This study explored an indoor system for tracking multiple humans and detecting falls, employing three Millimeter-Wave radars from Texas Instruments. Compared to wearables and camera methods, Millimeter-Wave radar is not plagued by mobility inconveniences, lighting conditions, or privacy issues. We conducted an initial evaluation of radar characteristics, covering aspects such as interference between radars and coverage area. Then, we established a real-time framework to integrate signals received from these radars, allowing us to track the position and body status of human targets non-intrusively. Additionally, we introduced innovative strategies, including dynamic Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering based on signal SNR levels, a probability matrix for enhanced target tracking, target status prediction for fall detection, and a feedback loop for noise reduction. We conducted an extensive evaluation using over 300 min of data, which equated to approximately 360,000 frames. Our prototype system exhibited a remarkable performance, achieving a precision of 98.9% for tracking a single target and 96.5% and 94.0% for tracking two and three targets in human-tracking scenarios, respectively. Moreover, in the field of human fall detection, the system demonstrates a high accuracy rate of 96.3%, underscoring its effectiveness in distinguishing falls from other statuses.

This paper investigates the energy savings that near-subthreshold processors can obtain in edge AI applications and proposes strategies to improve them while maintaining the accuracy of the application. The selected processors deploy adaptive voltage scaling techniques in which the frequency and voltage levels of the processor core are determined at the run-time. In these systems, embedded RAM and flash memory size is typically limited to less than 1 megabyte to save power. This limited memory imposes restrictions on the complexity of the neural networks model that can be mapped to these devices and the required trade-offs between accuracy and battery life. To address these issues, we propose and evaluate alternative ‘big–little’ neural network strategies to improve battery life while maintaining prediction accuracy. The strategies are applied to a human activity recognition application selected as a demonstrator that shows that compared to the original network, the best configurations obtain an energy reduction measured at 80% while maintaining the original level of inference accuracy.

Objective: Cuffless blood pressure (BP) monitoring technologies, primarily based on pulse transit time (PTT) or photoplethysmography (PPG), frequently suffer from calibration drift due to their reliance on blood volume surrogates rather than direct pressure measurement. To address this physiological limitation, this study presents a multi-modal deep learning framework that integrates superficial temporal artery tonometry (STAT), which captures high-fidelity pressure waveform morphology, with electrocardiography (ECG) and PPG signals. Approach: A custom wearable device was developed to simultaneously acquire these signals during dynamic perturbations. Extracted features included heart rate (HR) from ECG, PTT from ECG-PPG pairs, and BP-related metrics derived from PTT and STAT. Signal quality indices for ECG, PPG, and STAT signals were also computed to assess signal reliability. A temporal convolutional network (TCN) model was designed to capture the complex, non-linear dependencies between these multi-modal features and beat-to-beat BP. Main results: The approach was rigorously validated using Leave-One-Subject-Out Cross-Validation (LOSOCV) on 29 recordings from ten healthy volunteers undergoing isometric handgrip exercises. The proposed TCN model significantly outperformed traditional PTT and STAT-only baselines, achieving a Mean Absolute Difference (MAD) of 5.58 mmHg for Systolic BP (SBP), 4.39 mmHg for mean BP (MBP) and 4.34 mmHg for diastolic BP (DBP). Notably, the TCN model exhibited significantly lower errors (p < 0.05, Wilcoxon Test) during dynamic BP fluctuations compared to baseline models. Significance: The study demonstrates that fusing tonometry-derived pressure morphology with hemodynamic timing features effectively mitigates the limitations of conventional PTT methods. This approach offers a robust solution for continuous, calibration-resilient BP estimation.