透過您的圖書館登入
IP:18.224.63.87
  • 學位論文

應用人工智慧演算法於單向道路方向規劃問題

Artificial Intelligence Approaches for the One-Way Road Orientation Planning Problem

指導教授 : 謝益智
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


舉辦大型活動時,常因參與者同時進入場地及動線規劃不佳,進而造成場地周邊交通壅塞及道路混亂之現象。本研究探討單向道路方向規劃問題,此問題主要目的是提出一個有效的方法,將舉辦大型活動場地周邊既有的道路規劃成適當的單向通行路線,減少交通壅塞及路線混亂之現象,以便快速的疏通龐大的車流與人潮,使參與者能如期進入活動場地內,讓活動能順利進行。 本研究運用三種人工智慧演算法,包含免疫演算法(Immune Algorithm, IA)、基因演算法(Genetic Algorithm, GA)以及粒子群演算法(Particle Swarm Optimization, PSO),探討單向道路方向規劃問題,並提出新的編碼方式解決此問題。測試問題分為兩個部分,第一部分是格線問題,第二部分是實際的地圖問題。本研究將比較此三種演算法對此單向道路方向規劃問題的表現,實驗結果顯示,免疫演算法的求解品質優於其他兩種演算法,而粒子群演算法的求解速度優於其他兩種演算法。

並列摘要


In the event of large-scale activities, participants often leave the venue at the same time and it usually results in traffic congestion and road chaos near the site due to the improper traffic planning. The main purpose of this study is to propose an effective coding scheme to investigate the one-way orientation planning problem. In this paper, we use three artificial intelligence approaches to schedule the existing roads near large-scale activities into one-way routes and to reduce the road congestion and increase the traffic flow. In this thesis, it is assumed that participants of the activity need to return to their community after the event. If the number of vehicles to the community in the activity site is known, the problem to be addressed in this study is how to plan the one-way orientation of roads near the site such that the huge traffic can be quickly reduced. In this study, we propose a new coding scheme imbedded in algorithms to solve the one-way orientation planning problem. Finally, we apply three artificial intelligence algorithms, including Immune Algorithm (IA), Genetic Algorithm (GA), Particle Swarm Optimization (PSO) to solve the one-way road orientation planning problem. There are two sets of test problems in this thesis, namely, (1) designed grid problems, and (2) practical map problems. We compare the performance of these three algorithmsfor for the one-way road orientation planning problems. Nnumerical results show that Immune Algorithm is superior to the other two algorithms and Particle Swarm Optimization is faster than the other two algorithms.

參考文獻


[2]吳啟誠,2009,基因演算法於結構拓樸最佳化之應用,中原大學土木工程學系碩士論文。
[13]陳清良,2014,應用類神經網路與粒子群演算法於冰水主機負載分配最佳化,國立臺北科技大學能源與冷凍空調工程系博士班博士論文。
[10]洪歆雅,2007,整合類神經網路與粒子群演算法為輔之模糊神經網路於供應商選擇之應用,國立臺北科技大學工業工程與管理系碩士班碩士論文。
[3]李倩瑜,2014,應用基因演算法結合時間序列於台灣地區鋼鐵價格漲跌幅之預測,國立臺北科技大學工業工程與管理系碩士班碩士論文。
[14]陳維德,2009,應用免疫演算法最佳化火力機組調派,國立臺北科技大學電機工程系碩士班碩士論文。

被引用紀錄


涂榮城(2017)。應用人工智慧演算法於多選擇性及固定參觀時間之博物館路徑問題〔碩士論文,國立虎尾科技大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0028-0607201711102400

延伸閱讀