Representing and Detecting Label Ambiguity in IMU-Based Exercise Evaluation
2026-07-06 • Machine Learning
Machine Learning
AI summaryⓘ
The authors studied how to improve automatic systems that check exercise quality from sensors worn during home workouts. They found that some exercise repetitions are hard to classify clearly because they fall between categories, even for experts. Instead of forcing a strict label, their method lets the system show uncertainty by learning a range of possible labels. This approach worked as well or better than traditional methods and helped the system identify when an exercise repetition was ambiguous and what categories might apply.
home-based physiotherapyinertial measurement unitsclassificationlabel distributionambiguityKullback-Leibler divergenceone-hot encodingcross-entropy lossmachine learningexercise assessment
Authors
Andreas Spilz, Heiko Oppel, Michael Munz
Abstract
Home-based physiotherapy is performed without supervision, which leads to incorrect execution and motivates systems that assess movement automatically from inertial measurement units (IMUs). Such systems assign each repetition to a category, yet a relevant share of repetitions falls near a class boundary, where even trained raters disagree. Classifiers trained with one-hot labels collapse these borderline repetitions onto a single class and discard this ambiguity. We address this with a method that automatically generates a label distribution per repetition without a large rater pool. We train a network to reproduce the full distribution with a Kullback-Leibler objective, the ambiguity approach, and compare it against a one-hot cross-entropy baseline on four IMU exercise datasets. From the network output we further determine whether a repetition is ambiguous and which classes are relevant to it. The ambiguity approach matched or exceeded the baseline classification on all four datasets, and detected ambiguity and the relevant classes more reliably. Representing the label distribution in the training target therefore adds information about ambiguity at no cost to classification.