SCC-PG: JST: Privacy-enhanced data-driven health monitoring for smart and connected senior communities

SCC-PG：JST：针对智能互联老年社区的隐私增强型数据驱动健康监测

• 批准号: 1952192
• 负责人: Li Xiong
• 金额: $ 7.5万
• 依托单位: Emory University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1952192&HistoricalAwards=false
• 关键词: SCC; PG; JST; Privacy; enhanced

Many countries, including the United States and Japan, are facing a rapidly aging population. Improving the quality of healthcare and quality of life for senior citizens while managing and even reducing the health and social care costs is a critical challenge. The growth and accessibility of wearable devices enable continuous monitoring of a person’s vital signs and other health indicators. These wearable data, combined with medical records and other community and environment data, are particularly valuable for senior communities in order to identify new conditions or relapses for early intervention. Collectively, such data from different individuals, communities, and countries, can be used to learn better predictive models and improve population health at large. This project aims to build a multidisciplinary team including academic researchers with complementary expertise (big data, privacy and security, machine learning, human-computer interaction, sociology, and mobile health) and community stakeholders (seniors, community service providers, healthcare providers, and government agencies), to understand the unique challenges and form a research agenda for developing and deploying a health monitoring system for senior communities. The project will study: 1) data integration and machine learning techniques to integrate data from multiple sources in real time for monitoring and intervention; and to leverage the data from different communities to improve healthcare outcome and medical research; 2) privacy-enhancing techniques including differential privacy and federated learning to ensure the system is compliant with regulations, while balancing the privacy protection and utility of the system; and 3) social implications and cultural differences of the technology in the two countries via online surveys and qualitative studies to identify challenges and barriers in health monitoring for senior communities, and their impact on the design and adoption of the proposed technology. The project includes a set of community engagement activities in order to develop a research agenda that can not only empower the senior communities and improve their health and well-being, but also enable data-driven medical research that improves population health at large.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.

包括美国和日本在内的许多国家都面临着人口迅速老龄化的问题。改善老年人的医疗保健质量和生活质量，同时管理甚至降低医疗和社会护理成本是一项重大挑战。可穿戴设备的发展和普及使人们能够持续监测一个人的生命体征和其他健康指标。这些可穿戴数据与医疗记录和其他社区和环境数据相结合，对于老年社区来说特别有价值，可以确定新的情况或复发，以便进行早期干预。总的来说，来自不同个人、社区和国家的这些数据可用于学习更好的预测模型，并在很大程度上改善人口健康。该项目旨在建立一个多学科团队，包括具有互补专业知识（大数据、隐私和安全、机器学习、人机交互、社会学和移动医疗）的学术研究人员和社区利益相关者（老年人、社区服务提供者、医疗保健提供者和政府机构），以了解独特的挑战，并形成研究议程，为老年人社区开发和部署健康监测系统。该项目将研究：1)数据集成和机器学习技术，实时整合多源数据进行监测和干预；并利用来自不同社区的数据来改善医疗保健结果和医学研究；2)隐私增强技术，包括差分隐私和联邦学习，以确保系统符合法规，同时平衡隐私保护和系统的实用性；3)通过在线调查和定性研究，了解两国老年人健康监测技术的社会影响和文化差异，确定老年人健康监测面临的挑战和障碍，以及它们对拟议技术的设计和采用的影响。该项目包括一系列社区参与活动，以便制定一项研究议程，不仅能够增强老年人社区的权能，改善他们的健康和福祉，而且还能够开展数据驱动的医学研究，从而改善整个人口的健康。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

RobustFed: A Truth Inference Approach for Robust Federated Learning

• DOI: 10.1145/3511808.3557439
• 发表时间: 2021-07
• 期刊: Proceedings of the 31st ACM International Conference on Information & Knowledge Management
• 作者: Farnaz Tahmasebian;Jian Lou;Li Xiong

REACT: Real-Time Contact Tracing and Risk Monitoring via Privacy-Enhanced Mobile Tracking

REACT：通过隐私增强型移动跟踪进行实时接触者追踪和风险监控

• 发表时间: 2021
• 期刊: IEEE International Conference on Data Engineering
• 作者: Ahuja, R;Xiong, L;Shahabi, C
• 通讯作者: Shahabi, C

Private Stochastic Non-convex Optimization with Improved Utility Rates

• DOI: 10.24963/ijcai.2021/464
• 发表时间: 2021-08
• 作者: Qiuchen Zhang;Jing Ma;Jian Lou;Li Xiong

Projected Federated Averaging with Heterogeneous Differential Privacy

• DOI: 10.14778/3503585.3503592
• 发表时间: 2021-12
• 期刊: Proc. VLDB Endow.
• 作者: Junxu Liu;Jian Lou;Li Xiong;Jinfei Liu;Xiaofeng Meng

PrivLBS : Local Differential Privacy for Location-Based Services with Staircase Randomized Response

• 发表时间: 2022