# Edge-Efficient Two-Stream Multimodal Architecture for Non-Intrusive Bathroom Fall Detection

arXiv: https://arxiv.org/abs/2603.17069 · HTML: https://mlsanity.com/paper/2603.17069/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Vision and Inertial Sensing Fusion for Human Action Recognition : A Review](https://mlsanity.com/paper/2008.00380/) (2020)
- [A Survey on Radar-Based Fall Detection](https://mlsanity.com/paper/2312.04037/) (2023)
- [EGOFALLS: A visual-audio dataset and benchmark for fall detection using egocentric cameras](https://mlsanity.com/paper/2309.04579/) (2023)
- [Multispectral Remote Sensing for Weed Detection in West Australian Agricultural Lands](https://mlsanity.com/paper/2502.08678/) (2025)
- [P2MFDS: A Privacy-Preserving Multimodal Fall Detection System for Elderly People in Bathroom Environments](https://mlsanity.com/paper/2506.17332/) (2025)
- [Better than Counting Seconds: Identifying Fallers among Healthy Elderly using Fusion of Accelerometer Features and Dual-Task Timed Up and Go](https://mlsanity.com/paper/1609.05339/) (2016)
- [BAWSeg: A UAV Multispectral Benchmark for Barley Weed Segmentation](https://mlsanity.com/paper/2603.01932/) (2026)

## Abstract (arXiv)

Falls in wet bathroom environments are a major safety risk for seniors living alone. Recent work has shown that mmWave-only, vibration-only, and existing multimodal schemes, such as vibration-triggered radar activation, early feature concatenation, and decision-level score fusion, can support privacy-preserving, non-intrusive fall detection. However, these designs still treat motion and impact as loosely coupled streams, depending on coarse temporal alignment and amplitude thresholds, and do not explicitly encode the causal link between radar-observed collapse and floor impact or address timing drift, object drop confounders, and latency and energy constraints on low-power edge devices. To this end, we propose a two-stream architecture that encodes radar signals with a Motion--Mamba branch for long-range motion patterns and processes floor vibration with an Impact--Griffin branch that emphasizes impact transients and cross-axis coupling. Cross-conditioned fusion uses low-rank bilinear interaction and a Switch--MoE head to align motion and impact tokens and suppress object-drop confounders. The model keeps inference cost suitable for real-time execution on a Raspberry Pi 4B gateway. We construct a bathroom fall detection benchmark dataset with frame-level annotations, comprising more than 3~h of synchronized mmWave radar and triaxial vibration recordings across eight scenarios under running water, together with subject-independent training, validation, and test splits. On the test split, our model attains 96.1% accuracy, 94.8% precision, 88.0% recall, a 91.1% macro F1 score, and an AUC of 0.968. Compared with the strongest baseline, it improves accuracy by 2.0 percentage points and fall recall by 1.3 percentage points, while reducing latency from 35.9 ms to 15.8 ms and lowering energy per 2.56 s window from 14200 mJ to 10750 mJ on the Raspberry Pi 4B gateway.