论文信息 - PATTERN RECOGNITION SYSTEM FOR AUTOMATIC IDENTIFICATION OF ACOUSTIC SOURCES

PATTERN RECOGNITION SYSTEM FOR AUTOMATIC IDENTIFICATION OF ACOUSTIC SOURCES

An intelligent recognition system was designed using pattern recognition techniques to distinguish the noise signatures of five different types of acoustic sources. Information for classification was calculated from the power spectral density and autocorrelation taken from the output of a single microphone. The system included a training step where it learned to distinguish the sources and automatically select descriptive quantities for optimal classification performance. Information learned in training was stored and used to identify recordings of the five types of sources presented during testing. Results of testing indicate that the current optimal design could correctly identify 90% of the recordings. Identification of noise corrupted signatures and identification of recordings not used in training is discussed.

R. H. Cabell | C. R. Fuller

[1] Julius T. Tou,et al. Pattern Recognition Principles , 1974 .

[2] D. W. Thomas,et al. Vehicle Sounds and Recognition , 1978 .

[3] H. Bremermann. What Mathematics Can and Cannot Do for Pattern Recognition , 1971 .

[4] Jorge I. Aunon,et al. Classification and Detection of Single Evoked Brain Potentials Using Time-Frequency Amplitude Features , 1986, IEEE Transactions on Biomedical Engineering.

[5] Ashok K. Goel,et al. From numbers to symbols to knowledge structures: artificial intelligence perspectives on the classification task , 1988, IEEE Trans. Syst. Man Cybern..

[6] Roger W. Y. Chan,et al. A Case Study of Sensitivity of Some Pattern Classifiers Used in Sorting Acoustic Emission Signals , 1982 .

[7] Sing-Tze Bow,et al. Pattern recognition. Applications to large data-set problems , 1984 .

[8] Randolph H. Cabell. The automatic identification of aerospace acoustic sources , 1989 .

[9] Leonard Norton-Wayne,et al. Automatic Identification of Noise Pollution Sources , 1982, IEEE Transactions on Systems, Man, and Cybernetics.

[10] Francis J. Cook,et al. Establishing Signal Processing and Pattern Recognition Techniques for Inflight Discrimination between Crack-Growth Acoustic Emission and Other Acoustic Waveforms , 1982 .