Comparative performance analysis of machine learning models for breast cancer diagnosis

Ullah, Ghufran; Haiyan, Haiyan

doi:10.29322/ijsrp.10.01.2020.p9742

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The gradient boosting was found to provide the best accuracy which is 74.14% when compared to logistic regression, decision tree, random forest, k-nearest neighbor, SVM and naïve Bayes [9]. However, it was found that the highest accuracy belongs to random forest when compared to logistic regression, decision tree, k-nearest neighbor, naïve Bayes, SVM, and neural network [10]. Instead of using individual technique, bagging is used for the classification [11].…”

Section: Introductionmentioning

confidence: 97%

Cancer Prediction Using Cascade Generalization and Duo Output Neural Network

Nilnumpetch¹,

Amornsamankul²,

Kraipeerapun³

2022

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

This paper proposes the combination of cascade generalization and duo output neural network based on feedforward backpropagation neural networks for cancer prediction. Duo output neural network is a neural network that is created based on two opposite targets in order to predict two opposite results. Cascade generalization is a technique that consists of a set of machines that are sorted together in which the predicted output produced from the previous machine plus the original training input are used for the creation of each machine. In this study, cascade generalization is organized in two levels: the base level and the meta level. In this research, duo output neural network is trained in each level of cascade generalization. Two outputs produced from the base level which are truth output and non-falsity output are averaged. The average result plus the original input are used for training a machine in meta level. The proposed technique is tested using two cancer datasets from UCI machine learning repository and found that our technique provides the best overall results when compared with three individual techniques.

show abstract

Section: Introductionmentioning

confidence: 97%