Identification of best discrimination surface by mixed-integer semi-definite programming for support vector machine

This paper proposes two improvements to the support vector machine (SVM): (i) extension to a semi-positive definite quadratic surface, which improves the discrimination accuracy; (ii) addition of a variable selection constraint. However, this model is formulated as a mixed-integer semi-definite programming (MISDP) problem, and it cannot be solved easily. Therefore, we propose a heuristic algorithm for solving the MISDP problem efficiently and show its effectiveness by using corporate credit rating data.

Fast Quadratic Shape From Shading With Unknown Light Direction

An algorithm is proposed that extracts 3D shape from shading information in a digital image. The algorithm assumes that there is only a single source of light producing the image, that the surface of the shape giving rise to the image is Lambertian (matte) and that its shape can be locally approximated by a quadratic function. Previous work shows that under these assumptions, robust shape from shading is possible, though slow for large images because a non-linear optimization method is applied in order to estimate local quadratic surface patches from image intensities. The work presented here shows that local quadratic surface patch estimates can be computed, without prior knowledge of the light source direction, via a linear least squares optimization, thus greatly improving the algebraic complexity and run-time of the existing algorithms.

Fast Quadratic Shape From Shading With Unknown Light Direction

An algorithm is proposed that extracts 3D shape from shading information in a digital image. The algorithm assumes that there is only a single source of light producing the image, that the surface of the shape giving rise to the image is Lambertian (matte) and that its shape can be locally approximated by a quadratic function. Previous work shows that under these assumptions, robust shape from shading is possible, though slow for large images because a non-linear optimization method is applied in order to estimate local quadratic surface patches from image intensities. The work presented here shows that local quadratic surface patch estimates can be computed, without prior knowledge of the light source direction, via a linear least squares optimization, thus greatly improving the algebraic complexity and run-time of this existing algorithms.

Fast Quadratic Shape From Shading With Unknown Light Direction

An algorithm is proposed that extracts 3D shape from shading information in a digital image. The algorithm assumes that there is only a single source of light producing the image, that the surface of the shape giving rise to the image is Lambertian (matte) and that its shape can be locally approximated by a quadratic function. Previous work shows that under these assumptions, robust shape from shading is possible, though slow for large images because a non-linear optimization method is applied in order to estimate local quadratic surface patches from image intensities. The work presented here shows that local quadratic surface patch estimates can be computed, without prior knowledge of the light source direction, via a linear least squares optimization, thus greatly improving the algebraic complexity and run-time of this existing algorithms.

Kernel-Free Quadratic Surface Minimax Probability Machine for a Binary Classification Problem

In this paper, we propose a novel binary classification method called the kernel-free quadratic surface minimax probability machine (QSMPM), that makes use of the kernel-free techniques of the quadratic surface support vector machine (QSSVM) and inherits the advantage of the minimax probability machine (MPM) without any parameters. Specifically, it attempts to find a quadratic hypersurface that separates two classes of samples with maximum probability. However, the optimization problem derived directly was too difficult to solve. Therefore, a nonlinear transformation was introduced to change the quadratic function involved into a linear function. Through such processing, our optimization problem finally became a second-order cone programming problem, which was solved efficiently by an alternate iteration method. It should be pointed out that our method is both kernel-free and parameter-free, making it easy to use. In addition, the quadratic hypersurface obtained by our method was allowed to be any general form of quadratic hypersurface. It has better interpretability than the methods with the kernel function. Finally, in order to demonstrate the geometric interpretation of our QSMPM, five artificial datasets were implemented, including showing the ability to obtain a linear separating hyperplane. Furthermore, numerical experiments on benchmark datasets confirmed that the proposed method had better accuracy and less CPU time than corresponding methods.

Numerical Implementation of Drop Spin and Tilt Method For Five-Axis Tool Positioning For Tensor Product Surfaces

This paper presents an extension of multi point machining technique, called the Drop Spin and Tilt (DST) method, that spins the tool on two axes, allowing for the generation of multiple contact points at varying distances around the first point of contact. The multiple DST second points of contact were used to manually generate a toolpath with uniform spacing between the two points of contact. The original DST method used a symbolic algebra package to position the tool on a bi-quadratic surface; our extension is a numer- ical solution that allows positioning a toroidal tool on a tensor product Bezier surface. Further, we investigate the spread of possible second points of contact as the tool is spun around these two axes, demonstrating the feasability of using the method to control the machining strip width.