Open AccessBook data grouping in libraries using the k-means clustering method
Author(s) -
Saut Parsaoran Tamba,
M. Diarmansyah Batubara,
Windania Purba,
Maria Sihombing,
Victor Marudut Mulia Siregar,
Jaidup Banjarnahor
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1230/1/012074
Subject(s) - cluster analysis , sorting , cluster (spacecraft) , set (abstract data type) , computer science , group (periodic table) , data set , space (punctuation) , process (computing) , information retrieval , k means clustering , document clustering , data mining , algorithm , artificial intelligence , physics , quantum mechanics , programming language , operating system
Clustering is a process of sorting out a data set to become separate cluster groups and each has similarities, and aims to group the data into one cluster. This research aims to group the book information which is contained in Universitas Prima Indonesia, by using K-means clustering method. On this K-means clustering algorithm, the variables used as input are : NIM, Name, Book Title and Author. The output produced consists of 3 clusters, those are (C1) the most frequently borrowed book, (C2) book that is often borrowed, and (C3) book that is rarely borrowed. With the use of this K-means Clustering method, the final result obtained consists of member of cluster 1 as many as 19 members, member of cluster 2 as many as 22 members, and member of cluster 3 as many as 19 members. The information of grouping this book data can be used by the library. In the case of the selection of books that must be added to the library and to minimize the books that are rarely borrowed so as not to cause a buildup of books that are rarely borrowed, so there is a space for books to be added into the library.