Detecting behavioral deviations by measuring respiratory patterns in cohort groups

• US 8,218,871 B2
• Filed: 03/05/2008
• Issued: 07/10/2012
• Est. Priority Date: 03/05/2008
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Angell, Robert Lee, Kraemer, James R.
• Primary Examiner(s): Rahmjoo, Mike
• Application Number:
  US12/042,857
• Publication Number:
  US 20090226043A1
• Time in Patent Office: 1,588 Days
• Field of Search: 382/181, 382/118, 382/124, 382/116, 382/115, 340/573.1, 340/573.2, 340/573.3
• US Class Current: 382/181
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G08B 21/0476 Cameras to detect unsafe condition, e.g. video cameras
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/80 for detecting, monitoring or modelling epidemics or pandemics, e.g. flu

Abstract

A computer implemented method, apparatus, and computer usable program code for detecting behavioral deviations in members of a cohort group. In one embodiment, a member of a cohort group is identified. Each member of the cohort group shares a common characteristic. Respiratory metadata associated with the member of the cohort group is received in real-time as the respiratory metadata is generated. The respiratory metadata describes respiration associated with the member of the cohort group. Patterns of respiratory changes are identified using the respiratory metadata. The respiratory metadata is analyzed to identify the patterns of respiratory changes. In response to the patterns of respiratory changes indicating behavioral deviations in the member of the cohort group, the member of the cohort group is identified as a person of interest.

Claims

1. A computer implemented method for detecting behavioral deviations in members of a cohort group, the computer implemented method comprising:

identifying a member of the cohort group, wherein each member of the cohort group shares a common characteristic, and wherein the member is described using identification data, and further wherein the identification data includes;

action data regarding the member'"'"'s use of a web page, and device data regarding a computing device having a user interface and used by the member to interact with a data processing system associated with a transportation facility;

retrieving respiratory metadata in real-time as the respiratory metadata is generated, wherein the respiratory metadata is associated with the member of the cohort group, wherein the respiratory metadata describes respiration associated with the member of the cohort group;

identify patterns of respiratory changes using the respiratory metadata, wherein the respiratory metadata is analyzed to identify the patterns of respiratory changes;

responsive to the patterns of respiratory changes indicating behavioral deviations in the member of the cohort group, identifying the member of the cohort group as a person of interest;

analyzing audio data to identify human voices and phonetics of human speech to identify a voice print of the member of the cohort group, wherein the audio data describes non-respiratory characteristics of the member of the cohort group;

comparing the voice print of the member of the cohort group to each voice print included in a group of known voice prints to locate one of the voice prints included in the group of known voice prints that matches the voice print of the member of the cohort group; and

using the one of the voice prints included in the group of known voice prints that matches the voice print of the member of the cohort group to identify the member of the coherent group, wherein the action data includes page hits, sequence of hits, duration of page views, response to advertisements, and transactions made.

2. The computer implemented method of claim 1 wherein the respiratory metadata comprises metadata-describing breath sounds and sounds associated with inspiration and expiration of air by a respiratory system of the member of the cohort group.

3. The computer implemented method of claim 1 further comprising:

analyzing event metadata associated with a plurality of individuals in real-time to identify individuals in the plurality of individuals that share the common characteristic, wherein the metadata describes events associated with each individual and patterns of behavior associated with the each individual; and

identifying the individuals in the plurality of individuals that share the common characteristic to form the cohort group.

4. The computer implemented method of claim 3 wherein the transportation facility is an airport.

5. The computer implemented method of claim 1 wherein the cohort group is a group of people in a transportation facility.

6. The computer implemented method of claim 1 further comprising:

analyzing the patterns of respiration to identify a rate of respiration associated with the member of the cohort group.

7. The computer implemented method of claim 1 wherein the respiratory metadata comprises metadata describing changes in movements of a rib cage and abdomen of the member of the cohort group and further comprising:

analyzing the respiratory metadata to determine characteristics of the respiration by the member of the cohort group by determining if the member of the cohort group is exhibiting deep breathing, shallow breathing, fast breathing, and erratic breathing.

8. The computer implemented method of claim 1 wherein identifying patterns of respiratory changes using the respiratory metadata includes determining if the member of the cohort group is reacting in an atypical manner to external stimuli, the person is failing to display expected responses to external stimuli, the member of the cohort group is demonstrating an atypically high level of tension, the person is controlling their breathing, and the member of the cohort group is demonstrating a lack of emotion.

9. The computer implemented method of claim 1 further comprising:

responsive to identifying the member of the cohort group as the person of interest, increasing a level of monitoring associated with the person of interest.

