Deep Learning Approaches for Classifying Children With and Without Autism Spectrum Disorder Using Inertial Measurement Unit Hand Tracking Data: Comparative Study
John Mutersbaugh, Wan-Chun Su, Anjana Bhat, Amir Gandjbakhche, Andrew Coristine · 2025
Read Deep Learning Approaches for Classifying Children With and Without Autism Spectrum Disorder Using Inertial Measurement Unit Hand Tracking Data: Comparative Study by John Mutersbaugh, Wan-Chun Su, Anjana Bhat, Amir Gandjbakhche, Andrew Coristine (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-12721220.txt.
Description
John Mutersbaugh and co-authors report a 2025 study on spotting autism in children from hand motion data. Autism can be hard to diagnose because current checks rely on observed behavior. Children with autism often differ in motor control, so the team tracked arm motion with small wearable sensors. Data came from school-age children doing a reach and clean-up task.
The team cleaned the sensor data and trained several deep learning models on it. They tested the models with two forms of cross-checking, one that kept each child's data apart. Readers can see which model types sorted children with and without autism most reliably. The work points toward more objective aids for early diagnosis.
Catalog record
| CREATOR | John Mutersbaugh, Wan-Chun Su, Anjana Bhat, Amir Gandjbakhche, Andrew Coristine |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |