IMPLEMENTASI ALGORITMA K-MEANS DALAM PENGKLASTERAN MAHASISWA PELAMAR BEASISWA
DOI:
https://doi.org/10.33197/jitter.vol1.iss2.2015.56Abstract
[INA]
Pengelompokan data pelamar beasiswa Bantuan Belajar Mahasiswa (BBM) dikelompokan menjadi 3 kelompok yaitu berhak menerima, dipertimbangkan dan tidak berhak menerima beasiswa. Pengelompokan menjadi 3 kelompok ini berguna untuk memudahkan dalam menentukan penerima beasiswa BBM. Algoritma k-means merupakan algoritma dari teknik clustering yang berbasis partisi. Teknik ini dapat mengelompokan data mahasiswa pelamar beasiswa.
Tujuan dari penelitian ini adalah untuk pengukuran kinerja algoritma, Pengukuran ini di lihat dari hasil cluster dengan menghitung nilai kemurnian (purity measure) dari masing – masing cluster yang di hasilkan. Data yang digunakan dalam penelitian ini adalah data mahasiswa yang mengajukan beasiswa kepada Fakultas Ilmu Komputer UNSIKA sebanyak 36 mahasiswa. Data akan diubah menjadi 3 dataset dengan format yang berbeda-beda, yakni data atribut kodifikasi sebagian, atribut kodifikasi keseluruhan dan atribut data asli. Nilai purity pada dataset data kodifikasi sebagian untuk hasil cluster algoritma k-means sebesar 61.11%. Pada dataset kodifikasi keseluruhan nilai purity hasil cluster algoritma k-means sebesar 80.56%. Dan untuk dataset data asli nilai purity hasil cluster algoritma k-means sebesar 75%. Maka dapat di simpulkan bahwa algoritma k-means lebih cocok digunakan pada dataset dengan format atribut yang dikodifikasi keseluruhan.
[EN]
Data grouping scholarship applicants for Student Learning Assistance (BBM) grouped into 3 categories are entitled to receive, considered and not eligible to receive the scholarship. Grouping into 3 groups is useful to facilitate in determining scholarship recipients. K-means algorithm is an algorithm of clustering technique based partitions. This technique can categorize student data scholarship applicants.
The purpose of this research is to determine the algorithms for performance measurement, and measurement in view of the results of the cluster by calculating the value of purity (purity measure) of each - each cluster is generated. The data used in this research is data of students who apply for a scholarship to the School of Computer Science UNSIKA many as 36 students. The data will be converted into 3 datasets with different formats, ie attribute data codification in part, attributes and attribute the overall codification of the original data. Purity values in a dataset of data codification in part to the results of cluster k-means algorithm by 61.11%. At dataset codification overall value of purity results k-means cluster algorithm by 80.56%. And for the original data dataset purity value results k-means cluster algorithm by 75%. Then it can be concluded that the k-means algorithm is more suitable for use in datasets with formatting attributes that codified a whole
Â
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Submission of a manuscript implies that the submitted work has not been published before (except as part of a thesis or report, or abstract); that it is not under consideration for publication elsewhere; that its publication has been approved by all co-authors. If and when the manuscript is accepted for publication, the author(s) still hold the copyright and retain publishing rights without restrictions. Authors or others are allowed to multiply the article as long as not for commercial purposes. For the new invention, authors are suggested to manage its patent before published. The license type is CC-BY-SA 4.0.