Quantitative Discovery and Reasoning about Failure Mechanisms in Pavement

  • Nayel El-Shafei
Conference paper


This paper describes a hybrid system for quantitative discovery and its related qualitative reasoning. The system HOTEP, is currently under development at MIT. The application area is the Failure Mechanisms in Pavement. The separate areas of Quantitative Discovery, Qualitative Reasoning, and Explanation-based generalization have been investigated by other researchers, but no attempt has been made to hybridize all of them together into a robust discovery system. Faced by a real need for knowledge in the evolving domain of the Failure mechanisms in pavement, we found an incentive to pursue the research in this direction. The paper emphasizes the importance of integrating mathematical induction tools with symbolic techniques to develop better understanding of the new field. Beside the discovery activities, the system is capable of handling competing theories. The quantitative discovery system in HOTEP has been implemented already, and it was tested in several areas. We propose harvesting knowledge bases from the sites so we can combine experience, then broadcast said synthesis back to the sites.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Brachman, R.J., Fikes, R.E.& Levesque, H.J. KRYPTON: A Functional Approach to Knowledge Representation, pages 67–73. IEEE, October, 1983.Google Scholar
  2. Doyle, Richard. Hypothesizing and Refining Causal Models. Technical Report AIM 811, Massachusetts Institute Technology, December 1984.Google Scholar
  3. El-Shafei, Nayel S. Utilzing Quantitative Discovery in Qualitative Reasoning about Failure Mechanisms in Pavement. Master’s thesis, Massachusetts Institute Technology, 1985.Google Scholar
  4. Falkenhainer, Brian. ABACUS —Adding Domain Constraints to quantitative Scientific Discovery. Technical Report UIUC-DCS-F-84–1195 (1SG 84–7), University of Illinois, Urbana-Champaign, 1984.Google Scholar
  5. Findakly, Hani K. Stochastic Approach to the analysis of highway pavements. Master’s thesis, Massachusetts Institute Of Technology, 1971.Google Scholar
  6. Forbus, Kenneth. Qualitative Process Theory. Technical Report AI-TR-789, Massachusetts Institute Technology, AI Lab, July 1984.Google Scholar
  7. Golabi, Kamal, Kulkarni, N. Statistical State Transition in Pavement Management Systems. ASCE Interfaces, 1983, 1983, 30–55.Google Scholar
  8. Holland, John. Escaping Brittleness: The possibility of General Purpose Learning Algorithms applied to parallel rule-based systems. Technical Report 111, University of Michigan, 1984. A discussion of the problem of Credit Assignment.Google Scholar
  9. Langley, P. & Simon, H. The Search for Regularity: Four Aspects of Scientific Discovery. Technical Report CMU-RI-TR-84–20, Carnegie-Mellon University, 1984.Google Scholar
  10. Markow, M. & Brademeyer, B. EAROMAR-II, Technical Report. Technical Report FHWA/RD-82/086, FHWA, 1984.Google Scholar
  11. Michalski,Ryszard, A Theory and Methodology for Inductive Learning. In Michalski, R. et al. (Ed.), Machine Learning, Palo Alto,CA: Tioga Pub., 1984.Google Scholar
  12. Minsky,Marvin, A Framework for representing knowledge. In Winston,Patrick (Ed.), The Psychology of Computer Vision, New York: McGraw Hill Book Co., 1975.Google Scholar
  13. Minsky, Marvin. Society of Mind Cambridge,MA: Simon and Schuster, 1986.Google Scholar
  14. Mitchell, T., Keller, R., & Kedar-Cabelli, S. Explanation-Based Generalization, A Unifying View. Technical Report ML-TR-2, Lab for C.S.Research/The State Univ.of N.J.,Rutgers, August 1985.Google Scholar
  15. Moavenzadeh, F. & Brademeyer, B. A Stochastic Model for Pavement Performance and Management. Fourth International Conference on the structural design of Asphalt Pavements, Ann Arbor, MI, 1977.Google Scholar
  16. Mooney,Raymond & DeJong, Gerald. I earning Schemata for Natural Language Processing, pages 681–687. IJCAI, Los Angeles,CA, 1985.Google Scholar
  17. Pople, H.Jr. Heuristic methods for imposing structure on ill-structured problems:The structuring of Medical Diagnosis. In P. Szolovits (Ed.), Artificial Intelligence in Medicine. AAAS, 1979. The idea of Synthesized Links of Generalization as a vehicle for Polymorphism is proposed as a remedy.Google Scholar
  18. Rich, Charles. The Layered Architecture of a System for Reasoning about Programs. IJCAI, Los Angclcs,CA, 1985.Google Scholar
  19. Smillie, K.W. An Introduction to Regression and Correlation. London, U.K.: Academic Press, 1966.Google Scholar
  20. Taylor, E.S. Dimensional Analysis for Engineers. Oxford, U.K.:Clarendon Press, 1974.Google Scholar
  21. Williams,Brian C. Qualitative Analysis of MOS Circuits. Technical Report AI-TR-767, Massachusetts Institute Technology, AI Lab, July 1984.Google Scholar
  22. Yang, Nai. Design of Functional Pavements. New York:McGraw Hill, 1972.Google Scholar
  23. Yoder, E. & Witczak M. Principles of Pavement Design. New York:John Wiley Inc..,, 1975.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1986

Authors and Affiliations

  • Nayel El-Shafei
    • 1
  1. 1.MIT Artificial Intelligence LaboratoryCambridgeUSA

Personalised recommendations