10. A computer program product stored on a non-transistor computer-readable medium for detecting behavioral deviations in members of a cohort group, the computer program product comprising:

program code stored on the computer readable medium for identifying a member of the cohort group, wherein each member of the cohort group shares a common characteristic, and wherein the member is described using identification data, and further wherein the identification data includes;

action data regarding the member'"'"'s use of a web page, and device data regarding a computing device having a user interface and used by the member to interact with a data processing system associated with a transportation facility;

program code stored on the computer readable medium for retrieving respiratory metadata associated with the member of the cohort group in real-time as the respiratory metadata is generated, wherein the respiratory metadata describes respiration associated with the member of the cohort group;

program code stored on the computer readable medium for identifying patterns of respiratory changes using the respiratory metadata, wherein the respiratory metadata is analyzed to identify the patterns of respiratory changes;

program code stored on the computer readable medium for identifying the member of the cohort group as a person of interest in response to the patterns of respiratory changes indicating behavioral deviations in the member of the cohort group;

program code stored on the computer readable medium for analyzing audio data to identify human voices and phonetics of human speech to identify a voice print of the member of the cohort group, wherein the audio data describes non-respiratory characteristics of the member of the cohort group;

program code stored on the computer readable medium for comparing the voice print of the member of the cohort group to each voice print included in a group of known voice prints to locate one of the voice prints included in the group of known voice prints that matches the voice print of the member of the cohort group; and

program code stored on the computer readable medium for using the one of the voice prints included in the group of known voice prints that matches the voice print of the member of the cohort group to identify the member of the coherent group, wherein the action data includes page hits, sequence of hits, duration of page views, response to advertisements, and transactions made.

11. The computer program product of claim 10 wherein the respiratory metadata comprises metadata describing changes in movements of a rib cage and abdomen of the member of the cohort group and further comprising:

analyzing the respiratory metadata to determine characteristics of the respiration by the member of the cohort group by determining if the member of the cohort group is exhibiting deep breathing, shallow breathing, fast breathing, and erratic breathing.

12. An apparatus for detecting behavioral deviations in members of a cohort group, the apparatus comprising:

an analysis server, wherein the analysis server identifies a member of the cohort group based on data associated with the member of the cohort group gathered in real time, and wherein each member of the cohort group shares a common characteristic, and wherein the member is described using identification data, and further wherein the identification data includes;

action data regarding the member'"'"'s use of a web page, and device data regarding a computing device having a user interface and used by the member to interact with a data processing system associated with a transportation facility;

a video analysis system, wherein the video analysis system generates respiratory metadata associated with the member of the cohort group in real-time, wherein the respiratory metadata describes respiration by the member of the cohort group;

a respiratory pattern recognition engine, wherein the respiratory pattern recognition engine identifies patterns of respiratory changes associated with the respiration by the member of the cohort group using the respiratory metadata, wherein the respiratory metadata is analyzed to identify the patterns of respiratory changes;

a person of interest identification engine, wherein the person of interest identification engine identifies the member of the cohort group as a person of interest in response to the patterns of respiratory changes indicating behavioral deviations by the member of the cohort group;

a computer analyzing audio data to identify human voices and phonetics of human speech to identify a voice print of the member of the cohort group, wherein the audio data describes non-respiratory characteristics of the member of the cohort group;

the computer comparing the voice print of the member of the cohort group to each voice print included in a group of known voice prints to locate one of the voice prints included in the group of known voice prints that matches the voice print of the member of the cohort group; and

the computer using the one of the voice prints included in the group of known voice prints that matches the voice print of the member of the cohort group to identify the member of the coherent group, wherein the action data includes page hits, sequence of hits, duration of page views, response to advertisements, and transactions made.

13. The apparatus of claim 12 further comprising:

a cohort analysis component, wherein the cohort analysis component analyzes event metadata associated with a plurality of individuals to identify individuals in the plurality of individuals that share a common characteristic, wherein the metadata describes events associated with each individual and patterns of behavior associated with the each individual; and

wherein the cohort analysis component identifies the individuals in the plurality of individuals that share the common characteristic to form the cohort group.

14. The apparatus of claim 12 further comprising:

a risk assessment engine, wherein the risk assessment engine identifies a level of risk associated with the person of interest; and

wherein the risk assessment engine increases a level of monitoring associated with the person of interest in response to the level of risk associated with the person of interest exceeding a threshold level of risk.

15. The apparatus of claim 12 wherein the respiratory pattern recognition engine analyzes the patterns of respiration to identify a rate of respiration associated with the member of the cohort group.