Download PDFOpen PDF in browser

Data Driven Analytics of Road Quality

10 pagesPublished: March 13, 2019

Abstract

There is a lack of research into the impact of road roughness on ride quality and route choice. The scarcity of ride roughness data for local and urban roads is likely one reason for the lack of such studies. Existing methods of obtaining ride roughness data are expensive and require expert practitioners and laborious data processing by trained personnel. Sensors in most current vehicles provide an alternative source for road roughness data. This study emulated the data needed from vehicle sensors by using the accelerometer and gyroscope of a smartphone. The authors used data collected from two different bus routes to classify segments of roads into objectively distinct roughness clusters. The output enables map service applications to suggest better routing options based on expected ride quality and also quantifies road roughness consistently to enable optimized maintenance planning and decision-making for roadway assets.

Keyphrases: Clustering, Intelligent Transportation Systems, machine learning, road impact factor, road quality, route planning

In: Gordon Lee and Ying Jin (editors). Proceedings of 34th International Conference on Computers and Their Applications, vol 58, pages 454--463

Links:
BibTeX entry
@inproceedings{CATA2019:Data_Driven_Analytics_of,
  author    = {Ali Rahim Taleqani and Raj Bridgelall and Jill Hough and Kendall Nygard},
  title     = {Data Driven Analytics of Road Quality},
  booktitle = {Proceedings of 34th International Conference on Computers and Their Applications},
  editor    = {Gordon Lee and Ying Jin},
  series    = {EPiC Series in Computing},
  volume    = {58},
  pages     = {454--463},
  year      = {2019},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {https://easychair.org/publications/paper/w188},
  doi       = {10.29007/6vjj}}
Download PDFOpen PDF in browser