Mobile Phone Data Feature Denoising for Expressway Traffic State Estimation

Linlin Wu, Guangming Shou, Zaichun Xie and Peng Jing ()
Additional contact information
Linlin Wu: School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China
Guangming Shou: School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China
Zaichun Xie: Hunan Provincial Communications Planning, Survey & Design Institute Co., Ltd., Changsha 410200, China
Peng Jing: School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China

Sustainability, 2023, vol. 15, issue 7, 1-15

Abstract: Due to their wide coverage, low acquisition cost and large data quantity, the mobile phone signaling data are suitable for fine-grained and large-scale estimation of traffic conditions. However, the relatively high level of data noise makes it difficult for the estimation to achieve sufficient accuracy. According to the characteristics of mobile phone data noise, this paper proposed an improved density peak clustering algorithm (DPCA) to filter data noise. In addition, on the basis of the long short-term memory model (LSTM), a traffic state estimation model based on mobile phone feature data was established with the use of denoising data to realize the estimation of the expressway traffic state with high precision, fine granules, and wide coverage. The Shanghai–Nanjing Expressway was used as a case study area for method and model verification, the results of which showed that the denoising method proposed in this paper can effectively filter data noise, reduce the impact of extreme noise data, significantly improve the estimation accuracy of the traffic state, and reflect the actual traffic situation in a fairly satisfactory manner.

Keywords: density peak clustering; mobile phone signaling data; data denoising; traffic state estimation (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/7/5811/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/7/5811/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:15:y:2023:i:7:p:5811-:d:1108541

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().