Breast cancer data classification using deep neural network

Machine learning is the one of the famous Artificial Intelligence (AI) technique. Data Mining or Machine Learning techniques are most popular in medical diagnosis, classification, forecasting etc. K-Nearest Neighbor, SVM (Support Vector Machine), DT (Decision Tree),RF (Random Forest),NN (Neural Network) are famous classification algorithms. Neural Network is one of the popular techniques, which is used to refine the verdict of breast cancer. A neural network is otherwise known as Artificial Neural Network(ANN), which is mimicking of biological neurons of human brain. Genetic Algorithm (GA) is emerged bio inspired technique. Selection, Crossover, and Mutation are three operations in Genetic Algorithm. The performance of a genetic algorithm depends on the genetic operators, particularly crossover operator. Grey Wolfoptimization algorithm is inspired from hunting of wolf strategy. Alphas, Beta, Gamma are the three levels ofprocesses. In this paper, a novel hybrid Genetic Grey Wolf based Neural Network is introduced and we named it as G2NN. In the field of medical, we need more accuracy when compared to other field, because it relates to human life. Many researchers found new novel ideas for breast cancer data classification using neural network model. Among many diseases,Breast Cancer is one of the unsafe diseases among women in Indiaand in addition to the whole world. The early detection of cancer helps in curing the disease completely. In many research areas Genetic Algorithm and Grey wolf algorithm are used to train neurons in order to yield good accuracy. In this manuscript, a new GeneticGrey Wolf optimizer based Neural Network is introduced and we compare the proposed work with other techniques like SVM(Support Vector Machine),NN (Neural Network), Genetic based Neural Network, Grey wolf based Neural Network and the experimental results of proposed work produced better result. The proposed algorithm produces 98.9 % of accuracy on UCI Wisconsin breast cancer dataset.

Download Full-text

Emperical Evaluation of Machine Learning algorithms for Breast Cancer Data Classification

International Journal of Computer Sciences and Engineering ◽

10.26438/ijcse/v6i10.346351 ◽

2018 ◽

Vol 6 (10) ◽

pp. 346-351

Author(s):

S. Kumaravel ◽

S. Ophilia Domanica Vithya

Keyword(s):

Breast Cancer ◽

Machine Learning ◽

Learning Algorithms ◽

Data Classification ◽

Machine Learning Algorithms ◽

Breast Cancer Data ◽

Cancer Data

Download Full-text

Breast cancer diagnosis using multiple activation deep neural network

Concurrent Engineering ◽

10.1177/1063293x211025105 ◽

2021 ◽

pp. 1063293X2110251

Author(s):

K Vijayakumar ◽

Vinod J Kadam ◽

Sudhir Kumar Sharma

Keyword(s):

Breast Cancer ◽

Neural Network ◽

Deep Neural Network ◽

Breast Cancer Diagnosis ◽

Activation Function ◽

Linear Functions ◽

Cancer Data ◽

Final Layer ◽

Improved Performance ◽

Hidden Layer

Deep Neural Network (DNN) stands for multilayered Neural Network (NN) that is capable of progressively learn the more abstract and composite representations of the raw features of the input data received, with no need for any feature engineering. They are advanced NNs having repetitious hidden layers between the initial input and the final layer. The working principle of such a standard deep classifier is based on a hierarchy formed by the composition of linear functions and a defined nonlinear Activation Function (AF). It remains uncertain (not clear) how the DNN classifier can function so well. But it is clear from many studies that within DNN, the AF choice has a notable impact on the kinetics of training and the success of tasks. In the past few years, different AFs have been formulated. The choice of AF is still an area of active study. Hence, in this study, a novel deep Feed forward NN model with four AFs has been proposed for breast cancer classification: hidden layer 1: Swish, hidden layer, 2:-LeakyReLU, hidden layer 3: ReLU, and final output layer: naturally Sigmoidal. The purpose of the study is twofold. Firstly, this study is a step toward a more profound understanding of DNN with layer-wise different AFs. Secondly, research is also aimed to explore better DNN-based systems to build predictive models for breast cancer data with improved accuracy. Therefore, the benchmark UCI dataset WDBC was used for the validation of the framework and evaluated using a ten-fold CV method and various performance indicators. Multiple simulations and outcomes of the experimentations have shown that the proposed solution performs in a better way than the Sigmoid, ReLU, and LeakyReLU and Swish activation DNN in terms of different parameters. This analysis contributes to producing an expert and precise clinical dataset classification method for breast cancer. Furthermore, the model also achieved improved performance compared to many established state-of-the-art algorithms/models.

Download Full-text

A Novel Approach for Breast Cancer Data Classification Using Deep Forest Network

Smart Innovation, Systems and Technologies - Intelligent and Cloud Computing ◽

10.1007/978-981-15-6202-0_31 ◽

2020 ◽

pp. 309-316

Author(s):

Bishnupriya Panda ◽

Shrabanee Swagatika ◽

Sipra Sahoo ◽

Debabrata Singh

Keyword(s):

Breast Cancer ◽

Data Classification ◽

Breast Cancer Data ◽

Cancer Data ◽

Novel Approach ◽

Deep Forest

Download Full-text

Using new artificial bee colony as probabilistic neural network for breast cancer data classification

Frontiers in Engineering and Built Environment ◽

10.1108/febe-03-2021-0015 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Habib Shah

Keyword(s):

Breast Cancer ◽

Neural Network ◽

Artificial Bee Colony ◽

Probabilistic Neural Network ◽

Breast Cancers ◽

Breast Cancer Data ◽

Data Set ◽

Content Type ◽

Cancer Data ◽

Bee Colony

PurposeBreast cancer is an important medical disorder, which is not a single disease but a cluster more than 200 different serious medical complications.Design/methodology/approachThe new artificial bee colony (ABC) implementation has been applied to probabilistic neural network (PNN) for training and testing purpose to classify the breast cancer data set.FindingsThe new ABC algorithm along with PNN has been successfully applied to breast cancers data set for prediction purpose with minimum iteration consuming.Originality/valueThe new implementation of ABC along PNN can be easily applied to times series problems for accurate prediction or classification.

Download Full-text