PENGKLASTERAN RISIKO COVID-19 DI RIAU MENGGUNAKAN TEKNIK ONE HOT ENCODING DAN ALGORITMA K-MEANS CLUSTERING
Abstract
Coronavirus disease 2019 (COVID-19) is a new type known to infect humans in December 2019. COVID-19 cases have spread throughout the world, including in Indonesia. Riau Province is one of the provinces with a fairly high number of COVID-19 cases. Appropriate mitigation measures are needed to prevent the COVID-19 outbreak. Based on a literature review, COVID-19 outbreaks are infected based on the closest distance. Epidemiologists have also used the clustering method to group the areas affected by the COVID-19 pandemic. Therefore, this study applied the one-hot encoding technique and the k-means clustering algorithm to cluster regions with similar data characteristics. Twelve districts in Riau with seven features were obtained for clustering. Based on the experimental testing results, three clusters were obtained, namely C1 (Pekanbaru, Kampar), C2 (Siak, Bengkalis, Rokan Hulu, Kuantan Singingi), and C3 (Dumai, Indragiri Hilir, Indragiri Hulu, Pelalawan, Rokan Hilir, Meranti). The results of the cluster were tested with a silhouette score of 0.6. Thus, it can be concluded that the one-hot encoding technique and the k-means clustering algorithm have the potential to be used to cluster areas of the COVID-19 pandemic based on similar data characteristics.
Downloads
References
[2] S. R. Vadyala, S. N. Betgeri, E. A. Sherer, and A. Amritphale, “Prediction of the number of COVID-19 confirmed cases based on K-means-LSTM,” Array, vol. 11, p. 100085, 2021, doi: 10.1016/j.array.2021.100085.
[3] Z. Nabila, A. Rahman Isnain, and Z. Abidin, “Analisis Data Mining Untuk Clustering Kasus Covid-19 Di Provinsi Lampung Dengan Algoritma K-Means,” J. Teknol. dan Sist. Inf., vol. 2, no. 2, p. 100, 2021, [Online]. Available: http://jim.teknokrat.ac.id/index.php/JTSI.
[4] WHO, “WHO Coronavirus Disease (COVID-19) Dashboard,” 2020. https://covid19.who.int/ (accessed Jan. 31, 2022).
[5] Worldometers.info, “COVID-19 Coronavirus Outbreak,” Dadax, 2020. https://www.worldometers.info/coronavirus/ (accessed May 09, 2022).
[6] Henderi, M. Maulana, H. L. H. S. Warnars, D. Setiyadi, and T. Qurrohman, “Model Decision Support System for Diagnosis COVID-19 Using Forward Chaining: A Case in Indonesia,” 2020 8th Int. Conf. Cyber IT Serv. Manag. CITSM 2020, pp. 6–9, 2020, doi: 10.1109/CITSM50537.2020.9268853.
[7] “Total Kasus COVID-19 di Riau,” riau24.com, 2021. https://www.riau24.com/berita/baca/1611110272-total-kasus-pasien-covid-19-di-riau-sudah-27592-pekanbaru-nyaris-13-ribu-kasus (accessed Mar. 09, 2022).
[8] R. Baruri, A. Ghosh, R. Banerjee, A. Das, A. Mandal, and T. Halder, “An Empirical Evaluation of k-Means Clustering Technique and Comparison,” Proc. Int. Conf. Mach. Learn. Big Data, Cloud Parallel Comput. Trends, Prespectives Prospect. Com. 2019, pp. 470–475, 2019, doi: 10.1109/COMITCon.2019.8862215.
[9] F. S. Silfia, Rahmad Kurniawan, Nazruddin Safaat, Elvia Budianita, “Jurnal Teknik Informatika Atmaluhur,” J. Tek. Inform. Atmaluhur, vol. 6, no. 1, p. 40, 2018.
[10] M. W. Talakua, Z. A. Leleury, and A. W. Talluta, “Cluster Analysis by Using K-Means Method for Grouping of District/City in Maluku Provinse Industrial Based on Indicators of Maluku Development Index in 2014,” J. Ilmu Mat. dan Terap., vol. 11, pp. 119–128, 2017.
[11] A. Nur, R. Kurniawan, M. Z. A. Nazri, K. Rajab, P. Papilo, and A. Mas’ari, “Solution to Traveling Freelance Teacher Problem using the Simple K-Means Clustering,” Proc. - 2021 4th Int. Conf. Comput. Informatics Eng. IT-Based Digit. Ind. Innov. Welf. Soc. IC2IE 2021, pp. 112–116, 2021, doi: 10.1109/IC2IE53219.2021.9649086.
[12] S. Irna Yuniarfi, “Penerapan Algoritma K-Means untuk Pengelompokan Usia Calon Penerima Vaksin di Kab. Ngawi,” no. 2, p. 6, 2021.
