We describe and evaluate two algorithms for Neyman-Pearson (NP) classification problem which has been recently shown to be of a particular importance for bipartite ranking problems. NP classification is a nonconvex pr...
详细信息
We describe and evaluate two algorithms for Neyman-Pearson (NP) classification problem which has been recently shown to be of a particular importance for bipartite ranking problems. NP classification is a nonconvex problem involving a constraint on false negatives rate. We investigated batch algorithm based on dc programming and stochastic gradient method well suited for large-scale datasets. Empirical evidences illustrate the potential of the proposed methods.
An interval reduced basis approach (IRBA) is presented for analyzing acoustic response of coupled structural-acoustic system with interval parameters. Simultaneously an integrated framework based on IRBA is establishe...
详细信息
An interval reduced basis approach (IRBA) is presented for analyzing acoustic response of coupled structural-acoustic system with interval parameters. Simultaneously an integrated framework based on IRBA is established to deal with uncertain acoustic propagation using deterministic finite element (FE) software. The present IRBA aims to improve the accuracy of the conventional first-order approximation and also allow the efficient calculation of second-order approximation of acoustic response. In IRBA, acoustic response is approximated using a linear combination of interval basis vectors with undetermined coefficients. To get explicit expression of acoustic response in terms of interval parameters, the three terms of the second-order perturbation method are employed as basis vectors, and the variant of the Galerkin scheme is applied for derivation of the reduced-order system of equations. For the second-order approximation, the determination of acoustic response interval is reformulated into a series of quadratic programming problems, which are solved using the difference of convex functions (dc) algorithm effectively. The performance of IRBA and availability of the present framework are validated by numerical examples.
暂无评论