Preliminary Analysis of Collar Sensors for Guide Dog Training Using Convolutional Long Short-Term Memory, Kernel Principal Component Analysis and Multi-Sensor Data Fusion
Devon Martin, David L Roberts, Alper Bozkurt, Jacqueline Boyd · 2024
Read Preliminary Analysis of Collar Sensors for Guide Dog Training Using Convolutional Long Short-Term Memory, Kernel Principal Component Analysis and Multi-Sensor Data Fusion by Devon Martin, David L Roberts, Alper Bozkurt, Jacqueline Boyd (2024) 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-11640111.txt.
Description
Martin, Roberts, and Bozkurt tested smart collar sensors in twenty twenty-four that read guide dog acts during training. Guide dogs cost much to train, so too few reach the folks who need them. Their collar packs many sensors, and two learning methods read the stream for ten dog states.
Each method hit near forty percent truth on the ten-state task. One net worked best on thinned data, while a kernel method won on filled data and needs no training. Motion sensors gave most of the signal, with sound a small add. Some states could merge into wider ones to ease the tests, they note.
Catalog record
| CREATOR | Devon Martin, David L Roberts, Alper Bozkurt, Jacqueline Boyd |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 57 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |