Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Integra: Journal of Integrated Mathematics and Computer Science
Nurdin, Muhaymi
Unknown Affiliation
Computer Science & IT Mathematics

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Comparison of Support Vector Regression and Random Forest Regression Performance in Vehicle Fuel Consumption Prediction Nurdin, Muhaymi; Wamiliana; Junaidi, Akmal; Lumbanraja, Favorisen Rossyking
Integra: Journal of Integrated Mathematics and Computer Science Vol. 1 No. 2 (2024): July
Publisher : Magister Program of Mathematics, Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26554/integrajimcs.20241221

Abstract

Predicting vehicle fuel consumption is an important aspect in improving energy efficiency and supporting sustainable transportation. This study aims to compare the performance of Support Vector Regression (SVR) and Random Forest Regression (RFR) algorithms in predicting combined vehicle fuel consumption (COMBINED, a combination of 55% urban and 45% highway). The Canadian government's Fuel Consumption Ratings dataset was used, with 2015-2023 data (9,185 entries) for training and testing, and 2024 data (764 entries) for further testing. Pre-processing involved StandardScaler for numerical features and OneHotEncoder for categorical features, followed by hyperparameter optimization using Grid Search, resulting in optimal parameters: SVR (C=100, epsilon=0.5, gamma=1) and RFR (n_estimators=200, max_depth=None, min_samples_split=2). Results show RFR is superior with R2 0.8845, RMSE 0.9671, and MAE 0.6566, compared to SVR with R2 0.8648, RMSE 1.0462, and MAE 0.7150. Evaluation on 2024 data and visualization of error distribution corroborate the superiority of RFR. This study concludes RFR is more effective for COMBINED prediction, although SVR is competitive post-optimization, and contributes to the selection of machine learning models for green vehicle technology.
Co-Authors Akmal Junaidi Lumbanraja, Favorisen Rossyking Wamiliana