帳號:guest(18.220.233.82)          離開系統
字體大小: 字級放大   字級縮小   預設字形  

詳目顯示

以作者查詢圖書館館藏以作者查詢臺灣博碩士論文系統以作者查詢全國書目
作者(中文):陽岳瑾
作者(外文):Yang, Yueh-Chin
論文名稱(中文):基於機器學習探討自行車騎乘風險因素研究
論文名稱(外文):Machine Learning-Based Prediction of Risk Factors in Bicycle Riding
指導教授(中文):邱文信
指導教授(外文):Chiu, Wen-Hsin
口試委員(中文):相子元
陳家祥
口試委員(外文):Shiang, Tzyy-Yuang
Chen, Ja-Shen
學位類別:碩士
校院名稱:國立清華大學
系所名稱:運動科學系碩士在職專班
學號:111194509
出版年(民國):113
畢業學年度:112
語文別:中文
論文頁數:85
中文關鍵詞:自行車事故機器學習騎乘風險
外文關鍵詞:Bicycle AccidentsMachine LearningRiding Risk
相關次數:
  • 推薦推薦:0
  • 點閱點閱:0
  • 評分評分:*****
  • 下載下載:5
  • 收藏收藏:0
目的:本研究旨在分析自行車事故的關鍵因素,透過比較機器學習各種演算法的效能和準確度,以選擇最適模型深入預測及解析自行車騎乘時的風險。方法:本研究使用數據是基於「臺灣政府資料開放平臺」的2022年及2023年「傷亡道路交通事故資料」,並特別針對「腳踏自行車」進行資料篩選,利用羅吉斯迴歸、判別分析、決策樹及隨機森林等機器學習方法,找出可能導致自行車事故的主要因素,包含有發生月份、日期、時間、地點、天候、光線、道路類別、速限、道路型態類別、事故位置類別、路面狀況鋪裝、路面狀況狀態、路面狀況缺陷、道路障礙障礙物、品質、視距、號誌名稱、動作、車道劃分設施分向設施類別、車道劃分設施分道設施快車道或一般車道間、車道劃分設施分道設施路面邊線、事故類型及型態類別、性別、年齡、保護裝備、行動電話或電腦或其他相類功能裝置、當事者行為狀態類別及車輛撞擊部位類別等。結果:經混淆矩陣及權重加權計算後,隨機森林在預測事故嚴重程度方面評估為較適合模型,進而影響事故發生的關鍵因素包括發生時間、日期、年齡、地點、事故類型及型態子類別、月份、當事者行為狀態子類別、事故類型及型態類別、速限及保護裝備等。結論:本研究提供自行車事故多重因素數據與分析結果,可以使建議更具體、有效,並且更加符合實際情況,另外透過機器學習演算法技術進行高效處理和精確分析,其演算法優點能處理大量複雜的數據集,進而選擇最適模型及評估風險趨勢。
Objective: This study aims to analyze the key factors of bicycle accidents by comparing the performance and accuracy of various machine learning algorithms to select the most suitable model for in-depth prediction and analysis of bicycling risks. Methods: The study utilizes data from the "Taiwan Government Open Data Platform," specifically the "Road Traffic Accident Data" for the years 2022 and 2023, focusing on bicycles. Machine learning techniques including logistic regression, discriminant analysis, decision trees, and random forests were used to identify potential causes of bicycle accidents. Factors analyzed include the month, date, time, location, weather, lighting, road type, speed limit, road layout, accident location type, road surface condition and paving, road condition, road defects, road obstacles, quality, visibility, traffic signal names, actions, lane division facility types, separation between fast and general lanes, lane markings, accident types and categories, gender, age, protective gear, usage of mobile phones or similar devices, behavior of the involved parties, and the vehicle impact location. Results: After evaluating with a confusion matrix and weighted metrics, the random forest model was deemed most suitable for predicting the severity of accidents. Key factors influencing the occurrence of accidents include the time, date, age, location, accident type and subtype, month, behavior of involved parties, speed limit, and protective gear. Conclusion: This study provides a multifaceted analysis and data on bicycle accidents, enabling more specific, effective, and realistic recommendations. Furthermore, the application of machine learning algorithms facilitates efficient and precise analysis of large and complex datasets, allowing for the selection of the best model and the assessment of risk trends.
