Data mining is the withdrawal of concealed prescient information also obscure data, examples, connections and learning by investigating the enormous informational collections which are hard to discover and distinguish with customary measurable techniques. The major issues in text categorization are classification accuracy and computation time. To overcome these issues, an efficient classification method is needed for high differentiation exactness as fine as minimizing the computation period. In this work, we propose the classification of data using support vector machine for text categorization along with principle component analysis. Bolster Vector Machines is a managed learning system with numerous attractive characteristics that make it a prevalent calculation. Principle Component Analysis (PCA) is the feature removal technique is used towards mine the features with in the text. Chi-Square is a further assortment technique it is used to selecting the features from removed features. Finally by this proposed work, the classification accuracy also computation period is improved than other existing algorithms in many applications
Support Vector Machine with Principle Component Analysis for Road Traffic Crash Severity Classification
