Insufficiency of labeled training data is a major obstacle for automatic video annotation. Semi-supervised learning is an effective approach to this problem by leveraging a large amount of unlabeled data. However, existing semi-supervised learning algorithms have not demonstrated promising results in largescale video annotation due to several difficulties, such as large variation of video conte...

Title of dissertation: FAST ALGORITHMS FOR THE SOLUTION OF STOCHASTIC PARTIAL DIFFERENTIAL EQUATIONS Christopher W. Miller, Doctor of Philosophy, 2012 Dissertation directed by: Professor Howard Elman Department of Computer Science Institute for Advanced Computer Studies We explore the performance of several algorithms for the solution of stochastic partial differential equations including the s...

The likelihood for patterns of continuous features needed for probabilistic inference in a Bayesian network classifier (BNC) may be computed by kernel density estimation (KDE), letting every pattern influence the shape of the probability density. Although usually leading to accurate estimation, the KDE suffers from computational cost making it unpractical in many real-world applications. We smo...

We introduce a method for kinetic characterization of reversible binding of protein onto the inner capillary wall. In essence, a short plug of the protein solution is propagated through the capillary by pressure, and the protein is detected at the distal capillary end. The signal versus time profile is fitted with a numerical model which uses the rate constants of adsorption, kad, and desorptio...

We propose a distance based method for the outlier detection of body sensor networks. Firstly, we use a Kernel Density Estimation (KDE) to calculate the probability of the distance to k nearest neighbors for diagnosed data. If the probability is less than a threshold, and the distance of this data to its left and right neighbors is greater than a pre-defined value, the diagnosed data is decided...

In numerous psychological experiments, participants classify stimuli by pressing response keys. According to Lakens, Schneider, Jostmann, and Schubert (2011), classification performance is affected by physical distance between response keys--indicating a cognitive tendency to represent categories in spatial code. However, previous evidence for a key distance effect (KDE) from a color-naming Str...

This research investigates how women’s groups facilitate people’s participation in the open source community by examining the joining activities in KDE Women. Leveraging literatures on group membership roles and socialization, and adopting a qualitative research method, a joining script of different kinds of participants was identified. It is found that members developed organizational and lead...

INTRODUCTION Youth Excel was a 3-year pan-Canadian initiative to advance youth health through improving knowledge development and exchange (KDE) capacity. KDE capacity refers to an improvement cycle linking evidence and action. Capacities include local surveillance of youth behaviours; knowledge exchange; skills, resources and a supportive environment to use knowledge; and evaluation. METHODS...

We present results of experiments testing the Fast Gauss Transform, Improved Fast Gauss Transform, and Dual-Tree methods (using kd-tree and Anchors Hierarchy data structures) for fast Kernel Density Estimation (KDE). We examine the performance of these methods with respect to data set size, dimension, allowable error, and data set structure (“clumpiness”), measured in terms of CPU time and memo...

Utilization distributions (UDs) can be used to describe with what intensity an animal or human may use a certain geographical location within the environment it is living in. Such a density distribution model represents one way to describe and obtain an animals’ home range in wildlife ecology. Several methods to derive UDs and subsequently home ranges have been developed, for instance Kernel De...