Performance analysis for classification in balanced and unbalanced data set

Abstract

This paper focuses on performance evaluation of the classification algorithms for problems of unbalanced and balanced large data sets. Three methods such as ELM, MRAN, and SRAN have been proposed for solving the set classification problem and studied. The ELM is based on randomly chosen hidden nodes and analytically determines the output weights of SLFNs. Then the next method M-RAN is a sequential learning radial basis function neural network which combines the growth criterion of the resource allocating network (RAN) of Platt with a pruning strategy based on the relative contribution of each hidden unit to the overall network output. The last method SRAN uses of misclassification information and hinge loss error in growing/learning criterion helps in approximating the decision function accurately. The performance evaluation using balanced and imbalanced data sets shows that one of the proposed algorithms SRAN generates minimal network with higher classification performance.