Penerapan Algoritma K-Means Cluster dan Metode TOPSIS pada Pemilihan Mahasiswa kunjungan Industri
Abstract
Industrial visits are an applicable form of learning where educators and students can see directly the system or work pattern of an industry or software company. The importance of this activity, so it is necessary to select students who take part in it accurately and objectively. This study aims to make calculation standards to help facilitate study programs in selecting students. Using the K-Means Cluster Algorithm is used to streamline data by eliminating alternatives that do not meet the requirements and creating two clusters whose centroid initially uses the maximum and minimum values of the criteria. Then do the ranking process with the TOPSIS method. The results showed that calculating the distance using the Manhattan Distance has the closest coefficient value higher than the Euclidean distance, which is about 60% of all data. The first cluster consists of 25 people who meet the requirements and are ranked by the TOPSIS Method so that only 20 people are left to take part in the activity. By using the Euclidean distance, there are 70% of the 20 people selected, while the Manhattan distance is 75%. 30% and 25% are taken from the first and second clusters. The K-Means Algorithm can correctly group members according to the required characteristics so that it can streamline the initial data, then the MCDM method can speed up the calculation process accurately and objectively.
Keywords: K-Means; Clustering; Metode TOPSIS; Manhattan distance; Euclidien distance
Abstrak
Kunjungan industri merupakan salah satu bentuk pembelajaran yang aplikatif dimana pendidik dan peserta didik dapat melihat secara langsung sistem atau pola kerja suatu industri atau perusahaan perangkat lunak. Pentingnya kegiatan ini, sehingga perlu untuk memilih mahasiswa yang mengambil bagian di dalamnya secara akurat dan obyektif. Penelitian ini bertujuan membuat standar perhitungan untuk membantu mempermudah program studi dalam memilih mahasiswa. Menggunakan Algoritme K-Means Cluster yang digunakan untuk merampingkan data dengan Cara mengeliminasi alternatif yang tidak memenuhi syarat serta membuat dua kluster yang centroid awalnya menggunakan nilai maksimum dan minimum dari kriteria. Kemudian lakukan proses perangkingan dengan metode TOPSIS. Hasil penelitian menunjukkan, perhitungan jarak dengan Manhattan Distance memiliki nilai koefisien terdekat lebih tinggi dari Euclidean distance sekitar 60% dari seluruh data. Cluster pertama terdiri dari 25 orang yang memenuhi persyaratan dan dirangking dengan Metode TOPSIS, sehingga tersisa 20 orang untuk mengikuti kegiatan tersebut. Dengan menggunakan Euclidien distance, terdapat 70% dari 20 orang yang dipilih, sedangkan Manhattan distance adalah 75%. 30% dan 25% diambil dari cluster pertama dan kedua. Algoritme K-Means dapat dengan tepat mengelompokkan anggota sesuai karakteristik yang diperlukan sehingga dapat merampingkan data awal, kemudian metode MCDM dapat mempercepat proses perhitungan dengan akurat serta objektif.
Keywords
References
L. A. Manurung, “Kunjugan Industri Program Vokasi - Learning Experience.,” 2020. https://kalbelearningcentre.kalbe.co.id/News/ArtMID/547/ArticleID/30/Kunjungan-Industri-Program-Vokasi (accessed Feb. 21, 2021).
V. Nastiti1, A. C. Sukartiko, and N. E. Kristanti, “Analisis Kepuasan Pengunjung Terhadap Pelayanan Kunjungan Industri Di PT. Sido Muncul,” Repository, Universitas Gadjah Mada, 2016.
A. B. Hastuti, E. Utami, and E. T. Luthfi, “Implementasi Metode Fuzzy C-Means Dan Topsis Dalam Membangun Sistem Pendukung Keputusan Penentuan Jurusan SMA (Studi Kasus : Penentuan Jurusan Di SMA Negeri 1 Wonosari),” DASI, vol. 14, no. 2, pp. 9-15, 2013.
N. D. Budiana, R. R. A. Siregar, and M. N. I. Susanti, “Penetapan Instruktur Diklat Menggunakan Metode Clustering K-Means dan Topsis Pada PT PLN (Persero) Udiklat Jakarta,” petir, vol. 12, no. 2, pp. 111–121, Aug. 2019, doi: 10.33322/petir.v12i2.454.
Mirfan, “Sistem Pendukung Keputusan Pemilihan Destinasi Wisata Berbasis Web Dengan Algoritma K-Means Clustering Dan TOPSIS,” Jurnal INSTEK, vol. 5, no. 2, pp. 240–250, Oktober 2020.
E. Daniati and H. Utama, “Clustering K Means for Criteria Weighting With Improvement Result of Alternative Decisions Using SAW and TOPSIS,” in 2019 4th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), Yogyakarta, Indonesia, pp. 73–78, 2019, doi: 10.1109/ICITISEE48480. 2019.9003858.
K. Khomsatun, D. Ikhsan, M. Ali, and K. Kursini, “Sistem Pengambilan Keputusan Pemilihan Lahan Tanam Di Kabupaten Wonosobo Dengan K-Means Clustering Dan TOPSIS,” Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI), vol. 9, no. 1, pp. 55-62, Apr. 2020, doi: 10.23887/janapati.v9i1.23073.
