A Deep Learning Approach to Automatically Classify Ice Hockey Shooting Actions Using Acceleration Signals
Samuel Tremblay, Philippe J. Renaud, Shawn M. Robbins, David J. Pearsall, Philippe C. Dixon · 2026
Read A Deep Learning Approach to Automatically Classify Ice Hockey Shooting Actions Using Acceleration Signals by Samuel Tremblay, Philippe J. Renaud, Shawn M. Robbins, David J. Pearsall, Philippe C. Dixon (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-13259433.txt.
Description
Samuel Tremblay and colleagues classify hockey stick actions from wearable motion sensors in a 2026 study. Forty three elite players wore sensors while performing passes, several shot types, and rest actions. A convolutional network learned to name seven actions from acceleration signals alone.
Full body sensing reached the best balanced score across repeated test splits. Two hand sensors alone came remarkably close to that score. Sensor fitted gloves could therefore capture useful technique data in real rinks. Coaches gain objective counts of shot types during practice without video review. Players get feedback grounded in measured movement rather than impression.
Catalog record
| CREATOR | Samuel Tremblay, Philippe J. Renaud, Shawn M. Robbins, David J. Pearsall, Philippe C. Dixon |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |