Abstract
Road networks are critical assets supporting economies and communities. Despite budget and time constraints, road authorities strive to maintain them to ensure safety, ongoing service, and economic productivity. This paper proposes a virtual road network inspector (VRNI), which continuously monitors road conditions and provides decision support to managers and engineers. VRNI uses acceleration data from vehicle-mounted sensors to assess road conditions. It proposes a novel road damage detection method based on two adaptive one-class support vector machine models, which were applied on the vertical and lateral acceleration data. We evaluated this method on data from a real deployment on school buses in New South Wales, Australia. Experimental results show that our method consistently detects 97.5% of the road damage with a 4% false alarm rate that relate to benign anomalies such as expansion joints.
Similar content being viewed by others
Notes
Video recordings were only used as validation in the prototype testing. VRNI does not require and will not use video in a production deployment.
As mentioned earlier, in a real-world deployment VRNI might be deployed on a route, which at first may have no damage at all, i.e., only one class of data is available.
<url to download the data> will be made available upon paper publication.
References
Alamdari MM, Rakotoarivelo T, Khoa NLD (2017) A spectral-based clustering for structural health monitoring of the sydney harbour bridge. Mech Syst Signal Process 87(Part A):384–400. Retrieved from http://www.sciencedirect.com/science/article/pii/S0888327016304538
Anaissi A, Braytee A, Naji, M. (2018) Gaussian kernel parameter optimization in one-class support vector machines. In: 2018 International Joint Conference on Neural Networks (IJCNN), IEEE, pp 1–8
Anaissi A, Goyal M, Catchpoole DR, Braytee A, Kennedy PJ (2016) Ensemble feature learning of genomic data using support vector machine. PloS One 11(6):e0157330
Anaissi A, Kennedy PJ, Goyal M (2011) Feature selection of imbalanced gene expression microarray data. In: Software engineering, artificial intelligence, networking and parallel/distributed computing (snpd), 2011 12th acis International Conference on, IEEE, pp 73–78
Anaissi A, Kennedy PJ, Goyal M, Catchpoole DR (2013) A balanced iterative random forest for gene selection from microarray data. BMC Bioinform 14(1):261
Anaissi A, Khoa NLD, Alamdari MM, Wang Y, Mustapha S, Chen F (2017a) Adaptive one-class support vector machine for damage detection in structural health monitoring. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, Springer, pp 459–471
Anaissi A, Khoa NLD, Rakotoarivelo T, Alamdari MM, Wang Y (2017b) Self-advised incremental one-class support vector machines: an application in structural health monitoring. In: International Conference on Neural Information Processing, Springer, pp 484–496
Benjamin JR, Cornell CA (2014) Probability, statistics, and decision for civil engineers. Courier Corporation, Chelmsford
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Burningham S, Stankevich N (2005) Why road maintenance is important and how to get it done. The World Bank, Transport Note TRN-4
Chen Y, Zhou XS, Huang TS (2001) One-class svm for learning in image retrieval. In: Image Processing, 2001. Proceedings. 2001 International Conference on, vol 1, IEEE, pp 34–37
Clifford G (2005) Singular value decomposition and independent component analysis. J Biomed Image Process 93:49
Cong F, Hautakangas H, Nieminen J, Mazhelis O, Perttunen M, Riekki J, Ristaniemi T (2013) Applying wavelet packet decomposition and one-class support vector machine on vehicle acceleration traces for road anomaly detection. In: International Symposium on Neural Networks, Springer, pp 291–299
Cortes C, Vapnik V (1995) Support vector machine. Mach Learn 20(3):273–297
Eriksson J, Girod L, Hull B, Newton R, Madden S, Balakrishnan H (2008) The pothole patrol: using a mobile sensor network for road surface monitoring. In: proceedings of the 6th International Conference on Mobile systems, applications, and services, ACM, pp 29–39
Hampel FR (1974) The influence curve and its role in robust estimation. J Am Stat Assoc 69(346):383–393
Harikumar R, Vijayakumar T, Sreejith M (2011) Performance analysis of svd and support vector machines for optimization of fuzzy outputs in classification of epilepsy risk level from eeg signals. In: Recent Advances in Intelligent Computational Systems (RAICS), 2011 IEEE, IEEE, pp 718–723
Hassanpour H, Mesbah M, Boashash B (2004) Time-frequency feature extraction of newborn eeg seizure using svd-based techniques. EURASIP J Appl Signal Process 2004:2544–2554
Jeff R (2006) Guidelines for measuring and reporting the condition of road assets. http://www.dtpli.vic.gov.au/
Kemmler M, Rodner E, Wacker E-S, Denzler J (2013) One-class classification with gaussian processes. Pattern Recognit 46(12):3507–3518
Khazai S, Homayouni S, Safari A, Mojaradi B (2011) Anomaly detection in hyperspectral images based on an adaptive support vector method. IEEE Geosci Remote Sens Lett 8(4):646–650
Khoa NLD, Zhang B, Wang Y, Liu W, Chen F, Mustapha S, Runcie P (2015) On damage identification in civil structures using tensor analysis. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, Springer, pp 459–471
Perttunen M, Mazhelis O, Cong F, Kauppila M, Leppänen T, Kantola J, Collin J, Pirttikangas S, Haverinen J, Ristaniemi T, et al (2011) Distributed road surface condition monitoring using mobile phones. In: Ubiquitous Intelligence and Computing, Springer, pp 64–78
Runcie P, Mustapha S, Rakotoarivelo T (2014) Advances in structural health monitoring system architecture. In: International Symposium on Life-Cycle Civil Engineering, pp 1064 –1071
Schölkopf B, Williamson RC, Smola AJ, Shawe-Taylor J, Platt JC, et al (1999) Support vector method for novelty detection. In: NIPS, vol 12, Citeseer, pp 582–588
Shin K, Hammond J, White P (1999) Iterative svd method for noise reduction of low-dimensional chaotic time series. Mech Syst Signal Process 13(1):115–124
Xiao Y, Wang H, Xu W (2015) Parameter selection of gaussian kernel for one-class svm. IEEE Trans Cybern 45(5):941–953
Xiao Y, Wang H, Zhang L, Xu W (2014) Two methods of selecting gaussian kernel parameters for one-class svm and their application to fault detection. Knowl Based Syst 59:75–84
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Anaissi, A., Khoa, N.L.D., Rakotoarivelo, T. et al. Smart pothole detection system using vehicle-mounted sensors and machine learning. J Civil Struct Health Monit 9, 91–102 (2019). https://doi.org/10.1007/s13349-019-00323-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13349-019-00323-0