Method and apparatus for extracting low SNR transient signals from noise

• US 20040015894A1
• Filed: 09/26/2001
• Published: 01/22/2004
• Est. Priority Date: 12/30/1998
• Status: Active Grant

• Current Assignee: Algodyne Limited
• Original Assignee: Algodyne Limited
• Inventors: Lange, Daniel H.
• Granted Patent: US 6,898,582 B2
• Time in Patent Office: Days
• US Class Current: 717/138
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: G06F 2218/04 Denoising
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

A method and apparatus for processing a composite signal generated by a transient signal generation mechanism to extract a repetitive low SNR transient signal, such as an evoked potential (EP) appearing in an electroencephalogram (EEG) generated in response to sensory stimulation, by: (a) dynamically identifying, via a learning process, the major transient signal types in the composite signal; (b) decomposing the identified major transient signal types into their respective constituent components; (c) synthesizing a parametric model emulating the transient signal generation mechanism; and (d) utilizing the model and the constituent components to identify and extract the low SNR transient signal from the composite signal.

Claims

1. A method of processing a composite signal generated by a transient signal generation mechanism to extract a repetitive, low SNR transient signal from noise therein, comprising the following processes:

(a) dynamically identifying, via a learning process, the major transient signal types in said composite signal;

(b) decomposing the identified major transient signal types into their respective constituent components;

(c) synthesizing a parametric model emulating said transient signal generation mechanism; and

(d) utilizing said model and said constituent components to identify and extract said low SNR transient signal from said composite signal.

2. The method according to claim 1, wherein said process (a) is performed by using an adaptive, competitive neural network.

3. The method according to claim 2, wherein said neural network includes a group of artificial neurons divided into sets of inhibitory clusters in which all neurons within a cluster inhibit all other neurons in the cluster, resulting in a competition among the neurons in a cluster to respond to the major transient signal patterns in the composite signal.

4. The method according to claim 3, wherein said process (a) includes:

(i) initializing network weights;

(ii) selecting one input vector at random;

(iii) calculating all neural outputs in selecting a winner neuron;

(iv) updating the winning neuron weights;

(v) repeating the foregoing steps until a stopping criterion is achieved; and

(vi) displaying the identified signal types.

5. The method according to claim 1, wherein said decomposing process (b) is performed by treating peaks of the composite signal as independent components and analyzing said peaks.

6. The method according to claim 5, wherein said process (b) includes:

(i) initializing search limits;

(ii) calculating peak locations;

(iii) optimising first and second peak moments;

(iv) building a decomposition rule;

(v) executing a decomposition procedure to identify signal types; and

(vi) displaying the identified signal types.

7. The method according to claim 1, wherein the low SNR transient signal is an evoked potential (EP) appearing in an electroencephalogram (EEG) of a living being generated in response to sensory stimulation of the nervous system of the living being.

8. The method according to claim 7, wherein said synthesizing process (c) is performed by modelling the EEG via auto regressive (AR) analysis and modelling the EP as a sum of finite impulse responses (FIR) filtered EP components.

9. The method according to claim 8, wherein said synthesizing process (c) includes:

(i) assigning transition points;

(ii) building an AR model of the pre-stimulus EEG signal;

(iii) whitening the EEG and EP signals;

(iv) identifying the EP by performing a closed form least square solution of the model; and

(v) extracting the EP signal.

10. Apparatus for processing a composite signal generated by a transient signal generation mechanism to extract a repetitive, low SNR transient signal from noise therein, comprising:

(a) means for dynamically identifying, via a learning process, the major transient signal types in said composite signal;

(b) means for decomposing the identified major transient signal types into their respective constituent components;

(c) means for synthesizing a parametric model emulating said transient signal generation mechanism; and

(d) means for utilizing said model and said constituent components to identify and extract said low, SNR transient signal from said composite signal.

11. The apparatus according to claim 10, wherein said identifying means (a) includes an adaptive, competitive neural network.

12. The apparatus according to claim 11, wherein said neural network includes a group of artificial neurons divided into sets of inhibitory clusters in which all neurons within a cluster inhibit all other neurons in the cluster, resulting in a competition among the neurons in a cluster to respond to the major transient signal patterns in the composite signal.

13. The apparatus according to claim 12, wherein said means (a):

(i) initializes network weights;

(ii) selects one input vector at random;

(iii) calculates all neural outputs in selecting a winner neuron;

(iv) updates the winning neuron weights; and

(v) repeats the foregoing steps until a stopping criterion is achieved.

14. The apparatus according to claim 10, wherein said decomposing means (b) operates by treating peaks of the composite signal as independent components and analyzing said peaks;

15. The apparatus according to claim 10, wherein said decomposing means (b):

(i) initializes search limits;

(ii) calculates peak locations;

(iii) optimises first and second peak moments;

(iv) builds a decomposition rule; and

(v) executes a decomposition procedure to identify signal types.

16. The apparatus according to claim 10, wherein the low SNR transient signal is an evoked potential (EP) appearing in an electroencephalogram (EEG) of a living being generated in response to sensory stimulation of the nervous system of the living being, said synthesizing means (c) emulating the mechanism for generating said EP signal.

17. The apparatus according to claim 16, wherein said synthesizing means (c) models the EEG via an AR analysis, and models the EP as a sum of the FIR filtered EP components.

18. The apparatus according to claim 17, wherein said synthesizing means (c):

(i) assigns transition points;

(ii) builds an AR model of the pre-stimulus EEG signal;

(iii) whitens the EEG and EP signals;

(iv) identifies the EP by performing a closed form least square solution of the model; and

(v) extracts the EP signal.

19. The apparatus according to claim 10, wherein said means (a), (b), (c) and (d) are in the form of computer software.