輕軌系統在都市運輸中扮演關鍵角色，因其具備高可靠性與便利性而備受重視。然而，當輕軌系統於混合交通環境中，特別是交叉路口這類交通互動高度密集之處運行時，易因交織路權與行為不確定性而增加碰撞風險。由於虛驚事件（near-miss events）與實際事故具有相似的成因，因此可作為評估交通安全之重要指標。本研究針對高雄輕軌於2024年4月至2025年3月間所記錄之4,350筆虛驚事件進行分析，探討其發生頻率與潛在影響因子。
本研究採用零膨脹多變量廣義卜瓦松模型（Zero-Inflated Multivariate Generalized Poisson, ZMGP）分析高雄輕軌司機員配戴密錄器所蒐集之事件影像資料。相較於既有多數僅聚焦於事故資料之研究，本研究利用大量虛驚事件資料，有助於提升風險評估之敏感性與穩健性。此外，模型整合多元類別之解釋變數，包含路口幾何設計、環境條件與駕駛員特性，並以駕駛反應程度（涉入程度）作為事故嚴重性之代理指標，進一步探討不同層級虛驚事件之影響因子。
分析結果顯示，不同涉入程度之虛驚事件（如鳴笛、減速、緊急煞車）在特徵與相互影響上均具顯著差異。此外，透過結合 ZMGP 模型模擬結果與地理資訊系統（GIS）進行空間分析，成功辨識出高風險熱點，並評估科技執法設備對虛驚事件減少的實際成效。
本研究建立一套多層次風險評估架構，補足過去以事故為基礎之分析侷限，並可作為交叉口設計、執法策略與駕駛訓練計畫的實證依據，以強化混合交通環境下輕軌系統之運行安全。

Light rail systems are vital to urban transportation, valued for reliability and convenience. However, operating in mixed-traffic environments — especially at intersections — raises collision risks. Near-miss events, sharing similar causes with crashes, serve as key indicators for safety assessment. This study analyzes 4,350 near-miss events recorded on the Kaohsiung Light Rail from April 2024 to March 2025, exploring their frequency and influencing factors.
A Zero-Inflated Multivariate Generalized Poisson (ZMGP) model is employed to analyze event data derived from onboard video recordings of light rail vehicles. Addressing the limitations of previous research that primarily focused on crash data, this study leverages the abundance of near-miss events to enhance the robustness and sensitivity of risk assessments. The ZMGP model was adopted to accommodate excess structural zeros and heterogeneity across multiple levels of driver involvement, leveraging its multivariate and zero-inflated structure.
The results reveal significant variations and cross-level interactions among near-miss events of varying involvement levels (e.g., horn usage, deceleration, emergency braking). Furthermore, by integrating ZMGP simulation outputs with Geographic Information Systems, this study successfully identified spatial hotspots and evaluated the effectiveness of enforcement equipment in reducing near-miss incidents.
This study offers a multilayered risk assessment framework, addressing gaps in crash-based analyses and supporting intersection design, enforcement, and driver training to enhance light rail safety in mixed-traffic environments.

Abdallah, T. (2017). Sustainable mass transit. Sustainable Mass Transit, Elsevier, 1-14.
Abdel-Aty, M. A., & Radwan, A. E. (2000). Modeling traffic accident occurrence and involvement. Accident Analysis & Prevention, 32(5), 633-642.
Aldred, R. (2016). Cycling near misses: Their frequency, impact, and prevention. Transportation Research Part A: Policy and Practice, 90, 69-83.
Aldred, R., & Goodman, A. (2018). Predictors of the frequency and subjective experience of cycling near misses: Findings from the first two years of the UK Near Miss Project. Accident Analysis & Prevention, 110, 161-170.
Aminmansour, S., Maire, F., & Wullems, C. (2014). Near-miss event detection at railway level crossings. 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA),
Borowsky, A., Palacci, N., Itzhaki, M., & Shinar, D. (2019). The assessment of hazard awareness skills among light rail drivers. Transportation research part F: traffic psychology and behaviour, 67, 15-28.
Callari, T. C., Moody, L., Mortimer, M., Stefan, H., Horan, B., & Birrell, S. (2024). “Braking bad”: The influence of haptic feedback and tram driver experience on emergency braking performance. Applied Ergonomics, 116, 104206.
