Combining medical binary decision diagrams for analysis optimization

• US 8,719,214 B2
• Filed: 09/23/2011
• Issued: 05/06/2014
• Est. Priority Date: 09/23/2011
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Stergiou, Stergios, Jain, Jawahar
• Primary Examiner(s): Holmes, Michael B
• Application Number:
  US13/241,698
• Publication Number:
  US 20130080380A1
• Time in Patent Office: 956 Days
• Field of Search: None
• US Class Current: 706/57
• CPC Class Codes: G05B 23/0221 Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
• CPC Class Codes: G16H 40/60 for the operation of medical equipment or devices
• 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
• 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

Abstract

In particular embodiments, a method includes accessing first binary decision diagrams (BDDs) representing data streams from sensors, selecting portions from the first BDDs based on ease-of-analysis, and constructing a second BDD by performing an OR operation between the selected portions of the first BDDs.

Claims

1. A method comprising:

by one or more computing devices,

accessing one or more first binary decision diagrams (BDDs) representing sensor data from one or more sensors, wherein;

the sensor data comprise a plurality of components; and

the one or more first BDDs comprise a plurality of portions respectively corresponding to the plurality of components;

selecting, from the plurality of portions, one or more portions based on ease-of-analysis; and

constructing a second BDD representing the one or more selected portions by performing an OR operation between the one or more selected portions.

2. The method of claim 1, further comprising analyzing the second BDD.

3. The method of claim 2, wherein analyzing the second BDD is easier than analyzing the one or more selected portions included in the one or more first BDDs.

4. The method of claim 1, wherein selecting, from the plurality of portions, the one or more portions based on ease-of-analysis comprises:

identifying, from the plurality of components, one or more components relevant to an analytical process; and

selecting, from the plurality of portions, the one or more portions respectively corresponding to the one or more components relevant to the analytical process.

5. The method of claim 4, further comprising performing the analytical process using the second BDD.

6. The method of claim 1, wherein selecting, from the plurality of portions, the one or more portions based on ease-of-analysis comprises:

selecting, from the plurality of components, one or more components, such that for each of the one or more selected component, a BDD representing the selected component has a relatively high compression rate; and

selecting, from the plurality of portions, the one or more portions respectively corresponding to the one or more selected components.

7. The method of claim 1, further comprising identifying the plurality of components in the sensor data.

8. The method of claim 7, wherein the plurality of components in the sensor data is identified based on one or more structural characteristics of the sensor data.

9. The method of claim 8, wherein the one or more structural characteristics of the sensor data comprise one or more structural components of a waveform of a signal outputted by at least one of the one or more sensors.

10. The method of claim 8, wherein the one or more structural characteristics of the sensor data comprise a periodicity of a waveform of a signal outputted by at least one of the one or more sensors.

11. The method of claim 8, wherein the one or more structural characteristics of the sensor data comprise one or more identifiers embedded in the sensor data, which define one or more of the plurality of components.

12. The method of claim 7, wherein the plurality of components in the sensor data is identified based on one or more functional characteristics of the sensor data.

13. The method of claim 12, wherein the one or more functional characteristics of the sensor data comprise a rate of change of a waveform of a signal outputted by at least one of the one or more sensors.

14. The method of claim 7, wherein the plurality of components in the sensor data is identified based a plurality of component definitions provided by a user.

15. The method of claim 1, further comprising constructing one or more third BDDs respectively corresponding to one or more non-selected portions of the first BDDs.

16. The method of claim 15, further comprising:

storing the second BDD and the one or more third BDDs;

and deleting the one or more first BDDs.

17. The method of claim 15, further comprising optimizing the one or more first BDDs, the second BDD, and the one or more third BDDs.

18. The method of claim 1, wherein at least one of the one or more sensors is affixed to a person'"'"'s body.

19. An apparatus comprising:

one or more processors; and

a memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to;

access one or more first binary decision diagrams (BDDs) representing sensor data from one or more sensors, wherein;

the sensor data comprise a plurality of components; and

the one or more first BDDs comprise a plurality of portions respectively corresponding to the plurality of components;

select, from the plurality of portions, one or more portions based on ease-of-analysis; and

construct a second BDD representing the one or more selected portions by performing an OR operation between the one or more selected portions.

20. The apparatus of claim 19, wherein the processors are further operable when executing the instructions to analyze the second BDD.

21. The apparatus of claim 20, wherein analyzing the second BDD is easier than analyzing the one or more selected portions included in the one or more first BDDs.

22. The apparatus of claim 19, wherein selecting, from the plurality of portions, the one or more portions based on ease-of-analysis comprises:

identifying, from the plurality of components, one or more components relevant to an analytical process; and

selecting, from the plurality of portions, the one or more portions respectively corresponding to the one or more components relevant to the analytical process.

23. The apparatus of claim 22, wherein the processors are further operable when executing the instructions to perform the analytical process using the second BDD.

24. The apparatus of claim 19, wherein selecting, from the plurality of portions, the one or more portions based on ease-of-analysis comprises:

selecting, from the plurality of components, one or more components, such that for each of the one or more selected component, a BDD representing the selected component has a relatively high compression rate; and

selecting, from the plurality of portions, the one or more portions respectively corresponding to the one or more selected components.

