Please use this identifier to cite or link to this item: http://nopr.niscair.res.in/handle/123456789/55134
Title: Parking demand modelling using artificial neural network
Authors: Parmar, Janak
Das, Pritikana
Azad, Farhat
Issue Date: Jun-2020
Publisher: NISCAIR-CSIR, India
Abstract: In modern era, population and economic growth as well as increasing living standard of people are to blame for the rising number of private vehicles in the cities. The need for parking space is directly in nexus of demand associated with the upsurge in the vehicle plying on the roads. Hence, at planning and development stage, it is must to address the infrastructural and sometimes technological demands which has limited resources to supply. It is possible to develop a general model which can estimate the parking demand in terms of different criteria e.g., space, duration, number of visits, etc. This research work is emphasized on to develop the parking demand model as a parking space usage per visit for commercial cum business area based on the socio-economic as well as travel characteristics of the parkers using Artificial Neural Network technique. Two major CBDs namely Nehru Place and Bhikaji Cama Place have been selected in Delhi-NCR. Questionnaire has been prepared to carry out revealed preference survey in order to collect data of socio-economic and trip characteristics of parking users. Results reveals that the travel time and total cost including parking charges having most influence on the parking demand followed by the purpose of trip of an individual. The importance of each input variable has been derived. The study is helpful to incorporate the significant variable while making parking policies and same is supporting to the planners designing parking lot for different land use.
Page(s): 48-56
URI: http://nopr.niscair.res.in/handle/123456789/55134
ISSN: 0975-2412 (Online); 0771-7706 (Print)
Appears in Collections:BVAAP Vol.28(1) [June 2020]

Files in This Item:
File Description SizeFormat 
BVAAP 28(1) 48-56.pdf237.13 kBAdobe PDFView/Open


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