Street SAFE - Road fault monitoring and reporting

Jun Wei Lim, Timothy Tzen Vun Yap, Vik Tor Goh, Hu Ng, Wen Jiun Yap, Thiam Yong Kuek

Research output: Contribution to journalArticlepeer-review

Abstract

Maintaining roads have become challenging as road users are on the rise. Tough weather conditions and high traffic make road surfaces deteriorate swiftly. Manual detection on these defects is not efficient. Due to the rise of smartphone use, the accelerometers in the smartphone are employed for road fault classification. Supervised machine learning classification models of data pertaining to pothole, speed bump, hazard line, smooth road, uneven road, turn, and hard stop are trained with the Random Forest (RF) and Support Vector Machine (SVM) algorithms, which is then utilized in StreetSAFE (Smartphone Assisted Fault Examination), a machine learning aided system to detect road faults and report them in real time. Using statistical parameters, the system is found to able to distinguish road surface conditions. The system can potentially predict road damage, facilitate maintenance and resource management.

Original languageEnglish
Pages (from-to)120-124
Number of pages5
JournalInternational Journal of Engineering Trends and Technology
Issue number1
DOIs
Publication statusPublished - Aug 2020

Keywords

  • Accelerometer
  • Machine learning
  • Road faults
  • Statistical features

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Street SAFE - Road fault monitoring and reporting'. Together they form a unique fingerprint.

Cite this