NEURO TYPE-2 FUZZY BASED METHOD FOR DECISION MAKING

• US 20110071969A1
• Filed: 05/26/2009
• Published: 03/24/2011
• Est. Priority Date: 05/23/2008
• Status: Active Grant

• Current Assignee: Temenos Headquarters SA (Temenos AG)
• Original Assignee: Logical Glue Ltd. (Temenos AG)
• Inventors: Doctor, Faiyaz, Hagras, Hani
• Granted Patent: US 8,515,884 B2
• Time in Patent Office: Days
• US Class Current: 706/15
• CPC Class Codes: G05B 13/0275 using fuzzy logic only
• CPC Class Codes: G06N 3/043 based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
• CPC Class Codes: G06N 7/023 Learning or tuning the parameters of a fuzzy system

Abstract

According to a first aspect of the invention there is provided a method of decision-making comprising: a data input step to input data from a plurality of first data sources into a first data bank, analysing said input data by means of a first adaptive artificial neural network (ANN), the neural network including a plurality of layers having at least an input layer, one or more hidden layers and an output layer, each layer comprising a plurality of interconnected neurons, the number of hidden neurons utilised being adaptive, the ANN determining the most important input data and defining therefrom a second ANN, deriving from the second ANN a plurality of Type-1 fuzzy sets for each first data source representing the data source, combining the Type-1 fuzzy sets to create Footprint of Uncertainty (FOU) for type-2 fuzzy sets, modelling the group decision of the combined first data sources; inputting data from a second data source, and assigning an aggregate score thereto, comparing the assigned aggregate score with a fuzzy set representing the group decision, and producing a decision therefrom. A method employing a developed ANN as defined in Claim 1 and extracting data from said ANN, the data used to learn the parameters of a normal Fuzzy Logic System (FLS).

Claims

1. A method of decision-making comprising:

a data input step to input data from a plurality of first data sources into a first data bank;

analyzing said input data by means of a first adaptive artificial neural network (ANN), the neural network including a plurality of layers having at least an input layer, one or more hidden layers and an output layer;

each layer comprising a plurality of interconnected neurons, the number of hidden neurons utilized being adaptive;

the ANN determining the most important input data and defining therefrom a second ANN;

deriving from the second ANN a plurality of Type-1 fuzzy sets for each first data source representing the data source, combining the Type-1 fuzzy sets to create Footprint of Uncertainty (FOU) for type-2 fuzzy sets, modeling the group decision of the combined first data sources; and

inputting data from a second data source, and assigning an aggregate score thereto, comparing the assigned aggregate score with a fuzzy set representing the group decision, and producing a decision therefrom.

2. A method according to claim 1, wherein the internal consistency of data from a first data source is determined.

3. A method according to claim 1, wherein the consistency of data from a first data source is compared with the consistencies of other first data sources.

4. A method according to claim 2, wherein a weighting value is assigned to the consistency.

5. A method according to claim 4 wherein a first data source having a weighting value outside a preset range is discounted from further calculations.

6. A method according to claim 4 wherein further data from a first source is input, the consistency value for said source being recalculated.

7. A method according to claim 6 wherein should the recalculated consistency weighting value lie inside the preset range, the first data source is incorporated in further calculations.

8. A method according to claim 1 wherein the first data source is a human expert in the field of the particular decision.

9. A method according to claim 1, including the step of identifying the dominant factors affecting an outcome, assigning a weighting function to said dominant factors such that the decision produced is based on the dominant factors to a greater degree than those not so identified.

10. A method according to claim 9, wherein those factors having a weighing value below a outside preset value range are discounted from the decision making.

11. A method according to claim 1, allowing a desired decision to be entered, the method then determining required input data to achieve said decision.

12. A method according to claim 1, wherein the second ANN is used in combination with a generated adaptive Fuzzy Logic System (FLS) employing a plurality of Type-1 fuzzy sets for each first data source representing the data source, together forming a neuro-fuzzy model used to develop a predictive controller that can predict a specific output given specific input states.

13. A method according to claim 8, wherein inputs to the system are based on the dominant input factors selected from the input data.

14. A method according to claim 1, wherein a third ANN is used in combination with a generated adaptive Fuzzy Logic System (FLS) using a plurality of Type-1 fuzzy sets for each first data source to represent the data source, said FLS and Type-1 fuzzy sets together forming a neuro-fuzzy model used to develop an optimizer enabled to find the optimal input values to reach a given target output.

15. A method employing a developed ANN as defined in claim 1 and extracting data from it which is used to learn the parameters of a normal Fuzzy Logic System (FLS).