Granted Patent B2

US 12,333,452 · App. 18/391,198 · Granted Jun 17, 2025

Inventors: Mohammad Omer (Waterloo, CA); Stephen Arnold Devison (Kitchener, CA)

Assignee: Cognitive Systems Corp.

G06N7/01G06F17/16H04W4/027H04W84/18

Abstract

Claims (49)

1. A method comprising:

obtaining link disturbance values associated with a plurality of wireless links in a wireless communication network, the link disturbance values representing a level of disturbance detected on each of the plurality of wireless links based on wireless signals exchanged during a first time frame on the plurality of wireless links, each of the wireless links defined between a respective pair of wireless communication devices in the wireless communication network;

obtaining prior probability information representing probabilities that motion occurred at the respective wireless communication devices during a second time frame prior to the first time frame; and

by operation of one or more computer processors of a motion detection system, executing a Bayesian computational framework to determine, based on the link disturbance values and the prior probability information, a location of motion that occurred during the first time frame.

2. The method of claim 1 , comprising:

generating a first probability vector based on the link disturbance values, the first probability vector comprising first values assigned to the respective wireless communication devices, the first values representing first probabilities of motion at the respective wireless communication devices during the first time frame,

wherein the prior probability information is a second probability vector generated from motion data associated with the second time frame, the second probability vector comprising second values assigned to the respective wireless communication devices, the second values representing prior probabilities of motion at the respective wireless communication devices during the second time frame, and

wherein the Bayesian computational framework is executed based on the first probability vector and the second probability vector.

3. The method of claim 2 , comprising:

obtaining a transition probability matrix comprising:

transition values representing probabilities of motion transitioning between locations associated with distinct wireless communication devices; and

non-transition values representing probabilities of motion remaining within locations associated with the respective wireless communication devices; and

executing the Bayesian computational framework to determine the location of the motion that occurred during the first time frame based on the first probability vector, the second probability vector, and the transition probability matrix.

4. The method of claim 1 , comprising communicating, from the motion detection system to another system, output data indicating the location of motion that occurred during the first time frame.

5. The method of claim 1 , wherein executing the Bayesian computational framework generates second probability information representing second probabilities that motion occurred at the respective wireless communication devices during the first time frame.

6. The method of claim 5 , comprising:

identifying a first wireless communication device associate with a highest of the second probabilities; and

wherein determining the location comprises identifying a location associated with the first wireless communication device as the location of the motion detected during the first time frame.

7. The method of claim 6 , comprising:

repeating the operations, over multiple iterations of respective time frames, of obtaining the link disturbance values, obtaining the prior probability information, and executing the Bayesian computational framework to determine the location of motion; and

recursively updating the Bayesian computational framework by utilizing the second probability information of a previous iteration as the prior probability information of a present iteration.

8. The method of claim 1 , wherein the plurality of wireless links comprises sets of wireless links that allow bi-directional communication between a respective pair of wireless devices, each set of wireless links having at least one wireless link per direction in the bi-directional communication.

9. A motion detection system, comprising:

a plurality of wireless communication devices configured to exchange wireless signals on a plurality of wireless links, each of the wireless links defined between a respective pair of the wireless communication devices; and

a data processing apparatus configured to perform operations comprising:

obtaining link disturbance values associated with a plurality of wireless links in a wireless communication network, the link disturbance values representing a level of disturbance detected on each of the plurality of wireless links based on wireless signals exchanged during a first time frame on the plurality of wireless links, each of the wireless links defined between a respective pair of wireless communication devices in the wireless communication network;

obtaining prior probability information representing probabilities that motion occurred at the respective wireless communication devices during a second time frame prior to the first time frame; and

by operation of one or more computer processors of a motion detection system, executing a Bayesian computational framework to determine, based on the link disturbance values and the prior probability information, a location of motion that occurred during the first time frame.

10. The system of claim 9 , wherein the operations comprise:

generating a first probability vector based on the link disturbance values, the first probability vector comprising first values assigned to the respective wireless communication devices, the first values representing first probabilities of motion at the respective wireless communication devices during the first time frame; and

wherein the prior probability information is a second probability vector generated from motion data associated with the second time frame, the second probability vector comprising second values assigned to the respective wireless communication devices, the second values representing prior probabilities of motion at the respective wireless communication devices during the second time frame, and wherein the Bayesian computational framework is executed based on the first probability vector and the second probability vector.

11. The system of claim 10 , wherein the operations comprise:

obtaining a transition probability matrix comprising:

transition values representing probabilities of motion transitioning between locations associated with distinct wireless communication devices;

non-transition values representing probabilities of motion remaining within locations associated with the respective wireless communication devices; and

executing the Bayesian computational framework to determine the location of the motion that occurred during the first time frame based on the first probability vector, the second probability vector, and the transition probability matrix.

12. The system of claim 9 , wherein the operations comprise communicating, from the motion detection system to another system, output data indicating the location of motion that occurred during the first time frame.

13. The system of claim 9 , wherein executing the Bayesian computational framework generates second probability information representing second probabilities that motion occurred at the respective wireless communication devices during the first time frame.

14. The system of claim 13 , comprising:

identifying a first wireless communication device associate with a highest of the second probabilities; and

wherein determining the location comprises identifying a location associated with the first wireless communication device as the location of the motion detected during the first time frame.

15. The system of claim 14 , comprising:

repeating the operations, over multiple iterations of respective time frames, of obtaining the link disturbance values, obtaining the prior probability information, and executing the Bayesian computational framework to determine the location of motion; and

recursively updating the Bayesian computational framework by utilizing the second probability information of a previous iteration as the prior probability information of a present iteration.

16. The system of claim 9 , wherein the plurality of wireless links comprises sets of wireless links that allow bi-directional communication between a respective pair of wireless devices, each set of wireless links having at least one wireless link per direction in the bi-directional communication.

17. A non-transitory computer-readable medium containing program instructions for causing a data processing apparatus to perform operations comprising:

obtaining link disturbance values associated with a plurality of wireless links in a wireless communication network, the link disturbance values representing a level of disturbance detected on each of the plurality of wireless links based on wireless signals exchanged during a first time frame on the plurality of wireless links, each of the wireless links defined between a respective pair of wireless communication devices in the wireless communication network;

obtaining prior probability information representing probabilities that motion occurred at the respective wireless communication devices during a second time frame prior to the first time frame; and

by operation of one or more computer processors of a motion detection system, executing a Bayesian computational framework to determine, based on the link disturbance values and the prior probability information, a location of motion that occurred during the first time frame.

Assignments (1)

Continuity (3)

References Cited (249)