Sensor module

• US 5,910,765 A
• Filed: 03/22/1995
• Issued: 06/08/1999
• Est. Priority Date: 11/02/1993
• Status: Expired due to Fees

• Current Assignee: Advanced Optical Solutions Incorporated
• Original Assignee: Advanced Optical Solutions Incorporated
• Inventors: Lafferty, William Michael, Slemon, Charles S., Guest, Clark C.
• Primary Examiner(s): Hofsass, Jeffery
• Assistant Examiner(s): WONG, ALBERT KANG
• Application Number:
  US08/408,590
• Time in Patent Office: 1,539 Days
• Field of Search: 340/540, 340/517, 340/521, 340/522, 364/550, 364/551, 364/572, 364/574, 364/551.01, 395/22
• US Class Current: 340/517
• CPC Class Codes: G01D 1/00 Measuring arrangements giving results other than momentary value of variable, of general application G01D3/00 takes precedence; in tariff metering apparatus G01D4/00; transducers not specially adapted for a specific variable G01D5/00
• CPC Class Codes: G01D 21/02 Measuring two or more variables by means not covered by a single other subclass
• CPC Class Codes: G01N 1/26 with provision for intake from several spaces
• CPC Class Codes: G01N 33/0031 comprising two or more sensors, e.g. a sensor array electrochemical electrode arrays G01N27/27
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G08B 17/12 Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
• CPC Class Codes: G08B 29/186 Fuzzy logic; neural networks

Abstract

A device, and a method for using the device, to generate discrete information about an environmental event includes an array of sensors. All sensors in the array have a determinable detection capability and, preferably, some of these detection capabilities are redundant while others are overlapping. The individual sensors are positioned in the particular environment to detect characteristics of the event from different perspectives. The outputs which are generated by the various sensors in the array are selectively segmented and joined to create a convolved pattern of data which explicitly and implicitly includes information about the characteristics of the event. The convolved pattern is then presented to a pattern recognition unit, such as a neural network, where the characteristics are interpreted from the convolved pattern to generate the desired discrete information about the environmental event.

Claims

1. A detector for distinguishing a single specific environmental event from a plurality of distinctive environmental events, said detector comprising:

a plurality of sensors, all of said sensors being selectively arranged to directly detect a plurality of environmental characteristics of said plurality of distinctive environmental events from a plurality of spatially dispersed and parametrically different perspectives, each sensor of said plurality of sensors generating an output indicative of at least one said characteristic, and each said characteristic being detected by at least one said sensor;

a pre-processor connected to said plurality of sensors for eliminating repetitively redundant or superfluous data from said sensor outputs, and for joining related and overlapping data in said sensor outputs into data segments to create a convolved pattern of said data segments wherein each said data segment is representative of a specific said environmental characteristic; and

a neural network connected to said pre-processor for recognizing said convolved pattern of said joined data segments to extract information about each said distinctive environmental event from said convolved pattern.

2. A detector as recited in claim 1, wherein said sensors are formed as an array.

3. A detector as recited in claim 1, wherein each said sensor in said plurality of sensors has a detection capability, and at least two sensors in said plurality have substantially the same detection capability.

4. A detector as recited in claim 3, wherein said pre-processor further comprises means for correlating the outputs of said sensors having substantially the same detection capability.

5. A detector as recited in claim 1, wherein each said sensor in said plurality of sensors has a detection capability, and at least two sensors in said plurality have overlapping detection capabilities.

6. A detector for distinguishing a single specific environmental event from a plurality of distinctive environmental events which comprises:

a plurality of sensors, all of said sensors being selectively arranged to directly detect a plurality of environmental characteristics of said plurality of distinctive environmental events from a plurality of spatially dispersed and parametrically different perspectives, each sensor of said plurality of sensors generating an output indicative of at least one said characteristic and each said characteristic being detected by at least one said sensor;

a pre-processor connected to said plurality of sensors for eliminating repetitively redundant or superfluous data from said sensor outputs, and for joining related and overlapping data in said sensor outputs into data segments to create a convolved pattern of said data segments wherein each said data segment is representative of a specific said environmental characteristic; and

a fuzzy logic component connected to said pre-processor for recognizing said convolved pattern of said joined data segments to extract information of each said distinctive environmental event from said convolved pattern.

7. A detector as recited in claim 6, wherein said sensors are formed as an array.

8. A detector as recited in claim 6, wherein each said sensor in said plurality of sensors has a detection capability, and at least two sensors in said plurality have substantially the same detection capability.

9. A detector as recited in claim 8, wherein said pre-processor further comprises means for correlating the outputs of said sensors having substantially the same detection capability.

10. A detector as recited in claim 6, wherein each said sensor in said plurality of sensors has a detection capability, and at least two sensors in said plurality have overlapping detection capabilities.

11. A method for using a device having an array with a plurality of sensors, a pre-processor and a neural network to extract information indicative of a single specific environmental event from a plurality of distinctive environmental events, the method comprising the steps of:

tuning said neural network to recognize a selected pattern of convolved data indicative of said specific event, by exposing said neural network to said selected pattern of data while identifying said selected pattern to said neural network as being indicative of said specific event;

exposing all of said sensors in said array directly to a plurality of environmental characteristics of said plurality of distinctive environmental events from spatially dispersed and parametrically different perspectives to generate an output signal from each of said sensors;

using said pre-processor for collecting said output signals from each of said sensors, and for joining related and overlapping data in said output signals into data segments to generate a convolved pattern of said data segments wherein each said data segment is indicative of a specific said environmental event;

directing said convolved pattern of data segments to said neural network for recognition of said convolved pattern; and

producing a discrete signal from said neural network indicative of each said distinctive environmental event.

12. A method as recited in claim 11, further comprising the step of arranging said sensors in said array to detect characteristics of said environment from different spatial perspectives.

13. A method as recited in claim 11, wherein each said sensor in said plurality of sensors has a detection capability, and at least two sensors in said plurality have substantially the same detection capability, and at least two sensors in said plurality have overlapping detection capabilities, said method further comprising the step of correlating the output signals from said sensors having substantially the same detection capability.