Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.22498 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908604023439360 |
|---|---|
| author | Liu, Hao Hu, Yu Rayhana, Rakiba Bai, Ling Liu, Zheng |
| author_facet | Liu, Hao Hu, Yu Rayhana, Rakiba Bai, Ling Liu, Zheng |
| contents | Bed-related falls remain a major source of injury in hospitals and long-term care facilities, yet many commercial alarms trigger only after a patient has already left the bed. We show that early bed-exit intent can be predicted using only one low-cost load cell mounted under a bed leg. The resulting load signals are first converted into a compact set of complementary images: an RGB line plot that preserves raw waveforms and three texture maps-recurrence plot, Markov transition field, and Gramian angular field-that expose higher-order dynamics. We introduce ViFusionTST, a dual-stream Swin Transformer that processes the line plot and texture maps in parallel and fuses them through cross-attention to learn data-driven modality weights. To provide a realistic benchmark, we collected six months of continuous data from 95 beds in a long-term-care facility. On this real-world dataset ViFusionTST reaches an accuracy of 0.885 and an F1 score of 0.794, surpassing recent 1D and 2D time-series baselines across F1, recall, accuracy, and AUPRC. The results demonstrate that image-based fusion of load-sensor signals for time series classification is a practical and effective solution for real-time, privacy-preserving fall prevention. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_22498 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ViFusionTST: Deep Fusion of Time-Series Image Representations from Load Signals for Early Bed-Exit Prediction Liu, Hao Hu, Yu Rayhana, Rakiba Bai, Ling Liu, Zheng Computer Vision and Pattern Recognition Artificial Intelligence Bed-related falls remain a major source of injury in hospitals and long-term care facilities, yet many commercial alarms trigger only after a patient has already left the bed. We show that early bed-exit intent can be predicted using only one low-cost load cell mounted under a bed leg. The resulting load signals are first converted into a compact set of complementary images: an RGB line plot that preserves raw waveforms and three texture maps-recurrence plot, Markov transition field, and Gramian angular field-that expose higher-order dynamics. We introduce ViFusionTST, a dual-stream Swin Transformer that processes the line plot and texture maps in parallel and fuses them through cross-attention to learn data-driven modality weights. To provide a realistic benchmark, we collected six months of continuous data from 95 beds in a long-term-care facility. On this real-world dataset ViFusionTST reaches an accuracy of 0.885 and an F1 score of 0.794, surpassing recent 1D and 2D time-series baselines across F1, recall, accuracy, and AUPRC. The results demonstrate that image-based fusion of load-sensor signals for time series classification is a practical and effective solution for real-time, privacy-preserving fall prevention. |
| title | ViFusionTST: Deep Fusion of Time-Series Image Representations from Load Signals for Early Bed-Exit Prediction |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2506.22498 |