Search NASA⌕ Search

Engineering topics

Steinwart, Ingo

Publications and source records attributed to Steinwart, Ingo.

Using support vector machines for anomalous change detonation

We cast anomalous change detection as a binary classification problem, and use a support vector machine (SVM) to build a detector that does not depend on assumptions about the underlying data distribution. To speed up the computation, our SVM is implemented, in part, on a graphical processing unit. Results on real and simulated anomalous changes are used to compare performance to algorithms which effectively assume a Gaussian distribution. In this paper, we investigate the use of support vector machines (SVMs) with radial basis kernels for finding anomalous changes. Compared to typical applications of SVMs, we are operating in a regime of very low false alarm rate. This means that even for relatively large training sets, the data are quite meager in the regime of operational interest. This drives us to use larger training sets, which in turn places more of a computational burden on the SVM. We initially considered three different approaches to to address the need to work in the very low false alarm rate regime. The first is a standard SVM which is trained at one threshold (where more reliable estimates of false alarm rates are possible) and then re-thresholded for the low false alarm rate regime. The second uses the same thresholding approach, but employs a so-called least squares SVM; here a quadratic (instead of a hinge-based) loss function is employed, and for this model, there are good theoretical arguments in favor of adjusting the threshold in a straightforward manner. The third approach employs a weighted support vector machine, where the weights for the two types of errors (false alarm and missed detection) are automatically adjusted to achieve the desired false alarm rate. We have found in previous experiments (not shown here) that the first two types can in some cases work well, while in other cases they do not. This renders both approaches unreliable for automated change detection. By contrast, the third approach reliably produces good results, but at the cost of larger computational requirements caused by the need to estimate very small false alarm rates. To address these computational requirements, we employ a recently developed in-house solver for SVMs that is significantly faster than freely available standard solvers. But these computational issues are secondary to the larger question: do kernelized solutions provide better performance, in terms of detection rates and false alarm rates, than more traditional methods for change detection that effectively assume Gaussian data distributions? To this end, we will compare ROC curves obtained from the SVM with those from chronochrome, covariance equalization, and hyperbolic anomalous change detection.

97 MATHEMATICS AND COMPUTING↗

Oracle inequalities for SVMs that are based on random entropy numbers

In this paper we present a new technique for bounding local Rademacher averages of function classes induced by a loss function and a reproducing kernel Hilbert space (RKHS). At the heart of this technique lies the observation that certain expectations of random entropy numbers can be bounded by the eigenvalues of the integral operator associated to the RKHS. We then work out the details of the new technique by establishing two new oracle inequalities for SVMs, which complement and generalize orevious results.

97 MATHEMATICS AND COMPUTING↗

Training SVMs without offset

We develop, analyze, and test a training algorithm for support vector machine cla.'>sifiers without offset. Key features of this algorithm are a new stopping criterion and a set of working set selection strategies that, although inexpensive, do not lead to substantially more iterations than the optimal working set selection strategy. For these working set strategies, we establish convergence rates that coincide with the best known rates for SYMs with offset. We further conduct various experiments that investigate both the run time behavior and the performed iterations of the new training algorithm. It turns out, that the new algorithm needs less iterations and run-time than standard training algorithms for SYMs with offset.

97 MATHEMATICS AND COMPUTING↗