考量環境智慧之適性化行動學習平台

Adaptive Mobile Learning Platform Considering Ambient Intelligence

韓世翔(Shir-Shiang Han)

指導教授 ： 林志浩

中原大學/商學院/資訊管理研究所/碩士(2004年)

https://doi.org/10.6840/cycu200400679

摘要

無線通訊網路的發展使得使用者只要使用任何可連網的手持裝置即可取得網路上的資源，其中也包含數位學習（E-learning）的課程內容，數位學習除了提供學習者不受時間限制的學習需求外，若再透過手持裝置進行存取則能夠讓學習者的學習活動打破地點的限制。然而使用手持裝置進行學習活動較之數位學習更需要掌握學習者周遭環境的變化以及提供專為行動化環境編寫的課程內容，如此才能充分發揮行動學習（M-learning）個人化、行動化的主要特徵。
本研究認為行動學習主要在於能夠利用手持裝置個人化、行動化功能，反應學習者所處環境當下的特徵並提供適合該特徵的學習內容，讓學習者能夠在真實環境之中迅速認知到所習得的課程意涵，進而在下次面對到相似情境時能夠立即活用其內容，也就是以情境為主的學習方式，本研究以英文的學習作為情境化行動學習標的，同時透過系統實作展示行動學習的運作模型，本研究認為該系統平台具有情境式學習、系統偵測環境因子、鷹架式教學方式、模糊推論方法、課程動態調整以及學習者主導六大特色，在實作系統方面則參考學習物件描述、與環境相關的模糊資訊、相似性量測方法與流程模型作為系統建置的理論基礎。

關鍵字

行動學習 ； 學習物件 ； 智慧家教系統 ； 環境智慧 ； 情境化學習 ； 數位學習 ； 適性化教學

並列摘要

Today, improvements of wireless communicate network make the hand-hold device access network resources easily including E-learning’s content. E-learning supports the learner to learn at any time, and learning can be taken place at anywhere if the learner gets learning content with his hand-hold device. The character of using hand-hold device to access learning content is different from E-learning. It has to support the availability of sensing context about the learner and provide the learning content with mobile metadata.
The strength of M-leaning/Mobile leaning that the thesis argues is personalization and mobility. M-learning platform captures the specific (geographical or temporal) information about the learner’s environment and to infer a proper learning objects list for the learner through measuring the similarity of reality and learning object’s pattern. This strategy derives from the theory of situated learning, it claims that every idea and human action is a generalization, adapted to the ongoing environment, because what people see and what they do arise together. The thesis also proposes a prototype supports English learning at anytime and anywhere. There are six properties in the prototype, 1) Situated learning, 2) Context awareness, 3) Scaffolding teaching, 4) Fuzzy reasoning, 5) Adaptive navigation, and 6) Learner orientation. The prototype bases on some theories like learning object metadata, context dependent fuzzy knowledge, measure of similarity, and flow model.

並列關鍵字

Ambient Intelligence ； Learning Object ； Intelligence Tutor System ； M-learning ； Adaptive Navigation ； E-learning ； Situated Learning

參考文獻

【2】 林信成、彭啟峰，【OH! FUZZY 模糊理論剖析】，第三波文化事業股份有限公司，民國八十三年十月。

【15】 Brown, P.J., Bovey, J.D., Chen, X., “Context-aware Applications: From the Laboratory to the Marketplace,” Proceedings of IEEE Personal Communications, vol. 4, issue 5, 1997, pp.58-64.

【20】 Chen S., Ke J., and Chang J., “Knowledge representation using fuzzy Petri nets,” IEEE Trans. Knowl. Data Eng., vol. 2, no. 3, 1990, pp. 311–319.

【21】 Chen, S. M., Yeh, M. S., Hsiao, P. Y., “A comparison of similarity measures of fuzzy values,” Fuzzy Sets and Systems 72, 1995, pp.79-89.

【27】 Fan, J., and Xie, W., “Some notes on similarity measure and proximity measure,” Fuzzy Sets and Systems 101, 1999, pp.403-412.