Empirical validation of the performance of a class of transient detector

P. J. Jacob, A. D. Ball

Research output: Contribution to journalArticlepeer-review


Transient detection in the presence of noise is a problem which occurs in many areas of engineering. A desription is given of a classifier system suitable for the identification of high frequency waveforms. It uses the Wavelet Transform for signal pre-processing and a forward feature selection algorithm. A Radial Basis Function neural network is employed to model the class conditional probability density function. A short review of statistical pattern recognition is presented. The classifier is applied to the identification of a number of difficult to classify, high frequency Acoustic Emission signals.

Original languageEnglish
JournalIEE Colloquium (Digest)
Issue number261
Publication statusPublished - 1 Dec 1996
Externally publishedYes
EventIEE Colloquium on Intelligent Sensors - Leicester, United Kingdom
Duration: 19 Sep 199619 Sep 1996


Dive into the research topics of 'Empirical validation of the performance of a class of transient detector'. Together they form a unique fingerprint.

Cite this