近年來，隨著網際網路與資訊科技的迅速發展，學生的學習環境已由傳統的課堂教學與紙筆測驗，擴展到線上的數位學習。數位學習具有的網路存取特性，學習者可不受時空限制，隨時隨地進行學習活動，擁有豐富且多元的資料，可以有效提昇教學品質。但目前數位學習的線上測驗系統，通常只提供該次測驗的成績，正確的解答，以及顯示學習者不足的概念…等，無法針對學習者提供合適的補救教學。
本研究提出一個基於模糊推論(Fuzzy Inference)之補救教學系統，以C++程式語言為範例，提供學習者於考試測驗過後的補救學習。系統針對學習者的測驗結果，使用Apriori演算法至網路搜尋出題目的相關概念(Concepts)集合，並應用模糊推論與關聯比對機制，計算出學習的前後順序以組合成學習路徑，最後，系統根據學習者的學習風格(Learning Style)，至網路搜尋不同種類的教學教材，讓學習者進行補救學習。本研究建構於Moodle數位學習平台，整合多元的學習套件，可提供學習者完整的學習環境。透過學習成就與問卷的分析，證實本研究所提出的方法的確可以達到補救教學與適性學習的效果。

In recently years, learning environment has been changing because of the rapid development of Internet and information technology. Classroom learning and paper examinations are gradually migrating to online e-learning and assessing environments. The network access features make learners of e-learning system be able to learn at any time and in any place. With profuse and diverse learning materials, teaching quality can be effectively enhanced too. However, for the time being, most assessing system of e-learning environments can provide grades, correct answers and misconceptions of users in a test only, without any well-formed remedial instructions to the learners.
This study establishes a fuzzy inference-based remedial learning system to assist learners in remedial learning after an online assessment. C++ programming courses are used as a testing platform in this study. First, the system finds, from the Internet, the related concept set by apriori algorithm according to a learner’s misconceptions in a test and uses a fuzzy inference mechanism to decide a suitable learning path, comprising the concepts, for the learner. Then, the system searches learning materials and resources from the Internet for the concepts, based on the individual learner’s learning style, for conducting remedial learning of the learner. The system, proven by several conducted experiments, can offer a complete and stable remedial learning environment for any e-learning systems. The analysis of learners’ achievements and questionnaires has confirmed the method of this study achieve the effect of remedial learning and adaptive learning.

Agarwal, R., Aggarwal, C., & Prasad, V. (2001). A tree projection algorithm for generation of frequent item sets. Journal of parallel and Distributed Computing, 61(3):350-371.
Agrawal, R., Imieli ski, T., & Swami, A. (1993). Mining association rules between sets of items in large databases. ACM SIGMOD Record, 22(2):207-216.
Arrawal, R., & Srikant, R. (1994). Fast Algorithms for Mining Association Rules in Large Database. Paper presented at the The 20th International Conference on Very Large Data Bases.
Coenen, F., Leng, P., & Ahmed, S. (2004). Data structure for association rule mining: T-trees and P-trees. IEEE Transactions on Knowledge and Data Engineering, 16(6):774-778.
Dunn, R., Dunn, K., & Perrin, J. (1994). Teaching young children through their individual learning styles: Practical approaches for grades K-2: Allyn & Bacon.
Geiger, M., Boyle, E., & Pinto, J. (1992). A factor analysis of Kolb's revised Learning Style Inventory. Educational and Psychological Measurement, 52(3):753-768.
Han, J., Pei, J., Yin, Y., & Mao, R. (2004). Mining frequent patterns without candidate generation: A frequent-pattern tree approach. Data mining and knowledge discovery, 8(1):53-87.
Holt, J., & Chung, S. (2002). Mining association rules using inverted hashing and pruning. Information Processing Letters, 83(4):211-220.
Jiawei, H., Jian, P., & Yiwen, Y. (2000). Mining frequent patterns without candidate generation. Paper presented at the 2000 ACM SIGMOD international conference on Management of data.
Jing, L., Huang, H., & Shi, H. (2002). Improved feature selection approach TFIDF in text mining. Paper presented at the First International Conference on Machine Learning and Cybernetics.
Keefe, J. (1979). Learning style: An overview. Student learning styles: Diagnosing and prescribing programs, 1-17.
Kennedy, D. (2005). Challenges in evaluating Hong Kong students’ perceptions of Moodle. Balance, fidelity, mobility. Maintaining the momentum, 327–336.
Kolb, D. (1984). Experiential learning: Experience as the source of learning and development: New Jersey: Prentice Hall.
Kolb, D. (1985). Learning style inventory: Self-scoring inventory and interpretation booklet. Boston: McBer and Company.
