Kernel-based methods work by embedding the data into a feature space and then searching linear hypothesis among the embedding data points. The performance is mostly affected by which kernel is used. A promising way is...Kernel-based methods work by embedding the data into a feature space and then searching linear hypothesis among the embedding data points. The performance is mostly affected by which kernel is used. A promising way is to learn the kernel from the data automatically. A general regularized risk functional （RRF） criterion for kernel matrix learning is proposed. Compared with the RRF criterion, general RRF criterion takes into account the geometric distributions of the embedding data points. It is proven that the distance between different geometric distdbutions can be estimated by their centroid distance in the reproducing kernel Hilbert space. Using this criterion for kernel matrix learning leads to a convex quadratically constrained quadratic programming （QCQP） problem. For several commonly used loss functions, their mathematical formulations are given. Experiment results on a collection of benchmark data sets demonstrate the effectiveness of the proposed method.展开更多
Modern ammunition-rocket system is a complicated multidisciplinary system. During its development, undetermined factors will bring many risks. This paper elaborates the importance of risk analysis approach to ammuniti...Modern ammunition-rocket system is a complicated multidisciplinary system. During its development, undetermined factors will bring many risks. This paper elaborates the importance of risk analysis approach to ammunition-rocket system development and analyses various methods of risk analysis and estimation. Combined with practical situation of weapon system development, the risk measurement function with characteristics of risk preference is given provided that the risk preference characteristic of behavior maker is risk neutral of fixed constant. The development risk analysis based on risk measurement function enables effective risk decision to be made on the basis of quantified risk. Taking anti-helicopter intelligent mine warhead as an example, the paper verifies the efficiency of the method and shows that it has a scientific and practical value.展开更多
基金supported by the National Natural Science Fundation of China (60736021)the Joint Funds of NSFC-Guangdong Province(U0735003)
文摘Kernel-based methods work by embedding the data into a feature space and then searching linear hypothesis among the embedding data points. The performance is mostly affected by which kernel is used. A promising way is to learn the kernel from the data automatically. A general regularized risk functional （RRF） criterion for kernel matrix learning is proposed. Compared with the RRF criterion, general RRF criterion takes into account the geometric distributions of the embedding data points. It is proven that the distance between different geometric distdbutions can be estimated by their centroid distance in the reproducing kernel Hilbert space. Using this criterion for kernel matrix learning leads to a convex quadratically constrained quadratic programming （QCQP） problem. For several commonly used loss functions, their mathematical formulations are given. Experiment results on a collection of benchmark data sets demonstrate the effectiveness of the proposed method.
文摘Modern ammunition-rocket system is a complicated multidisciplinary system. During its development, undetermined factors will bring many risks. This paper elaborates the importance of risk analysis approach to ammunition-rocket system development and analyses various methods of risk analysis and estimation. Combined with practical situation of weapon system development, the risk measurement function with characteristics of risk preference is given provided that the risk preference characteristic of behavior maker is risk neutral of fixed constant. The development risk analysis based on risk measurement function enables effective risk decision to be made on the basis of quantified risk. Taking anti-helicopter intelligent mine warhead as an example, the paper verifies the efficiency of the method and shows that it has a scientific and practical value.
