DSpace collection: 博碩士論文

運用計算智慧探討智慧城市中農地重金屬再污染之研究：以桃園市為例;Development and Application of a Computational Intelligence–Based System for Assessing Heavy Metal Recontamination in Smart City Agricultural Land: A Case Study of Taoyuan City

title: 運用計算智慧探討智慧城市中農地重金屬再污染之研究：以桃園市為例;Development and Application of a Computational Intelligence–Based System for Assessing Heavy Metal Recontamination in Smart City Agricultural Land: A Case Study of Taoyuan City abstract: 桃園市為臺灣農地重金屬污染最嚴重之地區之一。雖經多次整治與復育，惟農地再污染風險仍未完全消除，顯示該區具有高度代表性與研究迫切性。傳統污染治理多倚賴靜態監測與事後補救，缺乏即時預警與動態預測機制，無法全面掌握污染再發生之潛勢，亦不利於智慧城市永續治理之推動。本研究旨在整合人工智慧與資料探勘技術，建立一套應用於智慧城市農地環境管理之重金屬再污染預測模型，以協助政府部門進行風險監控、污染預防及資源配置。透過引入多元學習模型與空間決策分析，提升污染風險預測之準確性與可操作性，期能提供污染防治及風險分級決策之量化依據。本研究以桃園市列管農地為研究對象，蒐集2004年至2021年間重金屬監測資料，選取鎘、銅與鋅三項主要污染因子。研究流程包含：（1）資料前處理與變數標準化；（2）特徵篩選與變數重要性排序；（3）模型建構與比較分析。在模型建構方面，除採用以隨機森林（Random Forest, RF）演算法外，並建構結合邏輯斯迴歸（Logistic Regression, LR）與深層神經網路（Deep Neural Network, DNN）之集成學習架構，並透過k倍交叉驗證（k-Fold Cross Validation）進行參數優化。同時結合地理資訊系統（GIS），進行污染熱區之空間視覺化分析與風險地圖繪製。結果顯示，隨機森林(RF)模型於再污染預測中表現最佳，其重金屬濃度變化預測準確率達75.76%，增量預測準確度高達99.95%；邏輯斯迴歸(LR)模型對銅、鋅、鎘之預測準確率分別為82%、83%與91%；深層神經網路(DNN)則展現高度適配性，其中鎘之預測R²值達0.98，顯示模型具高穩定性與解釋力。本研究以灌溉小組為單位建立污染風險分級制度，並提出「灌溉小組污染預防分級管理指標」，藉由GIS繪製污染風險地圖，識別高再污染潛勢區，作為環保單位實施分級管理與監測規劃之依據。本研究之主要貢獻在於開發具實務應用性之智慧型污染預測系統，能有效降低傳統採樣與監測成本，提升政府於污染防治、農地整治與土地治理上的前瞻性決策能力。綜上所述，本研究不僅建立人工智慧導向之污染預測模式，亦落實智慧城市永續環境治理之決策支援機制，對農地復育與污染防治政策制定具重要貢獻。 ;Taoyuan City is among the most severely affected regions in Taiwan in terms of agricultural heavy metal contamination. Despite multiple remediation and rehabilitation efforts, the risk of recontamination persists, underscoring both the representativeness of the region and the urgency for further investigation. Conventional pollution management primarily relies on static monitoring and post-remedial actions, lacking real-time early warning and dynamic prediction mechanisms. Such limitations impede a comprehensive understanding of potential recontamination processes and hinder the advancement of sustainable environmental governance in smart cities. This study aims to integrate artificial intelligence and data mining techniques to develop a predictive model for heavy metal recontamination in agricultural land, designed for environmental management within the smart city framework. The proposed model assists governmental agencies in risk monitoring, pollution prevention, and resource allocation. By incorporating multiple machine learning algorithms and spatial decision analysis, the study enhances the accuracy and operational applicability of pollution risk prediction. Furthermore, the analytical results provide quantitative evidence of the key factors influencing farmland recontamination, while the model offers quantitative support for decision-making in pollution control and risk-based land management. Focusing on regulated farmlands in Taoyuan City, this study utilized monitoring data from 2004 to 2021, targeting cadmium (Cd), copper (Cu), and zinc (Zn) as key pollutants. The analytical framework comprised three main stages: (1) data preprocessing and normalization, (2) feature selection and variable importance ranking, and (3) model development and comparative analysis. In terms of modeling approaches, this study adopts a Random Forest (RF) algorithm and an ensemble learning framework that integrates Logistic Regression (LR) and Deep Neural Networks (DNN). Model parameters were optimized using k-fold cross-validation to enhance predictive performance. In addition, Geographic Information Systems (GIS) were incorporated to perform spatial visualization of pollution hotspots and to generate risk maps. The results demonstrate that the RF model achieved the highest predictive performance, with an accuracy of 75.76% for heavy metal concentration changes and 99.95% for incremental prediction. The LR model achieved accuracies of 82%, 83%, and 91% for Cu, Zn, and Cd, respectively, while the Deep Neural Network (DNN) demonstrated strong adaptability, achieving an R² value of 0.98 for Cd, indicating high model stability and explanatory power. A pollution risk classification system was further established based on irrigation group units, accompanied by the proposal of “Irrigation Group Pollution Prevention and Classification Management Indicators.” The GIS-based risk maps effectively identified areas with high recontamination potential, supporting environmental agencies in implementing hierarchical management and monitoring strategies. The primary contribution of this study lies in the development of a practical, AI-driven pollution prediction system that substantially reduces traditional sampling and monitoring costs while enhancing proactive decision-making in pollution control, farmland remediation, and environmental governance. Overall, this research not only establishes an AI-driven pollution prediction model but also implements a decision-support mechanism for sustainable environmental governance in smart cities, contributing significantly to agricultural land rehabilitation and pollution control policy formulation.

