Automatic Detection of Magnetic Disturbances in Magnetic Inertial Measurement Unit Sensors Based on Recurrent Neural Networks
Elkyn Alexander Belalcazar-Bolaños, Diego Torricelli, José L. Pons · 2023
Read Automatic Detection of Magnetic Disturbances in Magnetic Inertial Measurement Unit Sensors Based on Recurrent Neural Networks by Elkyn Alexander Belalcazar-Bolaños, Diego Torricelli, José L. Pons (2023) 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-10747388.txt.
Description
Elkyn Alexander Belalcazar-Bolaños, Diego Torricelli, and José L. Pons built a neural network that spots magnetic interference in wearable motion sensors, in a 2023 paper. These sensors fuse motion and magnetic readings to track body movement, but stray magnetic fields corrupt them, and simple threshold checks miss many disturbances. Their network reads the magnetometer stream directly and labels each moment with a disturbance probability.
The team trained the system on a dataset that reproduces many kinds of interference and motion in a repeatable way. Testing across fifteen splits, varying the sensor, the interference direction, and the signal type, the network caught about ninety-eight percent of disturbances. They report a clear gain over the threshold methods in current use.
Catalog record
| CREATOR | Elkyn Alexander Belalcazar-Bolaños, Diego Torricelli, José L. Pons |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |