MULTIFACTORIAL OPTIMIZATION SYSTEM AND METHOD

• US 20180049043A1
• Filed: 10/05/2017
• Published: 02/15/2018
• Est. Priority Date: 10/04/2005
• Status: Active Application

• Current Assignee: Steven Mark Hoffberg
• Original Assignee: Steven Mark Hoffberg
• Inventors: Hoffberg, Steven M.
• Application Number:
  US15/726,031
• Publication Number:
  US 20180049043A1
• Time in Patent Office: Days
• CPC Class Codes: G06Q 10/0631 Resource planning, allocation, distributing or scheduling for enterprises or organisations
• CPC Class Codes: G06Q 10/0635 Risk analysis of enterprise or organisation activities
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 10/103 Workflow collaboration or project management
• CPC Class Codes: G06Q 20/065 using e-cash
• CPC Class Codes: G06Q 20/22 Payment schemes or models
• CPC Class Codes: G06Q 20/40 Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/08 Auctions
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
• CPC Class Codes: G06Q 50/188 Electronic negotiation
• CPC Class Codes: H04W 16/28 using beam steering
• CPC Class Codes: H04W 64/003 locating network equipment
• CPC Class Codes: H04W 72/541 using the level of interference
• CPC Class Codes: H04W 84/18 Self-organising networks, e.g. ad-hoc networks or sensor networks

Abstract

A method for controlling a system involving a physical event or process, comprising: providing a computer-implemented physical model of the physical event or process; performing at least a first transform of a time series of data in a time domain representing the physical event or process event into a non-time domain, according to a first transform algorithm to produce a transformed data set; processing the transformed data set to reduce noise and, dependent on the computer-implemented physical model, to extract at least one feature of the transformed data set, to produce a filtered data set and a classification of the at least one feature; and producing a control signal in dependence on at least the classification of the at least one feature, for at least one of: (a) altering the physical event or process, and (b) altering a relationship of a user of the system to the physical event or process.

Claims

1. A method for controlling a system involving a physical event or process, comprising:

providing a computer-implemented physical model of the physical event or process;

performing at least a first transform of a time series of data in a time domain representing the physical event or process event into a non-time domain, according to a first transform algorithm to produce a transformed data set;

processing the transformed data set to reduce noise and, dependent on the computer-implemented physical model, to extract at least one feature of the transformed data set, to produce a filtered data set and a classification of the at least one feature; and

producing a control signal in dependence on at least the classification of the at least one feature, for at least one of;

(a) altering the physical event or process, and (b) altering a relationship of a user of the system to the physical event or process.

2. The method according to claim 1,

wherein the physical or process event is associated with a risk parameter and a reliability parameter for the at least one feature, the risk parameter representing a predicted severity associated with a respective feature, and the reliability parameter representing a statistical probability distribution of the representation of the severity of the respective feature;

further comprising determining a relevance to the user of the at least one feature, based on both the risk and the reliability of the respective feature;

wherein the control signal is further dependent on the relevance to the user.

3. The method according to claim 2, wherein the at least one feature comprises a plurality of features, further comprising ranking the plurality of features according to at least the relevance to the user.

4. The method according to claim 2, wherein the predicted severity associated with the respective feature is expressed as an economic parameter having an associated cost or value.

5. The method according to claim 1, wherein the control signal is further dependent on a user profile representing subjective preferences of a user.

6. The method according to claim 1, wherein the control signal is further dependent on a risk-tolerance of a user of the system.

7. The method according to claim 1, wherein the first transform algorithm transforms the data between a time-domain and a hybrid time-frequency-domain.

8. The method according to claim 1, wherein the physical event or process relates to at least one of traffic and weather conditions associated with one or more regions of a roadway.

9. A method for analyzing a time-domain data set representing a physical event or process, each element comprising a magnitude, comprising:

performing at least a time-frequency domain transform of the time-domain data set;

filtering the transformed data set selectively in dependence on a noise model;

further transforming the filtered transformed data set,

predicting, with an automated processor, a time-domain magnitude of an element not represented in the data set at a specified time; and

producing a control signal output, in dependence on the predicted time-domain magnitude.

10. The method according to claim 9, further comprising applying a distance-selective function to the time-frequency hybrid domain representation of the data.

11. The method according to claim 9, further comprising applying a spatial filtering function to the time-frequency hybrid domain representation of the data.

12. The method according to claim 9, wherein at least one data point within the data set is associated with a probabilistic distribution, further comprising performing the at least one transform between the time domain and a time-frequency hybrid domain dependent on at least the probabilistic distribution.

13. The method according to claim 9, wherein a plurality of features represented within the data set are associated with respective probabilistic distributions expressed as probability density functions, further comprising transforming the probability density functions between the time domain and a time-frequency hybrid domain.

14. The method according to claim 13, further comprising performing the further transform of the probability density functions between the time domain and a time-frequency hybrid domain as at least one inverse transform between the hybrid time-frequency-domain and the time-domain.

15. The method according to claim 9, wherein the filtered transformed data set is represented as a sparse data matrix.

16. The method according to claim 9, wherein the data set represents a plurality of features, each respective feature comprising an associated a risk parameter and an associated reliability parameter independent of the associated risk parameter, said risk parameter representing a predicted cost or value associated with the respective feature and said reliability parameter representing a statistical probability distribution of the representation of the cost or value.

17. A control system, comprising:

a communication port;

a cryptographic processor configured to;

verify an authenticity of information defining a unit of a virtual currency having a unique index number, generated according to a cryptographic function, according to an audit trail comprising a source identifier and a chain of prior owners; and

conduct a transaction based on a transfer of the unit of virtual currency through the communication port, after the authenticity is verified; and

generate a control signal dependent on the conducted transaction.

18. The control system according to claim 17, wherein the unit of virtual currency has a value which is different from at least one unit of the virtual currency previously produced.

19. The control system according to claim 17, further comprising assigning a monetary value to the unit of virtual currency, wherein the conducted transaction comprises exchanging the unit of virtual currency for a unit of monetary currency.

20. The control system according to claim 17, wherein the control system comprises a game theoretic competition for allocation of at least one physical resource.