Counterfactual explanations (CEs) for multivariate time-series classifiers are often difficult to interpret in domains where experts reason in terms of semantic feature groups rather than individual channels. In rehabilitation movement analysis with multi-sensor inertial measurement units (IMUs), clinicians interpret motion through muscle-group and joint-segment abstractions; yet, most existing counterfactual methods operate at the channel level, producing scattered and biomechanically incoherent explanations.
arXiv:2607. 01838v1 Announce Type: new Abstract: Counterfactual explanations (CEs) for multivariate time-series classifiers are often difficult to interpret in domains where experts reason in terms of semantic feature groups rather than individual channels.
arXiv:2607. 20237v1 Announce Type: new Abstract: Rehabilitation scoring systems are most useful when their outputs can be reviewed and interpreted within clinical workflows.
arXiv:2608. 06122v1 Announce Type: cross Abstract: Inspired by recent evidence that transformer architectures benefit from Self-PreTraining (SPT) on long-context benchmarks, we investigate whether similar gains extend to multimodal, multivariate, and even simple univariate medical time series.
arXiv:2601. 14590v3 Announce Type: replace Abstract: Counterfactual explanations (CFEs) provide human-centric interpretability by identifying the minimal, actionable changes required to alter a machine learning model's prediction.
arXiv:2606. 24960v1 Announce Type: new Abstract: Tailoring stroke rehabilitation requires assessing how movements are organized, not merely if they succeed.
arXiv:2505. 24415v2 Announce Type: replace-cross Abstract: Automated evaluation of movement quality can enhance physiotherapeutic treatment and sports training by providing objective, real-time feedback.
arXiv:2608. 12695v1 Announce Type: new Abstract: Self-supervised electrocardiogram (ECG) models are often trained on a few seconds of ECG signal and, increasingly, on discretized token sequences.
arXiv:2607. 15447v1 Announce Type: new Abstract: Recent research in clinical machine learning, focusing on outcome predictions in intensive care unit (ICU), has shifted from bespoke supervised models to foundation models, utilising modern representation learning methods.
DiaSeg extracts diagonal segments from Dynamic Time Warping (DTW) paths, characterizing each with five geometric features to preserve local alignment information. In a study of 91 subjects across six clinical conditions, these segments revealed consistent unsupervised patterns aligned with biomechanical phases and achieved near-perfect separation of healthy and pathological gait. While cycle‑based methods reached higher overall accuracy, DiaSeg offers phase‑specific interpretability, pinpointing where coordination breaks down within the gait cycle.
arXiv:2606. 00345v1 Announce Type: new Abstract: Wearable and mobile sensing technologies enable continuous monitoring of human behavior and health in real-world settings.
The study introduces a framework that reconciles minute‑resolution athlete monitoring data with injury labels that are only available at the session level. By creating fixed‑time landmarks (10, 20, 30, 40, 50, and 60 minutes) and generating a single representation per athlete‑session up to each landmark, the authors evaluate several machine‑learning models and data‑augmentation strategies on elite women’s football data. Results show that discrimination varies across landmarks, with TabPFN outperforming Logistic Regression at later landmarks but not consistently beating Random Forest, and that synthetic augmentation offers benefits only in specific conditions.
The paper introduces the first federated learning framework for infant movement analysis, specifically targeting General Movement Assessment using skeletal motion data. It employs Monte Carlo Dropout to estimate predictive uncertainty and proposes an Uncertainty-Aware Federated Averaging (UA‑FedAvg) strategy that weights client updates by this uncertainty. Experiments with three clients show that federated learning outperforms local models and approaches centralized training performance, with UA‑FedAvg generally surpassing standard FedAvg.