IEEE J Biomed Health Inform. 2013 Jan;17(1):38-45. doi: 10.1109/TITB.2012.2226905.
As an essential branch of context awareness, activity awareness, especially daily activity monitoring and fall detection, is important to healthcare for the elderly and patients with chronic diseases. In this paper, a framework for activity awareness using surface electromyography and accelerometer (ACC) signals is proposed. First, histogram negative entropy was employed to determine the start- and end-points of static and dynamic active segments. Then, the angle of each ACC axis was calculated to indicate body postures, which assisted with sorting dynamic activities into two categories: dynamic gait activities and dynamic transition ones, by judging whether the pre- and post-postures are both standing. Next, the dynamic gait activities were identified by the double-stream hidden Markov models. Besides, the dynamic transition activities were distinguished into normal transition activities and falls by resultant ACC amplitude. Finally, a continuous daily activity monitoring and fall detection scheme was performed with the recognition accuracy over 98%, demonstrating the excellent fall detection performance and the great feasibility of the proposed method in daily activities awareness.
作为上下文感知的一个重要分支，活动感知，特别是日常活动监测和跌倒检测，对老年人和慢性病患者的医疗保健至关重要。本文提出了一种使用表面肌电和加速度计（ACC）信号的活动感知框架。首先，使用直方图负熵来确定静态和动态活动段的起点和终点。然后，计算每个 ACC 轴的角度以表示身体姿势，通过判断前后姿势是否都是站立的，将动态活动分为动态步态活动和动态过渡活动两类。接下来，使用双流隐马尔可夫模型识别动态步态活动。此外，通过 ACC 幅度的结果将动态过渡活动分为正常过渡活动和跌倒。最后，提出了一种连续的日常活动监测和跌倒检测方案，识别准确率超过 98%，证明了该方法在日常活动感知中具有出色的跌倒检测性能和很高的可行性。
