Abstract
Neural network based automated signal classification (ASC) systems are being increasingly used to classify data obtained from nondestructive testing of samples. This paper describes an ASC system using the Fuzzy ARTMAP network. Three important issues relevant to ASC systems, namely, incremental learning, confidence or reliability measures, and performance improvement, are studied. A fuzzy logic based algorithm is used to estimate the reliability of the network decision. The reliability of the classification decision is then incorporated into a feedback algorithm to improve the performance of the network. Results on ultrasonic signals obtained from inspection of piping welds in nuclear power plants are presented.
| Original language | English |
|---|---|
| Pages | 65-69 |
| Number of pages | 5 |
| Volume | 58 |
| No | 1 |
| Specialist publication | Materials Evaluation |
| State | Published - Jan 2000 |