臺灣博碩士論文加值系統

交通事故成因原即相當複雜，而我國事故現場蒐證資料則常有不盡周全之情形，加以鑑定會鑑定委員之經驗及對交通法規解釋觀點多所不同，致類似案件之鑑定結果常不盡相同；此外，各委員會甚少交流，新進委員在鑑定經驗傳承不足之情況下，各地區鑑定會之鑑定結果亦不易維持一致性；此種類似案件有不同判定結果之情形對鑑定單位之公信力有相當程度之傷害，如何讓鑑定機關間以統一標準鑑定類似案件之責任歸屬，顯然有其必要性，爰此，本研究嘗試以自我組織特徵映射圖網路建立一套行車事故責任鑑定支援系統，利用過去案件資料庫與自我組織特徵映射圖之特徵分群法則，整合出類似肇事案件援引系統，期能輔助各地鑑會、覆議會鑑定委員作為肇事責任研判之依據，同時也能承傳事故鑑定專業經驗與知識，並協助提升鑑定結果之公平性、準確性與效率性。
目前先針對兩車（汽車）碰撞之同向、橫向、對向三種碰撞型態建置各自的特徵映射圖分群模式，再計算出各個分群結果的輪廓係數，挑選輪廓係數最高者為最佳的分群模式。利用該分群結果，就能根據鑑定委員的需求，自動搜尋出所需參考的肇事案例經過與判定結果，再利用灰關聯度的高低，決定參考肇事案例的優先順序。本研究自逢甲大學車輛行車事故鑑定中心的肇事鑑定資料庫擷取所需資料，並透過特徵映射圖分群模式的訓練與驗證，初步估計新進肇事案例與該群落的參考案例之間的灰關聯度範圍介於1~0.6458之間，其中同向碰撞的平均灰關聯度約有0.8208；橫向碰撞的平均灰關聯度約有0.8668；對向碰撞的平均灰關聯度約有0.8641，表示該決策支援系統在某些程度上，確實能提供鑑定委員相同或極類似的肇事案例做為參考分析，協助鑑定委員進行肇事鑑定作業。
本研究最後應用所建構之特徵映射圖分群模式，以動態服務網頁(Active Sever Pages, ASP)模式建構不同碰撞型態之兩車交通事故責任鑑定支援系統，提供鑑定相關人員或社會大眾查詢過去相關案例之特性及鑑定結果。使用者僅需輸入欲查詢案例之變數選項，系統即透過內建運算過程，自動輸出過去類似案例及相關法規供參考，系統已初步完成，唯尚待進一步改良，謹檢附測試案例供交通安全界諸位先進參考。

Traffic accidents can be resulted from various factors. Consequently, authentication on accident liabilities can be very tedious and difficult. Due to the fact that information collected in traffic accident reports are normally incomplete and are varied from case to case. Similar cases can sometimes be authenticated with different liabilities. On the other hand, knowledge and experiences of committee members can also bias his/her judgment on similar cases at different time. Such variance of authentication on similar cases can easily be criticized by general public, and may hurt the image of government-established investigation committees. Consequently, it is apparent that there is a need to unify liability authentication of all traffic accident investigation committees. In this study, a liability authentication support system was constructed by using self-organizing feature maps. This system is intended to provide accident records and liability authentication results similar to inquiries as supplementary information to committee members. Hopefully, righteousness and fairness can be better reached with the help of this system.
Due to the fact that accidents involving more than three cars can be very complicated, this study was thus limited to two-car accidents. The first step to construct the proposed system is to establish a self-organizing feature map (SOM) model for two-car crashes. Effectiveness of SOM models were checked by using the Silhouette coefficients (SC). After SC value for every cluster being determined, the best clusters were chosen to be the proposed SOM models. Grey relation analysis was then employed to decide order of referable cases. Traffic accident information adopted in this study is abstracted from the database constructed by the center for traffic accident authentication in Feng Chia university. The grey relational values between new cases and reference cases calculated from the selected SOM models were found range between 0.6458 and 1. Average grey relational value of same crash was approximately 0.8208. Average grey relational value of crosswise crash was approximately 0.8668. Average grey relational value of opposite crash was approximately 0.8641. These values indicated that the proposed models do have ability to provide similar accident cases as the inquiry.