Chang, C. (2020). A Comparative Study of Signaling Control Strategy for Light Rail at B Type Right-of-Way Tamkang University].
Chen, F., Chen, S., & Ma, X. (2018). Analysis of hourly crash likelihood using unbalanced panel data mixed logit model and real-time driving environmental big data. Journal of safety research, 65, 153-159.
Chen, F., Ma, X., & Chen, S. (2014). Refined-scale panel data crash rate analysis using random-effects tobit model. Accident Analysis & Prevention, 73, 323-332.
Currie, G., & Reynolds, J. (2010). Vehicle and pedestrian safety at light rail stops in mixed traffic. Transportation research record, 2146(1), 26-34.
Currie, G., & Smith, P. (2006). Innovative design for safe and accessible light rail or tram stops suitable for streetcar-style conditions. Transportation research record, 1955(1), 37-46.
Das, A., & Abdel-Aty, M. A. (2011). A combined frequency–severity approach for the analysis of rear-end crashes on urban arterials. Safety science, 49(8-9), 1156-1163.
Di Bona, G., Silvestri, A., Forcina, A., & Petrillo, A. (2018). Total efficient risk priority number (TERPN): a new method for risk assessment. Journal of Risk Research, 21(11), 1384-1408.
Eluru, N., Bagheri, M., Miranda-Moreno, L. F., & Fu, L. (2012). A latent class modeling approach for identifying vehicle driver injury severity factors at highway-railway crossings. Accident Analysis & Prevention, 47, 119-127.
Famoye, F., & Singh, K. P. (2006). Zero-inflated generalized Poisson regression model with an application to domestic violence data. Journal of Data Science, 4(1), 117-130.
Famoye, F., Wulu, J. T., & Singh, K. P. (2004). On the generalized Poisson regression model with an application to accident data. Journal of Data Science, 2(3), 287-295.
Gnoni, M. G., Andriulo, S., Maggio, G., & Nardone, P. (2013). “Lean occupational” safety: an application for a near-miss management system design. Safety science, 53, 96-104.
Gnoni, M. G., & Saleh, J. H. (2017). Near-miss management systems and observability-in-depth: Handling safety incidents and accident precursors in light of safety principles. Safety science, 91, 154-167.
Gnoni, M. G., Tornese, F., Guglielmi, A., Pellicci, M., Campo, G., & De Merich, D. (2022). Near miss management systems in the industrial sector: A literature review. Safety science, 150, 105704.
Greibe, P. (2003). Accident prediction models for urban roads. Accident Analysis & Prevention, 35(2), 273-285.
Hu, S.-R., Li, C.-S., & Lee, C.-K. (2010). Investigation of key factors for accident severity at railroad grade crossings by using a logit model. Safety science, 48(2), 186-194.
Hu, S.-R., & Wu, K.-H. (2008). Accident risk analysis and model applications of railway level crossings. 2008 11th International IEEE Conference on Intelligent Transportation Systems,
Institute of Transportation, M. (2022). Highway Capacity Manual of Taiwan.
Jones, S., Kirchsteiger, C., & Bjerke, W. (1999). The importance of near miss reporting to further improve safety performance. Journal of Loss Prevention in the process industries, 12(1), 59-67.
Khorashadi, A., Niemeier, D., Shankar, V., & Mannering, F. (2005). Differences in rural and urban driver-injury severities in accidents involving large-trucks: an exploratory analysis. Accident Analysis & Prevention, 37(5), 910-921.
Kleindorfer, P., Oktem, U. G., Pariyani, A., & Seider, W. D. (2012). Assessment of catastrophe risk and potential losses in industry. Computers & chemical engineering, 47, 85-96.
Li, R., El-Basyouny, K., & Kim, A. (2015). Before-and-after empirical Bayes evaluation of automated mobile speed enforcement on urban arterial roads. Transportation research record, 2516(1), 44-52.
Lord, D., Washington, S. P., & Ivan, J. N. (2005). Poisson, Poisson-gamma and zero-inflated regression models of motor vehicle crashes: balancing statistical fit and theory. Accident Analysis & Prevention, 37(1), 35-46.
Marti, C. M., Kupferschmid, J., Schwertner, M., Nash, A., & Weidmann, U. (2016). Tram safety in mixed traffic: Best practices from Switzerland. Transportation research record, 2540(1), 125-137.
Mitra, S., & Washington, S. (2012). On the significance of omitted variables in intersection crash modeling. Accident Analysis & Prevention, 49, 439-448.
