Imputing Missing Values in Mammography Mass Dataset: Will it Increase Classification Performance of Machine Learning Algorithms?

Zahriah, Sahri and Fahmi, Arif and Sharifah Sakinah Syed, Ahmad and Rabiah, A (2017) Imputing Missing Values in Mammography Mass Dataset: Will it Increase Classification Performance of Machine Learning Algorithms? Proceeding 8th International Conference on Agricultural, Biological, Environmental and Medical Sciences (ABEMS-2017) Oct. 11-12, 2017 Bali (Indonesia).

Full text not available from this repository.
Official URL: http://eirai.org/images/proceedings_pdf/IAE1017305...

Abstract

Mammography is one of the most effective methods for breast cancer screening and the resulting images are normally reported using the BI-RADS standard. Missing values are found in this BI-RADS dataset which can reduce the classification performance of any machine learning algorithm. This study applies a few established imputation methods that estimate and replace the missing values found in a mammogram mass dataset. Then, a few machine learning algorithms learnt from these imputed datasets to classify between benign and malignant masses. Using classification accuracy as the performance metric, the experimental results showed an increase in accuracy for majority of the combination of machine learning algorithms algorithm and imputation methods.

Item Type: Article
Subjects: T Technology > T Technology (General)
Depositing User: Asep Kamaludin
Date Deposited: 08 Nov 2018 06:35
Last Modified: 08 Nov 2018 06:55
URI: http://eprints.itenas.ac.id/id/eprint/194

Actions (login required)

View Item View Item