Please use this identifier to cite or link to this item: http://dspace.spab.ac.in:80/handle/123456789/2282
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGuleria, Sanya-
dc.date.accessioned2023-11-15T11:19:13Z-
dc.date.available2023-11-15T11:19:13Z-
dc.date.issued2023-05-
dc.identifier.urihttp://dspace.spab.ac.in:80/handle/123456789/2282-
dc.description.abstractIndia's growing urbanisation has resulted in an increase in demand for public transit. In recent years, metro systems have been a popular means of transit due to its speed, dependability, and low cost. Overcrowding and excessive wait times at metro stations, on the other hand, have become a major concern in various Indian cities. Therefore, to mitigate these issues, accurate passenger flow prediction models are essential for optimizing the capacity of metro stations, improving operational efficiency, and enhancing passenger satisfaction ensuring smooth and safe transit operations, avoiding over-investment in infrastructure and reduce the need for idle resources, and improving profitability. In detailed project reports of Indian metros, various four-stage travel demand models are commonly used to predict passenger flow or ridership. However, it has been observed that these models may not always provide accurate data. As a result, there is a need to explore alternative approaches such as probabilistic models to improve the accuracy of ridership prediction. Probabilistic models offer a different perspective by considering the inherent uncertainties and variability in travel patterns. These models consider a range of factors, including socio-economic characteristics, land use patterns, transport, travel behaviour data and additionally, station characteristics such as accessibility, station design, and transfer facilities can also impact passenger flow. By incorporating probabilistic analysis, these models can provide a more realistic representation of travel demand.The results of the study demonstrate that the proposed probabilistic model is effective in predicting passenger flow and can provide valuable information for transit planners.With the use of advanced data analytics techniques and machine learning algorithms can help develop accurate models that can capture the complex interplay of these factors and provide valuable insights into passenger flow dynamics. This study emphasizes the importance of passenger flow prediction for efficient metro station operations and highlights the need for continued research in this field to improve the overall effectiveness of metro systems in Indiaen_US
dc.language.isoenen_US
dc.publisherSchool of Planning and Architectureen_US
dc.relation.ispartofseries2021MTPLM001;TH001979-
dc.subjectIndian metrosen_US
dc.subjectStation designen_US
dc.subjectStation characteristicsen_US
dc.titlePassenger flow prediction for metro stations using probabilistic modelen_US
dc.typeThesisen_US
Appears in Collections:Master of Transport Planning and Logistics Management

Files in This Item:
File Description SizeFormat 
TH001979 - 2021MTPLM001_Sanya_Thesis_Report.pdf
  Restricted Access
10.53 MBAdobe PDFView/Open Request a copy


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.