Feature extraction and learning decision rules from ultrasonic signals-applicability in non-destructive testing

[title]:Feature extraction and learning decision rules from ultrasonic signals-applicability in non-destructive testing

[Authors]:Perron;M.-C.

[Subject]:feature extraction;acoustic signal processing;learning decision rules;ultrasonic signals;non-destructive testing;flaw discrimination;decision-tree based algorithm;classification rules;acoustic signal processing;ultrasonic materials testing

[Corporate Source]:Electr. de France;Clamart;France

[Publisher]:Ultrasonics Symposium;1988. Proceedings.;IEEE 1988

[ISSN]:

[ConferenceDate]:2-5 Oct. 1988[Publish Date]:1988[Total Page]:2 vol. 1113[Pdf size]:293K[On Pages]:533_536 vol.1

[From]: School Papers schoolpapers.org

[Download]:Feature extraction and learning decision rules from ultrasonic signals-applicability in non-destructive testing

[Abstract]:The author presents a supervised multiple-concept learning method for generating decision rules from a set of ultrasonic data for defect characterization purposes in nondestructive testing. The first step towards flaw discrimination is to extract relevant information from the collected defect signatures. The large-dimension signal space is mapped into a smaller feature space. The learning set consists of preclassified examples described by a set of continuous attributes measuring the selected features. A decision-tree based algorithm is used to build classification rules able to classify any object from its values of attributes.

[在baidu中查找]:Feature extraction and learning decision rules from ultrasonic signals-applicability in non-destructive testing

[在google中查找]:Feature extraction and learning decision rules from ultrasonic signals-applicability in non-destructive testing

[Up]:Practical ultrasonic spectrometric measurement of solution concentrations by a tracking technique

[Next]:Ultrasonic techniques for measurement of coal slurry viscosity