Hyperparameter Tuning and Pipeline Optimization via Grid Search Method and Tree-Based AutoML in Breast Cancer Prediction

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@Article{Mat-Radzi:2021:JPM,

• author = "Siti Fairuz {Mat Radzi} and Muhammad Khalis {Abdul Karim} and M Iqbal Saripan and Mohd Amiruddin {Abd Rahman} and Iza Nurzawani {Che Isa} and Mohammad Johari Ibahim",
• title = "Hyperparameter Tuning and Pipeline Optimization via Grid Search Method and {Tree-Based} {AutoML} in Breast Cancer Prediction",
• journal = "Journal of Personalized Medicine",
• year = "2021",
• volume = "11",
• number = "10",
• keywords = "genetic algorithms, genetic programming, TPOT",
• ISSN = "2075-4426",
• URL = "https://www.mdpi.com/2075-4426/11/10/978",
• DOI = "doi:10.3390/jpm11100978",
• code_url = "https://github.com/sitifairuz9609/TPOT-Automated-Machine-Learning-with-Radiomics-Features",
• abstract = "Automated machine learning (AutoML) has been recognised as a powerful tool to build a system that automates the design and optimises the model selection machine learning (ML) pipelines. In this study, we present a tree-based pipeline optimisation tool (TPOT) as a method for determining ML models with significant performance and less complex breast cancer diagnostic pipelines. Some features of pre-processors and ML models are defined as expression trees and optimal gene programming (GP) pipelines, a stochastic search system. Features of radiomics have been presented as a guide for the ML pipeline selection from the breast cancer data set based on TPOT. Breast cancer data were used in a comparative analysis of the TPOT-generated ML pipelines with the selected ML classifiers, optimised by a grid search approach. The principal component analysis (PCA) random forest (RF) classification was proven to be the most reliable pipeline with the lowest complexity. The TPOT model selection technique exceeded the performance of grid search (GS) optimisation. The RF classifier showed an outstanding outcome amongst the models in combination with only two pre-processors, with a precision of 0.83. The grid search optimised for support vector machine (SVM) classifiers generated a difference of 12percent in comparison, while the other two classifiers, naive Bayes (NB) and artificial neural network--multilayer perceptron (ANN-MLP), generated a difference of almost 39percent. The method's performance was based on sensitivity, specificity, accuracy, precision, and receiver operating curve (ROC) analysis.",
• notes = "also known as \cite{jpm11100978}",

}

Genetic Programming entries for Siti Fairuz Bt Mat Radzi Muhammad Khalis Bin Abdul Karim M Iqbal Bin Saripan Mohd Amiruddin Bin Abd Rahman Iza Nurzawani binti Che Isa Mohammad Johari Bin Ibahim

Citations