Unsupervised explainable activity prediction in competitive Nordic Walking from experimental data

TL;DR

This paper presents an unsupervised, online activity prediction system for Nordic Walking using wearable sensors, achieving high accuracy and providing explainable results to distinguish between correct, incorrect, and cheating practices.

Contribution

It introduces a novel unsupervised, online clustering approach for activity recognition that enhances explainability and reduces computational and labeling burdens.

Findings

Achieved near 100% accuracy in activity prediction.

Enabled automatic expansion of limited activity labels.

Provided explainable classification distinguishing activity types.

Abstract

Artificial Intelligence (AI) has found application in Human Activity Recognition (HAR) in competitive sports. To date, most Machine Learning (ML) approaches for HAR have relied on offline (batch) training, imposing higher computational and tagging burdens compared to online processing unsupervised approaches. Additionally, the decisions behind traditional ML predictors are opaque and require human interpretation. In this work, we apply an online processing unsupervised clustering approach based on low-cost wearable Inertial Measurement Units (IMUs). The outcomes generated by the system allow for the automatic expansion of limited tagging available (e.g., by referees) within those clusters, producing pertinent information for the explainable classification stage. Specifically, our work focuses on achieving automatic explainability for predictions related to athletes' activities, distinguishing between correct, incorrect, and cheating practices in Nordic Walking. The proposed solution achieved performance metrics of close to 100 % on average.