Journal Search Engine
The Journal of The Korea Institute of Intelligent Transport Systems Vol.24 No.6 pp.17-34
심층생성모델과 활동기반모형을 활용한 노인 인구의 수요응답형 교통 분석 연구
A Study on Demand-Responsive Transport for the Elderly Using Deep Generative and Activity-Based Models
Abstract
This study addresses the limitations of public transport in aging rural areas by exploring operation strategies for Demand-Responsive Transport (DRT). We integrate an activity-based model with a deep generative model to construct a synthetic population reflecting future demographic change and to reproduce individual travel demand. Using Hongseong County (Korea) as a case study, we simulate 27 scenarios in a full-factorial design that varies demand characteristics, passenger group size, and vehicle fleet configuration. Results show that demand growth driven by population aging (from 2021 to 2039) increases the service rejection rate from 2.6% to 35.1% and average waiting time from 527 to 856 seconds—an increase of more than 62%—ultimately degrading overall service quality. Fleet configuration exhibits a clear trade-off between operational efficiency and user experience. These findings suggest that rural DRT systems require dynamic and adaptive fleet allocation rather than static, fixed operations to accommodate shifts in population structure and demand levels. However, because this study is based on a single case region (Hongseong), the generalizability of the quantitative results is limited. Future research should apply the proposed framework to diverse rural contexts with varying demographic and spatial characteristics to more rigorously assess its applicability and to develop generalizable operational guidelines.
