Privacy-Aware Bus Congestion Weather Scheduling

View at publisher Summarise with VIRAT
Authors: Qi Zhang, Xucheng Liu, Huan Wang, Zixuan Wang, Jiangke Cheng
Cited by: 0
References: 12

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Urban bus operations require timely identification of spatio-temporal congestion to support effective and accountable scheduling decisions. However, most studies treat congestion monitoring, weather impacts, and data privacy as separate problems, which limits deployability in intelligent transport systems that must also satisfy network-security and data-governance requirements. This study develops a reproducible and privacy-aware decision-support framework for corridor-level congestion identification and weather-responsive bus scheduling using large-scale AFC card data from Panzhihua City. The framework integrates multi-granularity congestion analytics (hourly peak characterization and line–direction–section overload detection via a high-quantile rule), interpretable weather-linked dispatching references (rain vs. non-rain demand ratio), and a privacy-governed publishing layer based on differential privacy (DP) aggregation. Empirical results reveal stable peak-hour structures and a significant weather–ridership relationship, with passenger demand on rainy days approximately 0.82 times that on non-rainy days. DP evaluation further shows that, under event-level adjacency, the Laplace mechanism introduces less than 0.002% mean absolute percentage error at the daily-aggregate level, indicating negligible utility loss for operational reporting. By jointly delivering actionable corridor prioritization, weather-adaptive scheduling cues, and auditable privacy protection, this work contributes an integrated paradigm aligned with intelligent computing and network security applications for urban transport.

Fields of Study & Subjects

Transportation Planning and Optimization Traffic Prediction and Management Techniques Human Mobility and Location-Based Analysis

Publication details

Journal / source
International Conference on Artificial Intelligence and Social Network Systems (AISNS)
Pages
111–119
Publication date
9 January 2026
Language
EN