一种基于时间序列聚类的道路交通状态在线辨识方法
By combining time-series-based FCM clustering and dynamic time warping algorithms with data processing from critical and non-critical traffic detection stations, the problem of unstable traffic state identification in existing technologies has been solved, achieving high-resolution online traffic state identification, improving the reliability of traffic management and reducing labor costs.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- YANGZHOU UNIV
- Filing Date
- 2025-01-06
- Publication Date
- 2026-07-17
AI Technical Summary
Existing unsupervised clustering methods struggle to capture the local fluctuations and evolution patterns of high-resolution traffic flow state parameters in road traffic state identification, resulting in unstable traffic state identification results that fail to meet the needs of online traffic management and are also costly in terms of manpower.
A high-resolution online traffic state identification model is constructed by employing time-series-based FCM clustering and dynamic time warping algorithms, combined with data processing methods for critical and non-critical traffic detection stations. Online traffic state smoothing is achieved through cluster center template matching and dynamic programming, thus realizing stable online identification.
It improves the stability and reliability of traffic condition identification, reduces human intervention and labor costs, and supports intelligent transportation decision-making.
Smart Images
Figure CN119889033B_ABST