越南建築業採用綠色材料面臨的障礙;Barriers to adoption of green materials in Vietnam′s construction industry

title: 越南建築業採用綠色材料面臨的障礙;Barriers to adoption of green materials in Vietnam′s construction industry abstract: 緊急轉向可持續建築對於越南等發展中經濟體至關重要，因為快速的城市化、資源枯竭和環境退化威脅著長期的社會與經濟穩定。本研究系統地調查了阻礙越南混凝土行業採用環保建材的多面向障礙。綜合文獻回顧確定了六大主要障礙類別：技術、經濟、法規、社會、認知和應用過程因素。技術限制包括材料質量不穩定、缺乏現場測試能力和設計標準不足，經濟障礙則來自高昂的前期投資成本、缺乏財務激勳和市場不穩定。法規挑戰涉及政策發展緩慢、指導方針模糊以及繁瑣的審批程序。社會和認知因素——例如風險規避、有限的培訓和成功範例的宣傳不足——進一步拖延了向綠色實踐轉型的過程。為了實證驗證這些發現，本研究採用了結構化問卷，並分發給建築專業人士、政策制定者和行業利益相關者。問卷設計基於廣泛的質性洞察，並通過與領域專家的試驗測試進行改進。數據使用結構方程模型（SEM）進行定量分析，利用SPSS和AMOS軟件，嚴格檢驗了識別的障礙群體對利益相關者意圖及實際採用環保建材的直接和間接影響。結果顯示，經濟障礙對應用環保混凝土材料的意圖具有最強的負面影響，而法規障礙也有顯著但相對較弱的影響。相反，一旦經濟和法規層面被控制，技術、社會和認知障礙的直接影響變得較弱或在統計上不顯著，儘管這些因素仍然與並加強了主要的經濟和制度性限制。研究結果表明，減少財務風險、改善經濟激勳和澄清法規框架比單純的技術干預對推動採用更具決定性作用。本文最後提出了一系列綜合政策和管理建議——如財務支持機制、協調的綠色標準、針對性的培訓計劃和示範項目——旨在增強利益相關者的信心、提高市場準備度，並加速越南混凝土行業中環保材料的主流應用。關鍵字：可持續建築；挑戰；綠色建材 ;The urgent shift toward sustainable construction is essential for developing economies such as Vietnam, where rapid urbanization, resource depletion, and environmental degradation threaten long-term social, economic stability. This research systematically investigates the multifaceted barriers impeding the adoption of eco-friendly construction materials in Vietnam′s concrete sector. A comprehensive literature review identifies six primary categories of barriers: technical, economic, regulatory, social, awareness-related, and application-process factors. Technical constraints include inconsistent material quality, lack of field testing capabilities, and limited design standards, while economic barriers stem from high up-front investment costs, the absence of financial incentives, and market instability. Regulatory challenges encompass slow policy development, vague guidelines, and complicated approval procedures. Social and awareness factors—such as risk aversion, limited training, and poor dissemination of successful examples—further stall the transition toward greener practices. To empirically validate these findings, the study employed a structured questionnaire distributed among construction professionals, policy makers, and industry stakeholders. The survey’s design was based on extensive qualitative insights and refined through pilot testing with domain experts. Data was quantitatively analyzed using Structural Equation Modeling (SEM) with SPSS and AMOS software, allowing for rigorous examination of both direct and indirect effects of the identified barrier groups on stakeholder intention and the practical adoption of eco-friendly materials. The results show that economic barriers exert the strongest negative influence on the intention to apply eco-friendly concrete materials, while regulatory barriers also have a significant but comparatively weaker effect. In contrast, once economic and regulatory dimensions are controlled, the direct effects of technical, social, and awareness-related barriers become weaker or statistically non-significant, although