan, Chaoyong Zhang, Kunlei Lian, X. Shao","doi":"10.1109/ICNC.2012.6234568","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234568","url":null,"abstract":"Assembly sequence planning (ASP) refers to taking the related constraint factors such as assembly features, assembly tools and machines into consideration to generate a low-cost feasible sequence. In this paper, a mathematical model of assembly sequence planning problem based on connectors is constructed, and a hybrid honey-bees mating optimization (HBMO) algorithm is proposed for solving this ASP problem. The proposed algorithm has two main innovative features compared to the conventional HBMO algorithm. Firstly, a crossover operator, called Multipoint Precedence Crossover (MPX), is proposed, which can avoid the generation of infeasible solutions and preserve the meaningful characteristics of the queen and broods. Secondly, worker bees utilize the simulated annealing (SA) algorithm as a local search method to improve the broods, which makes the proposed algorithm achieve the right balance between intensification and diversification. The hybrid HBMO algorithm is tested on three practical instances and compared with other approaches, such as Guided-GAs, MAs (memetic algorithm) and AIS (artificial immune systems). The superior results on these practical instances validate the effectiveness of the proposed algorithm.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"108 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":"115174027","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.2012.6234632
Chae-Ho Lee, Ji-Yong Park, Jae-Yong Park, Seog-young Han
Artificial bee colony algorithm (ABCA) as one of swarm intelligence methods and finite element analysis are first adopted for structural topology optimization. The objective of the paper is to examine the effectiveness and applicability of the suggested ABCA in structural topology optimization. This paper describes considerable modifications made to the ABCA in order to solve discrete topology optimization problems. The desirable conclusions are obtained through the results of the examples based on the suggested ABCA.
{"title":"Application of artificial bee colony algorithm for structural topology optimization","authors":"Chae-Ho Lee, Ji-Yong Park, Jae-Yong Park, Seog-young Han","doi":"10.1109/ICNC.2012.6234632","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234632","url":null,"abstract":"Artificial bee colony algorithm (ABCA) as one of swarm intelligence methods and finite element analysis are first adopted for structural topology optimization. The objective of the paper is to examine the effectiveness and applicability of the suggested ABCA in structural topology optimization. This paper describes considerable modifications made to the ABCA in order to solve discrete topology optimization problems. The desirable conclusions are obtained through the results of the examples based on the suggested ABCA.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"11 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":"116022721","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.2012.6234557
Xiaohuan Li, Zhixia Yang
In this paper we propose a new algorithm called adaptive support vector machine with homogeneous decision function. In our algorithm, the distribution of samples has been taken into consideration, so that the margin of bounding hyperplanes is as large as possible. Moreover, we introduce a pair of parameters v+ and v- to control bounds of the fractions of support vectors and margin errors. We also show that our algorithm can deal with imbalanced data effectively. Experiments on several artificial and UCI datasets indicate the proposed algorithm has good classification accuracy.
{"title":"Adaptive support vector machine with homogeneous decision function","authors":"Xiaohuan Li, Zhixia Yang","doi":"10.1109/ICNC.2012.6234557","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234557","url":null,"abstract":"In this paper we propose a new algorithm called adaptive support vector machine with homogeneous decision function. In our algorithm, the distribution of samples has been taken into consideration, so that the margin of bounding hyperplanes is as large as possible. Moreover, we introduce a pair of parameters v+ and v- to control bounds of the fractions of support vectors and margin errors. We also show that our algorithm can deal with imbalanced data effectively. Experiments on several artificial and UCI datasets indicate the proposed algorithm has good classification accuracy.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"1 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":"114704806","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.2012.6234728
Rui Li, Min Huang, Xingwei Wang
This paper studies logistics network design problem of fourth party logistics (4PL) in dynamic environment with disruptions to be considered. A two-stage stochastic optimization model is formulated. The first stage is to determine the network structure with the minimal total cost and the second stage is to minimize the operation cost of the network given disruption scenario. To solve it, a harmony search method is designed, which combines with Monte Carlo simulation. Several experiments are presented to test the significance of the model as well as the effectiveness of the proposed algorithm.
