Peramalan Gelombang Covid 19 Menggunakan Hybrid Nonlinear Regression Logistic – Double Exponential Smoothing di Indonesia dan Prancis
Abstract
ABSTRAK
Indonesia dan Prancis adalah dua Negara yang mengalami Covid 19 dengan pola pergerakan kasus Covid 19 yang berbeda. Kondisi Indonesia masih mengalami siklus one wave namun Prancis sudah masuk pada pola second wave. Makna second wave adalah kondisi epidemi Covid 19 yang baru muncul setelah epidemi sebelumnya dianggap selesai. Dalam peramalan kasus Covid 19 baik itu terkait informasi puncak dari terjadinya kasus Covid 19 serta ramalan terkait akan berakhirnya pandemi kasus Covid 19 suatu negara merupakan hal penting bagi pemerintah suatu Negara. Model hybrid meningkatkan akurasi ramalan dibandingkan model time series yang dilakukan secara terpisah. Tujuan penelitian ini adalah melakukan peramalan kasus Covid 19 di Indonesia dan Prancis dengan menggunakan metode hybrid dan membandingkan dengan peramalan dengan salah satu metode tunggal. Metode yang digunakan adalah metode tunggal yaitu Nonlinear Regression Logistic dan metode Hybrid Nonlinear Regression Logistic–Double Eksponensial Smoothing. Hasilnya adalah model peramalan Hybrid Nonlinear Regression Logistic and Doubel Exponential Smoothing lebih bagus digunakan dalam peramalan kasus Covid 19 di Indonesia dan Prancis. Terlihat bahwa nilai MAPE model Hybrid Nonlinear Regression Logistic–Double Eksponensial Smoothing jauh lebih kecil dibandingkan model peramalan Nonlinear Regression Logistic.
ABSTRACT
Indonesia and France are two countries that have experienced Covid 19 with different patterns of movement of Covid 19 cases. Indonesia's condition is still experiencing a one wave cycle but France has entered into the second wave pattern. The meaning of the second wave is the condition of the Covid 19 epidemic which only emerged after the previous epidemic was considered over. In forecasting the Covid 19 case, whether it is related to the peak information on the occurrence of the Covid 19 case and predictions regarding the end of the pandemic of the Covid 19 case in a country, it is important for the government of a country. The hybrid model improves forecast accuracy compared to the time series model which is carried out separately. The purpose of this study is to forecast the cases of Covid 19 in Indonesia and France using the hybrid method and comparing with forecasting with one single method. The method used is a single method, namely Nonlinear Logistic Regression and Hybrid Nonlinear Regression Logistic-Double Exponential Smoothing methods. The result is that the Hybrid Nonlinear Regression Logistic and Double Exponential Smoothing forecasting model is better used in forecasting the Covid 19 cases in Indonesia and France. It can be seen that the MAPE value of the Hybrid Nonlinear Regression Logistic – Double Exponential Smoothing model is much smaller than the Nonlinear Regression Logistic forecasting model.
Keywords
Full Text:
PDF [Indonesia]References
P. D. Pakan and U. N. Cendana, “Peramalan Kasus Positif di Indonesia Menggunakan LSTM 13,” vol. 6, no. 1, pp. 12–15, 2020.
N. Hasan, “A Methodological Approach for Predicting COVID-19 Epidemic Using EEMD-ANN Najmul Hasan Abstract” Internet of Things, p. 100228, 2020, doi: 10.1016/j.iot.2020.100228.
S. Harini, “Identification COVID-19 Cases in Indonesia with The Double Exponential Smoothing Method,” vol. 6, no. 1, pp. 66–75, 2020.
S. Singh, K. S. Parmar, J. Kumar, S. Jitendra, and S. Makkhan, “Development of New Hybrid Model of Discrete Wavelet Decomposition and Autoregressive Integrated Moving Average (ARIMA) Models in Application to One Month Forecast the Casualties Cases of COVID-19,” Chaos, Solitons Fractals Interdiscip. J. Nonlinear Sci. Nonequilibrium Complex Phenom., p. 109866, 2020, doi: 10.1016/j.chaos.2020.109866.
