The main idea of the paperpaper is to research the ability of geometry on Grade 4 in elementary and demonstrate the applicable of students mistaken types based on Bayesian Networks which is a probability analysis method. Students join the test through the Learning Educational Program online, which is developed based on the index of Grade 1-9 Curriculum in Taiwan. The system can show the subject comprehension and begin to the Learning Educational Program on the basis of the mistaken type distribution. There are four main purposes of the study as below. 1.Demonstrating the geometry index of mistaken types on Grade 4 in elementary. 2.Appling the Bayesian Networks to analyze geometry index of mistaken types on Grade 4 in elementary, set up the quiz question, and Bayesian Networks Framing. 3.Establishing the Learning Educational Program based on the mistaken types. 4.Demonstrating the effective of the computerized adaptive flash. According to the analysis of the test result by Bayesian Networks Model, the average corrective is up to 90% with mistaken types, sub-skills, and capable index. The first conclusion shows it is more adaptive by using dynamic classified method to improve the recognizable degree on inferring the test result. After giving the suitable teaching to the students by the attracting flash, the students get higher scores than before.(t-test, p<0.001) The second conclusion of the study shows it is significantly effective to the students to clear the geometry concept by using the Learning Educational Program.
