BodyScope: a wearable acoustic sensor for activity recognition
BodyScope: a wearable acoustic sensor for activity recognition
复制标题
DOI：
10.1145/2370216.2370269
复制
发表时间：
2012-09
期刊：
影响因子：
--
通讯作者：
K. Yatani;K. Truong
中科院分区：
文献类型：
--
作者：
K. Yatani;K. Truong
准确的活动识别使得能够开发各种无处不在的计算应用，例如上下文感知系统、生活记录和个人健康系统。可穿戴传感技术可用于收集活动识别数据，而无需在基础设施中安装传感器。然而，用户可能需要佩戴多个传感器以准确识别大量不同的活动。我们开发了一种名为BodyScope的可穿戴声学传感器，用于记录用户喉咙区域产生的声音，并将其分类为用户活动，如进食，饮水，说话，大笑和咳嗽。仅使用我们的BodyScope传感器对12种活动进行支持向量机分类的F测量值为79.5%。我们还进行了一项小规模的野外研究，发现BodyScope能够以71.5%的准确率识别四种活动（吃，喝，说话和笑）。
Accurate activity recognition enables the development of a variety of ubiquitous computing applications, such as context-aware systems, lifelogging, and personal health systems. Wearable sensing technologies can be used to gather data for activity recognition without requiring sensors to be installed in the infrastructure. However, the user may need to wear multiple sensors for accurate recognition of a larger number of different activities. We developed a wearable acoustic sensor, called BodyScope, to record the sounds produced in the user's throat area and classify them into user activities, such as eating, drinking, speaking, laughing, and coughing. The F-measure of the Support Vector Machine classification of 12 activities using only our BodyScope sensor was 79.5%. We also conducted a small-scale in-the-wild study, and found that BodyScope was able to identify four activities (eating, drinking, speaking, and laughing) at 71.5% accuracy.