these factors still correlate with and reinforce the dominant economic and institutional constraints. The findings suggest that reducing financial risks, improving economic incentives, and clarifying regulatory frameworks are more decisive for promoting adoption than purely technical interventions. The thesis concludes with an integrated set of policy and managerial recommendations—such as financial support mechanisms, harmonized green standards, targeted training programmes, and demonstration projects—aimed at enhancing stakeholder confidence, improving market readiness, and accelerating the mainstream application of eco-friendly materials in Vietnam’s concrete sector. Keywords: Sustainable construction; challenges; green materials

探究營建工程查核成效與缺失實務關連與分析之研究

title: 探究營建工程查核成效與缺失實務關連與分析之研究 abstract: 台灣工程界雖多年累積大量查核資料與標準化評分機制，但查核分數長期集中於中高分區間，難以有效區分不同缺失型態與嚴重度等級，加上查核成績與扣點、懲罰性違約金及機關與人員考績密切相關，評分文化與制度壓力可能使分數呈現壓縮與偏態，實務上亦難以清楚清楚說明缺失嚴重程度與查核成效之量化關聯。本文所謂之查核成效，係以查核制度之評分輸出作為操作化定義，實證分析中以查核總分作為主要量化指標。為回應此一問題，本研究以行政院公共工程委員會之公共工程標案管理系統之資料為基礎，整併多年度、多機關及多工程類型查核事件，建構以單次查核為分析單位之資料集，並保留嚴重、中等與輕微缺失件數作為缺失嚴重度結構核心指標。方法上，結合多元線性迴歸與隨機森林等統計與機器學習工具，檢視各類缺失與查核總分之關係，並運用 K-means 分群搭配肘部法則、輪廓係數與 z 分數，自缺失結構角度辨識工程案件之典型群組與其分數分布特徵。預期透過此一分析架構，本研究將能由制度實際運作之資料出發，釐清查核分數在多大程度上反映缺失嚴重程度，揭示制度設計盲點與改善方向，並協助主管機關將既有查核資料轉化為可支援缺失嚴重度分群與資源配置之決策基礎，同時提供承攬與監造單位進行自我診斷與品質精進之量化依據。;Taiwan’s construction sector has accumulated extensive inspection data and standardized scoring mechanisms, yet scores remain highly concentrated in the mid to high range. As inspection results are tied to demerit points, punitive liquidated damages, and performance evaluations, institutional and cultural pressures may compress and skew score distributions, making it unclear to what extent inspection scores truly reflect defect patterns and severity. In this study, “audit effectiveness” is operationalized as the scoring output of the public construction inspection system. Accordingly, the overall inspection score is adopted as the primary quantitative indicator in the empirical analyses. To address this issue, this study uses data from the Public Construction Bidding and Management System of the Public Construction Commission, constructing a dataset at the level of individual inspection events and retaining counts of severe, moderate, and minor defects as core indicators of defect severity. Multiple linear regression and random forest models are applied to examine the relationships between these defect categories and the normalized overall inspection score. K-means clustering, combined with the elbow method, silhouette coefficient, and z-score analysis, is then used to identify typical defect-structure clusters and their associated score patterns. The proposed framework aims to clarify how well inspection scores reflect defect structures, reveal blind spots in the current scoring design, and provide a basis for more informed defect severity, resource allocation, and data-driven quality improvement for both authorities and practitioners.

