CPS: Medium: Active Heterogeneous Sensing for Fall Detection and Fall Risk Assessment

该奖项是根据2009年美国复苏和再投资法案（公法111-5）资助的。本研究的目的是研究动态和非结构化家庭环境中使用视觉和声学传感器进行连续、可靠的跌倒检测和跌倒风险评估的主动传感和自适应融合。该方法将主动视觉与红外光源和摄像头控制、识别声音特征和位置的声学阵列以及基于Choquet积分和分层模糊逻辑系统的传感器融合结合起来，该系统支持在不同时间尺度、定性数据和风险因素下的不确定异构传感器数据。该项目将推进以下方面的技术进步：(1)动态和不可预测环境中用于人类活动识别的主动视觉传感，(2)非结构化环境中的声学传感，(3)动态和不可预测环境中使用异构传感器数据的自适应传感器融合和决策，(4)使用非可穿戴传感器的自动跌倒检测和跌倒风险评估，(5)用于网络物理系统的算法，用于解决异常检测（跌倒）和影响异常事件可能性的风险因素之间的相互作用。该项目将对老年人的保健和生活质量产生影响。新的方法将帮助医疗保健提供者尽早发现潜在的健康问题，为老年人护理技术提供一个模型，使老年人保持独立，同时降低医疗保健成本。该项目将训练下一代研究人员处理真实的网络物理系统。学生将得到指导，研究成果将融入课堂。计划举办新的外展活动，以接触长者社区和一般市民

This award is funded under the American Recovery and Reinvestment Act of 2009 (Public Law 111-5).The objective of this research is to study active sensing and adaptive fusion using vision and acoustic sensors for continuous, reliable fall detection and assessment of fall risk in dynamic and unstructured home environments. The approach is to incorporate active vision with infrared light sources and camera controls, an acoustic array that identifies the sound characteristics and location, and sensor fusion based on the Choquet integral and hierarchical fuzzy logic systems that supports uncertain heterogeneous sensor data at varying time scales, qualitative data, and risk factors. The project will advance the state of the art in (1) active vision sensing for human activity recognition in dynamic and unpredictable environments, (2) acoustic sensing in unstructured environments, (3) adaptive sensor fusion and decision making using heterogeneous sensor data in dynamic and unpredictable environments, (4) automatic fall detection and fall risk assessment using non-wearable sensors, and (5) algorithms for cyber physical systems that address the interplay of anomaly detection (falls) and risk factors affecting the likelihood of an anomaly event. The project will impact the health care and quality of life for older adults. New approaches will assist health care providers to identify potential health problems early, offering a model for eldercare technology that keeps seniors independent while reducing health care costs. The project will train the next generation of researchers to handle real, cyber-physical systems. Students will be mentored, and research outcomes will be integrated into the classroom. Novel outreach activities are planned to reach the elderly community and the general public