Description

Validation index for validating fuzzy clustering result

Usage

 `1` ```validation.index(object) ```

Arguments

 `object` fuzzy clustering object

Details

This function provide several validation indexs that calculated from fuzzy clustering result. Validation index can be used for choose best optimum parameter.

There are PC, MPC, CE, S, Xie Beni, Kwon, and Tang index. PC (Partition Coefficient), MPC (Modified Partition Coefficient), and CE (Classification Entropy) are calculated from membership matrix. S (Separation Index), Xie Beni, Kwon, and Tang use both distance and membership matrix.

The best cluster result can be decided with minimum value of index, except MPC and PC use maximum value.

Value

validation index object.

Slots

`XB`

Xie Beni Index

`PC`

Partition Coef.

`MPC`

Modifief Partition Coef.

`Kwon`

Kwon Index

`Tang`

Tang Index

`S`

Separation Index

`CE`

Classification Entropy

References

Wang, W., & Zhang, Y. (2007). On Fuzzy Cluster Validity Indices. Fuzzy Sets and System, 2095-2117.

Examples

 ```1 2 3 4``` ```fuzzy.CM(iris[,1:4],K=3,m=2,max.iteration=100,threshold=1e-5,RandomNumber=1234)->cl validation.index(cl)->valid #example for Xie Beni index XB(valid) ```

Example output

```Membership initialiazed randomly

iteration:	 1
iteration:	 2
iteration:	 3
iteration:	 4
iteration:	 5
iteration:	 6
iteration:	 7
iteration:	 8
iteration:	 9
iteration:	 10
iteration:	 11
iteration:	 12
iteration:	 13
iteration:	 14
iteration:	 15
iteration:	 16
iteration:	 17
iteration:	 18
iteration:	 19
iteration:	 20
iteration:	 21
iteration:	 22
iteration:	 23
iteration:	 24
iteration:	 25
iteration:	 26
iteration:	 27
iteration:	 28
Finish :)
[1] 0.1369082
```

advclust documentation built on May 30, 2017, 1:42 a.m.