LumiO: a plaque-aware toothbrush

LumiO: a plaque-aware toothbrush
复制标题

LumiO:牙菌斑感知牙刷

DOI:
10.1145/2971648.2971704
复制
发表时间:
2016
期刊:
Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing
影响因子:
--
通讯作者:
K. Yatani
K. Yatani
中科院分区:
--
文献类型:
--
作者:
T. Yoshitani;Masa Ogata;K. Yatani

文献摘要

被引文献

相似文献

刷牙在日常牙菌斑去除中起着重要的作用,用于预防牙科。先前的工作已经研究了利用传感技术对刷牙的改进。但现有的刷牙支持主要集中在估计刷牙覆盖率。因此,使用者只能间接了解刷牙去除牙菌斑的效果。我们介绍LumiO,这是一种牙刷,可为用户提供有关牙齿上牙菌斑数量的持续反馈。Lumio使用一种众所周知的斑块检测方法,称为定量光诱导荧光(QLF)。QLF利用了一种红色荧光特性,当蓝紫色光线投射时,菌斑中的细菌就会显示出这种特性。蓝紫光激发这种荧光特性,带有滤光片的相机可以捕捉粉红色的斑块。我们将这项技术结合到电动牙刷中,以提高日常牙齿护理中去除牙菌斑的性能。本文首先讨论了口腔活动和交互传感以及牙科护理技术的相关工作。然后,我们描述了QLF的原理,LumiO的硬件设计,以及我们基于视觉的斑块检测方法。我们的评估表明,基于视觉的斑块检测方法与三种机器学习技术可以实现的F-措施0.68 - 0.92用户依赖的训练。定性证据还表明,研究参与者能够提高对牙菌斑的认识,并建立对刷牙的信心。
Toothbrushing plays an important role in daily dental plaque removal for preventive dentistry. Prior work has investigated improvements on toothbrushing with sensing technologies. But existing toothbrushing support focuses mostly on estimating brushing coverage. Users thus only have indirect information about how well their toothbrushing removes dental plaque. We present LumiO, a toothbrush that offers users continuous feedback on the amount of plaque on teeth. Lumio uses a well-known method for plaque detection, called Quantitative Light-induced Fluorescence (QLF). QLF exploits a red fluorescence property that bacterium in the plaque demonstrates when a blue-violet ray is cast. Blue-violet light excites this fluorescence property, and a camera with an optical filter can capture plaque in pink. We incorporate this technology into an electric toothbrush to achieve improvements in performance on plaque removal in daily dental care. This paper first discusses related work in sensing for oral activities and interaction as well as dental care with technologies. We then describe the principles of QLF, the hardware design of LumiO, and our vision-based plaque detection method. Our evaluations show that the vision-based plaque detection method with three machine learning techniques can achieve F-measures of 0.68 -- 0.92 under user-dependent training. Qualitative evidence also suggests that study participants were able to have improved awareness of plaque and build confidence on their toothbrushing.