Representing and Detecting Label Ambiguity in IMU-Based Exercise Evaluation
For physiotherapy systems relying on IMU data, this work provides a way to capture and detect label ambiguity without sacrificing classification performance, improving reliability in unsupervised home settings.
The paper addresses label ambiguity in IMU-based exercise evaluation by automatically generating label distributions per repetition without a large rater pool. The proposed method matches or exceeds one-hot classification baselines on four datasets while reliably detecting ambiguous repetitions and relevant classes.
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.