Predicting edges in temporal network graphs described by near-bipartite data sets

Patent metadata

Field	Value
Publication number	US-9299042-B2
Application number	US-201313963439-A
Country	US
Kind code	B2
Filing date	Aug 9, 2013
Priority date	Aug 9, 2013
Publication date	Mar 29, 2016
Grant date	Mar 29, 2016

Abstract

Embodiments of a system and method for predicting a future state of a set of data are generally described herein. In some embodiments, a set of data in a first domain is obtained. The set of data in the first domain may be represented as a network graph. The set of data in the first domain is mapped into a set of data in a second domain. A plurality of prediction models are applied to the set of data in the second domain to produce a plurality of predicted sets of data. The predicted sets of data are combined to generate a combined predicted set of data having a best match. The combined predicted sets of data having the best match are reverse mapped to the first domain.

First claim

What is claimed is:

1. A method for predicting a future state of a set of data, comprising:
obtaining a set of data in a first domain;
mapping the set of data into a second domain;
applying a plurality of prediction models to the set of data in the second domain to produce a plurality of predicted sets of data including applying a Fourier transform to characterize each of the plurality of prediction models;
combining the predicted sets of data to generate a combined predicted set of data having a best match; and
reverse mapping the combined predicted sets of data having the best match to the first domain.

2. The method of claim 1 , wherein the applying the plurality of prediction models to the set of data in the second domain further comprises applying an Interacting Multiple Models (IMM) approach with a plurality of prediction models to produce a plurality of predicted sets of data in the second domain.

3. The method of claim 1 , wherein the combining the predicted sets of data to generate a combined predicted set of data having a best match further comprises generating a measure of uncertainty associated with the combined predicted set of data having a best match.

4. The method of claim 1 further comprising calculating a level of match of the set of data in the first domain to the predicted set of data to determine a measure of recognition of a situation associated with the set of data in the first domain.

5. The method of claim 1 further comprising quantifying a measure of confidence of a match between the set of data in the first domain and the predicted set of data.

6. The method of claim 1 , wherein the mapping the set of data in the first domain comprises applying a function to the set of data in the first domain that aggregates the set of data in the first domain.

7. The method of claim 1 further comprising representing the set of data in the first domain as a network of nodes and edges and wherein the applying the plurality of prediction models to the set of data in the second domain to produce a plurality of predicted sets of data further comprises applying at least one prediction model to the set of data in the second domain to predict an evolution of the network representing the set of data in the first domain.

8. A device for predicting a future state of a set of data, comprising:
an input device for providing a set of data in a first domain;
memory, coupled to the input device, for storing the set of data in the first domain;
a processor, coupled to the memory, the processor arranged to:
mapping the set of data into a second domain;
applying a plurality of prediction models to the set of data in the second domain to produce a plurality of predicted sets of data including applying a Fourier transform to characterize each of the plurality of prediction models;
combining the predicted sets of data to generate a combined predicted set of data having a best match; and
reverse mapping the combined predicted sets of data having the best match to the first domain.

9. The device of claim 8 , wherein the processor is further arranged to apply an Interacting Multiple Models (IMM) approach with a plurality of prediction models to produce a plurality of predicted sets of data in the second domain.

10. The device of claim 8 , wherein the processor is further arranged to generate a measure of uncertainty associated with the combined predicted set of data having a best match.

11. The device of claim 8 , wherein the processor is further arranged to calculate a level of match of the set of data in the first domain to the predicted set of data to determine a measure of recognition of a situation associated with the set of data in the first domain.

12. The device of claim 8 , wherein the processor is further arranged to apply a function to the set of data in the first domain that aggregates the set of data in the first domain.

13. The device of claim 8 , wherein the processor is further arranged to represent the set of data in the first domain as a network of nodes and edges and to apply at least one prediction model to the set of data in the second domain to predict an evolution of the network representing the set of data in the first domain.

14. At least one non-transitory machine readable medium comprising instructions that, when executed by the machine, cause the machine to perform operations for predicting a future state of a set of data, the operations comprising:
obtaining a set of data in a first domain;
mapping the set of data into a second domain;
applying a plurality of prediction models to the set of data in the second domain to produce a plurality of predicted sets of data including applying a Fourier transform to characterize each of the plurality of prediction models;
combining the predicted sets of data to generate a combined predicted set of data having a best match; and
reverse mapping the combined predicted sets of data having the best match to the first domain.

15. The at least one non-transitory machine readable medium of claim 14 , wherein the applying the plurality of prediction models to the set of data in the second domain further comprises applying an Interacting Multiple Models (IMM) approach with a plurality of prediction models to produce a plurality of predicted sets of data in the second domain.

16. The at least one non-transitory machine readable medium of claim 14 , wherein the combining the predicted sets of data to generate a combined predicted set of data having a best match further comprises generating a measure of uncertainty associated with the combined predicted set of data having a best match.

17. The at least one non-transitory machine readable medium of claim 14 , further comprising calculating a level of match of the set of data in the first domain to the predicted set of data to determine a measure of recognition of a situation associated with the set of data in the first domain.

Assignees

• Raytheon Co

Inventors

• Eck Christopher R

Classifications

• G06N5/04

  Inference or reasoning models · CPC title

• G06Q10/06 Primary

  Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling · CPC title

• G06F17/18

  for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} · CPC title