摘要 I
Abstract II
誌謝辭 III
目錄 IV
表目錄 VI
圖目錄 VII
第壹章 緒論 1
第一節、 研究動機 1
第二節、 研究目的 4
第三節、 名詞操作性定義 4
第四節、 研究範圍與限制 8
第貳章 文獻探討 9
第一節、 自行車騎乘風險之概述 9
第二節、 自行車騎乘影響因素 13
第三節、 機器學習在自行車事故預測的應用 17
第四節、 總結 21
第參章 研究方法 23
第一節、 研究步驟與流程 23
第二節、 資料來源 24
第三節、 資料變數名詞解釋 24
第四節、 資料分析方法 25
第五節、 模型衡量指標 32
第肆章 分析與討論 33
第一節、 敘述性統計 33
第二節、 羅吉斯迴歸 46
第三節、 判別分析 50
第四節、 決策樹 53
第五節、 隨機森林 55
第六節、 綜合討論 59
第伍章 結論與建議 64
第一節、 結論 64
第二節、 研究建議 65
參考文獻 67
附錄一 71
附錄二 78
一、中文部分
王立天、陳鈺翰、汪稚祐(2022)。探究天氣因素對市區交通事故之影響。資訊電子學刊,10(1),167-175。
世界衛生組織(2022)。道路交通事故。
交通部統計處自行車使用狀況調查摘要分析(2018)。中華民國交通部全球資訊網。
交通部道路交通安全規則(2024)。全國法規資料庫。
李福祥(2016)。從踏板2點8點談起 自行車運動下坡過彎技巧安全需知。學校體育,(156),126-128。
呂學建、賴淑芳(2014)。腳踏車路況安全系統。地理資訊系統季刊,8(3),33-36。https://doi.org/10.6628/GIS.2014.8(3).6
林國欽(2022)。人工智慧於體育運動領域之發展與運用。體育學報,55(3),233-244。https://doi.org/10.6222/pej.202209_55(3).0001
林樹旺(2008)。建構自行車使用者休閒涉入對休閒效益之影響。運動與遊憩研究,2(3),130-149。https://doi.org/10.29423/JSRR.200803_2(3).0010
邱弘毅、邱文達、葉錦瑩、陳怡樺(2006)。自行車事故傷害之探討與防制對策研究(衛生署國民健康局委託研究)。台北醫學大學。
胡大瀛、李岳洪(2022)。數據不平衡下以機器學習方法預測交通事故嚴重性之分析。運輸計劃季刊,51(4),275-301。
高雄市政府交通局(2023)。高雄市環島自行車路網改道規劃暨全市自行車道路網總體檢。
陳狄成、林政光、張育誠(2014)。自行車機械式碟煞卡鉗機構創新設計。鍛造,23(3),9-15。
陳俊銘、盧俊宏(2010)。自行車休閒運動流暢經驗形成歷程與影響因素模式之建構。大專體育學術專刊,(2010/05),418-424。https://doi.org/10.6695/AUES.201005_99.0052
張耕碩、張舜淵、鄭嘉盈、高錫鉦、田珍綺、邱顯明(2022)。自行車智慧型警示系統設置成果及未來展望。都市交通,37(2),19-34。
盧建中(2010)。急診室自行車與交通事故探討〔未出版之碩士論文〕。亞洲大學健康產業管理學系。
顏上堯、陳俊穎、王領(2014)。現有道路系統下通勤型自行車道初步路網設置之研究。運輸學刊,26(4),529-553。https://doi.org/10.6383/JCIT.201412_26(4).0004
簡彩完、陳鎰明、謝忠憲、榮琦、顧家安、黃慶煌(2019)。自行車使用者對自行車道的劃與設計之究研究。休閒保健期刊,(22),67-86。
薛凱峯(2022)。公共自行車資訊網站建置之研究。臺灣體育運動管理學報,22(1),97-113。https://doi.org/10.6547/tassm.202206_22(1).0005
鄭永祥、田蕙寧(2015)。騎乘自行車之潛在風險分析。運輸計劃季刊,44(3),271-287。
二、英文部分
Bei, Zhou., Zongzhi, Li., Shengrui, Zhang., Xinfen, Zhang., Xin, Liu., & Qiannan, Ma. (2019). Analysis of Factors Affecting Hit-and-Run and Non-Hit-and-Run in Vehicle-Bicycle Crashes: A Non-Parametric Approach Incorporating Data Imbalance Treatment. Sustainability, 11(5), 1327. https://doi.org/10.3390/su11051327
Cheng, Xu., Qiangwei, Li., Zhaowei, Qu., & Sheng, Jin. (2015). Predicting Free Flow Speed and Crash Risk of Bicycle Traffic Flow Using Artificial Neural Network Models. Mathematical Problems in Engineering, 11. https://doi.org/10.1155/2015/212050
Devon, Paige Willis., Kevin, Manaugh., & Ahmed, El-Geneidy. (2015). Cycling Under Influence: Summarizing the Influence of Perceptions, Attitudes, Habits, and Social Environments on Cycling for Transportation. International Journal of Sustainable Transportation, 9(8), 565-579. https://doi.org/10.1080/15568318.2013.827285
Eleonora, Sottile., Benedetta, Sanjust di Teulada., Italo, Meloni., & Elisabetta, Cherchi. (2018). Estimation and validation of hybrid choice models to identify the role of perception in the choice to cycle. International Journal of Sustainable Transportation, 13(8), 543-552. https://doi.org/10.1080/15568318.2018.1490465
Elsvig, Eilert-Petersson., & Lothar, Schelp. (1997). An epidemiological study of bicycle-related injuries. Accident Analysis & Prevention, 29(3), 363-372. https://doi.org/10.1016/S0001-4575(97)00002-X
Fatemehsadat, Tabei., Behnam, Askarian., & Jo, Woon Chong. (2021). Accident detection system for bicycle riders. in IEEE Sensors Journal, 21(2), 878-885. http://doi.org/10.1109/JSEN.2020.3021652
