Comparison of the Normalization Method of Data in Classifying Brain Tumors with the k-NN Algorithm

DOI

10.2991/978-94-6463-174-6_3How to use a DOI?

Keywords

Data Normalization; brain tumors; classification; k-NN

Abstract

One way to examine patients with brain tumors is the radiological examination, including Magnetic Resonance Image (MRI) with contrast. The classification process is needed to differentiate MRI images of people with brain tumors from those without brain tumors. The classification was based on MRI image feature extraction results with statistical features. Different statistical feature scale values for each dataset parameter can complicate the classification process. An unbalanced range of values can affect the quality of the classification results. For this reason, it is necessary to pre-process the data. The pre-processing method used is data transformation with normalization. Three normalization methods are used in data transformation: Min-Max normalization, z-score normalization, and T-Score Normalization. Data processed from each normalization method will be compared to see the results of the best classification accuracy using the K-NN algorithm. The k used in the comparison are 3, 5, 7, and 11. The normalized data from the dataset is divided into test data and training data with k-fold cross-validation. Based on the results of the classification test with the K-NN algorithm shows that the best accuracy lies in the Brain Tumor dataset, which has been normalized using the Min-Max normalization method with K = 3 of 85.92%. The average obtained is 79.68%.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Rinci Kembang Hapsari
AU  - Abdullah Harits Salim
AU  - Budanis Dwi Meilani
AU  - Tutuk Indriyani
AU  - Aery Rachman
PY  - 2023
DA  - 2023/05/22
TI  - Comparison of the Normalization Method of Data in Classifying Brain Tumors with the k-NN Algorithm
BT  - Proceedings of the 1st International Conference on Neural Networks and Machine Learning 2022 (ICONNSMAL 2022)
PB  - Atlantis Press
SP  - 21
EP  - 29
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-174-6_3
DO  - 10.2991/978-94-6463-174-6_3
ID  - Hapsari2023
ER  -