DEVELOPMENT OF A DECISION SUPPORT SYSTEM FOR ANALYSIS OF EMERGENCIES ON URBAN TRANSPORT
DOI:
https://doi.org/10.28925/2663-4023.2021.12.618Keywords:
decision support system, cluster analysis, urban transport, analysis of accidents and emergenciesAbstract
The article discusses some aspects of the design of a decision support system (DSS) module during the analysis of major accidents or emergencies in urban transport in large cities, megalopolises, as well as in Smart City. It is shown that the computational core of such a DSS can be based on the methods of cluster analysis (CA). It is shown that the implementation of even basic spacecraft algorithms in the computational core of the DSSS allows an iterative search for optimal solutions to prevent a large number of emergencies in urban transport by establishing characteristic signs of accidents and emergencies and measures of proximity between two objects. It is shown that such a toolkit as DSS can provide all interested parties with a scientifically grounded classification of multidimensional observations, which summarize the set of selected indicators and make it possible to identify internal connections between emergencies in urban transport. The DSS module for analyzing emergencies in urban transport is described. It has been found that to solve such a problem, it is possible to use the "weighted" Euclidean distance in the computational core of the DSS. It is this parameter that makes it possible to take into account the significance of each characteristic of emergency situations in urban transport, which, in turn, will contribute to obtaining reliable analysis results. It is shown that the spacecraft methods can also be in demand when, along with the analysis of emergency situations in urban transport, problems of designing and reconstructing the configurations of urban street-road networks are solved in parallel. This task, in particular, requires an analysis phase (not least using CA methods) in order to minimize unnecessary uncompensated costs in the event of errors in the road network. When solving such a problem, sections of the urban street and road network are analyzed in order to identify problem areas that need reconstruction or redevelopment. The use of CA methods in such conjugate problems is due to the absence of a priori hypotheses regarding the classes that will be obtained as a result.
Downloads
References
Thomas, G., Alexander, G., & Sasi, P. M. (2017). Design of high performance cluster based map for vehicle tracking of public transport vehicles in smart city. In 2017 IEEE Region 10 Symposium (TENSYMP) (pp. 1–5). IEEE.
Ghoneim, Osama A. "Traffic Jams Detection and Congestion Avoidance in Smart City Using Parallel K-Means Clustering Algorithm." Proceedings of International Conference on Cognition and Recognition. Springer, Singapore, 2018, 154-158.
Kaplan, S., & Prato, C. G. (2013). Cyclist–motorist crash patterns in Denmark: A latent class clustering approach. Traffic injury prevention, 14(7), 725–733.
Sun, M., Sun, X., & Shan, D. (2019). Pedestrian crash analysis with latent class clustering method. Accident Analysis & Prevention, 124, 50–57.
Maji, A., Velaga, N. R., & Urie, Y. (2018). Hierarchical clustering analysis framework of mutually exclusive crash causation parameters for regional road safety strategies. International journal of injury control and safety promotion, 25(3), 257–271.
Achu, A. L., Aju, C. D., Suresh, V., Manoharan, T. P., & Reghunath, R. (2019). Spatio-temporal analysis of road accident incidents and delineation of hotspots using geospatial tools in Thrissur District, Kerala, India. KN-Journal of Cartography and Geographic Information, 69(4), 255–265.
Liu, Z., Jia, H., & Wang, Y. (2020). Urban expressway parallel pattern recognition based on intelligent IOT data processing for smart city. Computer Communications, 155, 40–47.
Bellini, E., Nesi, P., Pantaleo, G., & Venturi, A. (2016, September). Functional resonance analysis method based-decision support tool for urban transport system resilience management. In 2016 IEEE International Smart Cities Conference (ISC2) (pp. 1–7). IEEE.
Sun, F., Pan, Y., White, J., & Dubey, A. (2016, May). Real-time and predictive analytics for smart public transportation decision support system. In 2016 IEEE International Conference on Smart Computing (SMARTCOMP) (pp. 1–8). IEEE.
Frez, J., Baloian, N., & Zurita, G. (2014, December). SmartCity: Public Transportation Network Planning Based on Cloud Services, Crowd Sourcing and Spatial Decision Support Theory. In International Conference on Ubiquitous Computing and Ambient Intelligence (pp. 365–371). Springer, Cham.
Romesburg, C. (2004). Cluster analysis for researchers. Lulu. com. P.333.