Forbes, AE., Schutzer-Weissmann J., Menassa, DA., & Wilson, MH. (2017). Head injury patterns in helmeted and non-helmeted cyclists admitted to a London Major Trauma Centre with serious head injury. PLoS ONE, 12(9): e0185367. https://doi.org/10.1371/journal.pone.0185367
Grigorios, Fountas., Achille, Fonzone., Niaz, Gharavi., & Tom, Rye. (2020). The joint effect of weather and lighting conditions on injury severities of single-vehicle accidents. Analytic Methods in Accident Research, 27, 2213-6657. https://doi.org/10.1016/j.amar.2020.100124
Harry, Lahrmann., Tanja, Kidholm Osmann Madsen., Anne, Vingaard Olesen., Jens, Chr. Overgaard Madsen., & Tove, Hels. (2018). The effect of a yellow bicycle jacket on cyclist accidents. Safety Science, 108, 209-217. https://doi.org/10.1016/j.ssci.2017.08.001
Jake, Olivier., Sofiane, Boufous., & Raphael, Grzebieta. (2019). The impact of bicycle helmet legislation on cycling fatalities in Australia. International Journal of Epidemiology, 48(4), 1197-1203. https://doi.org/10.1093/ije/dyz003
Livia, E. V. M. de Guerre., Said, Sadiqi., Loek, P. H. Leenen., Cumhur, F. Oner., & Steven, M. van Gaalen. (2018). Injuries related to bicycle accidents: an epidemiological study in The Netherlands. Eur J Trauma Emerg Surg, 46, 413-418. https://doi.org/10.1007/s00068-018-1033-5
Lynn, B. Meuleners., Mark, Stevenson., Michelle, Fraser., Jennie, Oxley., Geoffrey, Rose., & Marilyn, Johnson. (2019). Safer cycling and the urban road environment: A case control study. Accident Analysis & Prevention, 129, 342-349. https://doi.org/10.1016/j.aap.2019.05.032
Maria, Ohlin., Beatrix, Algurén., & Anders, Lie. (2019). Analysis of bicycle crashes in Sweden involving injuries with high risk of health loss. Traffic Injury Prevention, 20(6), 613–618. https://doi.org/10.1080/15389588.2019.1614567
Md, Sharikur Rahman., Mohamed, Abdel-Aty., Samiul, Hasan., & Qing, Cai. (2019). Applying machine learning approaches to analyze the vulnerable road-users' crashes at statewide traffic analysis zones. Journal of Safety Research, 70, 275-288. https://doi.org/10.1016/j.jsr.2019.04.008
Mi, Namgung., & Hee-Jung, Jun. (2018). The influence of attitudes on university bicycle commuting: Considering bicycling experience levels. International Journal of Sustainable Transportation, 13(5), 363-377. https://doi.org/10.1080/15568318.2018.1471557
Murat, Karacasu., Barış, Ergül., & Arzu, Altin Yavuz. (2013). Estimating the causes of traffic accidents using logistic regression and discriminant analysis. International Journal of Injury Control and Safety Promotion, 21(4), 305–313. https://doi.org/10.1080/17457300.2013.815632
Pazdan, Sylwia. (2020). The impact of weather on bicycle risk exposure. Archives of Transport, 56(4), 89-105. https://doi.org/10.5604/01.3001.0014.5629
Sathish, Kumar Sivasankaran., & Venkatesh, Balasubramanian. (2020). Exploring the severity of bicycle–vehicle crashes using latent class clustering approach in India. Journal of Safety Research, 72, 127-138. https://doi.org/10.1016/j.jsr.2019.12.012
Sergio, A. Useche., Luis, Montoro., Francisco, Alonso., & Francisco, M. Tortosa. (2018). Does gender really matter? A structural equation model to explain risky and positive cycling behaviors. Accident Analysis & Prevention, 118, 86-95. https://doi.org/10.1016/j.aap.2018.05.022
Siying, Zhu. (2021). Analysis of the severity of vehicle-bicycle crashes with data mining techniques. Journal of Safety Research, 76, 218-227. https://doi.org/10.1016/j.jsr.2020.11.011
 
 
 
 
第一頁 上一頁 下一頁 最後一頁 top
* *