Classification of genome data using Random Forest Algorithm: Review

Journal Article

Mohammed, Zakariah . 2014

• Publication Online URL: http://ijcta.com/documents/volumes/vol5issue5/ijcta2014050515.pdf
• Magazine \ Newspaper: Int.J.Computer Technology & Applications
• Issue Number: 5
• Volume Number: 5
• Pages: 1663-1669

Publication Abstract

Random Forest is a popular machine learning tool for classification of large datasets. The Dataset classified with Random Forest Algorithm (RF) are correlated and the interaction between the features leads to the study of genome interaction. The review is about RF with respect to its variable selection property which reduces the large datasets into relevant samples and predicting the accuracy for the selected variable. The variables are selected among the huge datasets and then its error rate are calculated with prediction accuracy methods, when these two properties are applied then the classification of huge data becomes easy. Various variable selection and accuracy prediction methods are discussed in this review.