Collaborative Research: CCSS: When RFID Meets AI for Occluded Body Skeletal Posture Capture in Smart Healthcare

合作研究：CCSS：当 RFID 与人工智能相遇，用于智能医疗保健中闭塞的身体骨骼姿势捕获

• 批准号: 2245607
• 负责人: Jian Zhang
• 金额: $ 18万
• 依托单位: Kennesaw State University Research and Service Foundation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-08-01 至 2026-07-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2245607&HistoricalAwards=false
• 关键词: Collaborative; Research; CCSS; When; RFID

The human body motion or posture capture plays a critical role in the early detection of risk and treating, monitoring, and diagnosing certain health conditions. This project aims to create and evaluate a low-cost, unobtrusive, and robust posture capture system for healthcare and home environments, especially for non-visible scenarios. With passive Radio-Frequency Identification (RFID) tags attached or fabricated into fitness clothing, wireless signals of RFID can be captured and analyzed to detect body motions. The posture capture system can be used in a healthcare facility or home environment for monitoring persons in need of preventative care, such as elders at high risk of falling, detecting abnormal body movements, and enhancing training and evaluation processes in rehabilitation settings. Successful completion of this project will significantly improve the state-of-the-art of wearable sensor networks and IoT systems. The project's education plan includes curriculum development and enhancement, engaging students with hands-on projects, and promoting participation of under-represented groups in research. This project aims to develop RFID localization methods to obtain precise positions of attached RFID tags. The posture and motion of the body can be reconstructed by registering tags to a skeletal model. With the captured posture and motion of the body, an AI-based method shall be proposed to provide diagnostic information. The research agenda includes: (i) Create a prototype for the RFID posture scanner (RFPS); (ii) Enabling RFPS for a complex and large-scale environment; (iii) Developing an intelligent tool for extracting healthcare data. This project also includes a thorough integration and assessment plan to test how the proposed system can be used in a healthcare facility or home environment to monitor persons in need of preventative care.This project is jointly funded by the CCSS program in the ECCS division of the Engineering Directorate, and the Established Program to Stimulate Competitive Research (EPSCoR).This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人体运动或姿势捕捉在早期发现风险以及治疗、监测和诊断某些健康状况方面发挥着至关重要的作用。该项目旨在为医疗保健和家庭环境（尤其是不可见场景）创建和评估低成本、不显眼且强大的姿势捕获系统。通过将无源射频识别 (RFID) 标签附加或制作到健身服装中，可以捕获并分析 RFID 的无线信号以检测身体运动。姿势捕捉系统可用于医疗机构或家庭环境中，用于监测需要预防性护理的人员，例如跌倒风险较高的老年人，检测异常的身体运动，并加强康复环境中的培训和评估过程。该项目的成功完成将显着提高可穿戴传感器网络和物联网系统的最先进水平。该项目的教育计划包括课程开发和强化、让学生参与实践项目以及促进代表性不足的群体参与研究。该项目旨在开发 RFID 定位方法，以获得所附 RFID 标签的精确位置。可以通过将标签注册到骨骼模型来重建身体的姿势和运动。通过捕获身体的姿势和运动，应提出基于人工智能的方法来提供诊断信息。研究议程包括： (i) 创建 RFID 姿势扫描仪 (RFPS) 原型； (ii) 为复杂和大规模的环境启用 RFPS； (iii) 开发提取医疗数据的智能工具。该项目还包括一个全面的集成和评估计划，以测试如何在医疗机构或家庭环境中使用拟议的系统来监测需要预防性护理的人员。该项目由 ECCS 部门的 CCSS 项目共同资助。工程理事会和刺激竞争研究既定计划 (EPSCoR)。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。