With the selected SOM models, a decision support system for traffic accident liability authentication is constructed using Active Sever Pages (ASP). The system is designed to provide characteristics and liability authentication results of cases similar to user input inquiries. Meanwhile, traffic safety rules related to the input inquiry can also be provided to the users for reference. Although initial results appeared to be acceptable, the system is still under development. In this paper, basic example is provided for better understanding of the system. Any comment or suggestion will certainly be sincerely appreciated.

誌謝 I
中文摘要 II
英文摘要 IV
目錄 VI
圖目錄 VIII
表目錄 IX
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
1.3 研究範圍 3
1.4 研究內容與流程 3
第二章 文獻評析 8
2.1 肇事鑑定與分析之相關研究 8
2.2 自我組織特徵映射圖網路之相關研究 16
2.3 決策支援系統之相關研究 22
第三章 資料分析與變數選取 25
3.1 樣本資料分析 25
3.2 交叉分析 43
3.3 判別分析 50
3.4 專家問卷 53
3.4.1 專家問卷之發放與回收 53
3.4.2 專家問卷之評估法 54
3.4.3 專家問卷實證分析 57
3.5 小結 59
第四章 分群模式建構與分析 63
4.1 類神經網路之基本理論 63
4.2 自我組織特徵映射圖網路 64
4.2.1 演算過程 65
4.2.2 鄰近區域函數與學習速率 67
4.2.3 分群模式訓練 72
4.3 分群效度驗證 75
4.3.1 分群效度指標 75
4.3.2 分群效度實證分析 77
4.4 肇事鑑定案件實證分析 84
4.4.1 灰色關聯分析 85
4.4.2 肇事案例之灰色關聯分析 86
4.5 肇事鑑定決策支援系統 86
4.5.1 系統操作介面 87
4.5.2 系統測試 89
第五章 結論與建議 95
5.1 結論 95
5.2 建議 96
參考文獻 98
附錄一 101
附錄二 107

1.中文部分
[1]周文生、陳蔚文，民國90年9月，「交通事故肇事原因分析決策支援系統之研究」，運輸計劃季刊，30卷，3期，頁635~頁656。
[2]邱志洲、李天行、周宇超、呂奇傑，民國91年3月，「整合鑑別分析與類神經網路在資料探勘上之研究」，工業工程學刊，19卷，2期，頁9~頁22。
[3]鄭祈全、陳永寬、王素芬，民國90年7月，「多尺度林地分級決策支援系統之研究」，航測及遙測學刊，6卷，2期，頁41~頁56。
[4]魏健宏、陳奕志，民國90年6月，「類神經網路模式在國內交通運輸研究之成果評析」，交通計劃季刊，30卷，2期，頁323~頁348。
[5]邵泰璋、史天元，民國89年3月，「類神經網路於多光譜影像分類之應用」，航測及遙測學刊，5卷，1期，頁1~頁14。
[6]陳繼藩、徐守道、陳世旺，民國86年3月，「應用非監督性類神經網路於SPOT衛星影像分類之研究」，航測與遙測學刊，2卷，1期，頁1~頁12。
[7]高立人，民國88年10月，「彩色影像系統中彩色分類方法之研究」，大漢學報，13卷，頁301~頁315。
[8]賴顯松，民國90年9月，「天然纖維織物特性分類之模式」，技術學刊，16卷，3期，頁497~頁504。
[9]李開，民國91年，「行車事故鑑定制度之研究」，中國文化大學政治學研究所碩士論文，台北市。
[10]鄭惠玲，民國93年，「行車事故鑑定對保險理賠影響之分析」，逢甲大學保險學系碩士班碩士論文，台中市。
[11]楊宗璟、艾嘉銘，民國91年，「交通違規事故責任鑑定影響因素之統計分析及模式建構」，中華民國運輸學會第17屆論文研討會。
[12]楊思瑜，民國92年，「小型車事故嚴重程度預測以桃竹苗地區為範圍」，逢甲大學交通工程與管理學研究所碩士論文。
[13]方守傑，民國93年，「兩車碰撞事故之肇事鑑定專家系統」，逢甲大學交通工程與管理學研究所碩士論文。
[14]曾士育，民國92年，「以自組織映射圖神經網路探勘金融投資決策之研究」，國立高雄第一科技大學資訊管理學系。
[15]吳憲斌，民國91年，「新行道路交通工程設施設置決策之探討」，國立成功大學交通管理科學研究所碩士論文。
[16]羅華強，民國90年，「類神經網路－MATLAB的應用」，清蔚科技股份有限公司。
[17]葉怡成，民國92年，「類神經網路模式應用與實作」，儒林圖書有限公司。
[18]張斐章等，民國92年，「類神經網路理論與實務」，台灣東華書局股份有限公司。
[19]周鵬程，民國93年，「類神經網路入門－活用Matlab」，全華科技股份有限公司。
2.英文部分
[1]Huidong Jin, Wing-Shum, Kwong-Sak Leung, Man-Leung Wong (2004) , ”Expanding Self-Organizing Map for data visualization and cluster analysis,” Information Sciences, Vol. 163, No.1-3, pp. 157-173.
