Related Experiment Video
Updated: Sep 22, 2025

06:52
An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field
Published on: May 26, 2020
8.1K
Pilot Study of Embedded IMU Sensors and Machine Learning Algorithms for Automated Ice Hockey Stick Fitting.
Taylor Léger1, Philippe J Renaud1, Shawn M Robbins2
1Department of Kinesiology and Physical Education, McGill Research Centre for Physical Activity and Health, McGill University, 475 Pine Avenue West, Montreal, QC H2W 1S4, Canada.
Sensors (Basel, Switzerland)
|May 20, 2022
Summary
Wearable inertial measurement unit (IMU) sensors and machine learning algorithms can rapidly and accurately fit ice hockey sticks. This technology offers a promising solution for personalized hockey equipment selection.
Area of Science:
- Sports Science
- Biomechanics
- Machine Learning
Background:
- Ice hockey stick fitting is crucial for player performance.
- Current methods can be time-consuming and subjective.
Purpose of the Study:
- To evaluate the feasibility of using IMU sensors and machine learning for instantaneous ice hockey stick fitting.
- To assess the accuracy of these technologies in identifying optimal stick characteristics for players.
Main Methods:
- Ten experienced players performed shots with four different hockey sticks.
- Custom IMUs in gloves captured hand kinematics.
- Optical motion capture tracked shot events and puck metrics.
- Machine learning algorithms analyzed kinematic data for classification.
Main Results:
- Machine learning models achieved 90-98% accuracy in classifying optimal stick flex, blade pattern, and kick point.
- Classification was highly accurate for both slap shots and wrist shots.
- The process was completed in fractions of a second.
Conclusions:
- Wearable sensors and machine learning show promise for reliable, rapid, and portable hockey stick fitting.
- This technology can enhance personalized equipment selection for players.
- Future applications may extend to real-time performance analysis.

