ANALYSE THE PERFORMANCE OF ENSEMBLE CLASSIFIERS USING SAMPLING TECHNIQUES
Journal Title: ICTACT Journal on Soft Computing - Year 2016, Vol 6, Issue 4
Abstract
In Ensemble classifiers, the Combination of multiple prediction models of classifiers is important for making progress in a variety of difficult prediction problems. Ensemble of classifiers proved potential in getting higher accuracy compared to single classifier. Even though by the usage ensemble classifiers, still there is in-need to improve its performance. There are many possible ways available to increase the performance of ensemble classifiers. One of the ways is sampling, which plays a major role for improving the quality of ensemble classifier. Since, it helps in reducing the bias in input data set of ensemble. Sampling is the process of extracting the subset of samples from the original dataset. In this research work, analysis is done on sampling techniques for ensemble classifiers. In ensemble classifier, specifically one of the probability based sampling techniques is being always used. Samples are gathered in a process which gives all the individuals in the population of equal chances, such that, sampling bias is removed. In this paper, analyse the performance of ensemble classifiers by using various sampling techniques and list out their drawbacks.
Authors and Affiliations
Balamurugan M, Kannan S
Keywords
Related Articles
- EP ID EP199912
- DOI 10.21917/ijsc.2016.0177
- Views 36
- Downloads 0
RELIABLE COGNITIVE DIMENSIONAL DOCUMENT RANKING BY WEIGHTED STANDARD CAUCHY DISTRIBUTION
Categorization of cognitively uniform and consistent documents such as University question papers are in demand by e-learners. Literature indicates that Standard Cauchy distribution and the derived values are extensively...
A NOVEL APPROACH FOR LONG TERM SOLAR RADIATION PREDICTION
With present stress, being laid on green energy worldwide, harnessing solar energy for commercial use has importance in sizing and long-term prediction of solar radiation. However, with continuous changing environment pa...
ENHANCED ALGORITHMS FOR MINING OPTIMIZED POSITIVE AND NEGATIVE ASSOCIATION RULE FROM CANCER DATASET
The most important research aspect nowadays is the data. Association rule mining is vital mining used in data which mines many eventual informations and associations from enormous databases. Recently researchers focus ma...
ENHANCED NEIGHBORHOOD NORMALIZED POINTWISE MUTUAL INFORMATION ALGORITHM FOR CONSTRAINT AWARE DATA CLUSTERING
Clustering of similar data items is an important technique in mining useful patterns. To enhance the performance of Clustering, training or learning is an important task. A constraint learning semi-supervised methodology...
OPTIMUM PARAMETERS SELECTION USING BACTERIAL FORAGING OPTIMIZATION FOR WEIGHTED EXTREME LEARNING MACHINE
Extreme Learning Machine (ELM) is a Single Layer Feed Forward Network (SLFN) model with extremely learning capacity and good generalization capabilities. Generally, the performance of ELM for classification task highly b...