Prediksi Jumlah Penumpang Dan Penambahan Gerbong Kereta Api Menggunakan Metode Support Vector Regression (svr)

Penulis

DOI:

https://doi.org/10.34818/eoe.v7i2.12408

Abstrak

Abstrak Transportasi kereta api dapat dibagi menjadi transportasi penumpang dan transportasi kargo. Oleh karena itu, proses perencanaan dan operasional terkait dengan kapasitas penumpang adalah bidang yang lebih menarik untuk dikaji lebih dalam dari masalah prediksi penambahan gerbong. Support Vector Regression (SVR) merupakan pengembangan dari metode Support Vector Machine untuk kasus regresi. Metode ini mampu mengatasi overfitting, dalam pemilihan parameter SVR menggunakan algoritma Grid Search. Data yang digunakan pada Tugas Akhir ini menggunakan data jumlah penumpang kereta api Argo Parahyangan periode 2019 dan jenis kelas kereta api dibagi menjadi 2, yaitu kelas Ekonomi dan kelas Eksekutif. Rata-rata dari hasil pengujian SVR menggunakan kernel RBF menghasilkan nilai performansi MAE (Mean Abosolute Error) sebesar 0.1276, MSE (Mean Square Error) sebesar 0.1796 dan MAPE (Mean Absolute Percentage Error) sebesar 0,00376. Kata kunci : Algoritma Grid Search, Kereta Api, Prediksi, Support Vector Regression. Abstract Rail transportation can be divided into passenger transportation and cargo transportation. Therefore, the planning and operational process related to passenger capacity is a more interesting field to study more deeply than the prediction problem of the addition of railway. Support Vector Regression (SVR) is a development of the Support Vector Machine method for regression cases. This method is able to overcome overfitting, in selecting SVR parameters using the Grid Search algorithm. The data used in this Final Project uses data on the total of Argo Parahyangan train passengers in the 2019 period and the types of train classes are divided into 2, namely Economy and Executive classes. The average SVR test results using RBF kernel produce MAE (Mean Abosolute Error) performance values of 0.1276, MSE (Mean Square Error) of 0.1796 and MAPE (Mean Absolute Percentage Error) of 0.00376. Keywords: Grid Search Algorithm, Prediction, Railway Train, Support Vector Regression

Unduhan

Data unduhan tidak tersedia.

Referensi

[1] I. Purnamasari, “Hubungan Struktur Sistem Pengendalian Manajemen dan Proses Sistem Pengendalian Manajemen dengan Kinerja Keuangan Perusahaan pada PT . Kereta Api Indonesia ( Persero ) ( The Correlation between the Structure of Management Control System and Process of Mana,” Fokus Ekon., vol. 4, no. 1, pp. 27–43, 2009.

[2] Q. Huang, J. Mao, and Y. Liu, “An Improved Grid Search Algorithm of SVR Parameters Optimization,” Int. Conf. Commun. Technol. Proceedings, ICCT, no. 2, pp. 1022–1026, 2012.

[3] R. Primartha, Belajar Machine Learning Teori dan Praktik. Bandung: Informatika, 2018.

[4] S. Shataee, S. Kalbi, A. Fallah, and D. Pelz, “Forest Attribute Imputation Using MachineLearning Methods and ASTER Data: Comparison of k-NN, SVR and Random Forest Regression Algorithms,” Int. J. Remote Sens., vol. 33, no. 19, pp. 6254–6280, 2012.

[5] D. Nguyen, "Learning Data Science - Predict Stock Price with Support Vector Regression (SVR)," IT Next Organizer, 1 Maret 2016.

[6] L. Septiningrum, J. Statistika, F. Sains, D. A. N. Matematika, and U. Diponegoro, “Prediksi Indeks Harga Saham Gabungan Menggunakan Support Vector Regression Dengan Algoritma Grid Search”, 2015.

[7] H. Yasin, R. E. Caraka, Tarno, and A. Hoyyi, “Prediction of Crude Oil Prices Using Support Vector Regression (SVR) With Grid Search - Cross Validation Algorithm,” Glob. J. Pure Appl. Math., vol. 12, no. 4, pp. 3009–3020, 2016.

[8] R. E. Caraka, “Peramalan Crude Palm Oil ( CPO ) Menggunakan Support Vector Regression Kernel Radial Basis,” vol. 7, no. 1, pp. 43–57, 2017.

[9] Furi, R. P., Jondri & Saepudin, D., “Peramalan Financial Time Series Menggunakan Independent Component Analysis dan Support Vector Regression (Studi Kasus: IHSG dan Jll), 2015.

Diterbitkan

2020-08-01

Terbitan

Halaman

4919-4926

Bagian

Program Studi S1 Teknik Komputer

Cara Mengutip

Aeni, U. N., Prasasti, A. L., & Kallista, M. (2020). Prediksi Jumlah Penumpang Dan Penambahan Gerbong Kereta Api Menggunakan Metode Support Vector Regression (svr). eProceedings of Engineering, 7(2), 4919-4926. https://doi.org/10.34818/eoe.v7i2.12408