TY - JOUR
T1 - Cerebral Infarction Classification Using the K-Nearest Neighbor and Naive Bayes Classifier
AU - Rukmawan, S. H.
AU - Aszhari, F. R.
AU - Rustam, Z.
AU - Pandelaki, J.
N1 - Funding Information:
This research supported financially by the Ministry of Research and Higher Education Republic of Indonesia (KEMENRISTEKDIKTI) with PTUPT 2020 research grant scheme. And we would like to thank Dr. dr. Jacub Pandelaki, Sp.Rad(K) from Department of Radiology, Cipto Mangunkusumo, for the dataset.
Publisher Copyright:
© Published under licence by IOP Publishing Ltd.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2021/2/15
Y1 - 2021/2/15
N2 - Cerebral infarction is one of the causes of stroke in the brain and is included in ischemic stroke. To detect infarction in the brain, classification in machine learning can be used. They are k-Nearest Neighbor (kNN) and Naive Bayes (NB). kNN is a simple and well-known machine learning method with high accuracy values. however, kNN can produce sub-optimal results if very little training data is used. Because it will produce accuracy from a biased model and has less than optimal performance. Meanwhile, Naive Bayes Classifier has a better level of accuracy compared to other classifier models. And only requires a small training test to get high accuracy. Therefore, this study will compare 2 different classifications to get the highest accuracy in the brain infarction dataset obtained from the Department of Radiology, dr. Cipto Mangunkusumo Hospital (RSCM). The accuracy of this method reaches 91% for kNN and 97% for Naive Bayes.
AB - Cerebral infarction is one of the causes of stroke in the brain and is included in ischemic stroke. To detect infarction in the brain, classification in machine learning can be used. They are k-Nearest Neighbor (kNN) and Naive Bayes (NB). kNN is a simple and well-known machine learning method with high accuracy values. however, kNN can produce sub-optimal results if very little training data is used. Because it will produce accuracy from a biased model and has less than optimal performance. Meanwhile, Naive Bayes Classifier has a better level of accuracy compared to other classifier models. And only requires a small training test to get high accuracy. Therefore, this study will compare 2 different classifications to get the highest accuracy in the brain infarction dataset obtained from the Department of Radiology, dr. Cipto Mangunkusumo Hospital (RSCM). The accuracy of this method reaches 91% for kNN and 97% for Naive Bayes.
KW - Classsification
KW - K-nearset neighbor
KW - naive bayes classifier
UR - http://www.scopus.com/inward/record.url?scp=85101768882&partnerID=8YFLogxK
U2 - 10.1088/1742-6596/1752/1/012045
DO - 10.1088/1742-6596/1752/1/012045
M3 - Conference article
AN - SCOPUS:85101768882
SN - 1742-6588
VL - 1752
JO - Journal of Physics: Conference Series
JF - Journal of Physics: Conference Series
IS - 1
M1 - 012045
T2 - 3rd International Conference on Statistics, Mathematics, Teaching, and Research 2019, ICSMTR 2019
Y2 - 9 October 2019 through 10 October 2019
ER -