2020
DOI: 10.26418/jp.v6i1.37606
|View full text |Cite
|
Sign up to set email alerts
|

Reduksi Atribut Menggunakan Information Gain untuk Optimasi Cluster Algoritma K-Means

Abstract: Proses clustering dengan algoritma K-Means pada dataset yang memiliki banyak atribut akan mempengaruhi besarnya jumlah iterasi. Pada penelitian ini, metode Information Gain digunakan untuk mereduksi atribut dataset. Dataset yang telah direduksi atribut akan dilanjutkan proses clustering dengan K-Means. Dataset yang dianalisis pada penelitian ini adalah data Hepatitis C Virus yang diperoleh dari UCI Machine Learning Repository, dengan 29 atribut dan 1385 jumlah data. Hasil penelitian ini menunjukkan bah… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
2
0
9

Year Published

2021
2021
2023
2023

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 11 publications
(11 citation statements)
references
References 5 publications
0
2
0
9
Order By: Relevance
“…The test is carried out by determining the smallest value from the DBI, where the smallest value in the number of clusters is 0.175 after the data has been processed. Study [17], the DBI value for the conventional K-Means was 2.1972, while the DBI for the K-Means which had been reduced from 1 attribute to 5 attributes obtained an average DBI value of 2.0290, 1.8771, 1.8641, 1.8389, and 1.8117. Study [14], The method used in this study is the K-method.…”
Section: Related Researchmentioning
confidence: 84%
“…The test is carried out by determining the smallest value from the DBI, where the smallest value in the number of clusters is 0.175 after the data has been processed. Study [17], the DBI value for the conventional K-Means was 2.1972, while the DBI for the K-Means which had been reduced from 1 attribute to 5 attributes obtained an average DBI value of 2.0290, 1.8771, 1.8641, 1.8389, and 1.8117. Study [14], The method used in this study is the K-method.…”
Section: Related Researchmentioning
confidence: 84%
“…K-means is one of the methods in machine learning that can group data or clustering a data into the form of one or more clusters so that data with the same characteristics are grouped into the same cluster and data with different characteristics are grouped into different groups [12]. In detail, K-means algorithm works is as follows:…”
Section: B K-meansmentioning
confidence: 99%
“…Selain itu dilakukan pula reduksi fitur pada pengelompokan dengan k-means dan FCM. Reduksi fitur menggunakan information gain untuk mengoptimalkan hasil clustering dengan k-means juga telah dilakukan [12]. Untuk meningkatkan performa FCM, pengelompokan dilakukan dengan menghitung bobot fitur individu secara otomatis dan secara bersamaan mereduksi komponen fitur yang tidak relevan [13].…”
Section: Pendahuluanunclassified