A two-stage black-spot identification model for inland waterway transportation

Abstract Inland shipping plays a significant role in the integrated transport system. Maritime safety has been one of the top concerns due to its high-risk characteristics. The historical accident data is treated as a valuable source for identifying the riskiest waters (also called black-spots) where special attention is necessary. In view of this, a two-stage black-spot identification model is proposed in this paper to identify and locate waterways with higher accident rates. In stage 1, the dynamic segmentation and equivalent accident number methods are proposed to identify the preliminarily black-spots. In stage 2, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is introduced to pinpoint the precise locations of the detailed black-spots based on the results from the first step. The model is further applied to the Jiangsu section of the Yangtze River based on the historical accident data between 2012 and 2016. The results show that altogether 12 preliminary black-spots and 5 detailed black-spots are identified in the investigated waters. This research provides helpful reference for optimizing the allocations of search and rescue resource as well as differentiated safety management of black-spot waters.

[1]  Salvatore Cafiso,et al.  Performance of Safety Indicators in Identification of Black Spots on Two-Lane Rural Roads , 2011 .

[2]  Di Zhang,et al.  Collision risk assessment in Jiangsu section of the Yangtze River based on evidential reasoning , 2021 .

[3]  C. Guedes Soares,et al.  Incorporating evidential reasoning and TOPSIS into group decision-making under uncertainty for handling ship without command , 2018, Ocean Engineering.

[4]  Wang Lei,et al.  Inland waterway ‘black spot’ identification model based on MEA-BP neural network algorithm , 2017, 2017 4th International Conference on Transportation Information and Safety (ICTIS).

[5]  C. Soares,et al.  Quantitative Analysis on Risk Influencing Factors in the Jiangsu Segment of the Yangtze River , 2020, Risk analysis : an official publication of the Society for Risk Analysis.

[6]  Maen Ghadi,et al.  A comparative analysis of black spot identification methods and road accident segmentation methods. , 2019, Accident; analysis and prevention.

[7]  Tian Zhang,et al.  BIRCH: A New Data Clustering Algorithm and Its Applications , 1997, Data Mining and Knowledge Discovery.

[8]  Xinping Yan,et al.  A distributed anti-collision decision support formulation in multi-ship encounter situations under COLREGs , 2015 .

[9]  S. Cafiso,et al.  Comparison of Italian and Hungarian Black Spot Ranking , 2016 .

[10]  A. P. Teixeira,et al.  Data mining approach to shipping route characterization and anomaly detection based on AIS data , 2020 .

[11]  Simon Fong,et al.  DBSCAN: Past, present and future , 2014, The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014).

[12]  Giulio Maternini,et al.  A NEW METHODOLOGY OF ACCIDENT ANALYSIS USING SAFETY INDICATORS RELATED TO FUNCTIONAL ROAD CLASSES , 2001 .

[13]  Sheng Neng Hu.  High-Grade Highway Safety Evaluation Method Based on Grey Clustering , 2012 .

[14]  Maen Ghadi,et al.  Comparison Different Black Spot Identification Methods , 2017 .

[15]  R A Krammes.  INTERACTIVE HIGHWAY SAFETY DESIGN MODEL: DESIGN CONSISTENCY MODULE , 1997 .

[16]  Carlos Guedes Soares,et al.  Causal factors in accidents of high-speed craft and conventional ocean-going vessels , 2008, Reliab. Eng. Syst. Saf..

[17]  Xiyu Liu,et al.  An improved MkNN clustering algorithm based on graph theory and membrane computing , 2019, J. Comput. Methods Sci. Eng..

[18]  Yetis Sazi Murat.  An Entropy (Shannon) based Traffic Safety Level Determination Approach for Black Spots , 2011 .

[19]  Jakub Montewka,et al.  Maritime transportation risk analysis: Review and analysis in light of some foundational issues , 2015, Reliab. Eng. Syst. Saf..

[20]  H. Sandhu,et al.  Identification of Black Spots on Highway with Kernel Density Estimation Method , 2016, Journal of the Indian Society of Remote Sensing.

