Enhancing Autism Detection Through Gaze Analysis Using Eye Tracking Sensors and Data Attribution with Distillation in Deep Neural Networks
Federica Colonnese, Francesco Di Luzio, Antonello Rosato, Massimo Panella, Vincenzo Randazzo, Eros Pasero · 2024
Read Enhancing Autism Detection Through Gaze Analysis Using Eye Tracking Sensors and Data Attribution with Distillation in Deep Neural Networks by Federica Colonnese, Francesco Di Luzio, Antonello Rosato, Massimo Panella, Vincenzo Randazzo, Eros Pasero (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-11645092.txt.
Description
Federica Colonnese and five co-authors published a study in twenty twenty-four on spotting autism from the way a child looks at the world. Eye trackers logged gaze, and a deep network learned the gaze traits that mark the spectrum. The catch: training data can be noisy, and noise drags a model down.
The team used a method that scores how much each training case pulls on the model, then dropped the worst pulls. Taught on just over three-quarters of the data, the leaner model scored near ninety-four percent, beating the same model taught on all of it. The kept cases also show which gaze traits drive the call. The authors pitch the mix of clean data and clear reasons as a path to tools doctors can trust.
Catalog record
| CREATOR | Federica Colonnese, Francesco Di Luzio, Antonello Rosato, Massimo Panella, Vincenzo Randazzo, Eros Pasero |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |