How to efficiently measure the distance between two basic probability assignments（BPAs） is an open issue. In this paper, a new method to measure the distance between two BPAs is proposed, based on two existing measu...How to efficiently measure the distance between two basic probability assignments（BPAs） is an open issue. In this paper, a new method to measure the distance between two BPAs is proposed, based on two existing measures of evidence distance. The new proposed method is comprehensive and generalized. Numerical examples are used to illustrate the effectiveness of the proposed method.展开更多
An object segment similarity function is taken into account from the continuous media frames to measure the individual streaming profit of certain segment versions of a media object.Therefore,a new segment version-bas...An object segment similarity function is taken into account from the continuous media frames to measure the individual streaming profit of certain segment versions of a media object.Therefore,a new segment version-based transcoding(SVT)mechanism is derived for a quality of service(QoS)of client-centric media streaming in wireless mobile networks.The derived function utilizes the fuzzy similarity of certain segment versions of an object.This mechanism provides the effectiveness of reduction of the stream startup latency among segment versions,and the average access of each version.Thus,the proposed segment version transcoding mechanism reduces packet loss which in turn increases streaming performance and throughput.The performance of the partitioned segment versions is simulated and some segment versions are completed.The simulation results show that the proposed mechanism outperforms the other mechanisms in average cache hit ratio and in average startup latency ratio.展开更多
A least squares version of the recently proposed weighted twin support vector machine with local information(WLTSVM) for binary classification is formulated. This formulation leads to an extremely simple and fast algo...A least squares version of the recently proposed weighted twin support vector machine with local information(WLTSVM) for binary classification is formulated. This formulation leads to an extremely simple and fast algorithm, called least squares weighted twin support vector machine with local information(LSWLTSVM), for generating binary classifiers based on two non-parallel hyperplanes. Two modified primal problems of WLTSVM are attempted to solve, instead of two dual problems usually solved. The solution of the two modified problems reduces to solving just two systems of linear equations as opposed to solving two quadratic programming problems along with two systems of linear equations in WLTSVM. Moreover, two extra modifications were proposed in LSWLTSVM to improve the generalization capability. One is that a hot kernel function, not the simple-minded definition in WLTSVM, is used to define the weight matrix of adjacency graph, which ensures that the underlying similarity information between any pair of data points in the same class can be fully reflected. The other is that the weight for each point in the contrary class is considered in constructing equality constraints, which makes LSWLTSVM less sensitive to noise points than WLTSVM. Experimental results indicate that LSWLTSVM has comparable classification accuracy to that of WLTSVM but with remarkably less computational time.展开更多
基金supported by the National High Technology Research and Development Program of China(863 Program)(2013AA013801)the National Natural Science Foundation of China(61174022+4 种基金61573290)the open funding project of State Key Laboratory of Virtual Reality Technology and Systemsthe Beihang University(BUAA-VR-14KF-02)the General Research Program of Natural Science of Sichuan Provincial Department of Education(14ZB0322)the Self-financing Program of State Ethnic Affairs Commission of China(14SCZ014)
文摘How to efficiently measure the distance between two basic probability assignments（BPAs） is an open issue. In this paper, a new method to measure the distance between two BPAs is proposed, based on two existing measures of evidence distance. The new proposed method is comprehensive and generalized. Numerical examples are used to illustrate the effectiveness of the proposed method.
基金Project(2011)financially supported by Research Funds of Chonbuk National University,Korea
文摘An object segment similarity function is taken into account from the continuous media frames to measure the individual streaming profit of certain segment versions of a media object.Therefore,a new segment version-based transcoding(SVT)mechanism is derived for a quality of service(QoS)of client-centric media streaming in wireless mobile networks.The derived function utilizes the fuzzy similarity of certain segment versions of an object.This mechanism provides the effectiveness of reduction of the stream startup latency among segment versions,and the average access of each version.Thus,the proposed segment version transcoding mechanism reduces packet loss which in turn increases streaming performance and throughput.The performance of the partitioned segment versions is simulated and some segment versions are completed.The simulation results show that the proposed mechanism outperforms the other mechanisms in average cache hit ratio and in average startup latency ratio.
基金Project(61105057)supported by the National Natural Science Foundation of ChinaProject(13KJB520024)supported by the Natural Science Foundation of Jiangsu Higher Education Institutes of ChinaProject supported by Jiangsu Province Qing Lan Project,China
文摘A least squares version of the recently proposed weighted twin support vector machine with local information(WLTSVM) for binary classification is formulated. This formulation leads to an extremely simple and fast algorithm, called least squares weighted twin support vector machine with local information(LSWLTSVM), for generating binary classifiers based on two non-parallel hyperplanes. Two modified primal problems of WLTSVM are attempted to solve, instead of two dual problems usually solved. The solution of the two modified problems reduces to solving just two systems of linear equations as opposed to solving two quadratic programming problems along with two systems of linear equations in WLTSVM. Moreover, two extra modifications were proposed in LSWLTSVM to improve the generalization capability. One is that a hot kernel function, not the simple-minded definition in WLTSVM, is used to define the weight matrix of adjacency graph, which ensures that the underlying similarity information between any pair of data points in the same class can be fully reflected. The other is that the weight for each point in the contrary class is considered in constructing equality constraints, which makes LSWLTSVM less sensitive to noise points than WLTSVM. Experimental results indicate that LSWLTSVM has comparable classification accuracy to that of WLTSVM but with remarkably less computational time.
