This paper presents a novel approach to feature subset selection using genetic algorithms. This approach has the ability to accommodate multiple criteria such as the accuracy and cost of classification into the proces...This paper presents a novel approach to feature subset selection using genetic algorithms. This approach has the ability to accommodate multiple criteria such as the accuracy and cost of classification into the process of feature selection and finds the effective feature subset for texture classification. On the basis of the effective feature subset selected, a method is described to extract the objects which are higher than their surroundings, such as trees or forest, in the color aerial images. The methodology presented in this paper is illustrated by its application to the problem of trees extraction from aerial images.展开更多
The test selection and optimization （TSO） can improve the abilities of fault diagnosis, prognosis and health-state evalua- tion for prognostics and health management （PHM） systems. Traditionally, TSO mainly focuse...The test selection and optimization （TSO） can improve the abilities of fault diagnosis, prognosis and health-state evalua- tion for prognostics and health management （PHM） systems. Traditionally, TSO mainly focuses on fault detection and isolation, but they cannot provide an effective guide for the design for testability （DFT） to improve the PHM performance level. To solve the problem, a model of TSO for PHM systems is proposed. Firstly, through integrating the characteristics of fault severity and propa- gation time, and analyzing the test timing and sensitivity, a testability model based on failure evolution mechanism model （FEMM） for PHM systems is built up. This model describes the fault evolution- test dependency using the fault-symptom parameter matrix and symptom parameter-test matrix. Secondly, a novel method of in- herent testability analysis for PHM systems is developed based on the above information. Having completed the analysis, a TSO model, whose objective is to maximize fault trackability and mini- mize the test cost, is proposed through inherent testability analysis results, and an adaptive simulated annealing genetic algorithm （ASAGA） is introduced to solve the TSO problem. Finally, a case of a centrifugal pump system is used to verify the feasibility and effectiveness of the proposed models and methods. The results show that the proposed technology is important for PHM systems to select and optimize the test set in order to improve their performance level.展开更多
Interact traffic classification is vital to the areas of network operation and management. Traditional classification methods such as port mapping and payload analysis are becoming increasingly difficult as newly emer...Interact traffic classification is vital to the areas of network operation and management. Traditional classification methods such as port mapping and payload analysis are becoming increasingly difficult as newly emerged applications （e. g. Peer-to-Peer） using dynamic port numbers, masquerading techniques and encryption to avoid detection. This paper presents a machine learning （ML） based traffic classifica- tion scheme, which offers solutions to a variety of network activities and provides a platform of performance evaluation for the classifiers. The impact of dataset size, feature selection, number of application types and ML algorithm selection on classification performance is analyzed and demonstrated by the following experiments： （1） The genetic algorithm based feature selection can dramatically reduce the cost without diminishing classification accuracy. （2） The chosen ML algorithms can achieve high classification accuracy. Particularly, REPTree and C4.5 outperform the other ML algorithms when computational complexity and accuracy are both taken into account. （3） Larger dataset and fewer application types would result in better classification accuracy. Finally, early detection with only several initial packets is proposed for real-time network activity and it is proved to be feasible according to the preliminary results.展开更多
Obtaining the average delay and selecting a route in a communication networkare multi-constrained nonlinear optimization problems . In this paper, based on the immune geneticalgorithm, a new fuzzy self-adaptive mutati...Obtaining the average delay and selecting a route in a communication networkare multi-constrained nonlinear optimization problems . In this paper, based on the immune geneticalgorithm, a new fuzzy self-adaptive mutation operator and a new upside-down code operator areproposed. This improved IGA is further successfully applied to solve optimal problems of computercommunication nets.展开更多
流分类技术在网络安全监控、QoS、入侵检测等应用领域起着重要的作用,是当前研究的热点。提出一种新的特征选择算法GATS-C4.5来构建轻量级的IP流分类器。该算法采用遗传算法与禁忌搜索相混合的搜索策略对特征子集空间进行随机搜索,然后...流分类技术在网络安全监控、QoS、入侵检测等应用领域起着重要的作用,是当前研究的热点。提出一种新的特征选择算法GATS-C4.5来构建轻量级的IP流分类器。该算法采用遗传算法与禁忌搜索相混合的搜索策略对特征子集空间进行随机搜索,然后利用提供的数据在C4.5上的分类正确率作为特征子集的评价标准来获取最优特征子集。在IP流数据集上进行了大量的实验,实验结果表明基于GATS-C4.5的流分类器在不影响检测准确度的情况下能够提高检测速度,并且基于GATS-C4.5的IP流分类器与NBK-FCBF(Nave Bayes method with Kernel densityesti mation after Correlation-Based Filter)相比具有更小的计算复杂性与更高的检测率。展开更多
文摘This paper presents a novel approach to feature subset selection using genetic algorithms. This approach has the ability to accommodate multiple criteria such as the accuracy and cost of classification into the process of feature selection and finds the effective feature subset for texture classification. On the basis of the effective feature subset selected, a method is described to extract the objects which are higher than their surroundings, such as trees or forest, in the color aerial images. The methodology presented in this paper is illustrated by its application to the problem of trees extraction from aerial images.
