Investigating and modelling the relationship between traffic volume and extracts from cellphone activity data. Issue 8 (14th May 2019)

• Record Type: Journal Article
• Authors: He, Shanglu; Ding, Fan; Zhou, Yang; Cheng, Yang; Ran, Bin
• Is Part Of: IET intelligent transport systems. Volume 13:Issue 8(2019)
• Page Start: 1299
• Page End: 1308
• Publication Date: 2019-05-14
• Subjects: road traffic -- pattern classification -- pattern clustering -- statistical analysis -- mobile computing; freeway links -- uncongested traffic condition -- generic linear relationship model -- DTW‐based classification step -- DTW‐based hierarchical clustering step -- UCC time‐series -- dynamic time warping‐based method -- traffic speed -- unique cellphone counts -- traffic features -- cellphone activity data -- traffic volume; Intelligent transportation systems -- Periodicals; Electronics in transportation -- Periodicals; 388.31205
• DOI: 10.1049/iet-its.2018.5525
• Languages: English
• ISSNs: 1751-956X

Abstract

Abstract : Two traffic features [unique cellphone counts (UCC) and pseudo speed (PS)] could be extracted from cellphone activity (CA) data that contain all wireless communication records of a standby or active cellphone. PS has been validated to be close to the traffic speed in the previous works. Further investigation was conducted in this study on the relationship between UCC and the traffic volume. First, a dynamic time warping (DTW)‐based method was proposed to analyse the UCC time‐series from different freeway links, which consisted of a DTW‐based hierarchical clustering step and a DTW‐based classification step. Field data was applied in the case study and this proposed analysis method found that UCCs varied from link to link. Besides, this method efficiently classified the links into different groups based on the similarity between UCC and the traffic volume. Moreover, the analysis results were applied to formalising the relationship model between UCC and traffic volume. The case study indicated that a generic linear relationship model might be calibrated, if those links were classified in the same group and were neighbouring enough for a shared close traffic volume value. Besides, it was validated that this model has a good performance under the uncongested traffic condition.