An Efficient Feed Foreword Network Model with Sine Cosine Algorithm for Breast Cancer Classification

An Efficient Feed Foreword Network Model with Sine Cosine Algorithm for Breast Cancer Classification

Santosh Kumar Majhi (VSS University of Technology, Burla, India)
Copyright: © 2018 |Pages: 14
DOI: 10.4018/IJSDA.2018040101

Abstract

This article describes how breast cancer is the most common invasive cancer in females worldwide and is major cause of deaths. The diagnoses of breast cancer include mammograms, breast ultrasound, magnetic resonance imaging (MRI), ductogram and biopsy. Biopsy is best and only way to know if the breast tumour is cancerous. Reports say that positive detection of breast cancer through biopsy can reach as low as 10%. So many statistical techniques and cognitive science approaches like artificial intelligence are being used to detect the type of breast cancer in a patient. This article presents the breast cancer classification using a feed foreword neural network trained by a sine-cosine algorithm. The superiority of the SCA-NN is shown by experimenting on the Wisconsin Hospital data set and comparing with the recently reported results. The evaluations show that the proposed approach is very robust, effective and gives better correct classification as compared to other classifiers.
Article Preview

1. Introduction

Breast cancer is the most common invasive cancer in females worldwide and is major cause of deaths. Experts claim that there exists no definite way to know and say why one person develops the disease while another does not. We are only aware of certain risk factors that can impact the odds of being diagnosed with one. The ability to detect early is the only way to treat breast cancer. Appropriate tests are needed to differentiate benign tumor from malignant one. The most common tests include mammograms, breast ultrasound, magnetic resonance imaging (MRI), ductogram and biopsy. Biopsy is best and only way to know if the breast tumor is cancerous. This is when a small sample is taken from the suspected area and is tested in a lab, in spite of this, positive detection of breast cancer through biopsy can reach as low as 10%. Many statistical techniques and cognitive science approaches like artificial intelligence are being used to detect the “malignant” group in a patient. The breast cancer diagnosis (BCD) problem is labelled as a classification problem. Researchers from various fields are drawn to study this problem and are using machine learning algorithms, artificial neural networks (ANN), Support Vector Machines (SVM) and other data mining techniques. ANN, SVM, and PNN have become effective alternatives in modeling classification problems due to their capability to capture complex nonlinear relationships among variables. Recently, functional networks have been introduced as a very effective scheme for the statistical pattern recognition problems and nonlinear complex prediction. Machine learning can be applied to get a cheap and reliable diagnosis. One of the methods of machine learning is feed forward artificial neural network (FFANN). The FFANN can be used to classify them into malignant and benign. The objective of this paper is to classify and diagnose breast cancer.

We have used various parameters of breast cancer, like: Clump Thickness, Uniformity of Cell Size, Uniformity of Cell Shape, Marginal Adhesion, Single Epithelial Cell Size, Bare Nuclei, Bland Chromatin, Normal Nucleoli and Mitoses are used for predicting the presence of breast cancer in a given sample.

In this paper, feed forward artificial neural network has been used. To optimise the weights of the model, Sine-Cosine Algorithm is used due to its proven advantages and application in various optimization problems reported in the litterateur (see Table 1). In section 2 Feed Forward Artificial Neural Network is discussed. In section 3 SCA is discussed. In section 4 the result is discussed. In section 5 comparisons with different published results are given. Finally, Section 6 concludes the work.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 8: 4 Issues (2019): Forthcoming, Available for Pre-Order
Volume 7: 4 Issues (2018): 3 Released, 1 Forthcoming
Volume 6: 4 Issues (2017)
Volume 5: 4 Issues (2016)
Volume 4: 4 Issues (2015)
Volume 3: 4 Issues (2014)
Volume 2: 4 Issues (2013)
Volume 1: 4 Issues (2012)
View Complete Journal Contents Listing