PENERAPAN MODEL HYBRID SARIMA-ELM UNTUK PERAMALAN JUMLAH PENUMPANG KERETA API

Elisa Febriyani, - (2024) PENERAPAN MODEL HYBRID SARIMA-ELM UNTUK PERAMALAN JUMLAH PENUMPANG KERETA API. S1 thesis, Universitas Pendidikan Indonesia.

Baca Full Text klik disini
[img] Text
S_MAT_1704180_Title.pdf
Download (309kB)
[img] Text
S_MAT_1704180_Chapter1.pdf
Download (62kB)
[img] Text
S_MAT_1704180_Chapter2.pdf
Restricted to Staf Perpustakaan
Download (595kB) | Request a copy
[img] Text
S_MAT_1704180_Chapter3.pdf
Download (316kB)
[img] Text
S_MAT_1704180_Chapter4.pdf
Restricted to Staf Perpustakaan
Download (1MB) | Request a copy
[img] Text
S_MAT_1704180_Chapter5.pdf
Download (76kB)
[img] Text
S_MAT_1704180_Appendix.pdf
Restricted to Staf Perpustakaan
Download (399kB) | Request a copy
Official URL: https://repository.upi.edu

Abstract

Penelitian ini membahas mengenai peramalan jumlah penumpang kereta api yang turun di Stasiun Yogyakarta, Stasiun Bandung, dan Stasiun Malang menggunakan model Hybrid SARIMA-ELM. Model SARIMA digunakan untuk menangkap pola linear pada data dan ELM digunakan untuk menangkap pola non-linear pada data dengan kelebihannya dalam learning speed. Tujuan dari penelitian ini adalah untuk mengetahui penerapan model Hybrid SARIMA-ELM serta mengetahui tingkat akurasi peramalannya. Peramalan didasarkan pada data jumlah penumpang pada periode sebelum Covid-19 (Agustus 2014-Desember 2018) dan periode saat Covid-19 (Januari 2020-Desember 2021). Peramalan diawali dengan mencari model SARIMA terbaik, kemudian residual dari SARIMA dimodelkan dengan ELM. Hasil peramalan model Hybrid SARIMA-ELM diukur keakuratannya menggunakan Mean Absolute Percentage Error (MAPE). Model SARIMA terbaik dari masing-masing stasiun yaitu SARIMA 〖(0,1,1)(0,1,0)〗^12 untuk fase sebelum Covid-19 dan model ARIMA (2,0,0) untuk fase saat Covid-19. Dengan perbandingan data 80:20, 3 fitur input, 1 neuron hidden layer, dan 1 output pada model ELM, diperoleh nilai MAPE model sebelum Covid-19 pada masing-masing stasiun sebesar 11,54%, 5,27%, dan 6,34% yang berarti peramalan baik untuk Stasiun Yogyakarta dan peramalan berakurasi tinggi untuk Stasiun Bandung dan Stasiun Malang. Sedangkan untuk model saat Covid-19 diperoleh nilai MAPE untuk masing-masing stasiun sebesar 14,60%, 13,43% , dan 18,75% yang berarti peramalan baik untuk ketiga stasiun. This study discusses forecasting the number of train passengers who get off at Yogyakarta Station, Bandung Station, and Malang Station using the Hybrid SARIMA-ELM model. The SARIMA model is used to capture linear patterns in the data and ELM is used to capture non-linear patterns in the data with its advantages in learning speed. The purpose of this study is to determine the application of the Hybrid SARIMA-ELM model and determine the level of forecasting accuracy. Forecasting is based on data on the number of passengers in the period before Covid-19 (August 2014-December 2018) and the period during Covid-19 (January 2020-December 2021). Forecasting begins with finding the best SARIMA model, then the residuals from SARIMA are modeled with ELM. Hybrid SARIMA-ELM model forecasting results are measured for accuracy using Mean Absolute Percentage Error (MAPE). The best SARIMA model from each station is SARIMA 〖(0,1,1)(0,1,0)〗^12 for the phase before Covid-19 and ARIMA (2,0,0) model for the phase during Covid-19. With a data ratio of 80:20, 3 input features, 1 hidden layer neuron, and 1 output in the ELM model, the MAPE value of the model before Covid-19 at each station is 11.54%, 5.27%, and 6.34%, which means good forecasting for Yogyakarta Station and high accuracy forecasting for Bandung Station and Malang Station. As for the model when Covid-19 obtained MAPE values for each station of 14.60%, 13.43%, and 18.75% which means good forecasting for the three stations.

Item Type: Thesis (S1)
Additional Information: https://scholar.google.com/citations?view_op=new_profile&hl=id ID SINTA Dosen Pembimbing: Fitriani Agustina: 5981275
Uncontrolled Keywords: Peramalan, Jumlah Penumpang, SARIMA, ELM Forecasting, Number of Passengers, SARIMA, ELM
Subjects: H Social Sciences > HE Transportation and Communications
L Education > L Education (General)
Q Science > QA Mathematics
Divisions: Fakultas Pendidikan Matematika dan Ilmu Pengetahuan Alam > Jurusan Pendidikan Matematika > Program Studi Matematika (non kependidikan)
Depositing User: Elisa Febriyani
Date Deposited: 10 Sep 2024 15:48
Last Modified: 10 Sep 2024 15:48
URI: http://repository.upi.edu/id/eprint/123557

Actions (login required)

View Item View Item