Practical demonstration: The use of machine learning for the classification of movement data using the example of the uniqueness of individual gait patterns

Duration: 2 Hours

Number of participants: <20

Fee: No Fee

Speaker: Fabian Horst


Artificial Intelligence and machine learning techniques have become almost ubiquitous in our daily lives by supporting or guiding our decisions and providing recommendations. Impressively, there are certain tasks, such as playing board games like chess and Go, or classifying images, that machine learning approaches have already been solving more efficiently and effectively than humans do. It is therefore not surprising that machine learning approaches are currently becoming increasingly popular in the various scientific and non-scientific disciplines. This trend has also been well recognized in the field of human movement and sport science.

In the last year, machine learning methods have been successfully employed for the classification of data related to human movements (using, e.g., biomechanical data in gait analysis or positional data in team sports) and recently there has been increasing discussion about possible applications that can support practitioners in their decisions.

This pre-conference session is aimed to bring together early-stage researchers who are interested in an exchange on the application of machine learning in the field of human movement and sport science. As an introduction, the uniqueness of individual gait patterns will be used to demonstrate how machine learning methods can be used to classify movement data. The demonstration includes and discusses the typical steps from the recording, processing and analysis of the data.

© Copyright ICSS. All rights reserved.