Interferometric-Based Vital-Sign Signature Identification with ML Validation for Privacy-Preserving Human Detection

Human presence detection is critical when building smart cities with use cases in sectors like smart homes, emergency evacuation, health-care monitoring and others. Existing human detection systems predominantly rely on camera-based imaging, raising privacy concerns. Moreover, conventional FMCW radar approaches are primarily motion-based, thus often failing to detect the presence of unconscious individuals, as in the case of search and rescue (SAR) operations. Some radar approaches use Doppler or spectral peak analysis to estimate respiration but fail to exploit phase coherence to resolve sub-millimeter chest displacement and higher-order physiological harmonics. This paper presents an interferometric radar framework that models multi-feature vital-sign signatures for human detection under controlled clinical settings using respiratory harmonic relationships, inter-harmonic consistency, chest-displacement spectral characteristics, and radar-derived cardiac mechanical signatures. Physiological relationships are used to establish the expected structure of the extracted features, while subject-to-subject variability and measurement uncertainty are used to determine practical acceptance regions from the training cohort. Experimental data from 30 healthy subjects were analyzed using a single interferometric radar sensor under controlled clinical conditions. The resulting signatures were subsequently evaluated using a machine-learning validation pipeline. With 243 test cases, the proposed framework achieved 89.71% accuracy, 95.26% precision, 94.15% F1-score, and 93.06% sensitivity. The study demonstrates that interferometric chest-displacement sensing can provide a privacy-preserving physiological feature space for human presence detection, while also identifying the limitations associated with unresolved multi-person signal superposition and hardware-induced phase uncertainty. Moreover, interferometric sensing by principle will work better than conventional radar approaches for SAR operations. Although validated in a controlled clinical environment, the framework establishes a foundational pathway towards future research for eventual deployment in next-generation smart systems.