[2]Khaled A. Abbas (2004) , ”Traffic safety assessment and development of predictive models for accidents on rural on rural roads in Egypt,” Accident Analysis and Prevention, Vol 36, No. 2, pp149-163.
[3]Lawrence T. Lam (2003) , ”Factors associated with young drivers’ car crash injury: comparisons among learner, provisional, and full licensees,” Accident Analysis and Prevention, Vol 35, No. 6, pp913-920.
[4]Rune Elvik (2003) , ”assessing the validity of road safety evaluation studies by analyzing causal chains,” Accident Analysis and Prevention, Vol 35, No. 5, pp741-748.
[5]Kate A. Smith, Alan Ng (2003) , ”Web page clustering using a self-organizing map of user navigation patterns,” Decision Support Systems, Vol 35, No. 2, pp245-256.
[6]R.J. Kuo, L.M. Ho, C.M. Hu (2003) , ”Integration of self-organizing feature map and K-means algorithm for market segmentation,” Computers and Operations Research, Vol 29, No.11, pp1475-1493.
[7]Melody Y. Kiang (2001) , ”Extending the Kohonen self-organizing map networks for clustering analysis,” Computational Statistics and Data Analysis, Vol 38, No. 2, pp161-180.
[8]Melody Y. Kiang, Uday R. Kulkarni, Kar Yan Tam (1995) , ” Self-organizing map network as an interactive clustering tool - An application to group technology,” Decision Support Systems, Vol 15, No. 4, pp351-374.
[9]Hsinchum Chen, Dmitri G. Roussinov (1999) , ”Document clustering for electronic meetings: an experimental comparison of two techniques,” Decision Support Systems, Vol 27, No. 1-2, pp67-79.
[10]Mascha Van Der Voort, Mark Dougherty, Susan Watson (1996) , ”Combining Kohonen maps with ARIMA time series models to forecast traffic flow” Transportation Research Part C, Vol 4, No. 5, pp307-318.
[11]Ching-Lai Hwang., and Shu-Jen Chen (1992) , “Fuzzy Multiple Attribute Decision Making, Method and Applications”, Springer-Verlag, NY.
[12]Hwang, C.L., and K.P.Yoon (1995) , “Multiple Attribute Decision making : An Introduction”, Sage University Paper Series on Quantitive Applications in the Social Science.
[13]George J.Klir and Bo Yuan (1995) , “Fuzzy Sets and Fuzzy Logic, The theory and Applications,” Prentice Hall International, Inc.
[14]Ronald K. Pearson, Tom Zylkin, James S. Schwaber, Gregory E.Gonye (2004) , “Quantitative Evaluation of Clustering Results Using Computational Negative Controls,” SIAM.
[15]A. Gordon (1999), “Classification,” Chapman and Hall, NewYork.
[16]L. Kaufman and P. Rousseeuw (1990) , “Finding Groups in data-An Introduction to Cluster Analysis,” Chapman and Hall, NewYork.