Cognitive networked electronic warfare

• US 8,494,464 B1
• Filed: 09/08/2010
• Issued: 07/23/2013
• Est. Priority Date: 09/08/2010
• Status: Active Grant

• Current Assignee: Rockwell Collins, Inc. (Rtx Corporation)
• Original Assignee: Rockwell Collins, Inc. (Rtx Corporation)
• Inventors: Haan, Benjamin J., Fuemmeler, Jason A., Spencer, W. Sam, Chavez, Carlos J., Frank, Robert J., Kadambe, Shubba L.
• Primary Examiner(s): DEAN, RAYMOND S
• Application Number:
  US12/877,418
• Time in Patent Office: 1,049 Days
• Field of Search: 455/67.11, 455/67.13, 455/114.2, 455/115.1, 455/115.3, 455/501, 342/14
• US Class Current: 455/115.1
• CPC Class Codes: G01S 5/06 Position of source determined by co-ordinating a plurality of position lines defined by path-difference measurements G01S5/12 takes precedence
• CPC Class Codes: H04K 3/226 Selection of non-jammed channel for communication spectrum sharing arrangements H04W16/14; selection of wireless resources by user or terminal H04W72/02
• CPC Class Codes: H04K 3/28 with jamming and anti-jamming mechanisms both included in a same device or system, e.g. wherein anti-jamming includes prevention of undesired self-jamming resulting from jamming
• CPC Class Codes: H04K 3/45 characterized by including monitoring of the target or target signal, e.g. in reactive jammers or follower jammers for example by means of an alternation of jamming phases and monitoring phases, called "look-through mode"

Abstract

An apparatus for sensing and classifying radio communications is provided. The apparatus includes one or more sensor units configured to detect radio frequency signals, a signal classifier configured to classify the detected radio frequency signals into a classification, the classification including at least one known signal type and an unknown signal type, a clustering learning algorithm capable of finding clusters of common signals among the previously seen unknown signals. The system is then further configured to use these clusters to retrain the signal classifier to recognize these signals as a new signal type.

Claims

1. An apparatus for cognitive networked electronic warfare that includes sensing and classifying radio communications comprising:

one or more sensor units configured to detect radio frequency signals;

a signal classifier configured to classify the detected radio frequency signals into a classification, the classification including at least one known signal type and an unknown signal type;

a clustering learning unit configured to find clusters of signal types in an unknown signal, the clusters being used to retrain the classifier and generate a new known signal type; and

a cognitive controller configured to initiate the clustering learning unit when the signal classifier classifies a detected radio frequency signal as an unknown signal type, the cognitive controller being further configured to re-train the signal classifier with the new known signal type when the clustering learning unit generates the new known signal type.

2. The apparatus of claim 1, wherein the cognitive controller maintains a knowledge base and is configured to initiate different functionalities based on an XML setup and policy input.

3. The apparatus of claim 1, wherein the one or more sensor units includes a software-defined radio.

4. The apparatus of claim 1, wherein the one or more sensor units includes a spectral sensor.

5. The apparatus of claim 1, wherein the signal classifier is further configured to determine and provide signal parameters for the detected radio frequency signal.

6. The apparatus of claim 5 further comprising a jammer configured to jam the detected radio frequency signal.

7. The apparatus of claim 6, wherein the jammer is configured to jam the detected radio frequency signal based on the provided signal parameters.

8. The apparatus of claim 7, wherein the jammer is a spot jammer.

9. The apparatus of claim 1, wherein the clustering learning unit utilizes a K-means clustering algorithm to identify new signal classes.

10. The apparatus of claim 9, wherein the clustering learning unit also utilizes a G-means clustering algorithm to identify new signal classes.

11. The apparatus of claim 1, wherein the signal classifier is configured to utilize a cumulant-based feature extraction algorithm to classify the detected radio frequency signal.

12. The apparatus of claim 11, wherein the cumulant-based feature extraction algorithm includes a Gaussian mixture model.

13. The apparatus of claim 6, further comprising:

a terrain analysis module configured to determine a physical location to place the jamming device.

14. The apparatus of claim 4, wherein the sensor is configured to perform a detection algorithm on received radio frequency data, wherein the algorithm compares the measured power of the received radio frequency data to a threshold to determine if the received radio frequency data contains signal plus noise or noise only.

15. The apparatus of claim 14, wherein the measured power of the received radio frequency data is integrated over a period of time to create an integrated received power, the integrated received power being compared to the threshold.

16. The apparatus of claim 15, wherein the threshold is calculated from an estimated mean of an integrated noise power, wherein the integrated noise power relates to the integrated received power.

17. The apparatus of claim 16, wherein the threshold is calculated from the estimated mean and estimated variance of the integrated noise power.

18. The apparatus of claim 16, wherein the estimated mean of the integrated noise power is calculated from the received radio frequency data after the received radio frequency data has been validated by the signal classifier as being a known or unknown signal class.

19. The apparatus of claim 17, wherein the estimated mean and estimated variance of the integrated noise power is calculated from the received radio frequency data after the received radio frequency data has been validated by the signal classifier as being a known or unknown signal class.