Method and system for detecting changes in data

• US 7,474,985 B1
• Filed: 04/25/2003
• Issued: 01/06/2009
• Est. Priority Date: 04/25/2003
• Status: Expired due to Fees

• Current Assignee: Navy Secretary of The United of America Office of Naval Research
• Original Assignee: the united states of america as represented by the secretary of the navy
• Inventors: Miranda, Patricia N., Pugh, Jamie K.
• Primary Examiner(s): Feliciano; Eliseo Ramos
• Assistant Examiner(s): Suarez; Felix E
• Application Number:
  US10/423,568
• Time in Patent Office: 2,083 Days
• Field of Search: 702/66, 702/69, 702/75, 702/120, 702/143, 702/179, 702/182, 702/188, 702/189, 358/1.3, 358/1.9, 342/77, 700/31, 705/37, 600/505, 600/529
• US Class Current: 702/179
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A adaptive recursive method for detecting statistically significant changes in data performs steps that include: determining a mean and standard deviation for incoming data; flagging non-conforming data; detecting signals, trends, and/or shifts in the data, and resetting the mean and standard deviation under prescribed circumstances based on predetermined criteria, and then displaying statistics derived from the data.

Claims

1. A method for detecting statistically significant changes in data, comprising the steps of:

a) receiving and storing i^th data in an array, where i is an index;

b) determining a mean and standard deviation from consistent data for use with said i^th data, and identifying and flagging non-conforming data from said array so that said consistent data exclude flagged non-conforming data if;

i) no a prior mean and standard deviation are available, ii) if there are less than C consistent data stored in said array, iii) if a prior determined standard deviation equals zero, or iv) if a mean and standard deviation reset are required and there is at least C data in a subset of said array selected for use in said mean and standard deviation reset, where C is a positive integer;

c) determining test statistics from said i^th data and said mean and standard deviation determined in said step (b), wherein said test statistics include a signal length;

d) flagging said i^th data if said i^th data is non-conforming;

e) determining a direction of any signal, shift, or trend indicated by said data array at said i^th data;

f) determining if any said signal, shift, or trend is indicated by said i^th data stored in said array at said i^th data define a statistically significant signal, shift, or trend;

g) displaying statistics representing said i^th data stored in said array; and

h) returning to said step (a) when (i+1)^th data is available and if a continue process instruction is received.

2. The method of claim 1 further including the step of terminating said method if an end process instruction is received.

3. The method of claim 1 wherein said step (g) includes displaying color coded images that represent value ranges of said statistics.

4. The method of claim 1 further including the step of defining a data set from said statistically significant signal, trend, or shift and said signal length, and resetting said mean and standard deviation from said i^th data stored in said array that correspond with said statistically significant signal, trend, or shift if i) said signal length includes at least C data;

ii) said signal, shift, or trend is statistically significant;

or iii) if said signal, shift, or trend satisfy predetermined conditions.

5. The method of claim 2 wherein said statistics represent variables from the group that includes said standard deviation, said mean, a length of said signal, amplitude of said signal, said shift trend, a standard score, cumulative sums, signal direction, an outlier, non-conforming data flags, said flagged i^th data.

6. The method of claim 1 wherein said i^th data represents medical signs.

7. The method of claim 1 wherein said i^th data represents data selected from the group that includes acoustic data, infrared data, radar data, and imaging data.

8. A computer program product, comprising:

a computer usable medium having computer readable program code means embodied therein for detecting statistically significant changes in data, said computer readable program code means including;

a) first computer readable program means for causing said computer to receive and store i^th data in an array, where i is an index;

b) second computer readable program means for causing said computer to determine a mean and standard deviation from consistent data for use with said i^th data, and to identify and flag non-conforming data from said array so that said consistent data exclude flagged non-conforming data if;

i) no a prior mean and standard deviation are available, ii) if there are less than C consistent data stored in said array, iii) if a prior determined standard deviation equals zero, or iv) if a mean and standard deviation reset are required and there is at least C data in a subset of said array selected for use in said mean and standard deviation reset, where C is a positive integer;

c) third computer readable program means for causing said computer to determine test statistics from said i^th data and said mean and standard deviation determined by said second computer readable program means, wherein said test statistics include a signal length;

d) fourth computer readable program means for causing said computer to flag said i^th data if said i^th data is non-conforming;

e) fifth computer readable program means for causing said computer to determine the direction of any signal, shift, or trend indicated by said data array at said i^th data;

f) sixth computer readable program means for causing said computer to determine if any signals, shifts or trends is indicated by said i^th data stored in said array at said i^th data define a statistically significant signal, shift, or trend;

g) seventh computer readable program means for causing said computer to display statistics representing said i^th data stored in said array; and

h) eighth computer readable program means for causing said computer to return to said first computer readable program means when (i+1)^th data is available and if a continue process instruction is received.

9. The computer program product of claim 8 further including a ninth computer readable program means for causing said computer to terminate a computer program implemented by said computer readable program code means if an end process instruction is received.

10. A system for detecting statistically significant changes in data, comprising:

a computer for executing a sequence of computer readable instructions for performing the computer executable steps of;

a) receiving and storing i^th data in an array, where i is an index;

b) determining a mean and standard deviation from consistent data for use with said i^th data, and identifying and flagging non-conforming data from said array so that said consistent data exclude flagged non-conforming data i) if no a prior mean and standard deviation are available, ii) if there are less than C consistent data stored in said array, iii) if a prior determined standard deviation equals zero, or iv) if a mean and standard deviation reset are required and there are at least C data in a subset of said array selected for use in said mean and standard deviation reset, where C is a positive integer;

c) determining test statistics from said i^th data and said mean and standard deviation determined in said step (b), wherein said test statistics include a signal length;

d) flagging said i^th data if said i^th data is non-conforming;

e) determining the direction of any signal, trend or shift indicated by said data array at said i^th data;

f) determining if any signal, shift, or trend is indicated by said i^th data stored in said array at said i^th data define a statistically significant signal, trend or shift;

g) displaying statistics representing said i^th data stored in said array; and

h) returning to said step (a) when (i+1)^th data is available, and if a continue process instruction is received.

11. The system of claim 10 further including the step of terminating said sequence of computer readable instructions if an end process instruction is received.

12. The system of claim 10 wherein said step (g) includes displaying color coded images that represent value ranges of said statistics.