運用類神經網路於四技二專統一入學測驗成績預測-以高雄市某職業學校商管群為例

Application of Neural Networks Forcasting on the Scores of Vocational Education College Entrance Exam – A Study of a Kaohsiung Vocational High School

黃幸慧(Xing-Hui Huang)

指導教授 ： 巫沛倉

義守大學/管理學院/工業管理學系/碩士(2014年)

https://doi.org/10.6343/ISU.2014.00145

摘要

現今技職院校林立，技職體系學生之升學需求逐年增加，學生如何在升學考試前了解自身複習狀況，以此調整讀書方法及步驟並預測可選擇之學校，一直是學生、教師、家長關心的問題。為此，本研究嘗試建立成績預測模型，使教師能利用已知的模擬考成績預測四技二專統一入學測驗成績，以供學生參考以採取相關升學策略。
本研究蒐集高雄市某高級商業職業學校102及103學年度商業管理學群三年級學生四技二專統一入學測驗成績，以及四次校外聯合模擬考成績，運用類神經網路建立成績預測模型以作為規劃未來升學道路之參考。經實驗後數據的分析與實際分數比對後得到以下的結果：(1)運用模擬考總成績來預測統測總成績的準確度比運用模擬考各科成績來預測統測各科成績的準確度還要高，(2)運用模擬考各科成績來預測統測各科成績時，以國文科的準確度較高，(3)運用模擬考各科成績來預測統測各科成績時，以數學科的變異較大，結果也最差。

關鍵字

類神經網路 ； 四技二專統一入學測驗 ； 成績預測

並列摘要

The demand of the admission for vocational students in Taiwan increased because the rapid development of vocational schools. It is always the main subject of students, teachers, and parents who concerned about that how their learning statuses and their learning methods can affect their choices of the schools before the college entrance exam. In this research, we attempted to build a prediction model which provides students and teachers about the scores allocations of the simulation tests that will relate to the results of the vocational education college entrance exam. Our forecasting models can provide students information about the allocations of their interests and choose the most appropriate programs for their continuing studies.
In this study, a collection of four simulation tests results and corresponding vocational education college entrance exam from a vocational high school in Kaohsiung for academic years 2013 and 2014 was investigated. The test results included the total scores for each simulation test and five indivisual scores for different courses such as Chinese literature, English, mathematics, professional subject I and professional subject II. These tests results were designed to be the inputs of the neural network training. Another set of collections were the results for the vocational entrance exam from the same students. These tests results were desigeded to be the outputs of the neural network training. After training the back propagation neural networks, the best prediction of corresponding network was selected to be the prediction model for our research.
From the performances of our prediction models, we can conclude that: (1) the performance of using total scores of the simulation tests results to predict the vocational entrance exam scores is much better than the performace of using individual scores of the simulation tests results, (2) the forecasting performance of using individual tests scores for Chinese is the most accuracte among the five courses, (3) the forecasting performance of using individual tests scores for mathematics is worse than other courses.

並列關鍵字

Artificial Neural Networks ； Vocational Education College Entrance Exam ； Forcasting

參考文獻

任眉眉、陳日昇、詹嘉豪（2005），統計與落點分析：大學指考選填志願的利器，中國統計學報，43(2)，165-181。

教育部（2003），技術及職業教育百科全書，第一冊：技職教育通論，台北：作者，頁199。

教育部（2009），技術及職業教育法規選輯（五版一刷），台北：作者。

任眉眉、陳日昇、林家立（2008），大學指考落點與實證分析，Journal of the Chinese Statistical Association, 46, 144-163。

李佳玲(2002)，大學入學考試中心學科能力測驗與高中在校成績關係之研究，國立台北師範學院國民教育研究所碩士論文。