Predicting missed alerts in detection dogs
Jörg Schultz, Liza Rothkoff, Edgar O Aviles-Rosa, Nathaniel J Hall, Michele N Maughan · 2026
Read Predicting missed alerts in detection dogs by Jörg Schultz, Liza Rothkoff, Edgar O Aviles-Rosa, Nathaniel J Hall, Michele N Maughan (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-13578711.txt.
Description
Jörg Schultz, Liza Rothkoff, Edgar Aviles-Rosa, Nathaniel Hall, and Michele Maughan show that a detection dog's missed alerts can be forecast from its state seconds before, in work from 2026. Such dogs guard against explosives and aid medical screening, yet even trained dogs sometimes miss a target scent. A miss can carry grave costs.
On a treadmill rig with precisely timed scent release, the team read movement and body signals before each trial. A model trained on pre-scent movement alone beat chance at calling misses. Adding heart and temperature data lifted the catch rate further. Stacking calls across trials gave a running risk gauge for the session. The authors propose live readiness watch for working dogs.
Catalog record
| CREATOR | Jörg Schultz, Liza Rothkoff, Edgar O Aviles-Rosa, Nathaniel J Hall, Michele N Maughan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 57 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |