Abstract
HIGHLIGHTS: What are the main findings? The privacy-preserving sensor array accurately classified the number and the timeframe of sitting, standing, and away periods in a desk-based environment. Proposed architecture differentiates between sitting, standing at a desk and physical absence while achieving 100% sensitivity for desk-based exercise repetition tracking. What are the implications of the main findings? A light-weight privacy-preserving sensor is capable of accurately detecting human behaviors and modifying movement prompt timing to reduce sedentary time and improve health. Real-time behavior recognition enables automated exercise logging, eliminating the human bias and burden inherent in self-reported compliance with exercise. The proposed sensor mechanism demonstrates the feasibility necessary to be integrated into a natural environment, as tested in an office. ABSTRACT: Occupational sedentary behavior presents a public health risk, yet current interventions often rely on subjective self-reports or context-blind prompts. This study validates a privacy-preserving, edge-computing time-of-flight (ToF) sensor that detects postural states and quantifies therapeutic exercise gestures in real time. The dual-sensor architecture distinguishes between sitting, standing, and absence, while capturing rapid sit-to-stand repetitions suitable for active-break interventions. In this paper, a laboratory study (N = 7) evaluated the system against ground truth comprising activPAL3 accelerometry and video analysis. Across 378 postural events, the sensor achieved high temporal fidelity (mean absolute error < 1.6 s) and 100% sensitivity in counting exercise repetitions. The system differentiated workstation occupancy from physical absence. These findings demonstrate that ToF sensing matches the accuracy of video analysis without privacy concerns while offering the contextual awareness required for just-in-time, adaptive workplace interventions.