A neural network-based automatic semi-variogram modeling approach for geomagnetic map construction in multi-source indoor and outdoor navigation
Chengsheng Zhan, Ping Huang, Bing Xue, Bin Lan · 2025
Read A neural network-based automatic semi-variogram modeling approach for geomagnetic map construction in multi-source indoor and outdoor navigation by Chengsheng Zhan, Ping Huang, Bing Xue, Bin Lan (2025) 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-12804931.txt.
Description
Chengsheng Zhan and three co-authors automate magnetic map making for navigation. Their 2025 paper improves geomagnetic maps used indoors and out. Such maps guide devices where satellite signals fail. Their accuracy hinges on kriging, a method that needs a well-fit variance model.
Fitting that model by hand leans on expert judgment and varies by person. The team's neural network reads samples and infers the model settings itself. An encoder-decoder design with an attention block sharpens the guesses. Maps built this way came out smoother and truer than standard kriging. The workflow also runs with less manual fuss. Better magnetic maps mean steadier navigation in signal dead zones.
Catalog record
| CREATOR | Chengsheng Zhan, Ping Huang, Bing Xue, Bin Lan |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |