Developing a passive, non-worn, system to detect falls at home among the elderly.

开发一种被动、非磨损系统来检测家里老年人的跌倒情况。

基本信息

  • 批准号:
    8250524
  • 负责人:
  • 金额:
    $ 16.46万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
  • 财政年份:
    2012
  • 资助国家:
    美国
  • 起止时间:
    2012-05-15 至 2013-06-30
  • 项目状态:
    已结题

项目摘要

DESCRIPTION (provided by applicant): Falls are the leading cause of injury death among elders in the United States and will cost the country $43B annually in 2020. Of particular concern is what is called the "long lie." Over one half of elders who fall are unable to get up without assistance and they are more likely to suffer additional complications and poorer prognoses. The investigators have previously developed a passive fall and activity detection system (PFADS) for use in skilled nursing facilities and other institutions. This project proposes to gather preliminary data to determine if a similar device can be designed to work in homes, thus allowing elders to live independently more safely and their caregivers to be reassured that if a fall occur help will immediately be summoned. The vision is to create a system that is as trustworthy and ubiquitous as a smoke detector - a system that is clearly so valuable that no person would ever consider being without one. Thus, like a smoke detector, the system must be simple enough to be installed and used by the elder or their caregiver; not require complex special equipment or technical skill (such as using an internet connection), and not require the elder to wear anything special, push any buttons or change their lifestyle in any way. The system will be highly immune to false alarms caused by pets, crawling grandchildren, laying down in bed, etc. It will not alarm even if the elder purposely gets down on the floor to search fo a dropped item. Finally, the system absolutely must be inexpensive enough to be broadly available. The basic principle of operation of the PFADS is to detect body heat in various horizontal "slices" of the room, then analyze this data in real-time to identify specific "fall signatures". Essentially the idea is to look for human- size emitters of infrared energy that rapidly accelerate toward the floor. This basic concept has been tested and shown to be effective in skilled nursing faculties; however, the institutional version is installed by professionals, has a central station monitoring it and is deployed in rooms with nearly identical physical layouts. The team will work with Dr. Katherine Hesse, an accomplished Gerontologist from Massachusetts General Hospital, to define the requirements for residential settings and then gather preliminary data to determine if a redesigned PFADS can meet the requirements of a residential application. Specifically, Aim 1 is to add a meshing radio and data logging capability to the current institution version of the PFADS to allow experimental data to be gathered in a laboratory/residential setting. Aim 2 is to gather this data in order to support Aim , which is to refine the fall detection algorithm to maximize it sensitivity and specificity in the residential setting and determine if it meets the requirements defined in Aim 1. PUBLIC HEALTH RELEVANCE: Approximately 1.8 million senior citizens need to visit the emergency department in the US each year due to falls; 15,000 of these people will die. The longer the elder has to wait to receive aid, the greater the chance of their death - 67% die if the don't receive help within 72 hours, but only 12% die if they get help within an hour. This objective of this research is to create a reliable, inexpensive, easy-to-use passive fall detection system for use in homes; the system will not require the elder to wear anything, push any buttons or change their life style in any way, yet it will immediately call for help if the elder flls down.
描述(由申请人提供):福尔斯是美国老年人受伤死亡的主要原因,到2020年,美国每年将花费430亿美元。尤其值得关注的是所谓的“长期谎言。“超过一半跌倒的长者在没有协助的情况下无法站起来,他们更有可能患上额外的并发症和更差的健康状况。研究人员以前开发了一种被动跌倒和活动检测系统(PFADS),用于专业护理机构和其他机构。该项目建议收集初步数据,以确定是否可以设计类似的设备在家中工作,从而使老年人能够更安全地独立生活,并使他们的照顾者放心,如果发生跌倒,将立即寻求帮助。我们的愿景是创建一个像烟雾探测器一样值得信赖和无处不在的系统-一个非常有价值的系统,没有人会考虑没有它。因此,就像烟雾探测器一样,该系统必须足够简单,以便老年人或其护理人员安装和使用;不需要复杂的特殊设备或技术技能(例如使用互联网连接),并且不需要老年人穿任何特殊的东西,按任何按钮或以任何方式改变他们的生活方式。该系统将高度免疫由宠物,爬行的孙子,躺在床上等引起的误报,即使老人故意趴在地板上寻找掉落的物品,它也不会报警。最后,该系统绝对必须足够便宜,以便广泛使用。PFADS的基本工作原理是检测房间各个水平“切片”中的体温,然后实时分析这些数据以识别特定的“跌倒特征”。从本质上讲,这个想法是寻找人体大小的红外能量发射器,快速加速向地板。这一基本概念已经过测试,并在熟练的护理学院中显示出有效性;然而,机构版本由专业人员安装,有一个中心站监控它,并部署在物理布局几乎相同的房间中。该团队将与马萨诸塞州总医院的资深老年病学家凯瑟琳黑森博士合作,确定住宅环境的要求,然后收集初步数据,以确定重新设计的PFADS是否能满足住宅应用的要求。具体而言,目标1是为PFADS的当前机构版本添加网格无线电和数据记录功能,以允许在实验室/住宅环境中收集实验数据。目标2是收集这些数据以支持目标,目标2是改进跌倒检测算法,以最大化其在住宅环境中的灵敏度和特异性,并确定其是否满足目标1中定义的要求。 公共卫生关系:在美国,每年大约有180万老年人因福尔斯摔倒而需要去急诊室就诊;其中15,000人将死亡。老人等待接受救助的时间越长,死亡的可能性就越大--如果72小时内没有得到救助,67%的人会死亡,但如果在一小时内得到救助,只有12%的人会死亡。本研究的目的是建立一个可靠的,廉价的,易于使用的被动跌倒检测 用于家庭的系统;该系统不要求老人穿任何衣服,按任何按钮或以任何方式改变他们的生活方式,但如果老人摔倒,它会立即呼救。

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Michael H Wollowitz其他文献

Michael H Wollowitz的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

相似海外基金

DMS-EPSRC: Asymptotic Analysis of Online Training Algorithms in Machine Learning: Recurrent, Graphical, and Deep Neural Networks
DMS-EPSRC:机器学习中在线训练算法的渐近分析:循环、图形和深度神经网络
  • 批准号:
    EP/Y029089/1
  • 财政年份:
    2024
  • 资助金额:
    $ 16.46万
  • 项目类别:
    Research Grant
CAREER: Blessing of Nonconvexity in Machine Learning - Landscape Analysis and Efficient Algorithms
职业:机器学习中非凸性的祝福 - 景观分析和高效算法
  • 批准号:
    2337776
  • 财政年份:
    2024
  • 资助金额:
    $ 16.46万
  • 项目类别:
    Continuing Grant
CAREER: From Dynamic Algorithms to Fast Optimization and Back
职业:从动态算法到快速优化并返回
  • 批准号:
    2338816
  • 财政年份:
    2024
  • 资助金额:
    $ 16.46万
  • 项目类别:
    Continuing Grant
CAREER: Structured Minimax Optimization: Theory, Algorithms, and Applications in Robust Learning
职业:结构化极小极大优化:稳健学习中的理论、算法和应用
  • 批准号:
    2338846
  • 财政年份:
    2024
  • 资助金额:
    $ 16.46万
  • 项目类别:
    Continuing Grant
CRII: SaTC: Reliable Hardware Architectures Against Side-Channel Attacks for Post-Quantum Cryptographic Algorithms
CRII:SaTC:针对后量子密码算法的侧通道攻击的可靠硬件架构
  • 批准号:
    2348261
  • 财政年份:
    2024
  • 资助金额:
    $ 16.46万
  • 项目类别:
    Standard Grant
CRII: AF: The Impact of Knowledge on the Performance of Distributed Algorithms
CRII:AF:知识对分布式算法性能的影响
  • 批准号:
    2348346
  • 财政年份:
    2024
  • 资助金额:
    $ 16.46万
  • 项目类别:
    Standard Grant
CRII: CSR: From Bloom Filters to Noise Reduction Streaming Algorithms
CRII:CSR:从布隆过滤器到降噪流算法
  • 批准号:
    2348457
  • 财政年份:
    2024
  • 资助金额:
    $ 16.46万
  • 项目类别:
    Standard Grant
EAGER: Search-Accelerated Markov Chain Monte Carlo Algorithms for Bayesian Neural Networks and Trillion-Dimensional Problems
EAGER:贝叶斯神经网络和万亿维问题的搜索加速马尔可夫链蒙特卡罗算法
  • 批准号:
    2404989
  • 财政年份:
    2024
  • 资助金额:
    $ 16.46万
  • 项目类别:
    Standard Grant
CAREER: Efficient Algorithms for Modern Computer Architecture
职业:现代计算机架构的高效算法
  • 批准号:
    2339310
  • 财政年份:
    2024
  • 资助金额:
    $ 16.46万
  • 项目类别:
    Continuing Grant
CAREER: Improving Real-world Performance of AI Biosignal Algorithms
职业:提高人工智能生物信号算法的实际性能
  • 批准号:
    2339669
  • 财政年份:
    2024
  • 资助金额:
    $ 16.46万
  • 项目类别:
    Continuing Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了