WTConv–TimesNet for Road Icing State Classification with IWOA-Based Hyperparameter Optimization
Lingqiu Cui, Yuxun Ji, Lijuan Zhang, Handong Li · 2026
Read WTConv–TimesNet for Road Icing State Classification with IWOA-Based Hyperparameter Optimization by Lingqiu Cui, Yuxun Ji, Lijuan Zhang, Handong Li (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-13210942.txt.
Description
Lingqiu Cui, Yuxun Ji, Lijuan Zhang, and Handong Li classify the icing state of roads from weather data, to warn drivers before the slide. Their 2026 paper builds on a time-series network that reads periodic patterns in multi-source monitoring streams. Icing is a fast, stage-jumping process, so the team adds wavelet-based convolution to catch sharp local changes across time scales.
A whale-inspired optimizer, improved by the authors, tunes the model, and correlation analysis prunes the inputs to the physically meaningful few. On a real road data set, the full model lifted accuracy from about ninety-three to nearly ninety-nine percent against its own baseline. Feature selection added another point, while steadying the scores across icing stages. The authors present the system as a practical early-warning tool for winter roads, where the difference between damp, frost, and ice is measured in accidents.
Catalog record
| CREATOR | Lingqiu Cui, Yuxun Ji, Lijuan Zhang, Handong Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |