Machine learning algorithms for wet road surface detection using acoustic measurements

Stratis Kanarachos, Mike Blundell, Olivier Haas, Michalis Kalliris, Rigas Kotsakis

Research output: Chapter in Book/Report/Conference proceedingConference proceedingpeer-review

6 Citations (Scopus)


—Precipitation can adversely influence road safety.
Slippery road conditions have traditionally been detected using
reactive methods requiring considerable excitation of the tire
forces. Alternatives rely on non-contact methods such as vision,
sound or ultrasonic sensors. This study proposes a cost-effective
wet road conditions detection method based on acoustic
measurements for urban and highway driving. It compared the
performance of a range of machine learning algorithms to
classify the road condition based on the audio features
calculated using octave-band frequency analysis. The approach
was evaluated experimentally using data collected from a
vehicle instrumented with a microphone, GPS and CAN bus
data logger. Support Vector Machines using Quadratic and
Cubic kernels, as well as Logistic Regression performed better
compared to other machine learning-based methods
Original languageEnglish
Title of host publicationProceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019
Number of pages6
ISBN (Electronic)9781538669594
Publication statusPublished - 24 May 2019
EventIEEE 2019 International Conference on Mechatronics - Technische Universität Ilmenau, Ilmenau, Germany
Duration: 19 Mar 201921 Mar 2019


ConferenceIEEE 2019 International Conference on Mechatronics
Internet address


  • acoustic measurements
  • wet road surface detection

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Automotive Engineering
  • Mechanical Engineering
  • Control and Optimization
  • Industrial and Manufacturing Engineering

Fingerprint Dive into the research topics of 'Machine learning algorithms for wet road surface detection using acoustic measurements'. Together they form a unique fingerprint.

Cite this