Optimised Surface Condition Classification of Flexible Road Pavement Using AutoWEKA Model

Year 2020, Volume: 3 Issue: 2, 73 - 89, 28.12.2020

Paul Terkumbur Adeke , Aper Zava Manasseh Tyogo

https://doi.org/10.47137/uujes.791586

Abstract

Abstract
The development of pavement management tools using intelligent algorithms requires a robust form of data mining – data classification for efficient and reliable analysis. The aim of this study is to investigate and optimally classify the surface condition of flexible road pavement along 60 km length of the Zaria – Kaduna Federal Highway in Northern Nigeria for maintenance decision. The study used data mining technique for the classification of pavement surface condition into good, satisfactory, fair, poor, very poor, serious or failed. A field survey was carried out to examine the surface area and length of various surface defects such as cracks, potholes, rutting and edge failure within Chainages measuring 200 meters apart, which was used to compute the Pavement Condition Index (PCI) values and section classification in accordance with procedures stated in ASTM D6433. The AutoWEKA model of Waikato Environment for Knowledge Analysis (WEKA) software was used to optimally classify the surface condition of the highway. Results indicated that 79.67% of the 300 total instances considered by the model were correctly classified while 20.33% of the instances were incorrectly classified. The optimum surface condition classification showed that worse pavement surface conditions of the sampled site were ‘Poor’, ‘Very Poor’ and ‘Failed’ at 77 (32.22%), 51 (21.34%) and 54 (22.59%) instances respectively of the correctly classified 239 instances out of the 300 total instances sampled. Based on its present condition, 76.15% of the road segment was bad. The rehabilitation or reconstruction of the Zaria – Kaduna Federal Highway was therefore recommended for improved condition and optimum performance.

Keywords

Zaria – Kaduna Highway, Data mining, Pavement Surface Condition, Optimization, WEKA Software

