Detection of debondings with Ground Penetrating Radar using a machine learning method

In the field of civil engineering, Ground Penetrating Radar (GPR) is the most widely used method of Non-Destructive Testing (NDT). Using supervised learning methods or signal processing methods, it is possible to analyze the sub-surface defects in pavement. In this paper, we propose to use a supervised machine learning method called Support Vector Machines (SVM) to detect the presence of debondings within the pavement. Here, the ground-coupled GPR in quasi mono-static configuration along with SVM is used to detect debondings. The experiments are done on bituminous concrete pavements with various material characteristics. The classification results show the efficiency of the detection process.

[1]  Christina Plati,et al.  Review of NDT Assessment of Road Pavements Using GPR , 2013 .

[2]  Dong Wang,et al.  Pavement Health Monitoring System Based on an Embedded Sensing Network , 2014 .

[3]  X. Derobert,et al.  Case study of detection of artificial defects in an experimental pavement structure using 3D GPR systems , 2014, Proceedings of the 15th International Conference on Ground Penetrating Radar.

[4]  Laura E. Ray,et al.  An autonomous robotic platform for ground penetrating radar surveys , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[5]  Chen Xiao-li,et al.  Feature extraction and classification of echo signal of ground penetrating radar , 2008, Wuhan University Journal of Natural Sciences.

[6]  Dimitri Solomatine,et al.  Support Vector Machines: Review and Applications in Civil Engineering , 2000 .

[7]  Johan Alexander Huisman,et al.  Measuring soil water content with ground penetrating radar , 2003 .

[8]  Olivier Durand,et al.  Detection of Debonding and Vertical Cracks with Non Destructive Techniques during Accelerated Pavement Testing , 2012 .

[9]  Chen Wang,et al.  Rapid Nondestructive-Testing Technique for In-Line Quality Control of Li-Ion Batteries , 2017, IEEE Transactions on Industrial Electronics.

[10]  J. Hołyst,et al.  Statistical analysis of 22 public transport networks in Poland. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[11]  T.E. Bell.  When bust is best (destructive testing) , 1991, IEEE Spectrum.

[12]  S. Chambon,et al.  Automatic Road Pavement Assessment with Image Processing: Review and Comparison , 2011 .

[13]  A. Benedetto.  Theoretical approach to electromagnetic monitoring of road pavement applied geophysics and stochastical model , 2004, Proceedings of the Tenth International Conference on Grounds Penetrating Radar, 2004. GPR 2004..

[14]  Madan Gopal,et al.  Binary Classification Using Linear SVM Pyramidal Tree , 2010, 2010 International Conference on Data Storage and Data Engineering.

[15]  Mehmet Saltan,et al.  Feasibility of Detecting Debonding of Hot Mix Asphalt Layer with Nondestructive Testing , 2013 .

[16]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[17]  Hui Zhao,et al.  A Classification Method Based on Non-linear SVM Decision Tree , 2007, Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007).

[18]  Anastasios Tefas,et al.  Using Support Vector Machines to Enhance the Performance of Elastic Graph Matching for Frontal Face Authentication , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Antonios Giannopoulos,et al.  Modelling ground penetrating radar by GprMax , 2005 .

[20]  Yogendra Kumar Jain,et al.  Min Max Normalization Based Data Perturbation Method for Privacy Protection , 2011 .

[21]  A. Robert.  Dielectric permittivity of concrete between 50 Mhz and 1 Ghz and GPR measurements for building materials evaluation , 1998 .

[22]  M. Wistuba,et al.  Crack detection in asphalt pavements - How useful is the GPR? , 2011, 2011 6th International Workshop on Advanced Ground Penetrating Radar (IWAGPR).

[23]  SATYAM MUKHERJEE,et al.  Statistical analysis of the road network of India , 2012, 1203.0313.

[24]  Jérôme Idier,et al.  Automatic Crack Detection on Two-Dimensional Pavement Images: An Algorithm Based on Minimal Path Selection , 2016, IEEE transactions on intelligent transportation systems (Print).

[25]  Lajos Hanzo,et al.  Support vector machine multiuser receiver for DS-CDMA signals in multipath channels , 2001, IEEE Trans. Neural Networks.

