Real-time swallowing detection based on tracheal acoustics
Real-time swallowing detection based on tracheal acoustics
复制标题
基于气管声学的实时吞咽检测
DOI：
--
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Maysam Ghovanloo
中科院分区：
文献类型：
--
作者：
Temiloluwa O. Olubanjo;Maysam Ghovanloo
可穿戴系统在持续健康监测中发挥着重要作用，有助于及早发现异常事件。自动实时检测吞咽的能力可以为饮食行为、药物依从性监测以及吞咽障碍的诊断和评估提供有价值的见解。在本文中，我们开发了一种基于声学信号的实时吞咽检测算法，该算法结合了计算成本低廉的特征，以实现与先前提出的使用声学和非声学数据的方法相当的性能。根据来自四名健康受试者的数据，包括常见的气管事件，如言语、咀嚼、咳嗽、清喉咙和吞咽不同液体，我们的结果显示，整体召回率为 79.9%，准确率为 67.6%。
Wearable systems play an important role in continuous health monitoring and can contribute to early detection of abnormal events. The ability to automatically detect swallowing in real-time can provide valuable insight into eating behavior, medication adherence monitoring, and diagnosis and evaluation of swallowing disorders. In this paper, we have developed a real-time swallowing detection algorithm based on acoustic signals that combines computationally inexpensive features to achieve comparable performance with previously proposed methods using acoustic and non-acoustic data. With data from four healthy subjects that includes common tracheal events such as speech, chewing, coughing, clearing the throat, and swallowing of different liquids, our results show an overall recall performance of 79.9% and precision of 67.6%.