Improving support vector machine level-based for person domain categorization

Classification technology refers to assigning of one or more suitable categories from multiple categories data sets. While previous work in classification focused on single classifier, we propose classification method of improving support vector machine level-based that can classify multiple categories. Actually, we use the weight calculation method of TFIDF and combine DAG-SVM and KNN algorithm to improve precise of classification. An experiment has been carried out to measure the performance of our proposed classification method. The results show that our method performs better for person domain data set comparing with single DAG-SVM method.