Algoritma Clustering Untuk Membentuk Cluster Zona Penyebaran Covid-19

Covid-19 yaitu suatu penyakit yang menyerang sistem pernapasan manusia dan dapat menular dengan mudah. Sumatera Utara salah satu daerah yang dilanda pandemi Covid-19. Melalui Gugus Tugas Percepatan dan Penanganan Covid-19 provinsi Sumatera Utara telah melakukan berbagai upaya untuk pencegahan penyebaran Covid-19 seperti belajar dan ibadah dirumah, himbauan pakai masker dan lain sebagainya. Untuk mempermudah identifikasi penyebaran Covid-19 Tim Gugus membagi zona penyebaran Covid-19 berdasarkan jumlah kasus positif. pembagian zona dengan menggunakan satu variabel yaitu positif menyebabkan penanganan Covid-19 tidak maksimal karena hanya terkonsentrasi pada zona dengan kasus positif yang terbanyak sedangkan potensi penyebaran bukan hanya dari kasus positif. Oleh karene itu, dibutuhkan teknik yang lain dapat mengelompokkan / cluster zona penyebaran Covid-19. Salah satu teknik yang sesuai untuk pengelompokkan / cluster yaitu algoritma clustering K-Medoids. Hasil dari implementasi algoritma Algoritma K-Medoids yaitu cluster zona penyebaran Covid-19 di Sumatera Utara dibagi dalam 3(tiga) Cluster yaitu cluster 1, cluster 2 dan cluster 3. Cluster 1 identik dengan zona merah, Cluster 2 identik dengan zona kuning dan cluster 3 identik dengan zona hijau. Abstract Covid-19 is a disease that attacks the human respiratory system and can be transmitted easily. North Sumatra is one of the areas hit by the Covid-19 pandemic. Through the Task Force for the Acceleration and Handling of Covid-19, the province of North Sumatra has made various efforts to prevent the spread of Covid-19, such as studying and worship at home, appealing to wear masks and so on. To make it easier to identify the spread of Covid-19, the Cluster Team divides the Covid-19 spread zones based on the number of positive cases. zoning by using one variable, namely positive, causes the handling of Covid-19 to be not optimal because it is only concentrated in the zone with the most positive cases, while the potential for spread is not only from positive cases. Therefore, another technique is needed to group / cluster the Covid-19 spread zones. One technique that is suitable for grouping / clustering is the K-Medoids clustering algorithm. The results of the implementation of the K-Medoids Algorithm algorithm, namely the Covid-19 spread zone cluster in North Sumatra is divided into 3 (three) clusters, namely cluster 1, cluster 2 and cluster 3. Cluster 1 is identical to the red zone, Cluster 2 is identical to the yellow zone and cluster 3 is identical to the green zone

Download Full-text

Implementation of K-Means Clustering Algorithm in Determining Classification of the Spread of the COVID-19 Virus in Bali

JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) ◽

10.24843/jlk.2021.v10.i01.p03 ◽

2021 ◽

Vol 10 (1) ◽

pp. 11

Author(s):

Putu Mas Anggita Putra ◽

I Gusti Agung Gede Arya Kadyanan

Keyword(s):

Infectious Disease ◽

Respiratory System ◽

Clustering Algorithm ◽

Task Force ◽

Clustering Algorithms ◽

Partition System ◽

Green Zone ◽

Using Data ◽

Human Respiratory System

The COVID-19 virus or also known as SARS-Cov-2 is an infectious disease caused by the Coronavirus which attacks the human respiratory system. The COVID-19 case has affected all provinces in Indonesia, including Bali. There is a total of 7481 cases in Bali and this is due to the lack of understanding of the community towards the COVID-19 prone areas in Bali. Therefore, it is necessary to group the areas prone to COVID-19 in Bali. One of the clustering algorithms is K-Means, this algorithm uses several groups for the placement of some data with a partition system. The grouping will be carried out using data from the Bali COVID-19 Task Force website on September 18, 2020, using RapidMiner application. The results obtained divided Bali into 3 clusters with Denpasar as the center of the highest spread of COVID-19 in Bali as the red zone, then Badung, Buleleng, Bangli, Gianyar, and Karangasem in the yellow zone, and other districts in the green zone.

Download Full-text