@article{MAKHILLJEAS2017121714777,
    title = {Point Operation to Enhance the Performance of Fuzzy Neural Network
Model for Breast Cancer Classification},
    journal = {Journal of Engineering and Applied Sciences},
    volume = {12},
    number = {17},
    pages = {4405-4410},
    year = {2017},
    issn = {1816-949x},
    doi = {jeasci.2017.4405.4410},
    url = {https://makhillpublications.co/view-article.php?issn=1816-949x&doi=jeasci.2017.4405.4410},
    author = {Dhoriva Urwatul and},
    keywords = {Point operation,Fuzzy Neural Network (FNN),breast cancer,mammographic images,models,GLCM},
    abstract = {Stadium of breast cancer can be detected by using mammographic images. The accuracy is
strongly influenced by the image quality. In this study, we propose a point operation of intensity adjustment
to enhance the quality of the images. We implement the Fuzzy Neural Network (FNN) Model for breast cancer
classification based on the enhaced mammographic images. Then, the images are extracted by using Gray Level
Co-occurrence Matrix (GLCM) method to obtain the parameter values of the images. The fuzzification of the
parameter values is required to generate the inputs of the FNN Model which are in the form of fuzzy numbers
instead of classic numbers. We compare the performances of the FNN models with and without the point
operation. The results demonstrate that on the training data both FNN models deliver satisfied performance with
no misclassified data. While on the testing data, the FNN Model with point operation outperforms the FNN
model without point operation. This result suggests a strong effectiveness of the mammographic images
preprocessing point operation to increase the accuracy of the FNN Model to classify breast cancer.}
    }