{"title":"Harmony search for dynamic logistics network design of 4PL with disruption","authors":"Rui Li, Min Huang, Xingwei Wang","doi":"10.1109/ICNC.2012.6234728","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234728","url":null,"abstract":"This paper studies logistics network design problem of fourth party logistics (4PL) in dynamic environment with disruptions to be considered. A two-stage stochastic optimization model is formulated. The first stage is to determine the network structure with the minimal total cost and the second stage is to minimize the operation cost of the network given disruption scenario. To solve it, a harmony search method is designed, which combines with Monte Carlo simulation. Several experiments are presented to test the significance of the model as well as the effectiveness of the proposed algorithm.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"1 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":"134536008","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.2012.6234609
Xing-Ling Wang, Xue-Lian Wu, Bing-Yu Sun
Predicting relief food demand effectively and accurately after nature disasters is a key to maintain the life of victims. Currently, the main methods for forecasting relief food are based on the experts and the predication results are influenced by the experiences of the experts. So how to predicate the relief food demand based on the obtained nature disaster cases is a very important problem. In this paper we present a novel method to predicate the relief food demand using support vector machine. To select the factors which have influence on relief food demand, recursive feature elimination algorithm is adopted. The experimental results on real disaster cases of Hubei province of China prove the performance of the proposed method.
{"title":"Factor selection and regression for forecasting relief food demand","authors":"Xing-Ling Wang, Xue-Lian Wu, Bing-Yu Sun","doi":"10.1109/ICNC.2012.6234609","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234609","url":null,"abstract":"Predicting relief food demand effectively and accurately after nature disasters is a key to maintain the life of victims. Currently, the main methods for forecasting relief food are based on the experts and the predication results are influenced by the experiences of the experts. So how to predicate the relief food demand based on the obtained nature disaster cases is a very important problem. In this paper we present a novel method to predicate the relief food demand using support vector machine. To select the factors which have influence on relief food demand, recursive feature elimination algorithm is adopted. The experimental results on real disaster cases of Hubei province of China prove the performance of the proposed method.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"118 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":"133297195","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.2012.6234674
Lingran Ma, Hang-jun Wang
This paper propose a new method for wood recognition based on texture analysis. At first, wood texture images are divided into several blocks in our method. Secondly, wood features are extracted from these blocked grey-scale images using different mask, which is knows as higher-order local autocorrelation (HLAC). Finally, Support Vector Machine (SVM) was used to verify the performance of the method. Experiments carried on the wood texture database demonstrate that our method outperforms the original HLAC method.
{"title":"A new method for wood recognition based on blocked HLAC","authors":"Lingran Ma, Hang-jun Wang","doi":"10.1109/ICNC.2012.6234674","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234674","url":null,"abstract":"This paper propose a new method for wood recognition based on texture analysis. At first, wood texture images are divided into several blocks in our method. Secondly, wood features are extracted from these blocked grey-scale images using different mask, which is knows as higher-order local autocorrelation (HLAC). Finally, Support Vector Machine (SVM) was used to verify the performance of the method. Experiments carried on the wood texture database demonstrate that our method outperforms the original HLAC method.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"63 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":"133922122","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.2012.6234739
Yun Lin, Yuan Zhang
Credit risk is one of the greatest risks faced by commercial banks in china. The BP neural network has self-learning ability, adaptive ability and fault tolerance. This paper adopts BP neural network to evaluate credit risk of 20 ceramic tile enterprises. The results show that credit risk evaluation using BP neural network and expert evaluation have the very good consistency.
{"title":"Credit risk assessment based on neural network","authors":"Yun Lin, Yuan Zhang","doi":"10.1109/ICNC.2012.6234739","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234739","url":null,"abstract":"Credit risk is one of the greatest risks faced by commercial banks in china. The BP neural network has self-learning ability, adaptive ability and fault tolerance. This paper adopts BP neural network to evaluate credit risk of 20 ceramic tile enterprises. The results show that credit risk evaluation using BP neural network and expert evaluation have the very good consistency.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"22 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":"132935030","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.2012.6234540
Khobaib Zaamout, John Z. Zhang
We consider using neural networks as an ensemble technique to improve classification accuracy. Neural networks are among the best techniques used for classification. In this work, we make use of ensemble approach to combine individual neural networks' outputs by another neural network. Furthermore, we propose to include original data as additional inputs for the ensemble neural network. The effectiveness of our proposed approach is demonstrated through a series of experiments on real and synthetic datasets.
{"title":"Improving classification through ensemble neural networks","authors":"Khobaib Zaamout, John Z. Zhang","doi":"10.1109/ICNC.2012.6234540","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234540","url":null,"abstract":"We consider using neural networks as an ensemble technique to improve classification accuracy. Neural networks are among the best techniques used for classification. In this work, we make use of ensemble approach to combine individual neural networks' outputs by another neural network. Furthermore, we propose to include original data as additional inputs for the ensemble neural network. The effectiveness of our proposed approach is demonstrated through a series of experiments on real and synthetic datasets.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"13 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":"122197981","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：