TY - JOUR
T1 - Street SAFE - Road fault monitoring and reporting
AU - Lim, Jun Wei
AU - Yap, Timothy Tzen Vun
AU - Goh, Vik Tor
AU - Ng, Hu
AU - Yap, Wen Jiun
AU - Kuek, Thiam Yong
N1 - Funding Information:
Financial support from the Ministry of Higher Education, Malaysia, under the Fundamental Research Grant Scheme with grant number FRGS/1/2018/ICT02/MMU/03/6, as well as the Multimedia University Mini Fund with Project ID MMUI/180239, are gratefully acknowledged.
Publisher Copyright:
© 2020 SSRG International Journal of Engineering Trends and Technology. All rights reserved.
PY - 2020/8
Y1 - 2020/8
N2 - 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.
AB - 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.
KW - Accelerometer
KW - Machine learning
KW - Road faults
KW - Statistical features
UR - http://www.scopus.com/inward/record.url?scp=85099279011&partnerID=8YFLogxK
U2 - 10.14445/22315381/CATI1P222
DO - 10.14445/22315381/CATI1P222
M3 - Article
AN - SCOPUS:85099279011
SN - 2349-0918
SP - 120
EP - 124
JO - International Journal of Engineering Trends and Technology
JF - International Journal of Engineering Trends and Technology
IS - 1
ER -