Student Class Grouping System for Informatics Engineering Using K-Means Clustering Method

Tiara Dinar Sabina, Muhammad Arhami, Muhammad Rizka

Abstract


Education has a very important role in the development of a country, higher education is one of the main institutions in supporting the improvement of the quality of education. The Informatics Engineering Study Program at Politeknik Negeri Lhokseumawe randomizes class assignments at the beginning of each academic year to foster an optimal learning environment. However, the results of class division show an imbalance in the level of student learning ability. Some classes have a high level of learning ability with a high average Grade Point Average and a fast learning pace. On the other hand, there are classes with lagging learning ability levels and low learning motivation. To solve this problem, this research develops a web-based system for class grouping using the K-Means Clustering method. The system clusters students based on GPA, gender, school origin, parents' occupation, residence, regional origin, and organization membership. The clustering results show three clusters, namely Cluster 0 with a Silhouette Score  of 0.0478 which indicates a high learning level, Cluster 1 with a Silhouette Score  of 0.2024 which indicates a medium learning level, and Cluster 2 with a Silhouette Score  of 0.1000 which indicates a low learning level. Cluster 1 has the best data separation, followed by clusters 2 and 0. This research is expected to create a more balanced learning environment and support student motivation.

References


K. Hengki Primayana, “Manajemen Sumber Daya Manusia Dalam Peningkatan Mutu Pendidikan Di Perguruan Tinggi,†J. Penjaminan Mutu, vol. 1, no. 2, p. 7, 2016, doi: 10.25078/jpm.v1i2.45.

G. A. Pradnyana and A. A. J. Permana, “Sistem Pembagian Kelas Kuliah Mahasiswa Dengan Metode K-Means Dan K-Nearest Neighbors Untuk Meningkatkan Kualitas Pembelajaran,†JUTI J. Ilm. Teknol. Inf., vol. 16, no. 1, p. 59, 2018, doi: 10.12962/j24068535.v16i1.a696.

M. F. Akbar and F. D. Anggraeni, “Teknologi Dalam Pendidikan : Literasi Digital dan Self-Directed Learning pada Mahasiswa Skripsi,†Indig. J. Ilm. Psikol., vol. 2, no. 1, pp. 28–38, 2017, doi: 10.23917/indigenous.v1i1.4458.

D. Jollyta, W. Ramdhan, and M. Zarlis, “Konsep Data Mining Dan Penerapan - Google Books,†Konsep Data Mining Dan Penerapan. p. 162, 2020. [Online]. Available:https://www.google.co.id/books/edition/Konsep_Data_Mining_Dan_Penerapan/piMJEAAAQBAJ?hl=id&gbpv=1

Ardianik and S. Kadar, “Tingkat Kemampuan Awal Mahasiswa Prodi Pendidikan Matematika FKIP Universitas Dr. Soetomo Surabaya Ditinjau dari Asal Daerah,†Semin. Nas. Pendidik. Mat. 2019, Univ. PGRI Adi Buana Surabaya, pp. 887–895, 2019.

C. P. Putri, M. D. Mayangsari, and D. R. Rusli, “Pengaruh Stres Akademik Terhadap Academic Help Seeking Pada Mahasiswa Psikologi Unlam Dengan Indeks Prestasi Kumulatif Rendah,†J. Kognisia, vol. 1, no. 2, pp. 28–37, 2018.

T. Nabillah and A. P. Abadi, “Faktor Penyebab Rendahnya Hasil Belajar Siswa†Pros. Semin. Nas. Mat. dan Pendidik. Mat. Sesiomadika 2019, p. 659, 2019, [Online].Available:https://journal.unsika.ac.id/index.php/sesiomadika/article/view/2685

Nidheesh, K. A. Abdul Nazeer, “An enhanced deterministic K-Means clustering algorithm for cancer subtype prediction from gene expression data,†Computers in biology and medicine, vol. 91, 2017.

Amalia, “Perbandingan Hasil Klasifikasi Rasa Minum Thai Tea yang Paling Digemari Menggunakan K-Means dan K-Medoids,†Pros.Sem.Nas.Unimus, vol.2, 2019.

J. Cui, J. Liu, and Z. Liao, “Research on K-Means clustering algorithm and its implementation,†no. Iccsee, pp. 1804–1806, 2013, doi: 10.2991/iccsee.2013.452. questionnaire (MSLQ). Ann Arbor, Michigan, 1991.


Refbacks

  • There are currently no refbacks.


Indexing :

Creative Commons License
Journal of Informatics Engineering and Software Applications (JIEngS) licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.