Lin, C., Lin, C., & Lee, C. (1995). Fuzzy adaptive learning control network with on-line neural learning. Fuzzy Sets and Systems, 71(1):25-45.
Lindley, D. (1982). Scoring rules and the inevitability of probability. International Statistical Review/Revue Internationale de Statistique, 50(1):1-11.
Marchionini, G. (1988). Hypermedia and Learning: Freedom and Chaos. Educational technology, 28(11):8-12.
MSDN library, http://msdn.microsoft.com/en-us/library/ms951256.aspx
Resta, P. (2000). The Internet and university teaching: will the networking technologies change the teaching-learning process. Paper presented at the The 8th International Conference on Computer-assisted Instruction.
Saggion, H., Teufel, S., Radev, D., & Lam, W. (2002). Meta-evaluation of summaries in a cross-lingual environment using content-based metrics. Paper presented at the COLING-2002.
Salton, G., & Lesk, M. (1968). Computer evaluation of indexing and text processing. Journal of the ACM (JACM), 15(1):8-36.
Tribus, M. (1979). Comments on Fuzzy sets, fuzzy algebra, and fuzzy statistics. Proceedings of the IEEE, 67(8):1168-1169.
Zadeh, L. (1965). Fuzzy sets. Information and control, 8(3):338-353.
中央研究院CKIP中文詞知識庫小組，http://rocling.iis.sinica.edu.tw/CKIP/。
王昌傑 (2005)，學習風格對國中生自然科學習成就之影響，慈濟大學教育研究所碩士論文。
台灣YAHOO知識網站，http://tw.knowledge.yahoo.com/。
余尚武、郭至軒 (2004)，運用基因演算法與模糊理論於台股指數期貨投資策略之研究，中華管理評論，7(2):132-157。
良葛格學習筆記網站，http://caterpillar.onlyfun.net/Gossip/。
林金錫、舒兆民、周中天、陳浩然、連育仁 (2007)，Moodl在華語文教學上之運用，第五屆全球華文網路教育研討會，台北市:國立台灣科學教育館。
吳天方 (1997)，我國師範大學工業教育學生學習風格之相關研究，教育研究資訊，5(5):114-132。
李允中、王小璠、蘇木春 (2003)，模糊理論及其應用，台北:全華科技圖書股份有限公司。
李健興、江俊志、張詠淳、郭耀煌 (2005)，支援CMMI專案監控網路服務之研究，中華民國九十四年全國計算機會議，台南:崑山科技大學。
花英德 (2007)，以科技接受模式探討國小學童Moodle教學平台使用行為之研究~以資訊議題教材為例，東海大學教育研究所碩士論文。
孫宗瀛、楊英魁 (1995)，Fuzzy 控制: 理論、實作與應用，台北:全華科技圖書股份有限公司。
逢甲大學資訊工程學系-資料探勘研究室，http://140.134.26.172:8080/mining/help/introduction.jsp#Apriori。
張春興 (1994)，教育心理學-三化取向的理論與實踐，台北:東華書局。
張家鳳 (2004)，利用資料挖掘技術建構保險業之差異化行銷模型，世新大學資訊管理研究所碩士論文。
郭重吉 (1987)，英美等國晚近對學生學習風格之研究，資優教育季刊，(22):2-8。
傅榮財 (2006)，虛擬實境教學對學習成效之影響-以國中自然與生活科技「日、地、月之相對運動及轉動的地球」單元為例，國立臺南大學數位學習科技研究所碩士論文。
彭彥瑋 (2004)，應用類神經模糊探討策略外部配適-以台灣醫療產業為例，靜宜大學企業管理研究所碩士論文。
游政男 (2001)，學習風格與超媒體網頁架構方式對學習鐘擺週期之影響，國立東華大學教育研究所碩士論文。
楊采璇、呂秉修、王子華 (2007)，不同學習風格國小學童在資訊科技融入教學環境之學習成效研究，TANET2007臺灣網際網路研討會，台北市:國立臺灣大學。
楊家興 (1993)，超媒體: 一個新的學習工具，教學科技與媒體，12:28-39。
楊敏生 (1994)，模糊理論簡介，數學傳播，18(1):7-11。
楊敏生、劉曼君 (1996)，可能性理論淺介，數學傳播，20(3):13-16。
酷！學園網站，http://phorum.study-area.org/。
論壇JavaWorld@TW，http://www.javaworld.com.tw/。
歐展嘉 (2006)，Moodle 數位學習課程管理平台，台北市:文魁資訊。
線上問卷網-my3q.com，http://www.my3q.com/。
謝章冠 (2002)，網路學習之學習路徑控制機制，國立中山大學資訊管理學系研究所碩士論文。
顏榮泉 (1996)，全球資訊網在教學與學習上之應用探討，教學科技與媒體(25):33-41。