Method and apparatus for opportunistic decision support from intermittent interconnected sensors and data archives

• US 6,915,239 B2
• Filed: 01/16/2002
• Issued: 07/05/2005
• Est. Priority Date: 01/19/2001
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Chang, Yuan-Chi, Smith, John R., Li, Chung-Sheng, Bergman, Lawrence D., Hill, Matthew Leon
• Primary Examiner(s): Hoff, Marc S.
• Assistant Examiner(s): MILLER, CRAIG S
• Application Number:
  US10/047,854
• Publication Number:
  US 20040068496A1
• Time in Patent Office: 1,266 Days
• Field of Search: 340/870.11, 340/870.13, 340229-240, 340/311, 340/915, 700 29- 31, 700/50, 700/51, 702187-194
• US Class Current: 702/188
• CPC Class Codes: G01S 7/003 Transmission of data between radar, sonar or lidar systems and remote stations
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• 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: H04L 67/125 involving control of end-device applications over a network
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]

Abstract

Described is a method and apparatus for obtaining accurate, timely information for event detection and prediction based on autonomous opportunism. The objective is to make the best possible use of all available resources at the time of acquisition, including historical data, multiple sensors, and multiresolution acquisition capabilities, under a given set of processing and communication bandwidth constraints. This method (and the corresponding apparatus) fuses multiple adaptively acquired data sources to prepare information for use by decision support models. The onboard data acquisition schedule is constructed to maximize the prediction accuracy of the decision models, which are designed to operate progressively, utilizing data representations consisting of multiple abstraction levels and multiple resolutions. Due to the progressive nature of these models, they can be executed onboard even with the use of substantially summarized (or compressed) datasets delivered from the ground or from other satellite platforms. Models are formulated to accept data with less than complete certainty, thus allowing real-time decisions to be made on locations where additional data is to be acquired based on predicted likelihood of the event of interest and uncertainties. Multi-abstraction-level multi-resolution data is expressed using standard-compliant representations, and progressively transmitted to the ground or other platforms. More detailed calculations can then be performed on the ground using all of the available real time and historical data.

Claims

1. A sensor subsystem for use in a system comprising one or more other similar sensor subsystems arid a base processing system, the sensor subsystem comprising:

a. Two or more data sources for gathering parameter data;

b. A data summarizer which fuses parameter data gathered by two or more data sources to create an abstract data parameter;

c. A progressive model, which takes as input abstract data parameters, and generates an output data model; and

d. Means, which takes as input the output data model and derives an optimized schedule for

i. (i) subsequent gathering of data by the sensor subsystem and

ii. (ii) subsequent transmission of model data to the base processing station

e. so as to maximize accuracy of a data model executed by the base station.

2. The sensor subsystem of claim 1, wherein the data sources include a data source on board the sensor subsystem, as well as a second sensor subsystem.

3. The subsystem of claim 1, wherein the data summarizer fuses data by using one or more of the following techniques:

spatial interpolation, temporal extrapolation, and error concealment.

4. The subsystem of claim 1, wherein the input and output of the progressive model includes an uncertainty estimate.

5. A base processing system for use in a system comprising two or more sensor subsystems, the base processing system comprising:

a. Two or more data sources for gathering parameter data, at least one of the data sources being a sensor subsystem for generating model representing data gathered by two or more sensor subsystems;

b. A data summarizer which fuses parameter data gathered by the two or more data sources to create an abstract data parameter;

c. A progressive model which takes as input abstract data parameters and generates an output date model upon which a decision maker can base a decision.

6. The base processing system of claim 5, wherein the model generated by the sensor subsystem includes an uncertainty estimate.

7. A method, performed by a first remote sensor subsystem, for enabling the a first remote censor subsystem to opportunistically collaborate with one or more other remote sensor subsystems in a system comprising two or more censor subsystems and a base processing system, the method comprising:

a. Performing a model based processing of information collected by sensors located on board the first remote sensor subsystem;

b. Seeking out one or more neighboring remote sensor subsystems;

c. If there is a neighboring remote sensor subsystem, passing information to the neighboring remote sensor subsystem, and if not, transmitting the information to the base processing system.

8. The method of claim 7, wherein step b further comprises exchanging information with one or more neighboring remote sensor subsystems to determine the capabilities of such neighboring remote or subsystems.

9. The method of claim 7, wherein only information critical to collaborative processing is passed from the first remote sensor subsystem to the neighboring sensor subsystem.

10. The method of claim 7, wherein the first remote sensor subsystem stores critical information on board for future processing.