25. The apparatus of claim 19, wherein the processors are further operable when executing the instructions to identify the plurality of components in the sensor data.

26. The apparatus of claim 25, wherein the plurality of components in the sensor data is identified based on one or more structural characteristics of the sensor data.

27. The apparatus of claim 26, wherein the one or more structural characteristics of the sensor data comprise one or more structural components of a waveform of a signal outputted by at least one of the one or more sensors.

28. The apparatus of claim 26, wherein the one or more structural characteristics of the sensor data comprise a periodicity of a waveform of a signal outputted by at least one of the one or more sensors.

29. The apparatus of claim 26, wherein the one or more structural characteristics of the sensor data comprise one or more identifiers embedded in the sensor data, which define one or more of the plurality of components.

30. The apparatus of claim 25, wherein the plurality of components in the sensor data is identified based on one or more functional characteristics of the sensor data.

31. The apparatus of claim 30, wherein the one or more functional characteristics of the sensor data comprise a rate of change of a waveform of a signal outputted by at least one of the one or more sensors.

32. The apparatus of claim 25, wherein the plurality of components in the sensor data is identified based a plurality of component definitions provided by a user.

33. The apparatus of claim 19, wherein the processors are further operable when executing the instructions to construct one or more third BDDs respectively corresponding to one or more non-selected portions of the first BDDs.

34. The apparatus of claim 33, wherein the processors are further operable when executing the instructions to:

store the second BDD and the one or more third BDDs;

and delete the one or more first BDDs.

35. The apparatus of claim 33, wherein the processors are further operable when executing the instructions to optimize the one or more first BDDs, the second BDD, and the one or more third BDDs.

36. The apparatus of claim 19, wherein at least one of the one or more sensors is affixed to a person'"'"'s body.

37. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

access one or more first binary decision diagrams (BDDs) representing sensor data from one or more sensors, wherein;

the sensor data comprise a plurality of components; and

the one or more first BDDs comprise a plurality of portions respectively corresponding to the plurality of components;

select, from the plurality of portions, one or more portions based on ease-of-analysis; and

construct a second BDD representing the one or more selected portions by performing an OR operation between the one or more selected portions.

38. The media of claim 37, wherein the software is further operable when executed to analyze the second BDD.

39. The media of claim 38, wherein analyzing the second BDD is easier than analyzing the one or more selected portions included in the one or more first BDDs.

40. The media of claim 37, wherein selecting, from the plurality of portions, the one or more portions based on ease-of-analysis comprises:

identifying, from the plurality of components, one or more components relevant to an analytical process; and

selecting, from the plurality of portions, the one or more portions respectively corresponding to the one or more components relevant to the analytical process.

41. The media of claim 40, wherein the software is further operable when executed to perform the analytical process using the second BDD.

42. The media of claim 37, wherein selecting, from the plurality of portions, the one or more portions based on ease-of-analysis comprises:

selecting, from the plurality of components, one or more components, such that for each of the one or more selected component, a BDD representing the selected component has a relatively high compression rate; and

selecting, from the plurality of portions, the one or more portions respectively corresponding to the one or more selected components.

43. The media of claim 37, wherein the software is further operable when executed to identify the plurality of components in the sensor data.

44. The media of claim 43, wherein the plurality of components in the sensor data is identified based on one or more structural characteristics of the sensor data.

45. The media of claim 44, wherein the one or more structural characteristics of the sensor data comprise one or more structural components of a waveform of a signal outputted by at least one of the one or more sensors.

46. The media of claim 44, wherein the one or more structural characteristics of the sensor data comprise a periodicity of a waveform of a signal outputted by at least one of the one or more sensors.

47. The media of claim 44, wherein the one or more structural characteristics of the sensor data comprise one or more identifiers embedded in the sensor data, which define one or more of the plurality of components.

48. The media of claim 43, wherein the plurality of components in the sensor data is identified based on one or more functional characteristics of the sensor data.

49. The media of claim 48, wherein the one or more functional characteristics of the sensor data comprise a rate of change of a waveform of a signal outputted by at least one of the one or more sensors.

50. The media of claim 43, wherein the plurality of components in the sensor data is identified based a plurality of component definitions provided by a user.

51. The media of claim 37, wherein the software is further operable when executed to construct one or more third BDDs respectively corresponding to one or more non-selected portions of the first BDDs.

52. The media of claim 51, wherein the software is further operable when executed to:

store the second BDD and the one or more third BDDs;

and delete the one or more first BDDs.

53. The media of claim 51, wherein the software is further operable when executed to optimize the one or more first BDDs, the second BDD, and the one or more third BDDs.

54. The media of claim 37, wherein at least one of the one or more sensors is affixed to a person'"'"'s body.

55. A system comprising:

means for accessing one or more first binary decision diagrams (BDDs) representing sensor data from one or more sensors, wherein;

the sensor data comprise a plurality of components; and

the one or more first BDDs comprise a plurality of portions respectively corresponding to the plurality of components;

means for selecting, from the plurality of portions, one or more portions based on ease-of-analysis; and

means for constructing a second BDD representing the one or more selected portions by performing an OR operation between the one or more selected portions.