References

• [1]. African Development Bank Group. Rail infrastructure in Africa – Financing Policy Options. International d’Abidjan, Abidjan, Côte d'Ivoire. 2015.
• [2]. Adeke, P. T., Atoo, A. A and Joel, E. A Policy Framework for Efficient and Sustainable Road Transport System to Boost Synergy between Urban and Rural Settlements in Developing Countries: A case of Nigeria, 1st International Civil Engineering Conference (ICEC 2018), Department of Civil Engineering, Federal University of Technology, Minna, Nigeria, 2018a.
• [3]. Abiola, O. S., Owolabi, A. O., Odunfa, S. O. and Olusola, A. Investigation into Causes of Premature Failure of Highway Pavements in Nigeria and Remedies. In proceedings of the Nigeria Institution of Civil Engineers (NICE) Conference, Abuja, 2010.
• [4]. Road Sector Development Team. Configuration and Calibration of HDM-4 to Nigeria Conditions, Government of the Federal Republic of Nigeria. Nigeria. 2014. Pp. 33.
• [5]. Dong, S., Zhong, J. Hao, P. Zhang, W., Chen, J., Lei, Y. and Schneider, A. Mining Multiple Association Rules in LTPP Database: An Analysis of Asphalt Pavement Thermal Cracking Distress, Construction and Building Materials, 2018, 191, 837 – 852.
• [6]. Garber, N. J. and Hoel, L. A. Traffic and Highway Engineering, 4th Edition, Cengage Leaning, Canada, 2009.
• [7]. Taylor, M. A. P. and Philip, M. L. Investigating the Impact of Maintenance Regimes on the Design Life of Road Pavements in a Changing Climate and the Implications for Transport Policy. Transport Policy, 2015; 41; 117 – 135.
• [8]. ASTM D6433-07 Standard Practice for Road and Parking Lots Pavement Condition Index Survey, American Standard for Testing and Materials, USA, Philadelphia; 2007.
• [9]. American Association of State Highway and Transportation Officials (AASHTO). AASHTO Guide for the Design of Pavement Structures. Washington, D.C., 1993.
• [10]. Lina, J. D., Huangb, W. H., Hungc, C. T., Chend, C. T. and Leee, J. C. Using Decision tree for Data Mining of Pavement Maintenance and Management, Applied Mechanics and Materials, 2013; 330; 1015 - 1019.
• [11]. Inkoom, S., Sobanjo, J., Barbu, A. and Niu, X. Prediction of the Crack Condition of Highway Pavements using Machine Learning Models, Structure and Infrastructure Engineering, Taylor and Francis, 2019; 1 - 14, DOI: 10.1080/15732479.2019.1581230.
• [12]. Li, Z., Cheng, C., Kwan, M. P., Tong, X. and Tian, S. Identifying Asphalt Pavement Distress Using UAV LiDAR Point Cloud Data and Random Forest Classification, International Journal of Geo-information, 2019; 8 (39); 1 – 26, DOI:10.3390/ijgi8010039.
• [13]. Miradi, M. Knowledge Discovery and Pavement Performance: Intelligent Data Mining, A PhD Thesis submitted to the Section of Road and Railway Engineering, Faculty of Civil Engineering and Geosciences, Delft University of Technology, The Netherlands, 2009. [14]. Yin, H. Integrating Instrumentation Data in Probabilistic Performance Prediction of Flexible Pavement, PhD Thesis in the Department of Civil and Environmental Engineering, Graduate School, The Pennsylvania State University, 2007.
• [15]. Mahmood, M. S. Network-Level Maintenance Decisions for Flexible pavement Using A soft Computing-Based Framework. PhD Thesis, Nottingham Trent University, United Kingdom, 2015.
• [16]. Fwa, T. F. and Shanmugam, R. Fuzzy Logic Technique for Pavement Condition Rating and Maintenance-Needs Assessment, Fourth International Conference on Managing Pavements, May 1998; Durban, South Africa, 1998. p. 465-476.
• [17]. Mahmood, M., Rahman, M., Nolle, L., and Mathavan, S. A Fuzzy Logic Approach for Pavement Section Classification. International Journal of Pavement Research and Technology, Chinese Society of Pavement Engineering, 2013; 6(5); 620 – 626, DOI: 10.6135/ijprt.org.tw/2013.6(5).620.
• [18]. Cheu, R. L., Wang, Y. and Fwa, T. F. Genetic Algorithm-Simulation Methodology for Pavement Maintenance Scheduling. Computer –Aided Civil and Infrastructural Engineering, 2004; 19; 446 – 455.
• [19]. Chassiakos, A. P.. A Fuzzy-based System for Maintenance Planning or Road Pavements. Proceedings of the 10th WSEAS International Conference on Computers, Vouliagmeni, Athens, Greece, 2006; 535 – 540.
• [20]. Liu, Y. and Sun, M. Fuzzy Optimization BP Neural Network Model for Pavement Performance Assessment, In: Grey Systems and Intelligent Services GSIS, IEEE International Conference, Nanjing, China, 2007; p. 1031-1034.
• [21]. Golroo, A. and Tighe, S. L. Fuzzy Set Approach to Condition Assessments of Novel Sustainable Pavements in the Canadian Climate, Canadian Journal of Civil Engineering, 2009; 36, 754-764.
• [22]. Bianchini, A. and Bandini, P. Prediction of Pavement Performance Through Neuro-Fuzzy Reasoning. Computer-aided civil and infrastructure engineering, 2010; 25; 39 – 54.
• [23]. Thube, D. T. Artificial Neural Network (ANN) Based Pavement Deterioration Models for Low Volume Roads in India. International Journal of Pavement Research and Technology, 2011; 5 (2); 115 -120.
