頁籤選單縮合
題名 | 臺北市政府的交通管理政策:人工智慧與決策支援系統的觀點=The Traffic Management Policy of the Taipei City Government: The Perspective of Artificial Intelligence and Decision Support Systems |
---|---|
作者姓名(中文) | 陳夢琨; | 書刊名 | 科際整合月刊 |
卷期 | 9:5 2024.05[民113.05] |
頁次 | 頁1-14 |
關鍵詞 | 交通管理; 人工智慧; 決策支援系統; 機器學習; 深度學習; Traffic management; Artificial intelligence; Decision support systems; Machine learning; Deep learning; |
語文 | 中文(Chinese) |
中文摘要 | 交通擁擠是城市地區普遍存在的問題,導致經濟損失、環境污染和生活品質下降。臺北市人口密度高,車輛數量不斷增加,面臨巨大的交通管理挑戰。傳統的交通管理方法缺乏有效解決這些複雜問題所需的適應性和預測能力。人工智慧(AI)和決策支援系統(DSS)的應用提供了一個充滿希望的機會。本研究旨在探討以人工智慧為基礎的決策支援系統在改善臺北市交通管理政策的應用。本研究採用多種研究方法:文獻探討、資料分析和建模技術。首先對交通領域現有的交通管理政策、決策支援系統和人工智慧應用進行全面審查。隨後,分析臺北市目前的交通管理策略,找出限制和改進機會。從各種資料(包括交通感測器資料、GPS資料、閉路電視錄影和社群媒體資訊)加以整合和處理,以用於特徵工程和模型訓練。從機器學習演算法(例如回歸、分類和聚類技術)、深度學習模型(例如卷積神經網路(CNN)以及循環神經網路(RNN)),以用於執行流量預測、事件檢測和最佳化等任務。從模型評估、驗證以及案例研究,以評估系統的性能和潛在的現實世界影響。研究結論:基於人工智慧的DSS的實施,將為臺北的交通管理帶來顯著的效益,包括改善交通流量、減少擁塞、提高運輸效率、經濟優勢、減輕環境影響、提高安全性以及數據驅動的決策能力;然而,為了成功實施,必須解決資料基礎設施、運算資源、模型可解釋性、隱私問題和利害關係人協作等挑戰。 |
英文摘要 | This study aims to explore the potential applications of AI-based decision support systems in improving Taipei City's traffic management policies. By utilizing advanced data analysis, machine learning, and deep learning techniques, the research seeks to develop a comprehensive framework to optimize traffic flow, reduce congestion, and enhance overall transportation performance. The study employs a multifaceted approach, combining literature review, data analysis, and modeling techniques. Firstly, an extensive review of existing traffic management policies, decision support systems, and AI applications in the transportation domain is conducted. Subsequently, an analysis of Taipei City's current traffic management strategies is performed to identify limitations and improvement opportunities. Various data sources (including traffic sensors, GPS data, CCTV footage, and social media information) are integrated and preprocessed for feature engineering and model training. Machine learning algorithms (such as regression, classification, and clustering techniques) as well as deep learning models (such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN)) are utilized to perform tasks like traffic prediction, event detection, and optimization. Model evaluation, validation, and case studies are conducted to assess the system's performance and potential real-world impact. The implementation of AI-based DSS is expected to bring significant benefits to Taipei's traffic management, including improving traffic flow, reducing congestion, enhancing transportation efficiency, economic advantages, mitigating environmental impacts, improving safety, and data-driven decision-making capability. However, successful implementation requires addressing challenges such as data infrastructure, computational resources, model interpretability, privacy issues, and stakeholder collaboration. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。