建構可重現性與可攜性GPR B-scan影像3D視覺疊合技術與流程之研究

title: 建構可重現性與可攜性GPR B-scan影像3D視覺疊合技術與流程之研究 abstract: 本研究旨在探討透地雷達（Ground Penetrating Radar, GPR）影像與3D幾何模型之整合，動機源自現有GPR多以2D雷達圖呈現，缺乏明確的座標基準與幾何脈絡，導致判讀高度依賴個人經驗。為形成可稽核與可傳遞的共通語言，本研究的目的是建立一套GPR B-scan 影像與三維幾何模型對位之基準架構，使影像能在穩定的空間座標與尺度下定位、被檢核並作為工程決策之有效依據。研究以實驗室混凝土試體為對象，使用1.6 GHz透地雷達量測，並於三維模型環境中設計包含：（1）影像標準化、（2）模型與切面建構、（3）UV 貼圖與B-scan影像貼附、（4）精度檢核與可攜式檔案結構建置等流程，採用水平方向均方根誤差（RMSE）須小於2mm或0.5%·Lx 作為對位標準，以檢驗疊合精度與流程可重現性。結果顯示，三組試體皆滿足預設精度標準，且OBJ、MTL、圖像檔與語意描述檔可於不同軟體環境中正確載入，證實本研究所建構之流程在對位精度與檔案可攜性方面具可行性。經整合後，疊合圖可同時呈現雷達反射特徵與構件幾何位置，有助於 GPR 技術人員與設計、維護單位在共同空間語境下討論異常訊號與潛在劣化區域，提升溝通效率與判讀透明度，未來可在此基準架構之上，進一步導入自動化影像判讀、結合BIM與數位孿生並擴展至實橋與既有結構之長期監測與維護決策應用。;The objective of this study is to establish a baseline framework for aligning GPR B-scan images with three-dimensional geometric models, enabling radar images to be placed in a consistent spatial coordinate system and scale and objectively verified for engineering use. Laboratory concrete specimens were scanned with a 1.6 GHz GPR, and a workflow was developed including: (1) image standardization, (2) 3D model and cutting-plane construction, (3) UV mapping with B-scan attachment, and (4) accuracy verification with a portable file structure. Alignment accuracy was evaluated using a horizontal RMSE criterion of < 2 mm or < 0.5%·Lx. All three specimens met the predefined threshold, and the OBJ/MTL, image, and semantic description files were successfully loaded across different software environments, demonstrating both alignment feasibility and file portability. The integrated visualization supports clearer cross-disciplinary discussion of anomalous signals and potential deterioration zones. Future work will focus on automated interpretation and integration with BIM/digital twins for long-term monitoring of in-service structures.