交通意外事故在世界各地都是導致死傷的常見原因之一，且交通意外事故通常也伴隨著很大的社會損失。2017年在台灣發生了兩起嚴重的交通安全意外事故，蝶戀花事件與阿羅哈客運事件總共導致39人死亡及22人受傷。這兩起事件的發生也使得民眾對於交通安全的意識日漸高漲，政府也有責任提供安全的交通環境給社會大眾，然而目前在台灣並沒有一個合適的客運業安全評鑑機制。在本研究裡，結合美國FMCSA的CSA計畫、日本租賃巴士安全評估認證及台灣現有的服務品質評鑑建立出一個合適於台灣使用的客運業安全評量機制模型。本研究利用兩階段決策方式來設計此模型，第一階段利用Fuzzy AHP去設定各公司的初始安全等級，第二階段利用機器學習方法分析資料與調整各屬性之權重，調整完之權重可被利用於計算各公司的安全表現與安全等級。將結果跟2016及2017年的肇事原因相比是很雷同的，由此可證明此研究的結果是合理的。而安全評鑑的結果可供消費者選擇時使用，也可以協助保險業者進行差別訂價，透過各屬性的重要性也能夠獲取管理意涵。

Vehicle crash is one of the most common reason that caused deaths and injuries all around the world. Also, it would make great loss. In 2017, there are two serious vehicle accidents happened in Taiwan, Nangang Tour bus accident and Aloha coach crash. These two accidents caused 39 killed and 22 injured in total. After these happened, the safety consciousness rises and the government has duty to provide safe environment for all people. However, there is no proper safety evaluation mechanism in Taiwan nowadays. In this study, we combine CSA program of FMCSA in the US, Renting Bus safety evaluation in Japan, and some of the service evaluation in Taiwan to develop a new passenger industry’s safety evaluation mechanism which could be suitable for Taiwan. In this study, we designed a two-stage decision making approach to develop this mechanism. We apply fuzzy AHP to set up the initial safety rank of each company in the first stage. In the second stage we use machine learning approaches to analyze the data and to adjust the attributes’ weights. We can calculate each company’s safety performance and divide them into different safety ranks. These ranks can be an index when we need service and can be used in insurance industry to do differential pricing. Also, we can get some insights from the importance of each attributes.

Ahmad, A., Hassan, M., Abdullah, M., Rahman, H., Hussin, F., Abdullah, H., & Saidur, R. (2014). A review on applications of ANN and SVM for building electrical energy consumption forecasting. Renewable and Sustainable Energy Reviews, 33, 102-109.
Breiman, L. (1996). Bagging predictors. Machine learning, 24(2), 123-140.
Breiman, L. (2001a). Random forests. Machine learning, 45(1), 5-32.
Breiman, L. (2001b). Statistical modeling: The two cultures (with comments and a rejoinder by the author). Statistical science, 16(3), 199-231.
Breiman, L. (2017). Classification and regression trees: Routledge.
Buckley, J. J. (1985). Fuzzy hierarchical analysis. Fuzzy sets and Systems, 17(3), 233-247.
Chang, D.-Y. (1996). Applications of the extent analysis method on fuzzy AHP. European journal of operational research, 95(3), 649-655.
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3), 273-297.
Cui, R., Gallino, S., Moreno, A., & Zhang, D. J. (2017). The operational value of social media information. Production and Operations Management.
Dağdeviren, M., & Yüksel, İ. (2008). Developing a fuzzy analytic hierarchy process (AHP) model for behavior-based safety management. Information Sciences, 178(6), 1717-1733.
de Colstoun, E. C. B., Story, M. H., Thompson, C., Commisso, K., Smith, T. G., & Irons, J. R. (2003). National Park vegetation mapping using multitemporal Landsat 7 data and a decision tree classifier. Remote sensing of environment, 85(3), 316-327.
Deng, H. (1999). Multicriteria analysis with fuzzy pairwise comparison. International journal of approximate reasoning, 21(3), 215-231.
Dong, L.-j., Li, X.-b., & Kang, P. (2013). Prediction of rockburst classification using Random Forest. Transactions of Nonferrous Metals Society of China, 23(2), 472-477.
Friedl, M. A., & Brodley, C. E. (1997). Decision tree classification of land cover from remotely sensed data. Remote sensing of environment, 61(3), 399-409.
Gumus, A. T. (2009). Evaluation of hazardous waste transportation firms by using a two step fuzzy-AHP and TOPSIS methodology. Expert systems with applications, 36(2), 4067-4074.
Ho, T. K. (1995). Random decision forests. Paper presented at the Document analysis and recognition, 1995., proceedings of the third international conference on.
Ho, T. K. (1998). The random subspace method for constructing decision forests. IEEE transactions on pattern analysis and machine intelligence, 20(8), 832-844.
HUANG, S., CAI, N., PACHECO, P. P., NARANDES, S., WANG, Y., & XU, W. (2018). Applications of Support Vector Machine (SVM) Learning in Cancer Genomics. Cancer Genomics-Proteomics, 15(1), 41-51.
Joshi, N., George, B., & Vanajakshi, L. (2012). Application of random forest algorithm to classify vehicles detected by a multiple inductive loop system. Paper presented at the Intelligent Transportation Systems (ITSC), 2012 15th International IEEE Conference on.
Kahraman, C., Cebeci, U., & Ulukan, Z. (2003). Multi-criteria supplier selection using fuzzy AHP. Logistics information management, 16(6), 382-394.
Klir, G., & Yuan, B. (1995). Fuzzy sets and fuzzy logic (Vol. 4): Prentice hall New Jersey.
Lal, S. K., & Craig, A. (2001). A critical review of the psychophysiology of driver fatigue. Biological psychology, 55(3), 173-194.
Liaw, A., & Wiener, M. (2002). Classification and regression by randomForest. R news, 2(3), 18-22.
Mejza, M. C., Barnard, R. E., Corsi, T. M., & Keane, T. (2003). Driver management practices of motor carriers with high compliance and safety performance. Transportation Journal, 16-29.
Millet, I., & Harker, P. T. (1990). Globally effective questioning in the analytic hierarchy process. European journal of operational research, 48(1), 88-97.
Mitchell, T. M. (1997). Machine learning. 1997. Burr Ridge, IL: McGraw Hill, 45(37), 870-877.
Morrow, P. C., & Crum, M. R. (2004). Antecedents of fatigue, close calls, and crashes among commercial motor-vehicle drivers. Journal of Safety research, 35(1), 59-69.
Peden, M. (2010). UN General Assembly calls for decade of action for road safety: BMJ Publishing Group Ltd.
Rodriguez-Galiano, V., Sanchez-Castillo, M., Chica-Olmo, M., & Chica-Rivas, M. (2015). Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geology Reviews, 71, 804-818.
Saaty, T. (1980). The Analytic Hierarchy Process:, New York, NY, McGraw Hill, reprinted by RWS Publication, Pittsburgh.
Saaty, T. L. (2008). Decision making with the analytic hierarchy process. International journal of services sciences, 1(1), 83-98.
Safavian, S. R., & Landgrebe, D. (1991). A survey of decision tree classifier methodology. IEEE transactions on systems, man, and cybernetics, 21(3), 660-674.
Samuel, A. L. (1959). Some studies in machine learning using the game of checkers. IBM Journal of research and development, 3(3), 210-229.
Strahan, C., Watson, B., & Lennonb, A. (2008). Can organisational safety climate and occupational stress predict work-related driver fatigue? Transportation Research Part F: Traffic Psychology and Behaviour, 11(6), 418-426.
Tai, P.-h. (2007). The study on drivers’ fatigue of inter-city bus transportation. 成功大學交通管理科學系學位論文, 1-116.
Ting, P.-H., Hwang, J.-R., Doong, J.-L., & Jeng, M.-C. (2008). Driver fatigue and highway driving: A simulator study. Physiology & behavior, 94(3), 448-453.
Tsangaratos, P., & Ilia, I. (2016). Landslide susceptibility mapping using a modified decision tree classifier in the Xanthi Perfection, Greece. Landslides, 13(2), 305-320.
Ture, M., Tokatli, F., & Kurt, I. (2009). Using Kaplan–Meier analysis together with decision tree methods (C&RT, CHAID, QUEST, C4. 5 and ID3) in determining recurrence-free survival of breast cancer patients. Expert systems with applications, 36(2), 2017-2026.
United States Department of Transportation [DOT], Federal Motor Carrier Safety Administration [FMCSA], Safety Measurement System (SMS) Methodology： Behavior Analysis and Safety Improvement Category (BASIC) Prioritization Status [Version 3.0.6]. Retrieved from https：//csa.fmcsa.dot.gov/
Van Laarhoven, P., & Pedrycz, W. (1983). A fuzzy extension of Saaty's priority theory. Fuzzy sets and Systems, 11(1-3), 229-241.
Wang, Q., Wang, H., & Qi, Z. (2016). An application of nonlinear fuzzy analytic hierarchy process in safety evaluation of coal mine. Safety science, 86, 78-87.
Youssef, A. M., Pourghasemi, H. R., Pourtaghi, Z. S., & Al-Katheeri, M. M. (2016). Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi Arabia. Landslides, 13(5), 839-856.
Yu, W.-S. (2004). 應用模糊層級分析法在提昇公共工程品質之研究. 2004. PhD Thesis.
Zadeh, L. A. (1996). Fuzzy sets Fuzzy Sets, Fuzzy Logic, And Fuzzy Systems: Selected Papers by Lotfi A Zadeh (pp. 394-432): World Scientific.
Zheng, G., Zhu, N., Tian, Z., Chen, Y., & Sun, B. (2012). Application of a trapezoidal fuzzy AHP method for work safety evaluation and early warning rating of hot and humid environments. Safety science, 50(2), 228-239.
Zhu, K.-J., Jing, Y., & Chang, D.-Y. (1999). A discussion on extent analysis method and applications of fuzzy AHP. European journal of operational research, 116(2), 450-456.
內政部警政署（2017，5月3日）。106 年第十八週警政統計通報。資料引自 http://www.npa.gov.tw/ count/main.htm
內政部警政署（2018，4月4日）。107 年第14週警政統計通報。資料引自 http://www.npa.gov.tw/ count/main.htm
日本公益法人日本巴士協會租賃巴士安全評估認證網站 http://www.bus.or.jp/safety/about.html