Synthetic Data–Guided Feature Selection for Robust Activity Recognition in Older Adults

Le résumé fourni par la source

Abstract Physical activity during hip fracture rehabilitation is essential for mitigating long-term functional decline in geriatric patients. However, it is rarely quantified in clinical practice. Existing continuous monitoring systems with commercially available wearable activity trackers are typically developed in middle-aged adults and therefore perform unreliably in older adults with slower and more variable gait patterns. This study aimed to develop a robust human activity recognition (HAR) system to improve continuous physical activity recognition in the context of hip fracture rehabilitation. 24 healthy older adults aged $$\ge $$ ≥ 80 years were included as an age-matched feasibility cohort. Participants performed activities of daily living under simulated free-living conditions for 75 min while wearing two accelerometers positioned on the lower back and anterior upper thigh. To address and enhance model robustness to inter-person variability, a novel synthetic data generation scheme was proposed to capture common gait characteristics across individuals. Our real data and synthetic data have been published along with this work. Leveraging this synthetic dataset, a feature selection pipeline was subsequently applied to identify a compact set of six discriminative features for classifying walking, standing, sitting, lying down, and postural transfers. Model robustness was evaluated using leave-one-subject-out cross-validation. The synthetic data demonstrated potential to improve generalization across participants. The resulting feature intervention model (FIM), aided by synthetic data guidance, achieved reliable activity recognition with mean F1-scores of 0.896 ± 0.100 for walking, 0.927 ± 0.039 for standing, 0.997 ± 0.004 for sitting, 0.937 ± 0.202 for lying down, and 0.816 ± 0.120 for postural transfers. Compared with a control condition model without synthetic data, the FIM significantly improved the postural transfer detection, i.e., an activity class of high clinical relevance that is often overlooked in existing HAR literature. In conclusion, these preliminary results demonstrate the feasibility of robust activity recognition in older adults. Further validation in hip fracture patient populations is required to assess the clinical utility of the proposed monitoring system.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.