System and method for event detection and correlation from moving object sensor data

• US 9,262,294 B2
• Filed: 10/31/2011
• Issued: 02/16/2016
• Est. Priority Date: 10/31/2011
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Inventors: Gupta, Chetan Kumar, Mehta, Abhay, Wang, Song
• Primary Examiner(s): Gillis, Brian J
• Assistant Examiner(s): TURRIATE GASTULO, JUAN CARLOS
• Application Number:
  US13/285,825
• Publication Number:
  US 20130111012A1
• Time in Patent Office: 1,569 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/3006 where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems multiprogramming arrangements G06F9/46; allocation of resources G06F9/50
• CPC Class Codes: G06F 11/3013 where the computing system is an embedded system, i.e. a combination of hardware and software dedicated to perform a certain function in mobile devices, printers, automotive or aircraft systems testing or monitoring of control systems or parts thereof G05B23/02
• CPC Class Codes: G06F 11/3058 Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations thermal management in cooling arrangements of a computing system G06F1/206
• CPC Class Codes: G06F 11/328 Computer systems status display G06F11/327 takes precedence

Abstract

An exemplary embodiment of the present techniques may detect and correlate events from moving object sensor data by receiving data from a sensor. The data received from the sensor may be mapped, and events may be detected based on the mapped sensor data. Events from the mapped sensor data may be correlated online.

Claims

1. A system for event detection and correlation from moving object sensor data, the system comprising:

a processor that is adapted to execute stored instructions; and

a memory device that stores instructions, the memory device comprising processor-executable code, that when executed by the processor, is adapted to;

receive data from a sensor attached to a moving object;

map the data received from the sensor;

detect events based on the mapped sensor data; and

correlate the events online using a hierarchical neighborhood tree (HNT) data structure, wherein a leaf node of the HNT data structure represents at least one segment, wherein a plurality of leaf nodes of the HNT data structure represents a smallest grouping of segments and a plurality of non-leaf nodes represents a larger grouping of segments, and wherein the HNT data structure computes correlations based on the distance between each event.

2. The system recited in claim 1, wherein a level of nodes above the leaf node represents a plurality of nodes.

3. The system recited in claim 1, wherein the memory device includes processor-executable code adapted to map the data received from the sensor by computing quantities related to each moving object and each segment from the data received across a network.

4. The system recited in claim 1, wherein the memory device includes processor-executable code adapted to detect events based on the mapped sensor data, the events including skyline events, static sensor anomaly events, or dynamic sensor anomaly events.

5. The system recited in claim 1, wherein the memory device includes processor-executable code adapted to detect events based on the mapped sensor data by discovering rules corresponding to the events.

6. The system recited in claim 1, wherein a static sensor anomaly event is described using an exponentially weighted moving average or Haar wavelets.

7. The system recited in claim 1, wherein the moving object is a vehicle and the segment is a roadway, or the moving object is an aircraft and the segment is a defined amount of airspace.

20. The method of claim 1, wherein the segment is a portion of an environment in which the moving object is located.

21. The method of claim 20, wherein the segment is a roadway and the moving object is a vehicle.

22. The method of claim 20, wherein the data associated with the segment is received from sensors located in the portion of the environment.

8. A method of event detection and correlation from moving object sensor data, the method comprising:

receiving data from a sensor;

mapping the data received from the sensor;

detecting events based on the mapped sensor data; and

correlating the events online using a hierarchical neighborhood tree (HNT) data structure, wherein a leaf node of the HNT data structure represents at least one segment, wherein a plurality of leaf nodes of the HNT data structure represents a smallest grouping of segments and a plurality of non-leaf nodes represents a larger grouping of segments, and wherein the HNT data structure computes correlations based on the distance between each event.

9. The method recited in claim 8, wherein a level of nodes above the leaf node represents a plurality of nodes.

10. The method recited in claim 8, wherein receiving data from a sensor includes receiving a position report from a sensor across a network.

11. The method recited in claim 8, comprising detecting events based on the mapped sensor data at various levels of abstraction or across multiple segments.

12. The method recited in claim 8, wherein detecting events based on the mapped sensor data includes detecting static anomaly events, dynamic sensor anomaly events, or skyline events based on the mapped sensor data.

13. The method recited in claim 8, wherein a static sensor anomaly event is described using an exponentially weighted moving average or Haar wavelets.

14. The method recited in claim 8, wherein a dynamic sensor anomaly event is detected by using an efficient indexing scheme over dynamic sensor data.

15. A non-transitory, computer-readable medium, comprising code configured to direct a processor to:

receive data from a sensor;

map the data received from the sensor;

detect events based on the mapped sensor data; and

correlate the events online using a hierarchical neighborhood tree (HNT), wherein the correlation of events is based on a distance between each event, wherein the HNT comprises nodes that correspond to segments, wherein a leaf node represents at least one segment, and wherein a plurality of leaf nodes of the hierarchical neighborhood tree (HNT) represents a smallest grouping of segments and a plurality of non-leaf nodes represents a largest grouping of segments.

16. The non-transitory, computer-readable medium recited in claim 15, wherein receiving data from a sensor includes receiving a position report from a sensor across a network.

17. The non-transitory, computer readable medium recited in claim 15, wherein detecting events based on the mapped sensor data includes detecting static sensor anomaly events, dynamic sensor anomaly events, or skyline events based on the mapped sensor data.

18. The non-transitory, computer-readable medium recited in claim 15, wherein a static sensor anomaly event is described using an exponentially weighted moving average or Haar wavelets.

19. The non-transitory, computer-readable medium recited in claim 15, comprising discovering rules corresponding to the events after the events are detected.