An information retrieval approach for robust prediction of road surface states

Jae Hyung Park, Kwanho Kim

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Recently, due to the increasing importance of reducing severe vehicle accidents on roads (especially on highways), the automatic identification of road surface conditions, and the provisioning of such information to drivers in advance, have recently been gaining significant momentum as a proactive solution to decrease the number of vehicle accidents. In this paper, we firstly propose an information retrieval approach that aims to identify road surface states by combining conventional machine-learning techniques and moving average methods. Specifically, when signal information is received from a radar system, our approach attempts to estimate the current state of the road surface based on the similar instances observed previously based on utilizing a given similarity function. Next, the estimated state is then calibrated by using the recently estimated states to yield both effective and robust prediction results. To validate the performances of the proposed approach, we established a real-world experimental setting on a section of actual highway in South Korea and conducted a comparison with the conventional approaches in terms of accuracy. The experimental results show that the proposed approach successfully outperforms the previously developed methods.

Original languageEnglish
Article number262
JournalSensors
Volume17
Issue number2
DOIs
StatePublished - Feb 2017

Keywords

  • Exponential moving average
  • Information retrieval
  • Machine learning
  • Ranking and scoring functions
  • Road surface radar
  • Road surface state detection
  • Smart highway

Fingerprint

Dive into the research topics of 'An information retrieval approach for robust prediction of road surface states'. Together they form a unique fingerprint.

Cite this