Multimodal Transformer for Nursing Activity Recognition

TL;DR

This paper introduces a multimodal transformer network that combines skeletal and acceleration data for nurse activity recognition, achieving state-of-the-art accuracy and outperforming existing methods.

Contribution

The paper proposes a novel multimodal transformer architecture that fuses skeletal and acceleration data for improved nurse activity recognition performance.

Findings

Achieved 81.8% accuracy on the NCRC dataset.

Outperformed state-of-the-art methods by 1.6%.

Demonstrated the effectiveness of multimodal fusion over single modalities.

Abstract

In an aging population, elderly patient safety is a primary concern at hospitals and nursing homes, which demands for increased nurse care. By performing nurse activity recognition, we can not only make sure that all patients get an equal desired care, but it can also free nurses from manual documentation of activities they perform, leading to a fair and safe place of care for the elderly. In this work, we present a multimodal transformer-based network, which extracts features from skeletal joints and acceleration data, and fuses them to perform nurse activity recognition. Our method achieves state-of-the-art performance of 81.8% accuracy on the benchmark dataset available for nurse activity recognition from the Nurse Care Activity Recognition Challenge. We perform ablation studies to show that our fusion model is better than single modality transformer variants (using only acceleration or skeleton joints data). Our solution also outperforms state-of-the-art ST-GCN, GRU and other classical hand-crafted-feature-based classifier solutions by a margin of 1.6%, on the NCRC dataset. Code is available at \url{https://github.com/Momilijaz96/MMT_for_NCRC}.