Search for collections on Itenas Repository

Analysis of Logistic Regression Algorithm for Predicting Types of Breast Cancer Based on Machine Learning

Maulidia, Annisa and Lidyawati, Lita and Jambola, Lucia and Kristiana, Lisa (2021) Analysis of Logistic Regression Algorithm for Predicting Types of Breast Cancer Based on Machine Learning. In: The 3rd Faculty of Industrial Technology International Congress 2021 International Conference, 28-29 October, 2021, Bandung.

[img]
Preview
Text
Analysis of logistic regression algorithm for predicting types of breast cancer based on machine learning.pdf

Download (2MB) | Preview

Abstract

Algorithms in machine learning are a very important part because the type of algorithm used has an impact on the level of prediction accuracy and classification of a data set that is used. Appropriate use is accompanied by machine learning capabilities, namely being able to study past patterns, making machine learning have an advantage in prediction accuracy which can reach up to 90%. Therefore, machine learning has the opportunity to be an alternative that can avoid diagnostic errors that occur in the case of breast cancer. Breast cancer is one of the highlights of the impact of diagnostic errors because there are 10-30% of cases due to diagnostic errors, thus we need an alternative that can help reduce these diagnostic errors. In this study, an analysis of the logistic regression algorithm was carried out using the python programming language. The evaluation method is very important to know the performance in the prediction process. By using three evaluation methods, namely cross-validation k=10, confusion matrix, and ROC AUC. From the results of this study, it was found that the algorithm Logistic regression has an accuracy of 96.5% and an error of 0.19.

Item Type: Conference or Workshop Item (Paper)
Subjects: Q Science > Q Science (General)
Divisions: Paper
Depositing User: Azizullah Putri Akbar
Date Deposited: 31 Mar 2023 04:10
Last Modified: 31 Mar 2023 04:10
URI: http://eprints.itenas.ac.id/id/eprint/2201

Actions (login required)

View Item View Item