Caregiver–patient traceability is essential for measuring care workload and interaction time in shared hospital rooms, where a single caregiver attends multiple patients and manual documentation is intrusive, time-consuming, and prone to errors. This paper proposes a non-invasive smart bedside sensing approach based on a commercial smartwatch worn by the caregiver and two compact ultra-wideband (UWB) localization anchors placed near the monitored beds. The smartwatch provides Magnetic, Angular Rate, and Gravity (MARG) data, while the UWB anchors enable bed-level proximity estimation without any device worn by the patient. The system was evaluated in a shared hospital room of approximately 5.0 × 4.8 m², with two hospital beds separated by 1.3–1.7 m. A dataset of four scenes totalling 19.9 min was collected, producing 1,140 one-second labeled samples and 1,074 valid windows after past–delayed sliding-window segmentation. Five supervised models were evaluated, including Long Short-Term Memory (LSTM) networks, a hybrid Convolutional Neural Network plus LSTM (CNN+LSTM) architecture, Extreme Gradient Boosting (XGBoost), and a non-linear Support Vector Machine (SVM). The Simple LSTM achieved the best performance, with 96% accuracy and a macro F1-score of 0.89. The results demonstrate accurate identification of the attended bed from wrist-worn and UWB signals alone, supporting scalable and objective caregiver–patient traceability in shared hospital rooms with minimal infrastructure.

Caregiver–patient traceability is essential for measuring care workload and interaction time in shared hospital rooms, where a single caregiver attends multiple patients and manual documentation is intrusive, time-consuming, and prone to errors. This paper proposes a non-invasive smart bedside sensing approach based on a commercial smartwatch with integrated Ultra-Wideband (UWB) radio worn by the caregiver and two compact UWB localization anchors deployed near the monitored beds. The classification approach uses a compact smartwatch feature set comprising three-axis magnetometer measurements and a four-component orientation quaternion provided by the device through Magnetic, Angular Rate, and Gravity (MARG)-based sensor fusion. No device is required to be worn by the patients. The system was evaluated in a shared hospital room measuring approximately $5.0\times 4.8$ m, with two hospital beds separated by 1.3–1.7 m. Three datasets involving two caregiver participants were included in the evaluation. Several supervised learning approaches were evaluated, including Long Short-Term Memory (LSTM) networks, a hybrid Convolutional Neural Network plus LSTM (CNN+LSTM) architecture, Extreme Gradient Boosting (XGBoost), and a non-linear Support Vector Machine (SVM). XGBoost and SVM achieved the best overall performance, reaching a macro F1-score of 0.97. The results demonstrate that compact wrist-worn magnetic and MARG-derived orientation signals can accurately identify the attended bed, supporting scalable and objective caregiver–patient traceability in shared hospital rooms with minimal infrastructure.