Research On Bayesian Network Classification Models And Its Application In Vocational College Test

It is newly required in the information system that people should find information in the oceans of data for policy decision, analysis and prediction. Developed from Bayesian statistics, Bayesian Networks are charactered by the unique unstable information expression, rich probability expression, the incremental learning method that has absorbed the transcendental knowledge; mean while, they show the probability distribution and the cause and effect relation between the objects. Therefore, Bayesian Networks attract more attention in the methods of data mining; and it become an important manner for knowledge discovery. This dissertation mainly deals with Bayesian Networks and the application study of the classification model. The main ideas are as follows:(1) This dissertation introduces the basic concept of data mining and its several classification and evaluation methods. Associated with the present situation of vocational education and the traits of vocational college students, it discusses the basic application of Bayesian Networks in vocational education.(2) It not only introduces the theory foundations, concept and nature traits of Bayesian Networks, but the parameter learning and structure learning of Bayesian Networks. According to the theory description, it analyzes the Bayesian Networks models through a typical case; and perfects the data structure learning through K2 Algorithm.(3) Based on K2 algorithm and with the help of machine learning, it builds a Bayesian Networks classifier for vocational college English ability test in matlab environment.(4) The application study in vocational college test based on Bayesian Networks Classification model. The verification experiments have been made through Bayesian Networks classification tools and ID3 Algorithm respectively. The author comparatively analyzes the experiment results. This model makes full use of students' information transcendental knowledge, which not only indicates the direction of English learning for college students, but also supports teaching, education and management in vocational colleges.