Vehicle Inspection Forecasting Through Processing and Ensemble Machine Learning - Temporal Signal Processing - Research Article

Sep 17, 2026

Uploaded by Theodora

Vehicle inspection services underpin transportation safety and regulatory compliance, yet daily inspection volumes in developing regions show strong stochastic fluctuations from operational closures and inconsistent reporting, making direct daily forecasting unstable. This study builds a weekly vehicle inspection forecasting framework using ensemble machine learning combined with temporal signal processing. Data from Malang Regency, Indonesia (Jan 2020–Dec 2024) are aggregated into 258 weekly observations to reduce high-frequency noise while preserving seasonal dynamics. Gradient Boosting achieves the best results among evaluated models.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Introduction

Problem motivation and forecasting challenges

Dynamical-system interpretation

Need for signal processing and robust forecasting

Eksakta : Berkala Ilmiah Bidang MIPA VOLUME 27 NO 03 2026, pp 431-448 ISSN : Print 1411-3724—Online 2549-7464 [DOI : htts://doi.org/10.24036/eksakta/vol27-iss03/706](DOI : htts://doi.org/10.24036/eksakta/vol27-iss03/706) Eksakta Berkala Ilmiah Bidang MIPA [http://www.eksakta.ppj.unp.ac.id/index.php/eksakta](http://www.eksakta.ppj.unp.ac.id/index.php/eksakta) | | | | | --- | --- | --- | | Article
Vehicle Inspection Forecasting Through Processing and Ensemble Machine Learning | Temporal | Signal | | | | | Bambang Sismanto1 , Nurhayati Nurhayati1 , Raden Roro Article Info Hapsari Peni Agustin Tjahyaningtijas1 , Ja'afar Mahmud2 , Raimundo Eider Figueredo3 , Atul Varshney4 Article history : Received June 02 , 2026 Revised June 15, 2026 Accepted June 20 , 2026 Published June 30, 2026 Keywords : Vehicle inspection forecasting, ensamble machine learning, temporal dynamics, signal precessing, time-series forecasting 1Department of Electrical Engineering, Faculty of Engineering, Universitas Negeri Surabaya, Surabaya, Indonesia 2Department of Electronics & Telecommunications Engineering, Faculty of Engineering, Ahmadu Bello University, Zaria, Nigeria 3Maxwell Microwave and Applied Electromagnetism Laboratory, Brazil 4ECE Department, FET, Gurukula Kangri (Deemed to be University), Haridwar-249404, Uttarakhand, India Abstract. Vehicle inspection services are essential for maintaining transportation safety and regulatory compliance. However, daily inspection volumes in developing regions exhibit high stochastic fluctuations due to operational closures and reporting inconsistencies, making direct daily forecasting unreliable. This study proposes a weekly vehicle inspection forecasting framework using ensemble machine learning with temporal signal processing. Accurate forecasting is critical for resource allocation, staffing, and service management. The dataset covers January 2020 to December 2024 from Malang Regency, Indonesia, aggregated into 258 weekly observations. Weekly aggregation acts as a low-pass filter (ω_c = 1/7 day⁻¹) to reduce high-frequency noise while preserving seasonal dynamics. Four regression models were evaluated: Random Forest (R² = 0 .6198, MAE = 69 .85), XGBoost (R² = 0.7198, MAE = 55.68), Gradient Boosting (R² = 0. 7373, MAE = 46.41), and a weighted ensemble (R² = 0.7164, MAE = 55. 89) . Conventional regression methods including Linear Regression, Ridge, and Lasso were also tested as baselines. Gradient Boosting achieved the best performance. The findings indicate that tree-based ensemble models capture nonlinear temporal dynamics more effectively than conventional approaches. This study demonstrates that ensemble machine learning with signal processing provides practical forecasting tools for transportation service planning. This is an open acces article under the CC-BY license. This is an open access article distributed under the Creative Commons 4.0 Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. ©2026 by author. Corresponding Author : Nurhayati Nurhayati Department of Electrical Engineering, Universitas Negeri Surabaya , Surabaya, Indonesia [Email :](Email : nurhayati@unesa.ac.id)[ ](Email : nurhayati@unesa.ac.id)[nurhayati@unesa.ac.id](Email : nurhayati@unesa.ac.id) 1. Introduction Surface transport has developed due to technological progress leveraging related fields like machine learning [1] . Regional transportation authorities have the duty of making sure that commercial vehicles comply with safety and emissions regulations via routine checks an essential element [2] in creating a cohesive inspection system is the establishment of contemporary, inified inspection framework [3] . From a dynamical systems perspective, vehicle inspection pass rates can be conceptualized as a time-varying state variable evolving according to underlying system dynamics influ

FAQs

Why is daily vehicle inspection forecasting unreliable in developing regions?

Daily inspection volumes fluctuate heavily due to operational closures and reporting inconsistencies, which introduce high-frequency noise and make direct prediction unstable.

How does the study prepare the data for weekly forecasting?

The dataset from January 2020 to December 2024 in Malang Regency is aggregated into 258 weekly observations, acting like a low-pass filter to reduce short-term noise while preserving seasonal dynamics.

Which models were compared and which performed best?

Random Forest, XGBoost, Gradient Boosting, and a weighted ensemble were tested, alongside baseline linear methods (Linear Regression, Ridge, Lasso). Gradient Boosting achieved the best performance.

Sep 17, 2026

Uploaded by Theodora