ViFusionTST: Deep Fusion of Time-Series Image Representations from Load Signals for Early Bed-Exit Prediction

TL;DR

This paper introduces ViFusionTST, a deep learning model that fuses multiple image representations of load signals from bed sensors to accurately predict early bed-exit intent, enhancing fall prevention in healthcare settings.

Contribution

The paper presents a novel dual-stream Swin Transformer that fuses waveform and texture image representations of load signals for improved early bed-exit prediction.

Findings

Achieved 0.885 accuracy and 0.794 F1 score on real-world data

Outperformed recent 1D and 2D time-series baselines

Demonstrated effectiveness of image-based load signal fusion for fall prevention

Abstract

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.