應用漸進式因果規則探勘分析學生學習歷程與就業表現;Employing Incremental Causal Rule Mining On Students’ Learning Portfolio And Employment Performance

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/89740

Please use this identifier to cite or link to this item: https://ir.lib.ncu.edu.tw/handle/987654321/89740

Title:	應用漸進式因果規則探勘分析學生學習歷程與就業表現;Employing Incremental Causal Rule Mining On Students’ Learning Portfolio And Employment Performance
Authors:	林良翰;Lin, Liang-Han
Contributors:	資訊工程學系
Keywords:	校務研究;資料探勘;關聯規則探勘;漸進式因果規則探勘;Institutional Research;Data Mining;Association Rule Mining;Incremental Causal Rule Mining
Date:	2022-07-07
Issue Date:	2022-10-04 11:58:10 (UTC+8)
Publisher:	國立中央大學
Abstract:	本研究提供漸進式因果規則分析的演算法，並於本校校務資料倉儲環境中驗證，確認得到良好的效能。過去五年來，本國政府及許多學校開始注重於校務研究，其目的為更好的去評斷及改善學校自身經營與教學績效，讓學校的決策者透過科學化的研究去協助學校進行策畫改善、透過資料蒐集、分析、解讀來提升學校辦學品質及學校發展。校務資料涵蓋的範圍相當廣泛，包括學生、教職員、教務、學務等學校有關的資源，本校校務研究單位雖已蒐集、整理各個單位的資料並進行整合，但仍有未被發掘的資訊尚待進行分析及利用。本研究以學生為主題切入，進行探索性數據分析，從學生的背景、學習歷程、畢業後狀況等的資料中分析學生發展趨勢，由不同面向挖掘具有因果關係的資料組合，提供校務人員多元化的分析議題、決策支援。此外，由於校務資料是會不斷新增的，新資料加入也會影響分析結果的正確性和適用性，為了更符合實務上的運用，本研究納入漸進式挖掘的系統架構，使得在資料在大量累進的情況下能有效率地提供決策者資料異動後因果規則的分析結果，進一步也大幅減輕系統常態維護與週期性分析的負擔。 ;In recent years, due to the rapid development of university education, many schools have begun to develop institutional research for the purpose of better evaluating and improving the school’s own operation and teaching performance, so that school decision makers can help schools to improve their planning through scientific research, and improve the quality of school operations and school development through data collection, analysis, and interpretation. The institutional research data covers a wide range of school-related resources, including students, staff, teaching and academic affairs. Although the institutional research office has collected, organized, and integrated data from various offices, there is still unexplored information that has yet to be analyzed and utilized. Our research use students as the theme to conduct exploratory data analysis and analyze the development trend of students from their background, learning history, and post-graduation status, etc. Our research explore the combination of data that have causality from different aspects to provide institutional research office with diversified analysis issues and decision support. In addition, since school data are constantly added, the addition of new data will affect the accuracy and applicability of the analysis results. In order to be more practical, our research design a incremental mining system framework, hoping to quickly provide decision makers with causal rule analysis results even when data are continuously added, and to reduce the possible loss caused by analysis delay.
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	134	View/Open

社群 sharing

Loading...