Skip to main content
Springer Nature Link
Log in

Extracting knowledge from examples: Induction of heuristic rules for wheelchair prescription

  • Published:
Journal of Intelligent and Robotic Systems Aims and scope Submit manuscript

Abstract

The feasibility of using an induction algorithm to discover heuristic rules for wheelchair equipment selection is investigated. Syntactical rules for two description languages (one to describe the disabled client and another to describe wheelchair equipment configurations) are presented. These languages allow the rulebase developer to describe training instances (examples) to the computer in an intelligible way. An induction learning algorithm is used to classify these training instances, thereby producing a decision tree. Heuristic rules can then be extracted from the tree and placed in a rulebase for an expert system called LEADER. LEADER is being developed to aid a wheelchair prescriber in the equipment selection process. There are two important objectives of this research: (1) to reduce the time and facilitate the development of an intelligent expert system rulebase by extracting knowledge embedded within existing examples and (2) to provide the expert system with the ability to learn new rules autonomously. The ability to learn makes the rulebase dynamic; the initial rulebase would be augmented with new rules as additional examples are provided to the system while it is in clinical use.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Bertrand, K. V., Napper, S. A., and Ezell, P. M.: An expert system to aid in the prescription of electronic augmentative communication devices, inProc. 11th Annual Internat. Conf. IEEE Engineering in Medicine and Biology Society, Vol. 6, IEEE, New York, NY, 1989, pp. 1861–1862.

    Google Scholar 

  2. Cios, K. J. and Liu, N.: A machine learning method for generation of a neutral network architecture: a continuous ID3 algorithm,IEEE Trans. Neural Networks 3(2) (1992), 280.

    Google Scholar 

  3. Durkin, J.: Induction via ID3,AI Expert 7(4) (1992), 48.

    Google Scholar 

  4. Hodges, J. E., Cordova, J. L., Graves, W. H., and Talor, C. R.: An expert system for the recommendation of visual aids,J. Intelligent Robotic Systems 4 (1991), 99–107.

    Google Scholar 

  5. Kondraske, G.: Rehabilitation engineering: towards a systematic process,IEEE Eng. Med. Biol. Magazine 10 (1988), 11–15.

    Google Scholar 

  6. Lee, K., Thomas, D., Balfour, L., and Parnes, P.: An assessment protocol for the selection of access systems for persons with physical disabilities, inProc. Internat. Conf. Assoc. Advancement of Rehabilitation Technol, RESNA Press, Washington DC, 1988, pp. 6–7.

    Google Scholar 

  7. Liang, T. P., Chandler, J. S. and Han, I.: An empirical investigation of some data effects on the classification accuracy of probit, ID3 and neural networks,Contemporary Accounting Research:J. Can. Acad. Accounting Ass. 9(1) (1992), 306.

    Google Scholar 

  8. McFarland, S. R.: Seeking information about wheelchair evaluation: a call for action,J. Rehabilitation Res. Develop. Clin. Suppl. No. 2, Choosing a Wheelchair System (1990), 86–87.

  9. McLaurin, C. A.: Current directions in wheelchair research,J. Rehabilitation Res. Develop. Clin. Suppl. No. 2, Choosing a Wheelchair System (1990), 88–99.

  10. Phillips, L. and Nicosia, A.: An overview of wheelchair selection with reflections past and present of a consumer,J. Rehabilitation Res. Develop. Clin. Suppl. No. 2, Choosing a Wheelchair System (1990), 1–2.

  11. Quinlan, J. R.: Induction of decision trees,Machine Learning 1 (1986), 81–106.

    Google Scholar 

  12. Quinlan, J. R.:C4.5 Programs for Machine Learning, Morgan Kaufmann, San Mateo, CA, 1993.

    Google Scholar 

  13. Voland, G. and Callahan, S. M.: Effective wheelchair prescription via a computerized intelligent advising system, Internal Report, Department of Industrial Engineering and Information Systems, Northeastern University Boston, MA (1993).

    Google Scholar 

  14. Wheeler, J. C., Koppa, R., McDermott, M., Ellis, N. and Huchington, R. D.: A knowledge based system to suggest adaptive equipment for disabled drivers, inProc. 11th Ann. Int. Conf. IEEE Eng. Med. Biol. Soc. Vol. 6, IEEE, New York, NY, 1989, pp. 1861–1862.

    Google Scholar 

  15. Wilson, Jr, A. B. and McFarland, S. R.:Wheelchairs:A Prescription Guide, Rehabilitation Press, Charlottesville, VA, 1986.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Industrial Engineering, and Information Systems, Northeastern University, Boston, MA, USA

    Sean M. Callahan & Gerard Voland

Authors
  1. Sean M. Callahan
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Gerard Voland
    View author publications

    You can also search for this author inPubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Callahan, S.M., Voland, G. Extracting knowledge from examples: Induction of heuristic rules for wheelchair prescription. J Intell Robot Syst 14, 133–153 (1995). https://doi.org/10.1007/BF01559609

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01559609

Key words