查詢教學大綱與進度

教學大綱與進度

課程基本資料：

學年期課號課程名稱階段學分時數修教師班級人撤備註

113-1 338595 都市數據進階分析與模型應用 1 3.0 3 ★ 林佑達創新AI學位學程 11 1 先1F MIT教室上課

學年期	課號	課程名稱	階段	學分	時數	修	教師	班級	人	撤	備註
113-1	338595	都市數據進階分析與模型應用	1	3.0	3	★	林佑達	創新AI學位學程	11	1	先1F MIT教室上課

教學大綱與進度：

教師姓名林佑達

Email Roylin918@gmail.com

最後更新時間 2024-06-04 16:39:16

課程大綱當代都市議題經常為跨領域、開放性的複雜問題，在資料蒐集與分析上，需要整合地理空間、時間的維度；在分析與對策上，須平衡公部門、私部門、民眾等多重利害關係者的，是一門相當複雜但重要的學問。本課程從真實的都市議題出發，教導學生掌握地理空間資訊、資料分析、資料建模、資訊視覺化、策略論述等綜合能力，培養學生對於都市複雜議題的觀察與剖析，進而對真實環境提出洞見與創意。 Contemporary urban issues are complex, requiring the integration of geographical, and temporal dimensions in data collection and analysis. Balancing the interests of stakeholders like the public, and private sectors is crucial. This course focuses on real urban issues, teaching skills in geographical information, data analysis, modeling, visualization, and strategic discourse. It aims to cultivate students' ability to observe, analyze urban issues, and propose insights for real environments. It's an advanced course, requiring basic programming and GIS concepts. Through group projects, students learn API usage, geographic computation, model building, and data visualization. The course includes one midterm report and one final project report.

課程進度第1週：都市數據應用概論第2週：地理空間資訊簡介與視覺化第3週：時空資料庫簡介與操作第4週：空間資料處理、地理運算第5週：機器學習簡介與模型實作第6-8週：分組實作第9週：期中分組報告第10-12週：模型調校第13-14週：模型解讀第15週：都市論述與策略建議第16-17週：分組實作第18週：期末分組報告 Week 1: Introduction to Urban Data Applications Week 2: Introduction to GIS and Visualization Week 3: Introduction to Spatiotemporal Database and ETL Week 4: Data Processing and Geoprocessing Week 5: Introduction to Machine Learning and Data Modeling Weeks 6-8: Group Projects Week 9: Midterm Group Report Weeks 10-12: Model Calibration Weeks 13-14: Model Interpretation Week 15: Urban Arguments and Strategies Weeks 16-17: Group Projects Week 18: Final Group Report

評量方式與標準個人課程參與 30%：平時上課出席率、討論參與度、每週進度等綜合評比。分組期中成果 30%：各組期中簡報的成果總體評比，同一組每個成員評分相同。分組期末成果 40%：各組期中簡報的成果總體評比，同一組每個成員評分相同。 Individual Course Participation 30%: Comprehensive assessment of regular class attendance, participation in discussions, weekly progress, etc. Group Midterm Results 30%: Overall evaluation of each group's midterm presentation results, with the same score given to each member within the same group. Group Final Results 40%: Overall evaluation of each group's final presentation results, with the same score given to each member within the same group.

使用教材、參考書目或其他 【遵守智慧財產權觀念，請使用正版教科書，不得使用非法影印教科書】

使用外文原文書：否
必備軟體/語言：Python, QGIS 選用軟體/語言：R-studio, Tableau Public 數據來源：國內外開放資料 Required Software/Languages: Python, QGIS Optional Software/Languages: R-studio, Tableau Public Data Sources: Domestic and international open data

課程諮詢管道 Instructor: roylin@mail.ntut.edu.tw

延伸教學與資源

課程對應SDGs指標 SDG11：永續城市與社區（Sustainable Cities and Communities）

課程是否導入AI

備註

教師姓名	林佑達
Email	Roylin918@gmail.com
最後更新時間	2024-06-04 16:39:16
課程大綱	當代都市議題經常為跨領域、開放性的複雜問題，在資料蒐集與分析上，需要整合地理空間、時間的維度；在分析與對策上，須平衡公部門、私部門、民眾等多重利害關係者的，是一門相當複雜但重要的學問。本課程從真實的都市議題出發，教導學生掌握地理空間資訊、資料分析、資料建模、資訊視覺化、策略論述等綜合能力，培養學生對於都市複雜議題的觀察與剖析，進而對真實環境提出洞見與創意。 Contemporary urban issues are complex, requiring the integration of geographical, and temporal dimensions in data collection and analysis. Balancing the interests of stakeholders like the public, and private sectors is crucial. This course focuses on real urban issues, teaching skills in geographical information, data analysis, modeling, visualization, and strategic discourse. It aims to cultivate students' ability to observe, analyze urban issues, and propose insights for real environments. It's an advanced course, requiring basic programming and GIS concepts. Through group projects, students learn API usage, geographic computation, model building, and data visualization. The course includes one midterm report and one final project report.
課程進度	第1週：都市數據應用概論第2週：地理空間資訊簡介與視覺化第3週：時空資料庫簡介與操作第4週：空間資料處理、地理運算第5週：機器學習簡介與模型實作第6-8週：分組實作第9週：期中分組報告第10-12週：模型調校第13-14週：模型解讀第15週：都市論述與策略建議第16-17週：分組實作第18週：期末分組報告 Week 1: Introduction to Urban Data Applications Week 2: Introduction to GIS and Visualization Week 3: Introduction to Spatiotemporal Database and ETL Week 4: Data Processing and Geoprocessing Week 5: Introduction to Machine Learning and Data Modeling Weeks 6-8: Group Projects Week 9: Midterm Group Report Weeks 10-12: Model Calibration Weeks 13-14: Model Interpretation Week 15: Urban Arguments and Strategies Weeks 16-17: Group Projects Week 18: Final Group Report
評量方式與標準	個人課程參與 30%：平時上課出席率、討論參與度、每週進度等綜合評比。分組期中成果 30%：各組期中簡報的成果總體評比，同一組每個成員評分相同。分組期末成果 40%：各組期中簡報的成果總體評比，同一組每個成員評分相同。 Individual Course Participation 30%: Comprehensive assessment of regular class attendance, participation in discussions, weekly progress, etc. Group Midterm Results 30%: Overall evaluation of each group's midterm presentation results, with the same score given to each member within the same group. Group Final Results 40%: Overall evaluation of each group's final presentation results, with the same score given to each member within the same group.
使用教材、參考書目或其他	【遵守智慧財產權觀念，請使用正版教科書，不得使用非法影印教科書】使用外文原文書：否必備軟體/語言：Python, QGIS 選用軟體/語言：R-studio, Tableau Public 數據來源：國內外開放資料 Required Software/Languages: Python, QGIS Optional Software/Languages: R-studio, Tableau Public Data Sources: Domestic and international open data
課程諮詢管道	Instructor: roylin@mail.ntut.edu.tw
延伸教學與資源
課程對應SDGs指標	SDG11：永續城市與社區（Sustainable Cities and Communities）
課程是否導入AI
備註