Operational Characteristics and Machine Learning-Based Idling Time Prediction for 119 Ambulances in South Korea

This study examined the potential value of operational records from the Driving Record Analysis System (eTAS) as supplementary information for future service life evaluations of 119 ambulances in South Korea.An international literature review was combined with regional and correlation analyses of 102 ambulances from seven metropolitan and provincial fire headquarters. Nine machine learning models predicting Idling Time were evaluated using 70 ambulances (52 training and 18 testing), excluding 32 Jeonnam ambulances because required operational variables could not be fully extracted. Idling Time differed by approximately six-fold among vehicles with similar Driving Distance. Total Operating Time was strongly correlated with Idling Time (r = 0.93), whereas Driving Distance showed a weaker association. Ridge Regression achieved a Test R2 of 0.883, compared with 0.726 for XGBoost. Excluding Total Operating Time reduced the respective Test R2 values to 0.654 and 0.533. However, because Idling Time is a component of Total Operating Time, the observed associations and predictive performance may partly reflect this compositional relationship rather than independent effects. The findings suggest that Driving Distance alone cannot fully characterize ambulance utilization and provide preliminary operational evidence for future evaluation frameworks. Relationships with mechanical deterioration, remaining service life, and replacement outcomes require further validation.

Authors

Institutions

Publication Details

Journal
Fire
Published
2026-11-12
DOI
https://doi.org/10.3390/fire9110506
Primary Topic
Reliability and Maintenance Optimization
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Operational Characteristics and Machine Learning-Based Idling Time Prediction for 119 Ambulances in South Korea

Sunyoung Park, Yongtaek Han
Fire
Reliability and Maintenance Optimization
article

Operational Characteristics and Machine Learning-Based Idling Time Prediction for 119 Ambulances in South Korea

Sunyoung Park, Yongtaek Han
article en

Abstract

This study examined the potential value of operational records from the Driving Record Analysis System (eTAS) as supplementary information for future service life evaluations of 119 ambulances in South Korea.An international literature review was combined with regional and correlation analyses of 102 ambulances from seven metropolitan and provincial fire headquarters. Nine machine learning models predicting Idling Time were evaluated using 70 ambulances (52 training and 18 testing), excluding 32 Jeonnam ambulances because required operational variables could not be fully extracted. Idling Time differed by approximately six-fold among vehicles with similar Driving Distance. Total Operating Time was strongly correlated with Idling Time (r = 0.93), whereas Driving Distance showed a weaker association. Ridge Regression achieved a Test R2 of 0.883, compared with 0.726 for XGBoost. Excluding Total Operating Time reduced the respective Test R2 values to 0.654 and 0.533. However, because Idling Time is a component of Total Operating Time, the observed associations and predictive performance may partly reflect this compositional relationship rather than independent effects. The findings suggest that Driving Distance alone cannot fully characterize ambulance utilization and provide preliminary operational evidence for future evaluation frameworks. Relationships with mechanical deterioration, remaining service life, and replacement outcomes require further validation.

FireVol. 9(11)
Hoseo University (KR)
Hoseo University
Industry, innovation and infrastructure, Good health and well-being, Sustainable cities and communities
Reliability and Maintenance Optimization
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon