Madhushri Priyanka, Ahmed Beena, Penzel Thomas, Jovanov Emil
Annu Int Conf IEEE Eng Med Biol Soc. 2015;2015:1837-40. doi: 10.1109/EMBC.2015.7318738.
Wireless sensors networks represent the architecture of choice for distributed monitoring due to the ease of deployment and configuration. We developed a distributed sleep monitoring system which combines wireless inertial sensors SP-10C by Sensoplex controlled by a custom smartphone application as an extension of the polysomnographic (PSG) monitor SOMNOscreen plus from Somnomedics. While existing activity monitors are wired to the SOMNOscreen, our system allows the use of wireless inertial sensors to improve user's comfort during sleep. The system is intended for monitoring of periodic leg movements (PLM) and user's activity during sleep. Wireless sensors are placed on ankle and toes of the foot in a customized sock. An Android app communicates with wireless sensors over Bluetooth Smart (BTS) link and streams 3D accelerometer values, 4D unit quaternion values and timestamps. In this paper we present a novel method of synchronization of data streams from PSG and inertial sensors, and original method of detection of PLM events. The system was tested using five experiments of simulated PLM, and achieved 96.51% of PLM detection accuracy.
由于易于部署和配置，无线传感器网络是分布式监测的首选架构。我们开发了一种分布式睡眠监测系统，该系统将Sensoplex公司的无线惯性传感器SP-10C与一款定制的智能手机应用程序相结合，作为Somnomedics公司多导睡眠图（PSG）监测仪SOMNOscreen plus的扩展。现有的活动监测仪是有线连接到SOMNOscreen的，而我们的系统允许使用无线惯性传感器，以提高用户睡眠期间的舒适度。该系统旨在监测睡眠期间的周期性腿部运动（PLM）和用户活动。无线传感器放置在定制袜子的脚踝和脚趾上。一款安卓应用程序通过蓝牙智能（BTS）链路与无线传感器通信，并传输三维加速度计值、四维单位四元数的值和时间戳。在本文中，我们提出了一种来自PSG和惯性传感器的数据流同步新方法，以及一种检测PLM事件的原始方法。该系统通过五个模拟PLM实验进行了测试，PLM检测准确率达到了96.51%。
