SBIR Phase I: Developing the internet of livable spaces for older adults

小型企业创新研究(SBIR)第一阶段项目的更广泛影响/商业潜力是改善目前受跌倒影响的老年人的生活质量。在美国，每年有超过70万老年人因跌倒相关的伤害而住院，这导致了340亿美元的直接医疗费用。拟议的技术将通过提供老年人的医疗团队(例如，医生、物理治疗师等)来减少首次和未来的跌倒。有跌倒病史和动态信息。坠落的历史很难获得，也不可靠(因为许多事件都不是自己报告的)。底层的技术开发可以进一步扩大，使智能建筑能够充当“第一响应者”的角色，在人为和自然灾害期间帮助居住者。这项技术的扩展在许多领域都有潜力，包括高效的能源管理系统、安全和威胁检测、应急响应和疏散以及结构健康监测。拟议的技术尊重隐私，同时使基础设施智能得到显著改善。这个小企业创新研究(SBIR)第一阶段项目将为受助家庭中的老年人开发一种最先进的生活方式监测系统，该系统具有预防和检测跌倒的全面方法。医疗保健行业投入了大量资源，根据以前的跌倒次数来预测跌倒，但由于不可靠的自我报告，目前的医疗保健专业人员获取单个患者跌倒历史的机会有限。此外，研究表明，通过及时的预防性治疗，未来跌倒的风险可以大大降低。这种预防是通过安装在地板上的加速计和数据分析处理来间接监测老年人的身体活动和跌倒来实现的。这一分析研究了跌倒、行走、摔门等事件记录数据中的固有模式。通过记录未报告的跌倒和健康史，可以进行预测。该系统的预期输出是一种检测、定位跌倒的手段，以及有效的历史数据存储，这将导致对老年人未来的风险评估更加准确。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is the improvement in the quality of life for older adults currently affected by falls. Every year over 700,000 older adults are hospitalized in the United States due to fall-related injuries, which result in $34B in direct medical costs. The proposed technology will reduce first and future falls by providing an older adult's medical treatment team (e.g., physician, physical therapist, etc.) with fall history and ambulatory information. Fall histories are difficult to obtain and unreliable (as many occurrences are not self-reported). The underlying technological development can be further expanded to allow smart buildings to behave as "first responders" and aid their occupants during man-made and natural disasters. Extensions of this technology have potential in many fields, including efficient energy management systems, security and threat detection, emergency response and evacuation, and structural health monitoring. The proposed technology respects privacy while enabling significant improvement in infrastructure intelligence.This Small Business Innovation Research (SBIR) Phase I project will develop a state-of-the-art lifestyle-monitoring system for older adults in assisted homes that has a comprehensive approach towards fall prevention and detection. The healthcare industry has invested significant resources in predicting falls based on the number of previous falls, but current healthcare professional's access to individual patient fall history is limited due to unreliable self-reporting. Additionally, research has shown that the risk of future falls can be greatly reduced through timely preventative treatments. This prevention is achieved by indirectly monitoring the physical activity and falls of older adults through floor-mounted accelerometers coupled with data analytics processing. This analysis studies inherent patterns in recorded data of events such as falls, walking, door slams, etc. Prediction is made possible through the recording of the unreported falls and health history. The anticipated output of this system is a means of detecting falls, locating them, and effective historical data storage, which will result in a more accurate future risk evaluation of the older adult.