Metric learning aims to embed one metric space into another to benefit tasks like classification and clustering. Although a greatly distorted metric space has a high degree of freedom to fit training data, it is prone to overfitting and numerical inaccuracy. This paper presents bounded-distortion metric learning (BDML), a new metric learning framework which amounts to finding an optimal Mahalan...

This report describes a simulation model of sonar tracking, developed to explore the effect of networking sonars on tracking performance. The tracker is an extended Kalman filter with data association by nearest-neighbour in Mahalanobis distance. Data fusion algorithms also use Mahalanobis distance. Simulation outputs have been verified against analytical results where possible.

BACKGROUND: Laser Induced Breakdown Spectroscopy (LIBS) can be used to measure trace element concentrations in solids, liquids and gases, with spatial resolution and absolute quantifaction being feasible, down to parts-per-million concentration levels. Some applications of LIBS do not necessarily require exact, quantitative measurements. These include applications in dentistry, which are of a m...

This paper systematically explores the capabilities of different forms of Dynamic Time Warping (DTW) algorithms and their parameter configurations in recognising whole-of-body gestures. The standard DTW (SDTW) (Sakoe and Chiba 1978), globally feature weighted DTW (Reyes et al. 2011) and locally feature weighted DTW (Arici et al. 2013) algorithms are particularly considered, while an enhanced ve...

Support Vector Machine (SVM) is a powerful technique for data classification. The SVM constructs an optimal separating hyper-plane as a decision surface, to divide the data points of different categories in the vector space. The Kernel functions are used to extend the concept of the optimal separating hyper-plane for the non-linearly separable cases so that the data can be linearly separable. T...

For more than a century, rigid-body displacements have been viewed as affine transformations described as homogeneous transformation matrices wherein the linear part is a rotation matrix. In group-theoretic terms, this classical description makes rigid-body motions a semi-direct product. The distinction between a rigid-body displacement of Euclidean space and a change in pose from one reference...

Abstract In geochemical data analysis, assessing the potential of new techniques to identify compositional time–space changes is great interest for monitoring purposes. This work aims evaluate, in light analysis perspective, performance different statistical indices tracing evolution a composition and relationships among its parts. To reach this goal, source-to-sink chemical water stream sedime...