PENGELOMPOKAN VAKSINASI COVID-19 DI INDONESIA MENGGUNAKAN ALGORITMA SPECTRAL CLUSTERING DENGAN UN-NORMALIZED DAN NORMALIZED LAPLACIAN

MILLENIA, WINADYA PUTRI (2022) PENGELOMPOKAN VAKSINASI COVID-19 DI INDONESIA MENGGUNAKAN ALGORITMA SPECTRAL CLUSTERING DENGAN UN-NORMALIZED DAN NORMALIZED LAPLACIAN. Sarjana / Sarjana Terapan (S1/D4) thesis, Universitas Muhammadiyah Semarang.

Preview	Text 1. HALAMAN DEPAN.pdf Download (526kB) | Preview
Preview	Text 6. ABSTRAK.pdf Download (501kB) | Preview
Preview	Text 13. BAB I .pdf Download (666kB) | Preview
Preview	Text 14. BAB II.pdf Download (692kB) | Preview
	Text 15. BAB III.pdf Restricted to Repository staff only Download (597kB) | Request a copy
	Text 16. BAB IV.pdf Restricted to Repository staff only Download (1MB) | Request a copy
Preview	Text 17. BAB V.pdf Download (510kB) | Preview
Preview	Text 19. DAFTAR PUSTAKA.pdf Download (510kB) | Preview
	Text 18. LAMPIRAN.pdf Restricted to Repository staff only Download (864kB) | Request a copy
	Text FULL TEKS.pdf Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

ABSTRAK Millenia Winadya Putri, 2021, Pengelompokan Vaksinasi COVID-19 di Indonesia Menggunakan Algoritma Spectral Clustering dengan Un-Normalized dan Normalized Laplacian. Skripsi, Program Studi Statistika, Universitas Muhammadiyah Semarang. Pembimbing: I. Dr. Rochdi Wasono, M.Si.. II. Indah Manfaati Nur, M.Si. Pandemi COVID-19 dalam kurun waktu dua tahun berhasil menginfeksi jutaan orang di seluruh dunia dan menyebabkan banyak kematian. Guna menghentikan penyebaran virus, pemerintah melakukan tindakan yaitu menerapkan protokol kesehatan dan mewajibkan vaksinasi kepada masyarakat. Namun, kegiatan vaksinasi masih lamban untuk mencapai target. Penelitian ini akan melakukan suatu pengelompokan untuk mengetahui tingkat persebaran vaksinasi di Indonesia menurut provinsi dengan data jumlah vaksinasi per-kategori masyarakat pada tanggal 1 Februari 2022. Salah satu algoritma pengelompokan dalam Data Mining yaitu Spectral Clustering dan terbagi menjadi beberapa macam rumus, diantaranya Un-Normalized Laplacian dan Normalized Laplacian. Pengelompokan spektral merupakan teknik yang mengikuti pendekatan konektivitas, dimana metode ini mengklasifikasikan titik-titik yang terhubung atau berbatasan langsung. Perbedaan kedua metode tersebut terletak pada pemakaian rumus untuk membuat matriks laplacian. Penelitian ini menghasilkan 3 klaster untuk rumus laplacian, yaitu klaster tingkat persebaran tinggi, sedang, dan rendah. Menurut hasil evaluasi menggunakan nilai Davies-Bouldin Index (DBI), metode yang lebih optimal digunakan sebagai metode clustering adalah Normalized Laplacian. Kata Kunci: Vaksinasi COVID-19, Data Mining, Spectral Clustering, Laplacian.   ABSTRACT Millenia Winadya Putri, 2021, Grouping of COVID-19 Vaccination in Indonesia Using Spectral Clustering Algorithm with Un-Normalized and Normalized Laplacian. Thesis, Statistics Study Program, Muhammadiyah Semarang University. Advisors: I. Dr. Rochdi Wasono, M.Si. II. Indah Manfaati Nur, M.Si. The COVID-19 pandemic within two years has infected millions of people worldwide and caused many deaths. In order to stop the spread of the virus, the government took action, namely implementing health protocols and requiring vaccinations to the public. However, vaccination activities are still slow to reach the target. This study will conduct a grouping to determine the level of vaccination distribution in Indonesia by province with data on the number of vaccinations per community category on February 1, 2022. One of the clustering algorithms in Data Mining is Spectral Clustering and is divided into several kinds of formulas, including Un-Normalized Laplacian and Normalized Laplacian. Spectral clustering is a technique that follows the connectivity approach, where this method classifies points that are connected or directly adjacent. The difference between the two methods lies in the use of the formula to create a laplacian matrix. This study resulted in 3 clusters for the Laplacian formula, namely clusters of high, medium, and low distribution levels. According to the results of the evaluation using the Davies-Bouldin Index (DBI) value, the more optimal method used as a clustering method is the Normalized Laplacian. Keywords: COVID-19 Vaccination, Data Mining, Spectral Clustering, Laplacian.

Actions (login required)

View Item