Collaborative Research: CISE-MSI: DP: CNS: Efficient Data Communication and Processing for Intelligent Medical Systems with Edge-Cloud Interplay

该奖项的全部或部分资金来自2021年美国救援计划法案(公法117-2)。医疗行业的数字化转型倡议是由对虚拟访问、远程患者监控和消费者可穿戴设备的需求推动的。这一计划的执行将产生大量和多样化的数据构件，需要对这些构件进行分析，以便随时随地为患者提供护理。对新冠肺炎的回应也有助于发展全方位和智能化的医疗能力。传统上，云计算技术一直被医疗保健提供商用于分析海量的健康数据。然而，该技术存在对中央仲裁器的依赖、网络延迟增加和高吞吐量等缺点。此外，缺乏可信的人工智能/机器学习(AI/ML)算法，这可能会导致错误的结果，在医疗保健领域造成灾难性影响，并增加对云基础设施的安全攻击频率。本项目旨在开发一个边缘-云交互平台，以实现智能医疗系统的高效数据通信和处理。该平台利用软件定义的5G和支持AI的分布式边缘云技术，确保安全管理关键健康数据并以响应方式提供。第一步是开发SDN驱动的架构，以便在边缘设备对医疗数据进行分类，以实现实时服务交付。接下来，该项目打算开发基于AI/ML算法的模型，以识别患者的潜在医疗状况。这些模型将通过计算从中央服务器到任何医疗单位的本地数据库的本地数据的访问时间并执行比较时间分析来验证。此外，还将研究边缘和云之间的相互作用，以支持医疗保健系统的实时应用需求。该项目将为来自人工智能、SDN、云和边缘技术交叉领域的未被充分代表的社区的学生提供研究经验，并支持Meharry医学院课程的现代化。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).The healthcare industry’s digital transformation initiative is driven by the need for virtual visits, remote patient monitoring, and consumer wearables. The execution of this initiative will generate vast and diverse data artifacts that need to be analyzed to deliver care to patients anywhere and anytime. The response to COVID-19 has also contributed to developing a holistic and intelligent healthcare capability. Traditionally, cloud computing technology has been employed by healthcare providers for analyzing vast health data. However, the technology suffers from drawbacks such as dependency on a central arbitrator, increase in network latency, and high throughput. In addition, there is a lack of trusted Artificial Intelligent/ Machine Learning (AI/ML) algorithms which can lead to erroneous results causing catastrophic impacts in the healthcare domain and increasing the frequency of security attacks on the cloud infrastructure. This project aims to develop an edge-cloud interplay platform to realize efficient data communication and processing for Intelligent Medical Systems. The platform leverages software-defined 5G and AI-enabled distributed edge-cloud technologies to ensure critical health data is managed securely and made available in a responsive manner. The first step is to develop an SDN-driven architecture to classify healthcare data at the edge devices for real-time service delivery. Next, the project intends to develop models based on AI/ML algorithms to identify patients’ potential medical conditions. The models are to be validated by calculating the access time of the local data from the central server to the local database in any healthcare unit and performing a comparative time analysis. Besides, the interplay between the edge and cloud will be investigated to support the demand for real-time applications for healthcare systems. The project will provide research experiences to students from underrepresented communities in areas at the intersection of AI, SDN, cloud, and edge technologies and also support the modernization of the curriculum at Meharry Medical College.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.