SPINDLES: A Smartphone Platform for Intelligent Detection and Notification of Leg Shaking
SPINDLES: A Smartphone Platform for Intelligent Detection and Notification of Leg Shaking
复制标题
SPINDLES：用于智能检测和通知腿部抖动的智能手机平台
DOI：
10.1145/3123024.3124408
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Xiaofan Jiang
中科院分区：
文献类型：
--
作者：
S. Xia;Yan Lu;Peter Wei;Xiaofan Jiang
对于许多人来说，抖腿的习惯是他们自己和周围人的烦恼。通过简单地意识到运动，一个人能够自愿停止颤抖。在这项工作中，我们提出了SPINDLES，一个低功耗，低延迟，非侵入性和高精度的移动的应用程序来检测腿抖动，并及时通知用户。SPINDLES对手机的放置具有鲁棒性，并实现了一个信号处理管道，消除了机器学习方法中常见的训练和校准阶段的需要。我们将SPINDLES与其他检测算法和现有的Google Play Store应用程序进行了比较，发现SPINDLES在准确性方面有重大改进，延迟和功耗相当。它的真阳性率为99.6%，真阴性率为97.6%，在各种情况下进行了500多次试验1。
For many people, the habit of leg shaking is an annoyance to themselves and people around them. By simply becoming aware of the motion, one is able to voluntarily stop shaking. In this work, we present SPINDLES, a low-power, low-latency, non-intrusive and high accuracy mobile application to detect leg shaking and notify the user in a timely manner. SPINDLES is robust to the placement of the phone and implements a signal processing pipeline that eliminates the need for training and calibration phases common in machine learning approaches. We compare SPINDLES with other detection algorithms and existing Google Play Store applications, and find that SPINDLES is a major improvement in terms of accuracy with comparable latency and power consumption. It has a true positive rate of 99.6%, as well as a true negative rate of 97.6%, taken over 500 trials in various situations1.