Finding Accuracy in Feature Selection Using Firefly Algorithm with Rough Set theory
Journal Title: International Journal of Innovative Research in Computer Science and Technology - Year 2017, Vol 5, Issue 6
Abstract
Feature selection techniques play a vital role in bioinformatics applications. In addition to the large group of techniques that have already been developed in the machine learning and data mining fields, specific applications in bioinformatics have led to possess of newly proposed techniques. In this paper, a method for feature selection is based on Firefly Optimization (FFO) with Rough Set Theory(RST) is proposed. Data sets include a large volume of features with irrelevant and redundant features. Redundant and irrelevant features reduce accuracy. The main aim of this paper is to select a subset of relevant features. A statistical metric-based feature selection technique has been proposed in order to reduce the size of the extracted feature vector. The proposed method shows the improvement significantly in terms of performance measure metrics: accuracy, sensitivity, specificity, computation time and so on. FFO technique is applied to determine the features globally according to the light intensity. Then the selected features are grouped together to make a subset and applied RST to find the optimized feature. This optimized feature is used to analyze the protein information in the organisms and improve the feature selection accuracy and reduce the computation time in protein data analysis.
Authors and Affiliations
A. Revathi, P. Sumathi
Keywords
Related Articles
- EP ID EP748308
- DOI 10.21276/ijircst.2017.5.6.4
- Views 34
- Downloads 0
Version Locking Mechanism in Database
The distributed database provides a resource sharing environment, where multiple transactions at different sites coexist in order to access the resources. In this paper we investigate multi version locking protocol in di...
Centralized Database: A Prerequisite for Security and Sustainable Development in Nigeria
The volume of data organizations and government agencies usually collect and store are increasing rapidly. Centralized database according to Elmasri and Navathe [1] stores data or information in a particular location wit...
EV Charging Using DC Storage and Sustainable Energy
As countries and automakers focus on initiatives such as "keeping green," climate action, and so on, the present worldwide inclination favoring electric vehicles is growing. An inherent aspect of this is the design of el...
Properties of Concrete on Adding Polypropylene Fibre and Polyvinyl Chloride Fibre
Concrete is a structure material that can't be ignored indeed if it's weak in tension and lead to environmental problems. Properties of concrete can be modified using fibre in concrete. Using fibre from waste of plastic...
Material Bottlenecks in the Future Development of Green Technologies
Reducing emissions global economies demands the development of "green technology," which entails a reorganization of the energy sector to use renewable energy sources and nitrogen transportation systems. This reconstruct...