This paper is published in Volume-3, Issue-4, 2017
Area
Image Processing
Author
Smitha Hallad, Prof. Roopa Hubballi
Org/Univ
KLE Society's Dr. M. S. Sheshgiri College of Engineering and Technology, Belagavi, Karnataka, India
Pub. Date
19 July, 2017
Paper ID
V3I4-1196
Publisher
Keywords
NN-Neural Network, RBF-Radial Basis Function, FF-feed forward, BP-BackPropagation.

Citationsacebook

IEEE
Smitha Hallad, Prof. Roopa Hubballi. Comparing Three Neural Network Techniques in the Classification of Breast Cancer, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Smitha Hallad, Prof. Roopa Hubballi (2017). Comparing Three Neural Network Techniques in the Classification of Breast Cancer. International Journal of Advance Research, Ideas and Innovations in Technology, 3(4) www.IJARIIT.com.

MLA
Smitha Hallad, Prof. Roopa Hubballi. "Comparing Three Neural Network Techniques in the Classification of Breast Cancer." International Journal of Advance Research, Ideas and Innovations in Technology 3.4 (2017). www.IJARIIT.com.

Abstract

Breast cancer is becoming common disease in women nowadays. Breast cancer is nothing but mass or group of uncontrollable growth of cells in body is called tumor. Benign is an initial stage of cancer and malignant is last stage of the cancer, these two are the stages of breast cancer. A man can survive or rate of survival is more in benign stage by taking a very good treatment by radiologist where as in malignant stage a man cannot survive directly it leads to death. Neural network is powerful classifier. Before classifying the neural network is to be trained by collecting the data or images from different datasets. After training the large dataset test the new data sample or breast image by extracting the new features from new image and then classifying the image into cancerous or non-cancerous. Finally, the results are compared with three neural network 1) Radial basis function 2) Feed forward neural network and 3) Back propagation neural network. Accuracy is calculated 95% of RBF, 96% of FFNN and 100% of BPNN.