E. Gjika, A. Ferrja, and A. Kamberi, “A study on the efficiency of hybrid models in forecasting precipitations and water inflow Albania case study,” Adv. Sci. Technol. Eng. Syst., vol. 4, no. 1, pp. 302–310, 2019, doi: 10.25046/aj040129.
P. Wang, X. Zheng, J. Li, and B. Zhu, “Prediction of epidemic trends in COVID-19 with logistic model and machine learning technics,” Chaos, Solitons and Fractals, vol. 139, p. 110058, 2020, doi: 10.1016/j.chaos.2020.110058.
A. Mwakisisile and A. Mushi, “Mathematical Model for Tanzania Population Growth,” Tanzania J. Sci., vol. 45, no. 3, pp. 346–354, 2019.
C. V. Hudiyanti, F. A. Bachtiar, and B. D. Setiawan, “Perbandingan Double Moving Average dan Double Exponential Smoothing untuk Peramalan Jumlah Kedatangan Wisatawan Mancanegara di Bandara Ngurah Rai,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 3, no. 3, pp. 2667–2672, 2019.
P. G. Zhang, “Time series forecasting using a hybrid ARIMA and neural network model,” Neurocomputing, vol. 50, pp. 159–175, 2003, doi: 10.1016/S0925-2312(01)00702-0.
D. I. Purnama and O. P. Hendarsin, “Peramalan Jumlah Penumpang Berangkat Melalui Transportasi Udara di Sulawesi Tengah Menggunakan Support Vector Regression (SVR),” Jambura J. Math., vol. 2, no. 2, pp. 49–59, 2020, doi: 10.34312/jjom.v2i2.4458.
M. N. Mara and N. Satyahadewi, “Kajian Teoritis Hybridizing Exponential Smoothing dan Neural Network untuk Peramalan Data Runtun Waktu”, Bimaster Ilmiah Mat. Stat. dan Terapannya, vol. 02, no. 3, pp. 205–210, 2013.
E. Pujiati, D. Yuniarti, and R. Goejantoro, “Peramalan Dengan Menggunakan Metode Double Exponential Smoothing Dari Brown (Studi Kasus: Indeks Harga Konsumen (IHK) Kota Samarinda),” J. Eksponensial, vol. 7, no. 1, pp. 33–40, 2016.
Z. Hajirahimi and M. Khashei, “Hybrid structures in time series modeling and forecasting: A review,” Eng. Appl. Artif. Intell., vol. 86, no. July, pp. 83–106, 2019, doi: 10.1016/j.engappai.2019.08.018.
O. C. A. ogwa, C. Eze, and C. R. O. nkwo, “Modeling the Cases of Road Traffic Crashes: A Case of Exponential Smoothing Approach,” Int. J. Math. Trends Technol., vol. 65, no. 1, pp. 46–52, 2019, doi: 10.14445/22315373/ijmtt-v65i1p508.
R. Fajri and T. M. Johan, “Implementasi Peramalan Double Exponential Smoothing Pada Kasus Kekerasan Anak Di Pusat Pelayanan Terpadu Pemberdayaan Perempuan Dan Anak,” J. ECOTIPE, vol. 4, no. 2, pp. 6–13, 2017, doi: 10.33019/ecotipe.v4i2.6.
V. N. Fitriani and K. D. Purnomo, “Estimasi Solusi Model Pertumbuhan Logistik dengan Metode Ensemble Kalman Filter Solution Estimation of Logistic Growth Model with Ensemble Kalman Filter Method,” J. Ilmu Dasar, vol. 14, no. 2, pp. 85–90, 2013.
DOI: https://doi.org/10.34312/jjom.v3i1.7771
Copyright (c) 2021 I.G.B.N. Diksa
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Jambura Journal of Mathematics has been indexed by
Jambura Journal of Mathematics (e-ISSN: 2656-1344) by Department of Mathematics Universitas Negeri Gorontalo is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. Powered by Public Knowledge Project OJS.
Editorial Office
Department of Mathematics, Faculty of Mathematics and Natural Science, Universitas Negeri Gorontalo
Jl. Prof. Dr. Ing. B. J. Habibie, Moutong, Tilongkabila, Kabupaten Bone Bolango, Gorontalo, Indonesia
Email: info.jjom@ung.ac.id.