Non-stationary signal classification using the joint moments of time-frequency distributions

We present a time-frequency based non-stationary time-series classification method which utilizes features derived from the joint moments of time-frequency distributions (TFDs). The method is applied to both synthetic and real signals, with comparison to classification performance utilizing features derived from temporal moments only and spectral moments only. The results show that a classification algorithm which utilizes joint time-frequency information, as quantified by the joint moments of the TFD, can improve performance over time or frequency-based features alone, for classification of non-stationary time series.

[1]  Patrick J. Loughlin,et al.  Time-frequency-based classification , 1996, Optics & Photonics.

[2]  M S Redfern,et al.  Time-varying characteristics of visually induced postural sway. , 1996, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[3]  Gary D. Bernard,et al.  The Applicability of Time-Frequency Analysis to Machine- and Process-Monitoring , 1997 .

[4]  K JainAnil,et al.  Small Sample Size Effects in Statistical Pattern Recognition , 1991 .

[5]  Patrick J. Loughlin,et al.  Time-scale energy density functions , 1996, IEEE Trans. Signal Process..

[6]  Ben Pinkowski.  Principal component analysis of speech spectrogram images , 1997, Pattern Recognit..

[7]  B. Hannaford,et al.  Approximating time-frequency density functions via optimal combinations of spectrograms , 1994, IEEE Signal Processing Letters.

[8]  Richard J. Prokop,et al.  A survey of moment-based techniques for unoccluded object representation and recognition , 1992, CVGIP Graph. Model. Image Process..

[9]  C. H. Chen.  Recognition of underwater transient patterns , 1985, Pattern Recognit..

[10]  L. Atlas,et al.  Automatic feature-finding for time-frequency distributions , 1996, Proceedings of Third International Symposium on Time-Frequency and Time-Scale Analysis (TFTS-96).

[11]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[12]  Tzay Y. Young,et al.  Classification, Estimation and Pattern Recognition , 1974 .

[13]  Patrick J. Loughlin,et al.  What are the joint time-frequency moments of a signal? , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.