Combining Data Mining Technique and Group Method of Data Handling (GMDH) Method to Assess Flexible Pavement Conditions

Abstract:

The pavement condition index (PCI), a numerical rating from 0 to 100, gives a good indication of the pavement condition. However, the pavement distress survey is a labor-intensive procedure which is performed quite subjectively by experienced pavement engineers. Then, a highly complicated calculation is required to determine the PCI of a road network. It is advantageous to determine the PCI from relevant pavement parameters. This study demonstrates how to develop a PCI assessment model based on pavement parameters by combining data mining technique and group method of data handling (GMDH) method. Records from provincial and county roads with asphalt surface and wide variety of pavement structure in Taiwan were employed. After conducting the find dependencies (FD) algorithm in data mining techniques, 120 dependent records were extracted from 253 raw records. For the PCI model development, 100 records were randomly selected as the training dataset. GMDH was successfully applied to develop a PCI assessment model that uses 7 critical pavement parameters and PCI as inputs and output, respectively. The R² for the training dataset is 0.849. The rest of 20 records were utilized as the testing dataset, which has 0.851 of R² based on the PCI assessment model. This study confirms that combining data mining technique and GMDH method has the potential to provide significant assistance in pavement condition assessment. The model proposed in this study provides a good foundation for further refinement when additional data is available.

• Periodical: Advanced Materials Research (Volumes 255-260)
• Pages: 4242-4246
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.255-260.4242
• Online since: May 2011
• Authors: Hui Mi Hsu, Sao Jeng Chao, Jia Ruey Chang
• Keywords: Data Mining (DM), Find Dependencies (FD), Flexible Pavement, Group Method of Data Handling (GMDH), Pavement Condition Index (PCI), Pavement Distress Survey

References

[1] M.Y. Shahin: Pavement Management for Airports, Roads, and Parking Lots, Second Edition, Springer, New York (2005).

[2] K.A. Abaza, S.A. Ashur and I.A. Al-Khatib: Integrated Pavement Management System with a Markovian Prediction Model, Journal of Transportation Engineering, ASCE, Vol. 130, No. 1 (2004), pp.24-33.

DOI: 10.1061/(asce)0733-947x(2004)130:1(24)

[3] ASTM D 6433: Standard Practice for Roads and Parking Lots Pavement Condition Index Surveys (1999).

DOI: 10.1520/d6433-23

[4] W.R. Hudson, F.N. Finn, R.D. Pedigo and F.L. Roberts: Relating Pavement Distress to Serviceability and Performance, Report No. FHWA-RD-80-098, Washington: Federal Highway Administration, D.C. (1980).

[5] I. Ishai, M. Herrin and D.G. Leveren: Analysis of Failure Modes and Related Required Properties in Asphalt-Treated Cold Mix Bases, Association of Asphalt Pavement Technology, Vol. 44, pp.519-536 (1975).

[6] Development of a Pavement Condition Index for Roads and Streets, Transportation Research Information Service (TRIS) Online Record, Research and Innovative Technology Administration (RITA), U.S. Department of Transportation (DOT), Retrieved from http: /ntlsearch. bts. gov/repository/record/tris/00183146. html.

[7] G.D. Cline, M.Y. Shahin and J.A. Burkhalter: Automated Pavement Condition Index Survey, 2002 FWD Users Group Presentations, Roanoke, Virginia, U.S. (2002).

[8] H.R. Madala and A.G. Ivakhnenko: Inductive learning algorithms for complex systems modeling, CRC Press Inc., Tokyo (1994).

[9] X. Wang, L. Li, D. Lockington, D. Pullar and D.S. Jeng: Self-organizing polynomial neural network for modelling complex hydrological processes, Research Report No R861, Department of Civil Engineering, The University of Sydney, Australia (2005).

[10] A.G. Ivakheneko and G.A. Ivakheneko: The review of problems solvable by algorithms of the GMDH, Pattern Recognition and Image Analysis, Vol. 5, No. 4 (1995), pp.527-535.

[11] F.R. Bennett, P. Crew and J.K. Muller: A GMDH approach to modelling gibbsite solubility in Bayer process liquors, International Journal of Molecular Sciences, Vol. 5 (2004), pp.101-109.

DOI: 10.3390/i5030101

[12] Megaputer Intelligence, Inc. PolyAnalyst 6, Retrieved on December 20, 2010 from http: /www. megaputer. com/polyanalyst. php.

[13] Ward Systems Group, Inc., NeuroShell 2 (Release 4. 2), Retrieved on December 25, 2010 from http: /www. wardsystems. com.