Unsupervised explainable activity prediction in competitive Nordic Walking from experimental data
This work addresses the need for explainable and efficient activity prediction in a specific sports domain, though it appears incremental by combining existing unsupervised methods with explainability.
The paper tackled the problem of opaque and computationally heavy human activity recognition in competitive Nordic Walking by applying an online unsupervised clustering approach with wearable sensors, achieving performance metrics close to 100% on average.
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.