Abstract
We have developed an expert system for interpretation of passive sonar images. A key component of the system is a group of event detection rules whose conditions consist of tests against thresholds. Due to the complexity, variability and clumpiness (i.e., tendency towards highly nonuniform distribution) of the data, tuning these thresholds for good performance under all conditions is a difficult task. We have implemented a procedure for learning rule thresholds whereby the detection capability of each rule continually improves as more and more data is played through the system. The learning procedure contains the following components: 1) a windowing mechanism that adds exceptions (i.e., false alarms and missed detections) into a training database of positive and negative examples and 2) a genetic algorithm to optimize the thresholds with respect to the training database. The genetic training algorithm allows the developer to explicitly choose an operating point on the Receiver Operating Characteristic (ROC) curve of a rule. Experiments have verified 1) the superiority of this automated approach to selecting rule thresholds over manual techniques and 2) the improvement of rule performance with experience.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Breiman, L., Friedman, J., Olshen, R., & Stone, C. (1984). Classification and regression trees. Monterey, CA: Wadsworth.
Davis, L. (1989). Adapting operator probabilities in genetic algorithms. Proceedings of the Third International Conference on Genetic Algorithms (pp. 61–69). San Mateo, CA: Morgan Kaufmann.
Goldberg, D. (1988). Genetic algorithms in search, optimization, and machine learning. Reading, MA: Addison-Wesley.
Gorman, R. & Sejnowski, T. (1988). Analysis of hidden units in a neural network trained to classify sonar targets. Neural Networks, Vol. 1, 75–89.
Marr, D. (1982). Vision. New York: W.H. Freeman and Company.
Michalski, R., Mozetic, I., Hong, J., & Lavrac, N. (1986). The multi-purpose incremental learning system AQ15 and its testing application to three medical domains. Proceedings of the Fifth National Conference on Artificial Intelligence (pp. 1041–1045).
Montana, D. & Davis, L. (1989). Training feedforward neural networks using genetic algorithms. Proceedings of the Eleventh International Joint Conference on Artificial Intelligence (pp. 762–767). San Mateo, CA: Morgan Kaufmann.
Montana, D. (in press). Automated parameter tuning for synthetic image interpretation. In. L. Davis (Ed.), The genetic algorithms handbook.
Nii, H.P., et al. (1982). Signal-to-symbol-transformation: HASP/SIAP case study. AI Magazine, 3, 23–35.
Quinlan, J.R. (1979). Discovering rules by induction from large numbers of examples: a case study. In D. Mitchie (Ed.), Expert systems in the micro-electronic age. Edinburgh University Press.
Quinlan, J.R. (1987). Generating production rules from decision trees. Proceedings of the Tenth International Conference on Artificial Intelligence (pp. 304–307).
Richardson, J., Palmer, M., Liepins, G., & Hilliard, M. (1989). Some guidelines for genetic algorithms with penalty functions. Proceedings of the Third International Conference on Genetic Algorithms (pp. 191–197). San Mateo, CA: Morgan Kaufmann.
Rosenblatt, R. (1959). Principles of neurodynamics. New York: Spartan Books.
Rumelhart, D., Hinton, G., & Williams, R. (1986). Learning representations by backpropagating errors. Nature, 323, 533–536.
Schlimmer, J., & Granger, R. (1986). A case study of incremental concept induction. Proceedings of the Fifth National Conference on Artificial Intelligence (pp. 502–507).
Shapiro, A. (1987). Structured induction in expert systems. Maidenhead, U.K.: Addison-Wesley.
Syswerda, G. (1989). Uniform crossover in genetic algorithms. Proceedings of the Third International Conference on Genetic Algorithms (pp. 2–9). San Mateo, CA: Morgan Kaufmann.
Wirth, J. & Catlett, J. (1988). Experiments on the costs and benefits of windowing in ID3. Proceedings of the Fifth International Conference on Machine Learning (pp. 87–99). San Mateo, CA: Morgan Kaufmann.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Montana, D.J. Empirical learning using rule threshold optimization for detection of events in synthetic images. Mach Learn 5, 427–450 (1990). https://doi.org/10.1007/BF00116879
Issue Date:
DOI: https://doi.org/10.1007/BF00116879