Chen Wang

TL;DR: This paper addresses the MKL for classification in hyperspectral images by extracting the most variation from the space spanned by multiple kernels and proposes a representative MKL (RMKL) algorithm that greatly reduces the computational load for searching optimal combination of basis kernels.

TL;DR: Experimental results prove that the proposed kernel-based nonparametric regression method is effective and adaptable to small-target detection under a complex background.

TL;DR: The high abundance of disorder in nucleiomes supports the notion that the nucleic acid binding proteins often require intrinsic disorder for their functions and regulation.

TL;DR: This work describes how to use the first computational method DisoRDPbind for high-throughput prediction of multiple functions of disordered regions and demonstrates the utility of the method based on two case studies, human BRCA1 protein that binds various proteins and DNA, and yeast 60S ribosomal protein L4 that interacts with proteins and RNA.

TL;DR: In this article, a registering control point extraction method combining multi-scale SIFT and area invariant moment features is proposed. But the method is not suitable for image registration, as it requires a large number of images to be processed.