The support vector machine (SVM) is a novel machine learning method, which has the ability to approximate nonlinear functions with arbitrary accuracy. Setting parameters well is very crucial for SVM learning results...The support vector machine (SVM) is a novel machine learning method, which has the ability to approximate nonlinear functions with arbitrary accuracy. Setting parameters well is very crucial for SVM learning results and generalization ability, and now there is no systematic, general method for parameter selection. In this article, the SVM parameter selection for function approximation is regarded as a compound optimization problem and a mutative scale chaos optimization algorithm is employed to search for optimal paraxneter values. The chaos optimization algorithm is an effective way for global optimal and the mutative scale chaos algorithm could improve the search efficiency and accuracy. Several simulation examples show the sensitivity of the SVM parameters and demonstrate the superiority of this proposed method for nonlinear function approximation.展开更多
Although there have been existing competitions among web service (WS) providers, they still have opportunities to cooperate together for common profits. WS community as a mean to provide an ontological organizati...Although there have been existing competitions among web service (WS) providers, they still have opportunities to cooperate together for common profits. WS community as a mean to provide an ontological organization of WSs that share the same domain of interest has realized this kind of fancy in the sense that providers can work together to compete against others outside the community. Service selection in WS community is different from the traditional service selection, since WS community should take into account its own benefits. Therefore, we propose a hybrid approach to make service selection in WS community. The approach considers the profits of both WS community and the services within it. The experimental evaluation shows that the approach has a great advantage over other approach without consideration of community's benefits.展开更多
Continuous top-k query over sliding window is a fundamental problem in database, which retrieves k objects with the highest scores when the window slides. Existing studies mainly adopt exact algorithms to tackle this ...Continuous top-k query over sliding window is a fundamental problem in database, which retrieves k objects with the highest scores when the window slides. Existing studies mainly adopt exact algorithms to tackle this type of queries, whose key idea is to maintain a subset of objects in the window, and try to retrieve answers from it. However, all the existing algorithms are sensitive to query parameters and data distribution. In addition, they suffer from expensive overhead for incremental maintenance, and thus cannot satisfy real-time requirement. In this paper, we define a novel query named (ε, δ)-approximate continuous top-κ query, which returns approximate answers for top-κ query. In order to efficiently support this query, we propose an efficient framework, named PABF (Probabilistic Approximate Based Framework), to support approximate top-κ query over sliding window. We firstly maintain a self-adaptive pruning value, which could filter out newly arrived objects who have a probability less than 1 - 5 of being a query result. For those objects that are not filtered, we combine them together, if the score difference among them is less than a threshold. To efficiently maintain these combined results, the framework PABF also proposes a multi-phase merging algorithm. Theoretical analysis indicates that even in the worst case, we require only logarithmic complexity for maintaining each candidate.展开更多
最大信息系数(Maximum information coefficient,MIC)可以对变量间的线性和非线性关系,以及非函数依赖关系进行有效度量.本文首先根据最大信息系数理论,提出了一种评价各维特征间以及每维特征与类别间相关性的度量标准,然后提出了基于...最大信息系数(Maximum information coefficient,MIC)可以对变量间的线性和非线性关系,以及非函数依赖关系进行有效度量.本文首先根据最大信息系数理论,提出了一种评价各维特征间以及每维特征与类别间相关性的度量标准,然后提出了基于新度量标准的近似马尔科夫毯特征选择方法,删除冗余特征.在此基础上提出了基于特征排序和近似马尔科夫毯的两阶段特征选择方法,分别对特征的相关性和冗余性进行分析,选择有效的特征子集.在UCI和ASU上的多个公开数据集上的对比实验表明,本文提出的方法总体优于快速相关滤波(Fast correlation-based filter,FCBF)方法,与Relief F,FAST,Lasso和RFS方法相比也具有优势.展开更多
基金the National Nature Science Foundation of China (60775047, 60402024)
文摘The support vector machine (SVM) is a novel machine learning method, which has the ability to approximate nonlinear functions with arbitrary accuracy. Setting parameters well is very crucial for SVM learning results and generalization ability, and now there is no systematic, general method for parameter selection. In this article, the SVM parameter selection for function approximation is regarded as a compound optimization problem and a mutative scale chaos optimization algorithm is employed to search for optimal paraxneter values. The chaos optimization algorithm is an effective way for global optimal and the mutative scale chaos algorithm could improve the search efficiency and accuracy. Several simulation examples show the sensitivity of the SVM parameters and demonstrate the superiority of this proposed method for nonlinear function approximation.
文摘Although there have been existing competitions among web service (WS) providers, they still have opportunities to cooperate together for common profits. WS community as a mean to provide an ontological organization of WSs that share the same domain of interest has realized this kind of fancy in the sense that providers can work together to compete against others outside the community. Service selection in WS community is different from the traditional service selection, since WS community should take into account its own benefits. Therefore, we propose a hybrid approach to make service selection in WS community. The approach considers the profits of both WS community and the services within it. The experimental evaluation shows that the approach has a great advantage over other approach without consideration of community's benefits.
基金This work is partially supported by the National Natural Science Fund for Distinguish Young Scholars of China under Grant No. 61322208, the National Basic Research 973 Program of China under Grant No. 2012CB316201, the National Natural Science Foundation of China under Grant Nos. 61272178 and 61572122, and the Key Program of the National Natural Science Foundation of China under Grant No. 61532021.
文摘Continuous top-k query over sliding window is a fundamental problem in database, which retrieves k objects with the highest scores when the window slides. Existing studies mainly adopt exact algorithms to tackle this type of queries, whose key idea is to maintain a subset of objects in the window, and try to retrieve answers from it. However, all the existing algorithms are sensitive to query parameters and data distribution. In addition, they suffer from expensive overhead for incremental maintenance, and thus cannot satisfy real-time requirement. In this paper, we define a novel query named (ε, δ)-approximate continuous top-κ query, which returns approximate answers for top-κ query. In order to efficiently support this query, we propose an efficient framework, named PABF (Probabilistic Approximate Based Framework), to support approximate top-κ query over sliding window. We firstly maintain a self-adaptive pruning value, which could filter out newly arrived objects who have a probability less than 1 - 5 of being a query result. For those objects that are not filtered, we combine them together, if the score difference among them is less than a threshold. To efficiently maintain these combined results, the framework PABF also proposes a multi-phase merging algorithm. Theoretical analysis indicates that even in the worst case, we require only logarithmic complexity for maintaining each candidate.