Abstract
We consider the application of several compute-intensive classification techniques to two significant real-world applications: disk drive manufacturing quality control and the prediction of chronic problems in large-scale communication networks. These applications are characterized by very high dimensions, with hundreds of features or tens of thousands of cases. The results of several learning techniques are compared, including linear discriminants, nearest-neighbor methods, decision rules, decision trees, and neural nets. Both applications described in this article are good candidates for rule-based solutions because humans currently resolve these problems, and explanations are critical to determining the causes of faults. While several learning techniques achieved competitive results, machine learning with decision rule inducton was most effective for these applications. It is demonstrated that decision (production) rule induction is practical in high dimensions, providing strong results and insightful explanations.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
C. Stanfill and D. Waltz, “Statistical methods, artificial intelligence, and information retrieval,” inText Based Intelligent Systems Lawrence Erlbaum: Hillsdale, NJ, 1992.
S. Weiss and C. Kulikowski,Computer Systems that Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning, and Expert Systems Morgan Kaufmann: San Mateo, CA, 1991.
B. Ripley, “Statistical aspects of neural networks,” inProceedings of Seminair Europeen de Statistique Chapman and Hall: London, UK, 1992.
M. James,Classification Algorithms John Wiley & Sons: New York, 1985.
R.O. Duda and P.E. Hart,Pattern Classification and Scene Analysis John Wiley & Sons: New York, 1973.
J.L. McClelland and D.E. Rumelhart,Explorations in Parallel Distributed Processing MIT Press: Cambridge, MA, 1989.
L. Breiman, J. Friedman, R. Olshen, and C. Stone,Classification and Regression Trees Wadsworth: Belmont, CA, 1984.
P. Clark and T. Niblett, “The CN2 induction algorithm,”Machine Learning vol. 3, pp. 26–283, 1989.
R. Michalski, I. Mozetic, J. Hong, and N. Lavrac, “The multi-purpose incremental learning system AQ15 and its testing application to three medical domains,” inProc. AAAI-86, San Mateo, CA, 1986, pp. 1041–1045.
G. Pagallo, “Learning DNF by decision trees,” inProc. IJCAI-89, San Mateo, CA, 1989, pp. 639–644.
J. Quinlan, “Generating production rules from decision trees,” inProc. IJCAI-87, San Mateo, CA, 1987, pp. 304–307.
S. Weiss and N. Indurkhya, “Reduced complexity rule induction,” inProc. IJCAI-91, San Mateo, CA, 1991, pp. 678–684.
R. Galen and S. Gambino,Beyond Normality: The Predictive Value and Efficiency of Medical Diagnoses John Wiley & Sons: New York, 1975.
R. Sasisekharan, Y-K. Hsu, and D. Simen, “Scout: An approach to automate diagnoses of faults in large scale networks,” inProc. of IEEE GLOBECOM '93, 1993, pp. 212–216.
T. Anand and G. Kahn, “SPOTLIGHT: A data explanation system,” inProc. Eighth IEEE CAIA, Piscataway, NJ, 1992, pp. 2–8.
P.J. Hayes, P.M. Andersen, I.B. Nirenburg, and L.M. Schmandt, “TCS: A shell for content-based text categorization,” inProc. Sixth IEEE CAIA, 1990, pp. 320–326.
Author information
Authors and Affiliations
Additional information
This research was performed while the author was a visiting researcher at IBM T.J. Watson Research Center and AT&T Bell Labs.
Rights and permissions
About this article
Cite this article
Apté, C., Sasisekharan, R., Seshadri, V. et al. Case studies in high-dimensional classification. Appl Intell 4, 269–281 (1994). https://doi.org/10.1007/BF00872093
Issue Date:
DOI: https://doi.org/10.1007/BF00872093