Consistency-Aware Weakly Supervised Anomaly Sensing for Large-Scale Expressway ETC Gantry Transactions
Yijia Li, Haiyan Jiang, Xiaoxue Xu, Vladimir Zyryanov · 2026
Read Consistency-Aware Weakly Supervised Anomaly Sensing for Large-Scale Expressway ETC Gantry Transactions by Yijia Li, Haiyan Jiang, Xiaoxue Xu, Vladimir Zyryanov (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13611106.txt.
Description
Li, Jiang, Xu, and Zyryanov detect anomalies in highway toll transactions in twenty twenty-six. Electronic toll gantries log huge numbers of vehicle passages daily. Finding fraud or errors usually needs labelled examples or outside data. Their method ranks records whose views disagree with each other.
The system blends money, timing, pattern, and context evidence. High confidence cases then train a gradient boosting model. Testing used over fourteen million transactions from thousands of gantries. Scores beat a standard isolation forest baseline on benchmark tasks. A blinded audit of twelve hundred records gave mixed results on one subset. All data came from one day in one province. The authors note wider testing is still needed.
Catalog record
| CREATOR | Yijia Li, Haiyan Jiang, Xiaoxue Xu, Vladimir Zyryanov |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 123 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |