Acoustic transient identification using neural networks

Thomas Lee Hemminger

Research output: Chapter in Book/Report/Conference proceedingConference contribution


This paper describes a transient classification paradigm based on adaptive pattern recognition, employing neural networks and the Hausdorff metric. Self-organization is used to provide generalization and rapid throughput while utilizing supervised learning for decision making. The overall approach is to temporally partition acoustic transient signals and study their trajectories through power spectral density space. This method has exhibited encouraging results when applied to a set of acoustic transient signals acquired from recordings of industrial machinery.

Original languageEnglish (US)
Title of host publicationIntelligent Engineering Systems Through Artificial Neural Networks
EditorsC.H. Dagli, L.I. Burke, B.R. Fernandez, J. Ghosh
Number of pages6
StatePublished - 1993
EventProceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93 - St.Louis, MO, USA
Duration: Nov 14 1993Nov 17 1993


OtherProceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93
CitySt.Louis, MO, USA

All Science Journal Classification (ASJC) codes

  • Software


Dive into the research topics of 'Acoustic transient identification using neural networks'. Together they form a unique fingerprint.

Cite this