[26]  F. Tosti,et al.  Prediction of rutting evolution in flexible pavement life cycle at the road network scale using an air-launched ground-penetrating radar system , 2016, 2016 16th International Conference on Ground Penetrating Radar (GPR).

[27]  Baigal tugsSanjaa,et al.  Malware detection using linear SVM , 2013, Ifost.

[28]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[29]  Jean-Michel Simonin,et al.  Progress in monitoring the debonding within pavement structures during accelerated pavement testing on the fatigue carousel , 2016 .

[30]  Yide Wang,et al.  Thin-Pavement Thickness Estimation Using GPR With High-Resolution and Superresolution Methods , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[31]  Guangyou Fang,et al.  Non-destructive survey of pavement layer thicknesses with ground penetrating radar , 2013, 2013 IEEE International Conference of IEEE Region 10 (TENCON 2013).

[32]  Chao Yu,et al.  An automatic recognition algorithm for GPR images of RC structure voids , 2013 .

[33]  C. Saranya,et al.  A Study on Normalization Techniques for Privacy Preserving Data Mining , 2013 .

[34]  Yang Shao,et al.  Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points , 2012 .

[35]  Massimiliano Pontil,et al.  Support Vector Machines for 3D Object Recognition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[36]  T. Scullion,et al.  Road evaluation with ground penetrating radar , 2000 .

[37]  Laura E. Ray,et al.  Crevasse Detection in Ice Sheets Using Ground Penetrating Radar and Machine Learning , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[38]  K. K. Sahu,et al.  Normalization: A Preprocessing Stage , 2015, ArXiv.

[39]  Dani Or,et al.  Ground-penetrating radar measurement of soil water content dynamics using a suspended horn antenna , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[40]  Bruno Beaucamp,et al.  Non-destructive assessment of hot mix asphalt compaction/ density with a step-frequency radar: case study on a newly paved road , 2015 .

[41]  W Hutter.  LONG-TERM PAVEMENT MONITORING EVALUATION OF IMPROVEMENTS TO COLORADO'S PAVEMENT MANAGEMENT PROGRAM. FINAL REPORT , 1984 .

[42]  S. Lambot,et al.  Full-waveform inversion using the step frequency radar in the GPR band to characterize the tack coat in hot-mix asphalt (HMA) layers of flexible pavements , 2016, 2016 16th International Conference on Ground Penetrating Radar (GPR).

[43]  James A. Bucklew,et al.  Support vector machine techniques for nonlinear equalization , 2000, IEEE Trans. Signal Process..

[44]  Xiaojing Yuan,et al.  SVM-based Texture Classification and Application to Early Melanoma Detection , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[45]  Abanti Shama Afroz.  An alternative approach of evaluating Dice Similarity Index for Pre-segmented blood vessels , 2014, The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014).

[46]  Nectaria Diamanti,et al.  Field observations and numerical models of GPR response from vertical pavement cracks , 2012 .

[47]  Yi Liu,et al.  Soft SVM and its application to video object extraction , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[48]  N. Aswini,et al.  Detection and classification of ground penetrating radar image using textrual features , 2014, 2014 International Conference on Advances in Electronics Computers and Communications.

[49]  B Indraratna,et al.  Automatic classification of GPR signals , 2010, Proceedings of the XIII Internarional Conference on Ground Penetrating Radar.

[50]  Anca L. Ralescu,et al.  Confusion Matrix-based Feature Selection , 2011, MAICS.

[51]  Wei-Ying Ma,et al.  Learning similarity measure for natural image retrieval with relevance feedback , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[52]  Ying Wu,et al.  Learning in content-based image retrieval , 2002, Proceedings 2nd International Conference on Development and Learning. ICDL 2002.

[53]  John H. Bradford,et al.  Estimating porosity with ground‐penetrating radar reflection tomography: A controlled 3‐D experiment at the Boise Hydrogeophysical Research Site , 2009 .

[54]  Yong Yao,et al.  A New Multi-class Classification Based on Non-linear SVM and Decision Tree , 2007, 2007 Second International Conference on Bio-Inspired Computing: Theories and Applications.