Applications III: Complex Systems Monitoring

Complex application problems, such as reliable monitoring and diagnosis of industrial plants, are likely to present large numbers of features, many of which will be redundant for the task at hand. With the use of FRFS, these extraneous features can be removed. This not only makes resultant rulesets generated from such data much more concise and readable, but can reduce the expense due to the monitoring of redundant features. The monitoring system is applied to water treatment plant data, producing better classification accuracies than those resulting from the full feature set and several other reduction methods.

R. Jensen and Q. Shen. Computational Intelligence and Feature Selection: Rough and Fuzzy Approaches. IEEE Press/Wiley & Sons.