针对浴室跌倒检测，提出高效双流模型，兼顾精度与边缘设备实时性。
Edge-Efficient Two-Stream Multimodal Architecture for Non-Intrusive Bathroom Fall Detection
- 用Mamba和Griffin分支分别捕捉长期运动与冲击瞬态特征
- 在测试集上达96.1%准确率，比最强基线高2.0个百分点
- 适合部署在树莓派等低功耗边缘设备，适合居家老人安全监测
老年人独居时浴室跌倒存在重大安全风险。现有毫米波雷达、振动传感及多模态方案虽能实现隐私保护的非侵入式检测，但仍将运动与冲击视为松散关联的流，依赖粗略时间对齐与幅度阈值，未能显式建模雷达观测到的坍塌与地面冲击间的因果关系，也未解决时序漂移、物品掉落干扰以及低功耗边缘设备的延迟与能耗问题。为此，我们提出一种双流架构：用Motion--Mamba分支提取长程运动模式，用Impact--Griffin分支突出冲击瞬态与跨轴耦合。通过低秩双线性交互与Switch--MoE头进行跨条件融合，对齐运动与冲击特征并抑制物品掉落干扰。模型推理成本适配树莓派4B网关实现实时运行。构建了含3小时以上同步毫米波雷达与三轴振动数据的浴室跌倒基准数据集，涵盖八种场景且有运行水流条件，提供独立于受试者的训练/验证/测试划分。在测试集上，模型达到96.1%准确率、94.8%精确率、88.0%召回率、91.1%宏平均F1和0.968的AUC。相比最强基线，准确率提升2.0个百分点，跌倒召回率提升1.3个百分点，同时将延迟从35.9毫秒降至15.8毫秒，每2.56秒窗口能耗由14200毫焦降至10750毫焦。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。