Detection methods and systems using sequenced technologies

• US 7,461,032 B2
• Filed: 01/31/2006
• Issued: 12/02/2008
• Est. Priority Date: 11/11/2002
• Status: Expired due to Fees

• Current Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Original Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Inventors: Heaton, Michael A., Most, David, Younkin, Shawn
• Primary Examiner(s): STARKS, WILBERT L
• Application Number:
  US11/343,492
• Publication Number:
  US 20060262901A1
• Time in Patent Office: 1,036 Days
• Field of Search: 706/10, 382/156, 367/131, 342/64
• US Class Current: 706/10
• CPC Class Codes: G01N 23/04 and forming images of the material
• CPC Class Codes: G01V 5/223 Mixed interrogation beams, e.g. using more than one type of radiation beam

Abstract

Methods and systems for interconnecting sub-systems and for identifying combinations of multiple technologies.

Claims

1. A method for detecting a presence of a characteristic in an object, the method comprising the steps of:

a) providing at least two detection technologies, each one of said at least two detection technologies providing a determination of the presence of the characteristic in the object;

b) establishing a plurality of decision rules, to arbitrate between results of detection technologies and to detect the presence of the characteristic in the object;

c) first determining, utilizing one of the at least two detection technologies, whether the characteristic is present in the object;

d) repeating step c) until all provided technologies have been utilized;

e) finally determining, utilizing said plurality of decision rules, whether the characteristic is present in the object.

2. The method of claim 1 wherein said plurality of rules comprises a neural network;

and wherein the step of establishing said plurality of decision rules comprises the step of training the neural network.

3. The method of claim 1 wherein the characteristic is an undesired substance within the object.

4. The method of claim 3 wherein the undesired substance comprises an explosive.

5. The method of claim 4 wherein each one of said at least three detection technologies utilizes a technology selected from the group consisting of X-ray technologies, Neutron-Based Bulk Explosives Detection Technologies, Nuclear non-neutron based Bulk Explosive Technologies, Nuclear Quadrupole Resonance Technologies, and Trace Detection Technologies.

6. A system for detecting presence of at least one characteristic in an object, the system comprising:

at least two detection sub-systems, each one of said at least two detection sub-systems providing a determination of presence of said at least one characteristic in the object;

means for establishing a plurality of decision rules, said plurality of decision rules being utilized to arbitrate between results of detection technologies and for detecting the presence of the characteristic in the object; and

decision means for determining, utilizing said plurality of decision rules, whether said at least one characteristic is present in the object.

7. The system of claim 6 wherein said decision means comprise a neural network;

and

wherein said means for establishing said plurality of decision rules comprise means for training said neural network.

8. The system of claim 6 further comprising:

at least one processor; and

a memory for storing data for access by an application program being executed on said at least one processor, said memory comprising;

a data structure stored in said memory, said data structure including information resident in a database used by said application program and including said plurality of decision rules.

9. The system of claim 8 wherein said detection means comprise a computer usable medium having computer readable code embodied therein, said computer readable code being capable of causing said at least one processor to:

a) determine, utilizing one of said at least two detection technologies, whether said at least one characteristic is present in the object;

b) repeat step a) until all provided technologies have been utilized;

e) finally determine, utilizing said decision means, whether said at least one characteristic is present in the object.

10. The system of claim 9 wherein said decision means comprise a neural network;

and wherein the means for establishing said plurality of decision rules comprises means for training the neural network.

11. The system of claim 9 wherein said decision means comprise an expert system.

12. The system of claim 6 wherein each one of said at least two detection sub-systems utilizes a technology selected from the group consisting of X-ray technologies, Neutron-Based Bulk Explosives Detection Technologies, Nuclear non-neutron based Bulk Explosive Technologies, Nuclear Quadrupole Resonance Technologies, and Trace Detection Technologies.

13. A method for providing data used to establish a plurality of decision rules to arbitrate between results of detection technologies and to detect presence of the characteristic in an object, the method comprising the steps of:

(a) providing a candidate system comprising at least two detection sub-systems, each one of said at least two detection sub-systems providing a determination of presence of said at least one characteristic in the object;

(b) performing a Monte Carlo analysis of detecting a presence of the at least one characteristic in an object;

(c) calculating a pre-defined figure of merit for the candidate system;

(d) providing the candidate system and the pre-defined figure of merit to a knowledge database.

14. The method of claim 13 wherein the step of providing the candidate system and the predefined figure of merit to the knowledge database comprises the step of providing the candidate systems and the predefined figure of merit as training data to a neutral network.