Radar-Based Fall Detection for Assisted Living: A Digital-Twin Representation Case Study

TL;DR

This study investigates how different radar data representations affect fall detection accuracy using a digital twin simulation, highlighting the importance of representation choice in radar-based assisted living systems.

Contribution

It introduces a digital twin simulation to compare various radar data representations for fall detection, providing insights into their effectiveness and limitations.

Findings

Temporal spectrograms achieve 98-99% accuracy

Static RDMs reach 89.4% accuracy

Representation choice significantly impacts detection performance

Abstract

Obtaining data on high-impact falls from older adults is ethically difficult, yet these rare events cause many fall-related health problems. As a result, most radar-based fall detectors are trained on staged falls from young volunteers, and representation choices are rarely tested against the radar signals from dangerous falls. This paper uses a frequency-modulated continuous-wave (FMCW) radar digital twin as a single simulated room testbed to study how representation choice affects fall/non-fall discrimination. From the same simulated range-Doppler sequence, Doppler-time spectrograms, three-channel per-receiver spectrogram stacks, and time-pooled range-Doppler maps (RDMs) are derived and fed to an identical compact CNN under matched training on a balanced fall/non-fall dataset. In this twin, temporal spectrograms reach 98-99% test accuracy with similar precision and recall for both classes, while static RDMs reach 89.4% and show more variable training despite using the same backbone. A qualitative comparison between synthetic and measured fall spectrograms suggests that the twin captures gross Doppler-time structure, but amplitude histograms reveal differences in the distributions of amplitude values consistent with receiver processing not modeled in the twin. Because the twin omits noise and hardware impairments and is only qualitatively compared to a single measured example, these results provide representation-level guidance under controlled synthetic conditions rather than ready-to-use clinical performance in real settings.