Method and an apparatus for the identification and/or separation of complex composite signals into its deterministic and noisy components

• US 6,208,951 B1
• Filed: 11/09/1998
• Issued: 03/27/2001
• Est. Priority Date: 05/15/1998
• Status: Expired due to Term

• Current Assignee: Hanger Solutions, LLC (IP Investments Group LLC)
• Original Assignee: Council of Scientific & Industrial Research
• Inventors: Vaish, Nitin, Dixit, Narendra Madhukar, Kulkarni, Bhaskar Dattatraya, Kumar, Viruthiamparambath Ravi
• Primary Examiner(s): Hoff, Marc S.
• Assistant Examiner(s): Barbee, Manuel L.
• Application Number:
  US09/186,062
• Time in Patent Office: 869 Days
• Field of Search: 702/32, 702/57, 702/66, 702/67-79, 702/124, 702/126, 702/179, 702/180, 702/190, 702/191, 702/194-198, 702/FOR.103, 702/104, 702/107-110, 702/FOR.164, 702/166, 702/168, 702/170, 702/171
• US Class Current: 702/191
• CPC Class Codes: G06T 2207/20064 Wavelet transform [DWT]
• CPC Class Codes: G06T 5/10 using non-spatial domain filtering
• CPC Class Codes: G06T 5/70 Denoising; Smoothing

Abstract

A process for the identification and/or separation of composite signal into its deterministic and noisy components wherein the process uses recursive wavelet transformations to separate the deterministic and noisy components of signals and uses the difference in the properties with regard to degree of correlation and dimensionality of these constituent components as a basis for separation, the said process of identification and/or separation has application in a variety of situations where digitized data is made available via an apparatus which converts the monitored signals.

Claims

1. A method for the identification and/or separation of composite signals obtained from an apparatus/equipment recording the variations in a system property as sequential or time-series data, from the said apparatus/equipment, into its deterministic(true signal) and noisy parts, comprising the steps of:

(a) obtaining a signal to be identified and/or separated from an apparatus/equipment;

(b) digitizing the said composite signal, obtained as sequential or time-series data, relating to a variation in a system property;

(c) computing and subjecting the said digitized data obtained from step (b) above to wavelet transform to obtain a scalogram in terms of wavelet coefficients;

(d) computing and organizing the said resulting wavelet coefficients in each of the scales to form new sets of data;

(e) computing for taking each of the above said data sets and carry out their wavelet transform to obtain another scalogram in terms of wavelet coefficients;

(f) computing for implementing steps (d) and (e), recursively with testing for the constancy in the power distribution, (the said power distribution being the ratio of the power in a particular scale with respect to the total power in all the scales of that scalogram for two consecutive recursive scalograms) and thereby identifying the recursive wavelet scales contributing to noise in the signal;

(g) eliminating the above said wavelet coefficients in the recursive wavelet scales contributing to noise by setting term to zero; and

(h) inverting the above said wavelet coefficients by inverse recursive wavelet transformation and thereby determining the deterministic signal component (true signal) separated from the noise component.

2. A method as claimed in claim 1 wherein the source of the signal obtained in step (a) is from suitable sensors appropriately located in the apparatus/equipment.

3. A method as claimed in claim 1 wherein the step of wavelet identification and/or separation of composite signals is used for discrete, biorthogonal, and continuous wavelet.

4. A method as claimed in claim 1, wherein the wavelet types used are selected from the type s Haar, Morlet, Mexican Hat, biorthogonal spline, Daubechies, Malvar, Lemarie, Coiflet, Meyer, and Symlet.

5. A method as claimed in claim 1 wherein the source for obtaining sequential or time-series data is selected from medical diagnostic and scanning equipment, seismographic instruments, tomography, image analyzers, molecular spectroscopy and chemical reactors.

6. A method as claimed in claim 1 wherein the source for obtaining sequential or time-series data is selected from deterministic systems exhibiting chaotic dynamics.

7. A method as claimed in claim 1 wherein means for hard and soft thresholding of the wavelet coefficients at various scales is not required because of recursive wavelet transformation.

8. A method as claimed in claim 1 wherein digitized deterministic signal components are converted to analog signals using a digital analog converter.

9. A method as claimed in claim 1 wherein the analog signal are converted to yield digitized numbers by feeding them into a programmed device for a general purpose digital computer, with a storage medium.

10. A method as claimed in claim 1 wherein the identification and/or separation of composite signals is done by dividing the signal into a number of sub-interval signals and applying recursive wavelet transformation to each subinterval signal.

