Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.13078 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915622332399616 |
|---|---|
| author | Jin, Liuyi Gunawardena, Pasan Haroon, Amran Wang, Runzhi Lee, Sangwoo Stoleru, Radu Middleton, Michael Huo, Zepeng Kim, Jeeeun Moats, Jason |
| author_facet | Jin, Liuyi Gunawardena, Pasan Haroon, Amran Wang, Runzhi Lee, Sangwoo Stoleru, Radu Middleton, Michael Huo, Zepeng Kim, Jeeeun Moats, Jason |
| contents | Emergency Medical Technicians (EMTs) operate in high-pressure environments, making rapid, life-critical decisions under heavy cognitive and operational loads. We present EMSGlass, a smart-glasses system powered by EMSNet, the first multimodal multitask model for Emergency Medical Services (EMS), and EMSServe, a low-latency multimodal serving framework tailored to EMS scenarios. EMSNet integrates text, vital signs, and scene images to construct a unified real-time understanding of EMS incidents. Trained on real-world multimodal EMS datasets, EMSNet simultaneously supports up to five critical EMS tasks with superior accuracy compared to state-of-the-art unimodal baselines. Built on top of PyTorch, EMSServe introduces a modality-aware model splitter and a feature caching mechanism, achieving adaptive and efficient inference across heterogeneous hardware while addressing the challenge of asynchronous modality arrival in the field. By optimizing multimodal inference execution in EMS scenarios, EMSServe achieves 1.9x -- 11.7x speedup over direct PyTorch multimodal inference. A user study evaluation with six professional EMTs demonstrates that EMSGlass enhances real-time situational awareness, decision-making speed, and operational efficiency through intuitive on-glass interaction. In addition, qualitative insights from the user study provide actionable directions for extending EMSGlass toward next-generation AI-enabled EMS systems, bridging multimodal intelligence with real-world emergency response workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_13078 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Smart-Glasses for Emergency Medical Services via Multimodal Multitask Learning Jin, Liuyi Gunawardena, Pasan Haroon, Amran Wang, Runzhi Lee, Sangwoo Stoleru, Radu Middleton, Michael Huo, Zepeng Kim, Jeeeun Moats, Jason Machine Learning Audio and Speech Processing Image and Video Processing Emergency Medical Technicians (EMTs) operate in high-pressure environments, making rapid, life-critical decisions under heavy cognitive and operational loads. We present EMSGlass, a smart-glasses system powered by EMSNet, the first multimodal multitask model for Emergency Medical Services (EMS), and EMSServe, a low-latency multimodal serving framework tailored to EMS scenarios. EMSNet integrates text, vital signs, and scene images to construct a unified real-time understanding of EMS incidents. Trained on real-world multimodal EMS datasets, EMSNet simultaneously supports up to five critical EMS tasks with superior accuracy compared to state-of-the-art unimodal baselines. Built on top of PyTorch, EMSServe introduces a modality-aware model splitter and a feature caching mechanism, achieving adaptive and efficient inference across heterogeneous hardware while addressing the challenge of asynchronous modality arrival in the field. By optimizing multimodal inference execution in EMS scenarios, EMSServe achieves 1.9x -- 11.7x speedup over direct PyTorch multimodal inference. A user study evaluation with six professional EMTs demonstrates that EMSGlass enhances real-time situational awareness, decision-making speed, and operational efficiency through intuitive on-glass interaction. In addition, qualitative insights from the user study provide actionable directions for extending EMSGlass toward next-generation AI-enabled EMS systems, bridging multimodal intelligence with real-world emergency response workflows. |
| title | A Smart-Glasses for Emergency Medical Services via Multimodal Multitask Learning |
| topic | Machine Learning Audio and Speech Processing Image and Video Processing |
| url | https://arxiv.org/abs/2511.13078 |