Monod, A. (2014). Random effects modeling and the zero-inflated Poisson distribution. Communications in Statistics-Theory and Methods, 43(4), 664-680.
Naweed, A., & Rose, J. (2015). “It's a frightful scenario”: a study of tram collisions on a mixed-traffic environment in an Australian metropolitan setting. Procedia Manufacturing, 3, 2706-2713.
Naweed, A., Rose, J., Singh, S., & Kook, D. (2017). Risk factors for driver distraction and inattention in tram drivers. Advances in Human Aspects of Transportation: Proceedings of the AHFE 2016 International Conference on Human Factors in Transportation, July 27-31, 2016, Walt Disney World®, Florida, USA,
Naznin, F., Currie, G., & Logan, D. (2017). Key challenges in tram/streetcar driving from the tram driver’s perspective–A qualitative study. Transportation Research part F: traffic psychology and behaviour, 49, 39-48.
Novales, M., Teixeira, M., & Fontaine, L. (2014). LRT urban insertion and safety: European experiences. Transportation Research Record: Journal of the Transportation Research Board, 2419(1), 63-81.
Oh, J., Washington, S. P., & Nam, D. (2006). Accident prediction model for railway-highway interfaces. Accident Analysis & Prevention, 38(2), 346-356.
Quddus, M. A. (2008). Time series count data models: an empirical application to traffic accidents. Accident Analysis & Prevention, 40(5), 1732-1741.
Saleh, J. H., Saltmarsh, E. A., Favarò, F. M., & Brevault, L. (2013). Accident precursors, near misses, and warning signs: Critical review and formal definitions within the framework of Discrete Event Systems. Reliability Engineering & System Safety, 114, 148-154.
Sommerville, A. (2021). Understanding near miss reporting at Australian rail level crossings: The train driver perspective CQUniversity].
Thoroman, B., Goode, N., & Salmon, P. (2018). System thinking applied to near misses: a review of industry-wide near miss reporting systems. Theoretical Issues in Ergonomics Science, 19(6), 712-737.
Tzouras, P. G., Farah, H., Papadimitriou, E., van Oort, N., & Hagenzieker, M. (2020). Tram drivers' perceived safety and driving stress evaluation. A stated preference experiment. Transportation research interdisciplinary perspectives, 7, 100205.
Wang, X., Fan, T., Chen, M., Deng, B., Wu, B., & Tremont, P. (2015). Safety modeling of urban arterials in Shanghai, China. Accident Analysis & Prevention, 83, 57-66.
Wright, L., & Van der Schaaf, T. (2004). Accident versus near miss causation: a critical review of the literature, an empirical test in the UK railway domain, and their implications for other sectors. Journal of hazardous materials, 111(1-3), 105-110.
Wullems, C., Dell, G., & Toft, Y. (2014). Improving the railway's understanding of accident causation through an integrated approach to human factors analysis and technical safety data recording. Advances in Human Aspects of Transportation, Part I: Proceedings of the 5th International Conference on Applied Human Factors and Ergonomics, AHFE 2014,
Xie, K., Wang, X., Huang, H., & Chen, X. (2013). Corridor-level signalized intersection safety analysis in Shanghai, China using Bayesian hierarchical models. Accident Analysis & Prevention, 50, 25-33.
Yaacob, W. F. W., Lazim, M. A., & Wah, Y. B. (2010). Evaluating spatial and temporal effects of accidents likelihood using random effects panel count model. 2010 International Conference on Science and Social Research (CSSR 2010),
Zamani, H., & Ismail, N. (2014). Functional form for the zero-inflated generalized Poisson regression model. Communications in Statistics-Theory and Methods, 43(3), 515-529.
Zhang, Z., Trivedi, C., & Liu, X. (2018). Automated detection of grade-crossing-trespassing near misses based on computer vision analysis of surveillance video data. Safety science, 110, 276-285.
Zhao, S., Iranitalab, A., & Khattak, A. J. (2019). A clustering approach to injury severity in pedestrian-train crashes at highway-rail grade crossings. Journal of Transportation Safety & Security, 11(3), 305-322.
Zhou, C., Ding, L., Skibniewski, M. J., Luo, H., & Jiang, S. (2017). Characterizing time series of near-miss accidents in metro construction via complex network theory. Safety science, 98, 145-158.