GBFES

Usage

You can run GBRAD.py:

if __name__ == '__main__':
    sigma = 8   # Set the parameter for calculating the fuzzy similarity relation.
    lammda = 0.35  # Set the trade-off factor between the LOF of the sample and the fuzzy relative entropy of the GB to which the sample belongs.

    data_name = 'iris_Irisvirginica_11_variant1'
    Exmaple = io.loadmat(r"..\\datasets\\" + data_name)
    data = Exmaple['trandata'][:, :-1]  # data
    target = Exmaple['trandata'][:, -1]  # label

    samples_scores = GBFES(data, sigma, lammda)
    print(samples_scores)

You can get outputs as follows:

out_scores =
[0.56852951 0.56220482 0.56166894 0.56610321 0.57634269 0.55168037
 0.67227353 0.57349341 0.65231337 0.56491212 0.54824842 0.59392103
 0.56220482 0.67253473 0.58359968 0.65078837 0.54863375 0.56499992
 0.54970207 0.54715088 0.61126751 0.54072254 0.67227353 0.65
 0.65       0.56540983 0.65       0.57693929 0.57016597 0.55559967
 0.56109633 0.64135861 0.56231636 0.58724613 0.56491212 0.63823249
 0.640307   0.56491212 0.63064544 0.56677136 0.56607287 0.67246558
 0.61425543 0.65       0.54072254 0.56650682 0.54991706 0.57286746
 0.55033502 0.57996698 0.6758916  0.63183821 0.66304807 0.57377668
 0.59896377 0.55102147 0.62754754 0.62876961 0.59320891 0.58519577
 0.65       0.63120673 0.62609478 0.61751452 0.56229379 0.65305861
 0.65       0.55185371 0.67965351 0.556827   0.64195518 0.58959254
 0.63106175 0.59369354 0.59253188 0.59253188 0.59527081 0.65750005
 0.62973865 0.55644034 0.56314407 0.57683223 0.54616373 0.63033943
 0.65       0.63731164 0.65360681 0.64847723 0.55443809 0.55831154
 0.5353676  0.62180784 0.54048951 0.61701362 0.54362486 0.55613474
 0.5514881  0.59873914 0.61774073 0.55668029 0.79567881 0.83863296
 0.86587723 0.83159342 0.79567881 0.85099034 0.86766416 0.83159342
 0.79882563 0.80796655 0.83274632]

Citation

## Contact
If you have any questions, please contact wangsihan0713@foxmail.com or yuanzhong@scu.edu.cn.