[21]  Maria Hänninen,et al.  Analysis of the marine traffic safety in the Gulf of Finland , 2009, Reliab. Eng. Syst. Saf..

[22]  Ferit Yakar,et al.  Identification of Accident-Prone Road Sections by Using Relative Frequency Method , 2015 .

[23]  Jeffrey A. Cardille,et al.  Representative Landscapes in the Forested Area of Canada , 2011, Environmental Management.

[24]  Kyriacos C. Mouskos,et al.  Black spots identification through a Bayesian Networks quantification of accident risk index , 2013 .

[25]  Bin Li,et al.  Study on Road Traffic Safety Evaluation Based on Improved Bayes Model , 2011 .

[26]  Wang Peng,et al.  Grid-based DBSCAN Algorithm with Referential Parameters , 2012 .

[27]  Carlos Guedes Soares,et al.  Risk assessment in maritime transportation , 2001, Reliab. Eng. Syst. Saf..

[28]  Qing He,et al.  Parallel CLARANS Clustering Based on MapReduce , 2011 .

[29]  Floris Goerlandt,et al.  Traffic simulation based ship collision probability modeling , 2011, Reliab. Eng. Syst. Saf..

[30]  Hans-Peter Kriegel,et al.  OPTICS: ordering points to identify the clustering structure , 1999, SIGMOD '99.

[31]  K. W. Ogden,et al.  Road Safety Audit: a New Tool for Accident Prevention , 1995 .

[32]  Artur Petrov.  Model of Calculation and Subsequent Assessment of the Economic Losses of the Ural Federal District Subjects in Case of Death and Injury in Road Traffic Accidents , 2017 .

[33]  Ronnie Johansson,et al.  Choosing DBSCAN Parameters Automatically using Differential Evolution , 2014 .

[34]  Arthur T. DeGaetano,et al.  Spatial grouping of United States climate stations using a hybrid clustering approach , 2001 .

[35]  Xinping Yan,et al.  Maritime Transportation Risk Assessment of Tianjin Port with Bayesian Belief Networks , 2016, Risk analysis : an official publication of the Society for Risk Analysis.

[36]  D F Jarrett,et al.  Estimating the regression-to-mean effect associated with road accident black spot treatment: towards a more realistic approach. , 1988, Accident; analysis and prevention.

[37]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2010, Pattern Recognit. Lett..

[38]  Adrian E. Raftery,et al.  Model-Based Clustering, Discriminant Analysis, and Density Estimation , 2002 .

[39]  Bing Wu,et al.  A probabilistic consequence estimation model for collision accidents in the downstream of Yangtze River using Bayesian Networks , 2020, Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability.

[40]  Wen Cheng,et al.  Experimental evaluation of hotspot identification methods. , 2005, Accident; analysis and prevention.

[41]  Ricardo A. Daziano,et al.  Computational Bayesian Statistics in Transportation Modeling: From Road Safety Analysis to Discrete Choice , 2013 .

[42]  Di Zhang,et al.  Analysis of risk factors influencing the safety of maritime container supply chains , 2019, International Journal of Shipping and Transport Logistics.

[43]  C. Guedes Soares,et al.  Quantitative assessment of collision risk influence factors in the Tianjin port , 2018, Safety Science.

[45]  Ling Shao,et al.  Real-Time Superpixel Segmentation by DBSCAN Clustering Algorithm , 2016, IEEE Transactions on Image Processing.

[46]  T. Abdul Razak,et al.  A Comparative Study of Different Density based Spatial Clustering Algorithms , 2014 .

[47]  P. Silveira,et al.  Use of AIS Data to Characterise Marine Traffic Patterns and Ship Collision Risk off the Coast of Portugal , 2013, Journal of Navigation.

[48]  Lang Xu,et al.  Evaluation and governance of green development practice of port: A sea port case of China , 2020 .

[49]  Xinping Yan,et al.  An advanced fuzzy Bayesian-based FMEA approach for assessing maritime supply chain risks , 2019, Transportation Research Part E: Logistics and Transportation Review.

[50]  Eleni I. Vlahogianni,et al.  Statistical methods for detecting nonlinearity and non-stationarity in univariate short-term time-series of traffic volume , 2006 .