貝氏網路是人工智慧方面相當熱門的領域。它在預測及診斷上的能力、在醫學、工程方面應用相當廣泛,近年來也被應用在教育方面。 本研究擬以國小四年級數學領域「代數、統計與機率」能力指標為依據,嚐試採用以機率推理為基礎的貝氏網路作為分析工具,以探討應用貝氏網路於診斷學生錯誤類型的可行性。同時將子技能納入分析,探討哪些子技能的缺失造成這些錯誤類型的產生。發展一套以九年一貫能力指標為基礎的智慧型電腦線上測驗及補救教學系統,讓學生透過網路參加測驗並了解自己的測驗結果。當學生測驗完畢之後,即時呈現作答結果、學科概念的診斷情形,並根據錯誤類型的分布狀況,進行線上補救教學。 根據本研究的結果分析,可以得到以下結論: ㄧ、電腦化診斷測驗部分 當使用動態分類決斷值時,錯誤類型辨識率高達97.01%,能力指標與子技能的辨識率也高達86.32%,所以貝氏網路的推論在國小四年級「代數、統計與機率」相關能力指標的診斷測驗具有可行性。 二、電腦化補救教學部分 學生成績進步情形,以前、後測成績成對樣本t檢定分析,達到顯著水準,證實本研究的電腦化補救教學動畫具有可行性。而學生依照不同的錯誤類型進行個別化適性補救教學是傳統測驗無法做到的,這是本研究的一大特色與優勢。
Bayesian Networks is a fashion division in up-to-date artificial intelligence field.Not only it rewarded much praise from prediction and examination on educational teaching but also it has been extensively applied in the fields of medicine and engineering. The main idea of the study is to research the ability of Algebra 、 Statistics and probability on Grade 4 and demonstrate the applicable of students mistaken types based on Bayesian Networks which is a probability analysis method. Students attend the test through the Learning Educational Program online, which is developed based on the index of Grade 1-9 Curriculum. The system can show the subject comprehension and begin to the Learning Educational Program on the basis of the mistaken type distribution. Due to the analysis result, there are two conclusions as below. 1. Computerized diagnosing test part Using the dynamic classified decision-point to identify the mistaken types and ability&sub-skills classified index, the scores are up to 97.01 and 86.32 respectively.It is suitable to use the ability index of Algebra 、 Statistics and probability on Grade 4 by Bayesian Networks. 2. Computerized remedy instructions part One of the program advantages is to give individual remedy instructions based on mistaken types, and it is un-available by traditional paper test. According to the t-test result on the scores which come from adopting and un-adopting remedy instructions groups, it is significantly effective to use the program.