• [24]. Setyawan, A., Nainggolan, J. and Budiarto, A. Predicting the Remaining Service Life of Road using Pavement Condition Index, the 5th International Conference of Euro Asia Civil Engineering Forum, 2015.
• [25]. Adeke, P. T., Atoo, A. A. and Orga, S. G.. Assessment of Pavement Condition Index: A Case of Flexible Road Pavements on the University of Agriculture Makurdi Campus. Nigerian Journal of Technology, 2018b; 38 (1); 15 – 21.
• [26]. Dabous, S. A., Zeiada, W., Al-Ruzouq, R., Hamad, K. and Al-Khayyat, G. Distress-Based Evidential Reasoning Method for Pavement Infrastructure Condition Assessment and Rating, International Journal of Pavement Engineering, 2019; 1–12, DOI: 10.1080/10298436.2019.1622012.
• [27]. Premkumar, L. and Vavrik, W. R.. Enhancing Pavement Performance Prediction Models for the Illinois Tollway System, International Journal of Pavement Research and Technology, 2016; 9; 14 – 19. DOI: http://dx.doi.org/10.1016/j.ijprt.2015.12.002.
• [28]. Hamed, R. I. and Kakarash, Z. A. Evaluate the Asphalt Pavement Performance of Rut Depth based on Intelligent Method. International Journal of Engineering and Computer Science, 2016; 5 (1); 15474 – 15481.
• [29]. Surendrakuma, K., Prashant, N. and Mayuresh, P. Application of Markovian probabilistic process to develop a decision support system for Pavement maintenance management. International Journal of Scientific and Technology Research, 2013; 2 (8); 295 – 303.
• [30]. Salpisoth, H. Simple Evaluation Methods for Road Pavement Management in Developing Countries. PhD Thesis - Graduate School of Engineering, Kyoto University, Japan, 2014.
• [31]. Arifuzzaman, M., Gazder, U., Alam, M. S. and Sirin, O. Modelling of asphalt’s Adhesive Behaviour Using Classification and Regression Tree (CART) Analysis. Computational Intelligence and Neuroscience, ID 3183050, Hindawi. https://doi.org/10.1155/2019/3183050, 2019.
• [32]. Huang, Y. H. Pavement Analysis and Design, 2nd Edition, Pearson Prentice Hall, Inc. United State of America, 2004.
• [33]. Saltan, M., Terzi, S. and Kucuksille, E. U. Backcalculation of Pavement Layer Moduli and Poisson’s Ratio Using Data Mining. Expert Systems with Applications, 2011; 38; 2600–2608.
• [34]. Hutter, F., Kotthoff, L. and Vanschoren, J. Automated Machine Learning – Methods, Systems, Challengers, The Springer Series on Challenges in Machine Learning. Springer, Switzerland, 2019.
• [35]. Inkoom, S., Sobanjo, J., Barbu, A. and Niu, X. Prediction of the Crack Condition of Highway Pavements Using Machine Learning Models, Structure and Infrastructure Engineering, 2018, DOI: 10.1080/15732479.2019.1581230.
• [36]. Cox, E. Fuzzy Modelling and Genetic Algorithms for Data Mining and Exploration. Morgan Kaufmann Publishers, San Francisco, 2005.
• [37]. Pawlak, Z.. Rough Sets. International Journal of Computer and Information Sciences. 1982; 11; 341 - 356.
• [38]. Pawlak, Z. "Rough Sets." Rough Sets and Data Mining, T. Y. Lin, Cercone, N., ed., Kluwer Academic Publisher, Dordrecht, 1997.
• [39]. Pawlak, Z. Rough Sets and Intelligent Data Analysis. Information Sciences, 2002; 147, 1 – 12.
• [40]. Witten, I. H., Frank, E. Hall, M. A. and Pal, C. J. The WEKA workbench – Data Mining Practical Machine Learning Tools and Techniques, 4th edition, Morgan Kaufmann, Elsevier, London 2016.
• [41]. Fox, C. Data Science for Transport; Self-Study Guide with Computer Exercises. Springer International Publishing, Switzerland, 2018.
• [42]. Mohd, A., Yuk, Y., Wei-Chang, Y., Noorhaniza, W., and Ahmad, M. Classification Technique using Modified Particle Swarm Optimization. Modern Applied Science, 2011, 5(5); 150–164.
• [43]. Araujo, J. P. C., Palha, C. A. O., Martins, F. F. and Silva, H. M. R. D. Estimation of Energy Consumption on the Tire-pavement Interaction for Asphalt Mixtures with Different Surface Properties using Data Mining Techniques. Transport Research Part D, 2019; 67, 421 – 432.
• [44]. Luca, M. D., Abbondati, F., Pirozzi, M. and Zilioniene, D. Preliminary Study on Runway Pavement Friction Decay using Data Mining. 6th Transport Research Area April 18 – 21, 2016; 14, 3751 – 3760.
• [45]. Sharma, T. C. and Jain, M. WEKA Approach for Comparative Study of Classification Algorithm. International Journal of Advanced Research in Computer and Communication Engineering, 2013; 2 (4); 1925 – 1931.
• [46]. WEKA. Waikato Environment for Knowledge Analysis: User’s Manual, The University of Waikato, New Zealand, 2018.
• [47]. Marianingsih, S. and Utaminingrum, F. Comparison of Support Vector Machine Classifier and Naïve Bayes Classifier on Road Surface Type Classification, 2018. DOI: 978-1-5386-7407-9/18/$31.00.
• [48]. Marianingsih, S., Utaminingrum, F and Bachtiar, F. A. Road Surface Types Classification using Combined of K-Nearest Neighbor and Naïve Bayes based on GLCM, International Journal of Advances in Soft Computing and its Applications, 11 (2), 2019, 15 – 27.
• [49]. Gong, H., Sun, Y., Shu, X. and Huang, B. Use of Random Forest Regression for Predicting IRI of Asphalt Pavements, Construction and Building Materials, 2018, 189, 890 – 897.