基金supported by the National Natural Science Foundation of China(51175502)
文摘The test selection and optimization （TSO） can improve the abilities of fault diagnosis, prognosis and health-state evalua- tion for prognostics and health management （PHM） systems. Traditionally, TSO mainly focuses on fault detection and isolation, but they cannot provide an effective guide for the design for testability （DFT） to improve the PHM performance level. To solve the problem, a model of TSO for PHM systems is proposed. Firstly, through integrating the characteristics of fault severity and propa- gation time, and analyzing the test timing and sensitivity, a testability model based on failure evolution mechanism model （FEMM） for PHM systems is built up. This model describes the fault evolution- test dependency using the fault-symptom parameter matrix and symptom parameter-test matrix. Secondly, a novel method of in- herent testability analysis for PHM systems is developed based on the above information. Having completed the analysis, a TSO model, whose objective is to maximize fault trackability and mini- mize the test cost, is proposed through inherent testability analysis results, and an adaptive simulated annealing genetic algorithm （ASAGA） is introduced to solve the TSO problem. Finally, a case of a centrifugal pump system is used to verify the feasibility and effectiveness of the proposed models and methods. The results show that the proposed technology is important for PHM systems to select and optimize the test set in order to improve their performance level.
基金Supported by the National High Technology Research and Development Programme of China (No. 2005AA121620, 2006AA01Z232)the Zhejiang Provincial Natural Science Foundation of China (No. Y1080935 )the Research Innovation Program for Graduate Students in Jiangsu Province (No. CX07B_ 110zF)
文摘Interact traffic classification is vital to the areas of network operation and management. Traditional classification methods such as port mapping and payload analysis are becoming increasingly difficult as newly emerged applications （e. g. Peer-to-Peer） using dynamic port numbers, masquerading techniques and encryption to avoid detection. This paper presents a machine learning （ML） based traffic classifica- tion scheme, which offers solutions to a variety of network activities and provides a platform of performance evaluation for the classifiers. The impact of dataset size, feature selection, number of application types and ML algorithm selection on classification performance is analyzed and demonstrated by the following experiments： （1） The genetic algorithm based feature selection can dramatically reduce the cost without diminishing classification accuracy. （2） The chosen ML algorithms can achieve high classification accuracy. Particularly, REPTree and C4.5 outperform the other ML algorithms when computational complexity and accuracy are both taken into account. （3） Larger dataset and fewer application types would result in better classification accuracy. Finally, early detection with only several initial packets is proposed for real-time network activity and it is proved to be feasible according to the preliminary results.
文摘Obtaining the average delay and selecting a route in a communication networkare multi-constrained nonlinear optimization problems . In this paper, based on the immune geneticalgorithm, a new fuzzy self-adaptive mutation operator and a new upside-down code operator areproposed. This improved IGA is further successfully applied to solve optimal problems of computercommunication nets.
文摘流分类技术在网络安全监控、QoS、入侵检测等应用领域起着重要的作用,是当前研究的热点。提出一种新的特征选择算法GATS-C4.5来构建轻量级的IP流分类器。该算法采用遗传算法与禁忌搜索相混合的搜索策略对特征子集空间进行随机搜索,然后利用提供的数据在C4.5上的分类正确率作为特征子集的评价标准来获取最优特征子集。在IP流数据集上进行了大量的实验,实验结果表明基于GATS-C4.5的流分类器在不影响检测准确度的情况下能够提高检测速度,并且基于GATS-C4.5的IP流分类器与NBK-FCBF(Nave Bayes method with Kernel densityesti mation after Correlation-Based Filter)相比具有更小的计算复杂性与更高的检测率。
