實驗室成員‎ > ‎

鍾穎

鍾穎 Ying Chung

碩士論文 (2007)

適性化案例學習之案例調適機制研發
Development of a Case Adaptation Mechanism for Adaptive Case-based Learning

關鍵字 Keywords

類神經網路, 案例式推理, 案例學習, 適性化學習, 案例調適
Adaptive Learning, Case-based Learning, Case-based Reasoning, Artificial Neural Network, Case Adaptation

摘要

21世紀被喻為知識經濟的時代,最重要的資產就是知識工作者及其生產力,教師雖身為教育領域中最重要的知識工作者,但長久以來師資教育就一直存在著理論和實務的隔閡,因此利用網際網路快速傳播、資訊內容可以結構化和易於搜尋的優勢,協助學生教師或在職教師促進自我的專業成長及知識建構,有其必要性。 本研究以教師為主要學習者,將教學敘事等實務知識以學習案例(Learning Case)呈現,發展適性化案例學習模式與案例調適機制以符合上述學習需求,它具有適性化、系統化、可調適性等特色,目的是要在Web-based之環境下,以案例式學習與適性化學習等理論為基礎,設計適性化案例學習 (Adaptive Case-based Learning) 模式,再結合類神經網路(Artificial Neural Network)與案例式推理(Case-based Reasoning)等人工智慧技術的應用,根據上述模式發展案例調適(Case Adaptation)機制,針對多層次的教學知識進行推論和細部規劃,期能藉由適性化案例內容的產生與調適,讓學習者(教師)透過此一適性化案例學習模式獲得最適切的教學目標、教學策略、教學步驟、教學方法等系統化之知識內容,以作為實務應用及問題解決的參考,進而收知識建構之效益。 適性化案例學習之案例調適機制研發提供教學輔助及參考等應用,除了可透過此一適性化案例式學習模式獲得適切的實務知識內容,還可藉由案例調適的互動及適性化案例內容自動地產生、調適,保持學習者(教師)的學習動機。本機制的設計與開發,不但彌補了多數案例式推理系統無法達到自動調適的缺失,在案例調適演算法部分更是當前相關數位學習機制研究中鮮少出現的應用。

Abstract

The 21 century is known as the era of the knowledge economy, and the most important assets are knowledge workers and their productivity. Teachers could be one of the most important knowledge workers for the educational domain, however, there’s been a gap permanently between the theory and practice in teacher education. It’s necessary to assist student teachers and on-the-job teachers in pushing ahead with their professional growth and knowledge construction by the rapid spread of the Internet as well as the advantage of the information content that can be structuralized and easily searched. This research investigates the development of the adaptive case-based learning model and the case adaptation mechanism provided with adaptive, systematic and adaptable characteristics to meet the aforementioned learning requirements, in which the teachers are viewed as major learners, and the practical knowledge like teaching narrations are presented as learning cases. Building on theories from case-based learning and adaptive learning, the goal of this research is to develop the case adaptation mechanism for adaptive case-based learning in web-based environment by designing the adaptive case-based learning model and using both artificial neural network and case-based reasoning techniques so that the proposed mechanism is capable of reasoning and planning multilayer pedagogic knowledge. With the generation and adaptation of learning contexts as practical applications and problem solving references, teachers will gain the systematic knowledge including exact teaching objectives, teaching strategies, teaching procedures, teaching methods and so on. The results of this research provide the pedagogic assistance and reference, so as to support exact practical knowledge content in the adaptive case-based learning model, as well as make learners keep their learning motives with generating the further adapted learning content automatically.


Comments