One of the most challenging issues for municipalities in the U.S. is to secure federal funding, state funding, or both, for local roadway improvement. Existing frameworks such as manual data collection, light detection and ranging have proven to be expensive and cumbersome. In this paper, a low-cost pavement management framework is proposed using artificial intelligence (AI). AI has solidified itself across industries as a revolutionary advancement that can automate many tasks that were performed by humans. AI has the potential to make roadway assessment easier and more cost-effective than ever, but this application has been hindered by dataset quality and quantity. Roadway datasets are often imbalanced, containing many more images of certain deformations than others. This decreases the performance of AI models. In this paper, different methods of pavement dataset labeling are tested to gain an understanding of which is best for pavement distress detection using a classification neural network. An AI-friendly pavement condition index is designed to give a clear indicator of the current pavement condition and provide a metric by which to rank the roads based on the need to repair them. The best-performing AI model is incorporated into the low-cost pavement management framework.
ShubhenduS.VijayJ.Applicability of Artificial Intelligence in Different Fields of Life. International Journal of Scientific Engineering and Research (IJSER), Vol. 1, No. 1, 2013, pp. 28–35.
5.
MachinM.SanguesaJ. A.GarridoP.MartinezF.On the Use of Artificial Intelligence Techniques in Intelligent Transportation Systems. Proc., 2018 IEEE Wireless Communications and Networking Conference Workshops (WCNCW), Barcelona, Spain, 2018. https://doi.org/10.1109/wcncw.2018.8369029.
6.
DemosthenousG.VassiliadesV.Continual Learning on the Edge with TensorFlow Lite. arXiv Preprint arXiv:2105.01946, 2021.
7.
HowardA.ZhuM.ChenB.KalenichenkoD.WangW.WeyandT.AndreettoM.AdamH.MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv Preprint arXiv:1704.04861, 2017.
8.
IandolaF. N.HanS.MoskewiczM. W.AshrafK.DallyW. J.KeutzerK.SqueezeNet: AlexNet-Level Accuracy with 50x Fewer Parameters and <0.5MB Model Size. arXiv Preprint arXiv:1602.07360, 2016.
9.
PetkovaM.Deploying Drones for Autonomous Detection of Pavement Distresses. Massachusetts Institute of Technology, Cambridge, MA, 2016.
10.
MogawerW. S.XieY.AustermanA. J.DillC.JiangL.GittingsJ. E.The Application of Unmanned Aerial Systems in Surface Transportation - Volume II-B: Assessment of Roadway Pavement Condition with UAS. No. 19-010. University of Massachusetts, Lowell, 2019.
11.
ApeagyeiA.AdemolakeT. E.Adom-AsamoahM.Evaluation of Deep Learning Models for Classification of Asphalt Pavement Distresses. International Journal of Pavement Engineering, Vol. 24, No. 1, 2023, p. 2180641. https://doi.org/10.1080/10298436.2023.2180641.
12.
JainA.PatelH.NagalapattiL.GuptaN.MehtaS.GuttulaS.MujumdarS.AfzalS.Sharma MittalR.MunigalaV.Overview and Importance of Data Quality for Machine Learning Tasks. Proc., KDD ’20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event CA, USA, July 6–10, 2020, Association for Computing Machinery, New York, NY.
13.
GuptaN.MujumdarS.PatelH.MasudaS.PanwarN.BandyopadhyayS.MehtaS., et al. Data Quality for Machine Learning Tasks. Proc., KDD’21: The 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Association for Computing Machinery, New York, NY, 2021, pp. 4040–4041. https://doi.org/10.1145/3447548.3470817.
14.
ZhengW.JinM.The Effects of Class Imbalance and Training Data Size on Classifier Learning: An Empirical Study. SN Computer Science, Vol. 1, 2020, Article 71. https://doi.org/10.1007/s42979-020-0074-0.
15.
GoodfellowI. J.MirzaM.XiaoD.CourvilleA.BengioY.An Empirical Investigation of Catastrophic Forgetting in Gradient-based Neural Networks. arXiv Preprint arXiv:1312.6211, 2013.
TianS.LiL.LiW.RanH.NingX.TiwariP.A Survey on Few-Shot Class-Incremental Learning. Neural Networks, Vol. 169, 2023, pp. 307–324. https://doi.org/10.48550/arXiv.2304.08130.
18.
SomeL.Automatic Image-Based Road Crack Detection Methods. KTH Royal Institute of Technology, Stockholm, 2016.
19.
RomeroM.InterianY.SolbergT.ValdesG.Targeted Transfer Learning to Improve Performance in Small Medical Physics Datasets. Medical Physics, Vol. 47, No. 12, 2020, pp. 6246–6256. https://doi.org/10.1002/mp.14507.
20.
PanS. J.YangQ.A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, Vol. 22, No. 10, 2010, pp. 1345–1359. https://doi.org/10.1109/TKDE.2009.191.
21.
ShortenC.KhoshgoftaarT. M.A Survey on Image Data Augmentation for Deep Learning. Journal of Big Data, Vol. 6, 2019, Article 60. https://doi.org/10.1186/s40537-019-0197-0.
22.
SrivastavaN.HintonG. E.KrizhevskyA.SutskeverI.SalakhutdinovR.Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research, Vol. 15, No. 1, 2014, pp. 1929–1958.
23.
TibshiraniR.Regression Shrinkage and Selection via the Lasso. Journal of the Royal Statistical Society: Series B (Methodological), Vol. 58, No. 1, 1996, pp. 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x.
24.
SelvarajuR. R.CogswellM.DasA.VedantamR.ParikhD.BatraD.Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. International Journal of Computer Vision, Vol. 128, 2020, pp. 336–359. https://doi.org/10.1007/s11263-019-01228-7.
CristianiniN.Shawe-TaylorJ.An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods, 1st ed.Cambridge University Press, UK, 2000.
27.
García-PedrajasN.Ortiz-BoyerD.An Empirical Study of Binary Classifier Fusion Methods for Multiclass Classification. Information Fusion, Vol. 12, No. 2, 2011, pp. 111–130. https://doi.org/10.1016/j.inffus.2010.06.010.
28.
LorenaA.De CarvalhoA.GamaJ.A Review on the Combination of Binary Classifiers in Multiclass Problems. Artificial Intelligence Review, Vol. 19, 2008, Article 19. https://doi.org/10.1007/s10462-009-9114-9.
29.
DietterichT.Ensemble Methods in Machine Learning. In Multiple Classifier Systems (GoosG.HartmanisJ.Van LeeuwenJ., eds.), Springer Berlin, Heidelberg, 2000, pp. 1–15. https://doi.org/10.1007/3-540-45014-9_1.
30.
ChiccoD.JurmanG.The Advantages of the Matthews Correlation Coefficient (MCC) Over F1 Score and Accuracy in Binary Classification Evaluation. BMC Genomics, Vol. 21, 2020, Article 6.
31.
RebuffiS.KolesnikovA.SperlG.LampertC.iCaRL: Incremental Classifier and Representation Learning. arXiv Preprint arXiv:1611.07725, 2017.