11. A method as claimed in claim 1 for identification and/or separation of composite signals obtained from an instrument/equipment recording the variations in a system property as sequential or time-series data from the said instrument/equipment'"'"'s (selected from medical diagnostic and scanning equipment, seismographic instruments, tomography, image analyzers, molecular spectroscopy, chemical reactors/reactions), into its deterministic (true signal) and noisy parts.

12. An apparatus for identification and/or separation of composite signals obtained from an instrument/equipment recording the variations in a system property as sequential or time-series data from the said instrument/equipment (selected from medical diagnostic and scanning equipment, seismographic instruments, tomography, image analyzers, molecular spectroscopy, chemical reactors/reactions), into its deterministic (true signal) and noisy parts, said apparatus comprising:

(a) source means for obtaining a signal to be identified and/or separated from suitable sensors appropriately located in an apparatus/equipment;

(b) means for digitizing the said composite signal, obtained as sequential or time-series data, relating to a variation in a system property;

(c) computing means for subjecting the said digitized data obtained from step (b) above to wavelet transform to obtain a scalogram in terms of wavelet coefficients;

(d) computing means for organizing the said resulting wavelet coefficients in each of the scales to form new sets of data;

(e) computing means for taking each of the above said data sets and carry out their wavelet transform to obtain another scalogram in terms of wavelet coefficients;

(f) computing means for implementing steps (d) and (e), recursively with testing for the constancy in the power distribution (the said power distribution being the ratio of the power in a particular scale with respect to the total power in all the scales of that scalogram for two consecutive recursive scalograms) and thereby identifying the recursive wavelet scales contributing to noise in the signal;

(g) computing means for eliminating the above said wavelet coefficients in the recursive wavelet scales contributing to noise by setting terms to zero; and

(h) computing means for inverting the above said wavelet coefficients by inverse recursive wavelet transformation and thereby determining the deterministic signal component (true signal) separated from the noise component.

13. An apparatus as claimed in claim 12, wherein the apparatus employs one or more of discrete, biorthogonal, and continuous wavelets to identify and/or separate a composite signal.

14. An apparatus as claimed in claim 12 wherein wavelet types used are selected from types Haar, Morlet, Mexican hat, biorthogonal spline, Daubechies, Malvar, Lemarie, Coiflet, Meyer, or Symlet, preferably Haar.

15. An apparatus as claimed in claim 12 wherein the source for obtaining sequential or time-series data is selected from medical diagnostic and scanning equipment, seismographic instruments, tomography, image analyzers, molecular spectroscopy and chemical reactors.

16. An apparatus as claimed in claim 12 wherein the source for obtaining sequential or time-series data is selected from deterministic systems exhibiting chaotic dynamics.

17. An apparatus as claimed in claim 12 wherein means for hard and soft thresholding of the wavelet coefficients at various scales is not required because of recursive wavelet transformation.

18. An apparatus as claimed in claim 12 wherein digitized deterministic signal components are converted to analog signals using digital analog converter.

19. An apparatus as claimed in claim 12 wherein the converting means employed is a digital to analog converter.

20. An apparatus as claimed in claim 12, wherein the computing means employed is a device or a programmed general purpose digital computer, provided with a storage medium.

21. An apparatus as claimed in claim 12, wherein the digitized deterministic signal component is converted to an analog signal using a D to A converter.

22. A method for separating a sampled composite signal into its true and noisy components, the method comprising the steps of:

(a) performing a first wavelet transform to obtain a scalogram in terms of a first set of wavelet coefficients;

(b) organizing the first set of wavelets coefficients at different scales to form new sets of data;

(c) computing a second wavelet transform on each of the new sets of data to form another scalogram comprising a second set of wavelet coefficients

(d) repeating steps (b) and (c) recursively while testing for constancy in a distribution of power among the scales to thereby identify at least one wavelet scale which contributes to the noisy component;

(e) setting, to zero, the at least one wavelet scale which contributes to the noisy component; and

(f) inverting the wavelet coefficients after the at least one wavelet scale has been set to zero.

23. The method according to claim 22, wherein the wavelets used are either discrete, biorthogonal or continuous.

24. The method according to claim 22, wherein the wavelets used are selected from the group consisting of Haar, Morlet, Mexican Hat, biorthogonal spline, Daubechies, Malvar, Lemarie, Coiflet, Meyer and Symlet.

25. The method according to claim 22, wherein the composite signal is first divided into a number of sub-interval signals, with each of the sub-interval signals being subjected to steps (a)-(f).

26. The method according to claim 22, wherein constancy in the distribution of power is determined by taking the ratio of the power in a particular scale to the total power in all the scales of that scalogram for two consecutive recursive scalograms.