CIVIC-PG Track B: Creating an AI-based Community-wide Efficient and Equitable Response System

CIVIC-PG Track B：创建基于人工智能的全社区高效、公平的响应系统

• 批准号: 2228607
• 负责人: Meiyi Ma
• 金额: $ 5万
• 依托单位: Vanderbilt University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-01 至 2023-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2228607&HistoricalAwards=false
• 关键词: CIVIC; PG; Track; Creating; AI

With a growing number of requests and national labor shortages in city governments and contracted services, the need for efficient, easily accessible, and equitable response systems is more urgent than ever. To address this need, this university-community collaboration aims to revolutionize the next generation of emergency services by applying state-of-the-art AI techniques to response systems that will reduce emergency response times while increasing their accessibility and equity. To do so, this project takes the following steps: 1) automate responses to non-emergency requests and thus ensuring 9-1-1 dispatchers are available to provide quick assistance to those who may be adversely affected by emergencies; 2) precisely ascertain emergency response times, which can maximize the efficiency of the placement of stations and response units and potentially result in an improved (insurance services) ISO rating and lower insurance rates for the citizens and businesses, 3) extract on-scene information to support first-responders operations to save lives and time during emergencies, and 4) create a community-centric approach to ensure equitable and trustworthy emergency and non-emergency response systems. This planning grant aims to identify sources of inefficiency, inequity, and inaccessibility present in existing emergency and non-emergency response systems and remedy them by developing novel AI-based interventions. In this planning effort, the project team consisting of university researchers, public safety professionals, and community partners is collaborating with members of underserved communities to identify crucial bottlenecks in the response system that reduce efficiency, equity, and accessibility of these systems. The vision is to develop prototypes of interventions to address these bottlenecks using principled techniques from AI and data-driven learning.This project is in response to the Civic Innovation Challenge program—Track B. Bridging the gap between essential resources and services & community needs—and is a collaboration between NSF, the Department of Homeland Security, and the Department of Energy.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.

随着城市政府和合同服务机构的请求数量不断增加以及全国劳动力短缺，对高效、易于访问和公平的响应系统的需求比以往任何时候都更加迫切。为了满足这一需求，这种大学与社区的合作旨在彻底改变下一个问题。通过将最先进的人工智能技术应用于响应系统来生成紧急服务，这将减少紧急响应时间，同时提高其可访问性和公平性为此，该项目采取以下步骤：1）自动响应非紧急情况。请求，从而确保 9-1-1调度员可以为可能受到紧急情况不利影响的人员提供快速援助；2) 准确确定紧急响应时间，这可以最大限度地提高站点和响应单位的部署效率，并有可能提高（保险服务）ISO 评级并降低公民和企业的保险费率，3）提取现场信息以支持急救人员的行动，以在紧急情况下挽救生命和时间，4）创建以社区为中心的方法，以确保公平且值得信赖的紧急和非紧急情况回复该规划拨款旨在找出现有紧急和非紧急响应系统中存在的低效率、不公平和不可访问性的根源，并通过开发基于人工智能的新型干预措施来解决这些问题。公共安全专业人员和社区合作伙伴正在与服务不足的社区成员合作，以确定响应系统中降低这些系统的效率、公平性和可访问性的关键瓶颈。我们的愿景是开发干预措施原型，以使用原则性技术来解决这些瓶颈。人工智能。该项目是为了响应公民创新挑战计划（Track B）。弥合基本资源和服务与社区需求之间的差距，是 NSF、国土安全部和国防部之间的合作项目能源。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。

项目成果

Guiding Federated Learning with Inferenced Formal Logic Properties

• DOI: 10.1145/3576841.3589633
• 发表时间: 2023-05
• 期刊: Proceedings of the ACM/IEEE 14th International Conference on Cyber-Physical Systems (with CPS-IoT Week 2023)
• 作者: Ziyan An;Meiyi Ma