Skip to main content

Table 3 The results of investigating capability of NEFPROX in learning parameter of membership function (MF) of a FIS reflecting the ability of ANFIS to learn differences (changes of the membership function output values -- bold/underlined)

From: Development of a neuro-fuzzy technique for automated parameter optimization of inverse treatment planning

  

Locations of MF [-1;1.2]

  
 

Membership Functions

Old FIS

New FIS

Location Difference

Mean Percentage Difference

Input

MF 1

-1.0

-1.0

0.0

0.83%

 

MF 2

1.0

0.9

0.1

 
 

MF 1

-1.0

-1.0

0.0

 
 

MF 2

1.0

1.0

0.0

 
 

MF 1

-1.0

-1.0

0.0

 
 

MF 2

1.0

1.0

0.0

 

Output

MF 1

-1.0

-1.2

0.2

8.88%

 

MF 2

0.5

0.2

0.3

 
 

MF 3

1.0

1.2

0.0

 
 

MF 1

-1.0

-1.2

0.2

 
 

MF 2

0.5

0.4

0.1

 
 

MF 3

1.0

1.2

0.2

 
 

MF 1

-1.0

-1.2

0.2

 
 

MF 2

0.5

0.3

0.2

 
 

MF 3

1.0

1.2

0.2