Semi-Supervised Discriminant Analysis Based On Data Structure
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2015, Vol 17, Issue 3
Abstract
Abstract: Dimensionality reduction is a key data-analytic technique for mining high-dimensional data. In thispaper, we consider a general problem of learning from pairwise constraints in the form of must-link and cannotlink.As one kind of side information, the must-link constraints imply that a pair of instances belongs to the sameclass, while the cannot-link constraints compel them to be different classes. Given must-link and cannot-linkinformation, the goal of this paper is learn a smooth and discriminative subspace. Specifically, in order togenerate such a subspace, we use pairwise constraints to present an optimization problem, in which a leastsquares formulation that integrates both global and local structures is considered as a regularization term fordimensionality reduction. Experimental results on benchmark data sets show the effectiveness of the proposedalgorithm
Authors and Affiliations
Xuesong Yin , Rongrong Jiang, Lifei Jiang
Keywords
Related Articles
- EP ID EP105992
- DOI -
- Views 138
- Downloads 0
Efficient design of feedforward network for pattern classification
A feedforward neural network is a computing device whose processing units (the nodes) are distributed in adjacent layers connected through unidirectional links (the weights).Feedforward networks are widely used...
Stationary Wavelet Transform Image Fusion and Optimization Using Particle Swarm Optimization
The complementary nature of imaging sensors of different modalities all brought a great need of image fusion to extract relevant information images. Medical image fusion using Stationary wavelet transform (SWT) an...
Opinion Search and Retrieval from WWW
Opinion retrieval has established itself as an important part of search engines ratings, opinion trends and representative opinions enrich the search experience ofusers when combined with traditional document ret...
Enhanced Threshold Sensitive Stable Election Protocol
Abstract: A wireless sensor network (WSN) consists of inexpensive power constrained sensor nodes collectingdata from the sensing area and transmits data towards the base station in a synergetic way. The basic goal ofwire...
WMNs: The Design and Analysis of Fair Scheduling
Abstract: In this paper an attempt has been made to address the matter of scheduling in wireless mesh networks. First, we offer a comparison of existing scheduling algorithms and then classify them based on the schedulin...