Subset Selection in High Dimensional Data by Using Fast Clustring Technique
Journal Title: International Journal of Engineering Sciences & Research Technology - Year 30, Vol 3, Issue 7
Abstract
A feature subset selection is an effective method for reducing dimensionality, removing irrelevant data, increasing learning accuracy and improving results comprehensibility. This process enhanced by cluster based FAST Algorithm using MST construction. With the aim of choosing a subset of good features with respect to the target concepts, feature subset selection is an effective way for dropping dimensionality, remove irrelevant data, rising learning accuracy, and improving result comprehensibility. Features in different clusters are moderately independent. The clustering-based strategy of FAST has a high probability of producing a subset of useful and independent features. The proposed algorithm not only reduces the number of features, but also improves the performances of the four wellknown different types of classifiers such as the probability-based Naive Bays, the tree-based C4.5, the instance-based IB1, and the rule-based RIPPER before and after feature selection. We can build FAST algorithm with prim’s algorithm based on MST Construction. Our investigational results show that improves the performances of the four types of classifiers.
Authors and Affiliations
C. Pearley Vinitta Sharon
Keywords
Related Articles
- EP ID EP132725
- DOI -
- Views 75
- Downloads 0
Simulation and Analysis of Fuzzy Logic based Unified Power Flow Controller connected to Transmission Line
The Unified Power Flow Controller (UPFC) is used to control the flow of power in the transmission systems by controlling the impedance, voltage magnitude and phase angle. The Unified Power Flow Controller (UPFC)...
DIRICHLET AVERAGE OF ADVANCED MODIFIED M- FUNCTION AND FRACTIONAL DERIVATIVE
In this work we set up a relation between Dirichlet average of Advanced Modified M- function [16] and fractional derivative.
Analysis of Component Integration in Component-based Development Paradigm
Component-based software development is achieving more popularity in today’s software development community due to the increasing complexity of software systems, increasing costs of maintenance, and decreasing co...
COMPUTERIZED COURSE RESULT GRADE SHEET LAYOUT UPGRADE
Result computation occupies an important space in the running of a border university administration as it brings to culmination the exercise for the products' output for which the University is instituted. This paper del...
AN EFFICIENT FRAMEWORK FOR IMAGE DATA RECOGNITION & RETRIEVAL
Valuable information can be hidden in images, however, few research discuss data mining on them. Image retrieval means searching, browsing and retrieving images from image databases. There are two different methodo...