Aggregation of sensory data for distributed decision-making

• US 20040117157A1
• Filed: 12/11/2002
• Published: 06/17/2004
• Est. Priority Date: 12/11/2002
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Hosn, Rafah A., Sow, Daby M., Bantz, David F., Davis, John S. II, Perret, Veronique, Mitchell, Nicholas M., Sussman, Jeremy B.
• Granted Patent: US 6,865,517 B2
• Time in Patent Office: Days
• US Class Current: 702/188
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: Y10S 706/934 Information retrieval or Information management
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A method, apparatus and computer product that enables a processor associated with a node in a computer system having various nodes, the nodes having sensors which provide data, and the nodes being connected by a communications facility acquiring local data from the sensor and remote data from other nodes via the data transfer facility. The nodes process data from a local sensor at the node and from remote sensors at other nodes; and analyze the local data, data from other nodes and local decisions made at and received from other nodes to make a local decision for action at the node. A local decision made at a node is in turn communicated to other nodes.

Claims

1. In a distributed computing system having a plurality of nodes, each node having a sensor for providing local data and a processor, said computing system having a data transfer facility for transferring data between nodes, a method for processing data comprising:

acquiring local data, remote data and remote action decisions at a node;

analyzing the local data, the remote data and the remote action decisions at said node; and

making a local action decision for said node based said local data, said remote data, and said remote action decisions.

2. The method of claim 1, further comprising:

analyzing the local data and the remote data to determine whether a situation exists; and

selecting a local action based on said situation.

3. The method of claim 2, wherein said determining of whether a situation exists, comprises:

extracting statistical measures from remote sensor data;

comparing said measures to a series of templates; and

determining that a situation exists if said measures compare to one of said templates with a predetermined tolerance value.

4. The method of claim 3, wherein the comparing comprises:

forming a comparison vector from said measures; and

comparing said vector to said series of templates.

5. The method of claim 4, wherein said selecting an action and acquiring remote action plans based on said situation comprises:

using a situation index to select a local action;

querying remote nodes for action plans; and

creating a vector of local and remote action plans.

6. The method of claim 2, further comprising:

acquiring remote action plans based on said situation;

modifying a local action based on said remote action plans; and

initiating a modified local action.

7. The method of claim 1, further comprising communicating a local action decision to nodes in said system other than where the decision was made.

8. The method of claim 1, wherein each node queries each other node.

9. The method of claim 1, wherein a node queries each other node for data obtained from respective local sensors associated with each other node.

10. The method of claim 6, further comprising processing the data to remove noise.

11. The method of claim 10, wherein the data is processed to remove noise at the node from which the data is obtained.

12. The method of claim 1, wherein a node queries each other node to determine what course of action has been determined by said other nodes.

13. The method of claim 1, wherein in response to a query, a node determines whether the query is for sensor data, local action data, or both sensor data and local action data, and the node sends to an inquiring node at least one of local sensor data and local action data.

14. The method of claim 1, wherein said data transfer facility is a wireless data transfer facility.

15. The method of claim 1, wherein the sensors are bio-sensors, and the data produced by the sensors is bio-data.

16. The method of claim 1, wherein the sensors are traffic sensors, and the data produced by the sensors relates to traffic.

17. The method of claim 1, wherein the sensors are audio sensors, and the data produced by the sensors relates to events producing a significant audio component.

18. The method of claim 1, wherein the event producing a significant audio component is a gunshot.

19. A computing system comprising:

a plurality of nodes, each node having a sensor for acquiring data, and a processor for processing data, said processor having computer program components;

a data transfer facility for transferring data between the nodes;

said program components being for acquiring local data from said sensor and remote data from said other nodes via said data transfer facility, said program components also analyzing said local data, data from other nodes and local decisions made at and received from other nodes to make a local decision for action at said node.

20. The system of claim 19, wherein each of said nodes comprises:

a memory for storing data and programs, wherein said programs include an operating system, middleware and an application.

21. The system of claim 19, further comprising:

a component for analyzing the local data and the remote data to determine whether a situation exists; and

a component for selecting a local action based on said situation.

22. The system of claim 19, further comprising:

a component for extracting statistical measures from remote sensor data;

a series of templates, each template corresponding to a situation;

a component for comparing said measures to said series of templates; and

a component for determining that a situation exists if said measures compare to one of said templates within a predetermined tolerance value.

23. The system of claim 22, wherein the component for comparing comprises:

a component for forming a comparison vector from said measures; and

a component for comparing said vector to said series of templates.

24. The system of claim 21, wherein said component for selecting an action based on said situation comprises:

a situation index to select a local action;

a component for querying remote nodes for action plans; and

a component for creating a vector of local and remote action plans.

25. The system of claim 21, further comprising:

a component for acquiring remote action plans based on said situation;

a component for modifying a local action based on said remote action plans; and

a component for initiating a modified local action.

26. The system of claim 19, further comprising a component for communicating a local action decision to nodes in said system other than where the decision was made.

27. The system of claim 19, wherein each node comprises a component for querying each other node.

28. The system of claim 19, wherein each node has a component for querying each other node for data obtained from respective local sensors associated with each other node.

29. The system of claim 19, further comprising a component for processing data to remove noise.

30. The system of claim 19, wherein components for processing data to remove noise are located at the nodes from which the data is obtained.

31. The system of claim 19, comprising a component for causing a node to query each other node to determine what course of action has been determined by said other nodes.

32. The system of claim 19, comprising a component which, in response to a query, permits a node to determine whether the query is for sensor data, local action data, or both sensor data and local action data, and caused the node to send to an inquiring node at least one of local sensor data and local action data.

33. The system of claim 19, wherein said data transfer facility is a wireless data transfer facility.

34. An article of manufacture comprising a computer usable medium having computer readable program code means embodied therein for running on a processor associated with a node in a computer system having various nodes, the nodes having sensors which provide data, and the nodes being connected by a communications facility, said program code being for:

acquiring local data from said sensor and remote data from other nodes via said data transfer facility,

processing data from a local sensor at said node and from remote sensors at other nodes; and

analyzing said local data, data from other nodes and local decisions made at and received from other nodes to make a local decision for action at said node.

35. The article of manufacture as recited in claim 34, wherein said program code comprises:

a component for analyzing the local data and the remote data to determine whether a situation exists; and

a component for selecting a local action based on said situation.

36. The article of manufacture as recited in claim 35, wherein said program code comprises:

a component for extracting statistical measures from remote sensor data;

a series of templates, each template corresponding to a situation;

a component for comparing said measures to said series of templates; and

a component for determining that a situation exists if said measures compare to one of said templates within a predetermined tolerance value.

37. The article of manufacture as recited in claim 36, wherein the component for comparing comprises:

a component for forming a comparison vector from said measures; and

a component for comparing said vector to said series of templates.

38. The article of manufacture as recited in claim 35, wherein said component for selecting an action based on said situation comprises:

a situation index to select a local action;

a component for querying remote nodes for action plans; and

a component for creating a vector of local and remote action plans.

39. The article of manufacture as recited in claim 35, wherein the computer code further comprises:

a component for acquiring remote action plans based on said situation;

a component for modifying a local action based on said remote action plans; and

a component for initiating a modified local action.

40. The article of manufacture as recited in claim 34, further comprising a computer code component for communicating a local action decision to nodes in said system other than where the decision was made.

41. The article of manufacture as recited in claim 34, wherein the computer code comprises a component for querying each other node.

42. The article of manufacture as recited in claim 34, wherein the computer code has a component for querying each other node for data obtained from respective local sensors associated with each other node.

43. The article of manufacture as recited in claim 34, further comprising a computer code component for processing data to remove noise.

44. The article of manufacture as recited in claim 34, comprising a computer code component for causing the node to query each other node to determine what course of action has been determined by said other nodes.

45. The article of manufacture as recited in claim 34, comprising a computer code component which, in response to a query, permits the node to determine whether the query is for sensor data, local action data, or both sensor data and local action data, and

a computer code component for causing the node to send to an inquiring node at least one of local sensor data and local action data.

46. The article of manufacture as recited in claim 34, in combination with a program storage device for communicating with a computer, the program storage device communicating to the computer the program code.