In this work, we propose a novel K-ary splitting method for regression trees and incorporate it into the regression forest framework. Unlike standard binary splitting, where the splitting rule is selected from a predefined set of binary splitting rules via trial-and-error, the proposed K-ary splitting method first finds clusters of the training data which at least locally minimize the empirical...

A graph G is k-colorable if G has a proper vertex coloring with k colors. The chromatic number (G) is the minimum number k such that G is k-colorable. A bcoloring of a graph with k colors is a proper coloring in which each color class contains a color dominating vertex. The largest positive integer k for which G has a b-coloring with k colors is the b-chromatic number of G, denoted by b(G). Th...

Spectral Clustering as a relaxation of the normalized/ratio cut has become one of the standard graph-based clustering methods. Existing methods for the computation of multiple clusters, corresponding to a balanced k-cut of the graph, are either based on greedy techniques or heuristics which have weak connection to the original motivation of minimizing the normalized cut. In this paper we propos...

Spatial patterning of cells is of great importance in tissue engineering and biotechnology, enabling, for example the creation of bottom-up histoarchitectures of heterogeneous cells, or cell aggregates for in vitro high-throughput toxicological and therapeutic studies within 3D microenvironments. In this paper, a single-step process for creating peelable and resilient hydrogels, encapsulating a...

Forecasting the future states of a complex system is a complicated challenge that is encountered in many industrial applications covered in the community of Prognostics and Health Management (PHM). Practically, states can be either continuous or discrete: Continuous states generally represent the value of a signal while discrete states generally depict functioning modes reflecting the current d...

Let A be a unital C-algebra. Its unitary group, UA, contains a wealth of topological information about A. However, the homotopy type of UA is out of reach even for A = M2(C). There are two simplifications which have been considered. The first, well-traveled road, is to pass to π∗(U(A⊗K)) which is isomorphic (with a degree shift) to K∗(A). This approach has led to spectacular success in many are...

Continuous monitoring of spatial queries has received significant research attention in the past few years. In this paper, we propose two efficient algorithms for the continuous monitoring of the constrained k nearest neighbor (kNN) queries. In contrast to the conventional k nearest neighbors (kNN) queries, a constrained kNN query considers only the objects that lie within a region specified by...

Continuously monitoring kNN queries in a highly dynamic environment has become a necessity to many recent location-based applications. In this paper, we study the problem of continuous kNN query on the dataset with an in-memory grid index. We first present a novel data access method – CircularTrip. Then, an efficient CircularTrip-based continuous kNN algorithm is developed. Compared with the ex...

Existing methods for retrieving k-nearest neighbours suffer from the curse of dimensionality. We argue this is caused in part by inherent deficiencies of space partitioning, which is the underlying strategy used by almost all existing methods. We devise a new strategy that avoids partitioning the vector space and present a novel randomized algorithm that runs in time linear in dimensionality an...

Information streams are mainly produced today by social networks, but current methods for continuous top-k processing of such streams are still limited to contentbased similarity. We present the SANTA algorithm, able to handle also social network criteria and events, and report a preliminary comparison with an extension of a state-of-the-art algorithm.