Pemodelan Fungsi Transfer Multi-input Dan Multi-output Untuk Analisis Hubungan Faktor Iklim Dan Jumlah Kasus COVID-19 Di Surabaya

Hudiyanti, Cinthia Vairra (2021) Pemodelan Fungsi Transfer Multi-input Dan Multi-output Untuk Analisis Hubungan Faktor Iklim Dan Jumlah Kasus COVID-19 Di Surabaya. Masters thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 05111950010015-Master_Thesis.pdf] Text
05111950010015-Master_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2023.

Download (3MB) | Request a copy

Abstract

Telah muncul virus baru Coronavirus Disease-19 (COVID-19) yang sebelumnya tidak dikenal sebelum terjadi wabah di Kota Wuhan, Tiongkok, bulan Desember 2019. COVID-19 adalah penyakit menular yang disebabkan oleh jenis coronavirus yang baru ditemukan. 2 Maret 2020 kasus pertama COVID-19 ditemukan di Indonesia. Kota Surabaya adalah kota kedua dengan jumlah kasus terbanyak di Indonesia. Di Indonesia klasifikasi pasien dibagi menjadi tiga yaitu Konfirmasi, Suspect, dan Probable. Terdapat sebuah penelitian yang mengatakan jika adanya hubungan antara temperatur dan kelembapan udara dengan jumlah kasus COVID-19 di sebuah daerah. Maka dilakukan penelitian atas hubungan faktor iklim dengan jumlah kasus harian COVID-19 yaitu konfirmasi, suspect dan probable di Surabaya.
Mencari hubungan antara temperatur dan kelembapan udara dengan jumlah kasus hari COVID-19 dilakukan untuk mencari kemungkinan peningkatan dan penurunan angka kasus COVID-19 di Surabaya berdasarkan faktor iklim. Hasil pemodelan dapat digunakan untuk mendapatkan nilai delay time antara faktor iklim dengan jumlah kasus harian COVID-19 serta mendapatkan nilai hasil peramalan untuk beberapa waktu kedepan. Hasil peramalan tersebut dapat digunakan sebagai nilai perkiraan laju transmisi COVID-19 di Surabaya pada masa yang akan datang.
Pemodelan fungsi transfer multi-input dan multi-output akan digunakan dalam penelitian ini dengan keluaran berupa jumlah kasus konfirmasi, suspect dan probable dan masukan berupa jumlah kasus harian serta nilai faktor iklim berupa temperatur dan kelembapan udara di kota Surabaya. Hasil model fungsi transfer berupa model matriks. Matriks didapatkan dari hasil analisis autoregressive integrated moving average (ARIMA) dan hubungan tiap variabel masukan.
Hasil analisis menunjukkan temperatur udara mempengaruhi jumlah suspect dengan nilai delay time 2 hari. Variabel lain yang saling mempengaruhi adalah jumlah konfirmasi dan suspect dengan nilai delay time 5 hari. Sedangkan kelembapan udara tidak mempengaruhi jumlah konfirmasi, suspect atau probable. Nilai Mean Absolute Percentage Error (MAPE) data testing untuk konfirmasi adalah 44,83 dikategorikan sedang kemudian meningkat menjadi 19,204 yang dikategorikan baik. Nilai MAPE suspect dalam model ARIMA adalah 54,563 yang dikategorikan buruk kemudian ditingkatkan menjadi 32,427 yang dikategorikan sedang bahkan peramalan jumlah suspect dapat memiliki nilai MAPE sebesar 26,857 untuk satu masukan yaitu konfirmasi.
======================================================================================================
A new virus, COVID-19 that was previously unknown before the outbreak occurred in Wuhan City, China, in December 2019. COVID-19 is an infectious disease caused by a newly discovered type of coronavirus. March 2, 2020, the first case of COVID-19 was found in Indonesia. The city of Surabaya is the second city with the highest number of cases in Indonesia. In Indonesia, the classification of patients is divided into three, namely Confirm, Suspect, and Probable. A study says there is a relationship between temperature and humidity with the number of COVID-19 cases in an area. Therefore, a study was conducted on the relationship between climate factors and the number of daily COVID-19 cases, namely confirmation, suspect and probable in Surabaya.
The relationship between temperature and humidity with number of cases of COVID-19 on a day is done to look for the possibility of increasing and decreasing the number of COVID-19 cases in Surabaya based on climatic factors. The modelling results can be used to obtain the value of the delay time between climate factors and the number of daily cases of COVID-19 and to obtain the value of forecasting results for some time to come. The forecasting results can be used as an estimated value of the COVID-19 transmission rate in Surabaya in the future.
Multi-input and multi-output transfer function modelling will be used in this study with the output in the form of the number of confirmed, suspect and probable cases and the input in the form of daily cases and the value of climate factors in the form of temperature and humidity in the city of Surabaya. The result of the transfer function model is a matrix model. The matrix is obtained from the autoregressive integrated moving average (ARIMA) analysis and the relationship between each input variable.
The analysis results show that air temperature affects the number of suspects with a delay time value of 2 days. Other variables that influence each other are the number of confirmations and suspects with a delay time value of 5 days. At the same time, air humidity does not affect the number of confirmations, suspect or probable. The Mean Absolute Percentage Error (MAPE) value of the testing data for confirmation was 44.83, categorized as moderate and then increased to 19,204, which was categorized as good. The MAPE suspect value in the ARIMA model is 54.563, which is categorized as bad and then increased to 32.427, which is categorized as moderate even forecasting the number of suspects can have a MAPE value of 26.857 for one input, namely confirmation.

Item Type: Thesis (Masters)
Uncontrolled Keywords: COVID-19, multi-input, multi-output, fungsi transfer, konfirmasi, suspect, probable, temperatur, kelembapan, MAPE. ========================================================= COVID-19, multi-input, multi-output, transfer function, confirmation, suspect, probable, temperature, humidity, MAPE.
Subjects: Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry)
Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science)
T Technology > T Technology (General) > T57.5 Data Processing
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55101-(S2) Master Thesis
Depositing User: Cinthia Vairra Hudiyanti
Date Deposited: 12 Aug 2021 11:29
Last Modified: 12 Aug 2021 11:29
URI: http://repository.its.ac.id/id/eprint/86040

Actions (login required)

View Item View Item