SHB: Medium: Assistive Cloudlet-Based Mobile Computing for the Cognitively Impaired

该项目通过在三个主要分支学科的交叉点产生科学见解、算法、系统设计、实现技术和实验验证来推进计算机科学。这些分支学科是(1)计算机系统（包括移动计算、操作系统和无线网络），(2)视觉技术（包括计算机视觉和机器学习），以及(3)人机交互（包括活动推理、减少分心和上下文感知）。这些将被整合在一起，创造出认知辅助系统，可以在“野外”运行，具有足够的功能、性能和可用性，在任何时间和地点都有价值，为认知受损的人提供帮助。从社会的角度来看，这项研究有可能改善那些因自然衰老、疾病或创伤而认知能力下降的人的生活质量（估计有2000万美国人）。此外，认知支持可以确保安全使用并遵守康复和慢性疾病管理的指示。从教育的角度来看，这项研究提供了许多独特的机会来培养研究生和本科生如何从广泛的多学科视角来解决问题。通过与工业界的密切合作，这项研究有可能影响移动计算，使资源贫乏的移动设备能够在任何时间和地点运行交互式的、计算密集型的应用程序。虽然这一建议侧重于将这种新能力应用于认知辅助问题，但它也可以解决一般人群的重要需求。此外，由此产生的云架构具有改变商业、工程、医疗保健和国防等多种领域的潜力。

This project advances computer science by producing scientific insights, algorithms, system designs, implementation techniques, and experimental validations at the intersection of three major subdisciplines. These subdisciplines are (1) computer systems (including mobile computing, operating systems, and wireless networking), (2) vision technologies (including computer vision and machine learning), and (3) human-computer interaction (including activity inferencing, distraction reduction, and context awareness). These will be integrated to create cognitive assistive systems that can function "in the wild" with sufficient functionality, performance and usability to be valuable at any time and place to provide help for the cognitively impaired.From a societal perspective, this research has the potential to improve the quality of lives of individuals whose cognitive capabilities have declined due to natural aging, illness or traumatic injuries (estimated at 20 million Americans). In addition, cognitive support can assure safe use and compliance with instructions in rehabilitation and management of chronic illness. From an educational viewpoint, this research offers many unique opportunities to train graduate and undergraduate students on how to approach problems from a broad multi-interdisciplinary perspective. In close partnership with industry, this research has the potential to impact mobile computing by empowering resource-poor mobile devices to run interactive, compute-intensive applications at any time and place. While this proposal focuses on applying this new capability to the problem of cognitive assistance, it can also address important needs of the general population. Further, the resulting cloudlet architecture has the potential to transform arenas as diverse as business, engineering, health care, and defense.