A. Masruro and E. T. Luthfi, “Sistem Penunjang Keputusan Penentuan Lokasi Wisata Menggunakan K-Means Clustering Dan TOPSIS,” vol. 15, no. 04, pp. 1-5, Desember 2011.
M. A. Raharja, I. K. A. Surya, and I. K. A. Mogi, “Clustering Customer For Determine Market Strategy Using K-Means And TOPSIS: Case Study,” Vol. 2, pp. 61-71, 2022.
F. Sun and J. Yu, “Improved energy performance evaluating and ranking approach for office buildings using Simple-normalization, Entropy-based TOPSIS and K-means method,” Energy Reports, vol. 7, pp. 1560–1570, Nov. 2021, doi: 10.1016/j.egyr.2021.03.007.
B. Trstenjak, A. rijana K. Kavran, and I. Bujan, “Evaluation of Croatian Development Strategies Using SWOT Analyses with Fuzzy TOPSIS Method and K-Means Methods,” JOEBM, vol. 3, no. 7, pp. 687–693, 2015, doi: 10.7763/JOEBM.2015.V3.267.
Haviluddin et al., “A Performance Comparison of Euclidean, Manhattan and Minkowski Distances in K-Means Clustering,” in 2020 6th International Conference on Science in Information Technology (ICSITech), Palu, Indonesia, pp. 184–188, 2020. doi: 10.1109/ICSITech49800.2020.9392053.
M. Nishom, “Perbandingan Akurasi Euclidean Distance, Minkowski Distance, dan Manhattan Distance pada Algoritma K-Means Clustering berbasis Chi-Square,” jpit, vol. 4, no. 1, pp. 20–24, Jan. 2019, doi: 10.30591/jpit.v4i1.1253.
A. Setiawan, “Perbandingan Penggunaan Jarak Manhattan, Jarak Euclid, dan Jarak Minkowski dalam Klasifikasi Menggunakan Metode KNN pada Data Iris,” juses, vol. 5, no. 1, pp. 28–37, May 2022, doi: 10.24246/juses.v5i1p28-37.
W.-Y. Chiu, G. G. Yen, and T.-K. Juan, “Minimum Manhattan Distance Approach to Multiple Criteria Decision Making in Multiobjective Optimization Problems,” IEEE Trans. Evol. Computat., vol. 20, no. 6, pp. 972–985, Dec. 2016, doi: 10.1109/TEVC.2016.2564158.
S. B. Sakur, M. Silangen, and E. H. Israel, “Penggunaan Metode Technique For Order Performance Of Similarity To Ideal Solution (TOPSIS) Dan Vector Normalization Pada Pemilihan Mahasiswa Kunjungan Industri,” Politeknik Negeri Nusa Utara, Tahuna, Laporan Penelitian Unggulan Perguruan Tinggi 461/Sistem Informasi, Nov. 2021.
S. B. Sakur, “Data Excel Proses Analisis Kunjungan Industri Metode TOPSIS,” Repositori Stendy B. Sakur, Nov. 21, 2021. https://drive.google.com/file/d/ 1Z8UmqyJ7v5Nc4Y42zLWOv7kxjzoI78ny/view?usp=sharing (accessed Nov. 21, 2021).
N. Arief, I. S. Damanik, and E. Irawan, “Penerapan Algoritma K- Medoids Dalam Mengelompokkan Tingkat Kasus Kejahatan di Setiap Provinsi,” KLIK: Kajian Ilmiah Informatika dan Komputer, vol. 2, no. 3, pp. 111–116, 2021.
N. Islam, “Defining Homogenous Climate zones of Bangladesh using Cluster Analysis,” vol. 6, no. 1, pp. 119–129, Feb. 2019.
C.-L. Hwang and K. Yoon, “Methods for multiple attribute decision making,” in Multiple attribute decision making, Springer, pp. 58–191, 1981.
M. Abedi and G.-H. Norouzi, “A general framework of TOPSIS method for integration of airborne geophysics, satellite imagery, geochemical and geological data,” International Journal of Applied Earth Observation and Geoinformation, vol. 46, pp. 31–44, Apr. 2016, doi: 10.1016/j.jag.2015.11.016.
M. Behzadian, S. Khanmohammadi Otaghsara, M. Yazdani, and J. Ignatius, “A state-of the-art survey of TOPSIS applications,” Expert Systems with Applications, vol. 39, no. 17, pp. 13051–13069, Dec. 2012, doi: 10.1016/j.eswa.2012.05.056.
D. M. Pavlicic, “Normalisation Affects the Results Of Madm Methods,” vol. 11, no. 2, pp. 261–265, 2001.
D. Sinwar, R. Kaushik, “Study of Euclidean and Manhattan distance metrics using simple k-means clustering”. Int. J. Res. Appl. Sci. Eng. Technol, vol. 5, no. 2, pp. 270-274, 2014.
How To Cite This :
Refbacks
- There are currently no refbacks.
