Human Gait Monitoring Using Footstep-Induced Floor Vibrations Across Different Structures
Human Gait Monitoring Using Footstep-Induced Floor Vibrations Across Different Structures
复制标题
利用脚步引起的跨不同结构的地板振动进行人体步态监测
DOI：
10.1145/3267305.3274187
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
H. Noh
中科院分区：
文献类型：
--
作者：
Mostafa Mirshekari;Jonathon Fagert;Amelie Bonde;Pei Zhang;H. Noh
在本文中，我们提出了一种利用脚步引起的地板振动来监测人体步态的结构自适应方法。人体步态信息对于及时、准确地评估和诊断许多健康状况至关重要。在以前的工作中，足迹诱发的振动监测已经被引入，作为一种准确且经济有效的手段来提供室内环境中的连续步态监测。以往在该领域的工作通常依赖于逆建模方法来将信号特征映射到步态信息，但由于每个新的部署结构中的信号特征不同，因此受到限制。当试图在另一个结构中使用在一个结构中训练的模型时，这些变化的特征会引入错误。为了克服这一挑战，我们提出了一种结构自适应方法，该方法能够将在一个结构中训练的模型转移到不存在训练数据的新结构中。为此，我们首先找到一个低维空间，在这个空间中，各种结构的振动响应具有相似性，并在目标结构中对数据进行标记。然后，我们使用标记的数据来训练一个新的模型，用于该结构中的足迹检测和监控。我们通过三种类型的结构(木结构、混凝土结构和钢结构)的真实世界实验对我们的方法进行了评估。我们的评估结果表明，我们的方法获得了85%到97%的足迹检测准确率和86%到97%的F1得分，分别比基线方法提高了3-10倍和2.2-15倍。
In this paper, we present a structure-adaptive approach for monitoring human gait using footstep-induced floor vibrations. Human gait information is critical for timely and accurate assessment and diagnosis of many health conditions. Footstep-induced vibration monitoring has been introduced in prior works as an accurate and cost-effective mean to provide continuous gait monitoring in indoor environments. Prior works in this field typically rely on inverse modeling approaches to map signal characteristics to gait information, but are limited due to varying signal characteristics in each new deployment structure. These changing characteristics introduce errors when attempting to use a model trained in one structure in another structure. To overcome this challenge, we propose a structure-adaptive approach that enables the transfer of a model trained in one structure to a new structure where no training data is present. To this end, we first find a lower-dimension space in which vibration responses share similarity across various structures and label the data in the target structure. Then, we use the labeled data to train a new model for footstep detection and monitoring in that structure. We evaluated our approach through real-world experiments in three types of structures (wood, concrete, and steel). Our evaluation results show that our approach achieves a footstep detection accuracy of between 85 and 97 percent and F1-score of between 86 and 97 percent, which represents 3-10X and 2. 2-15X improvements over the baseline approach, respectively.
影响因子：
4.7
作者：
Shijia Pan;Mostafa Mirshekari;Jonathon Fagert;C. G. Ramirez;Albert Jin Chung;C. C. Hu-C.;John Paul Shen;Pei Zhang;H. Noh
通讯作者：
Shijia Pan;Mostafa Mirshekari;Jonathon Fagert;C. G. Ramirez;Albert Jin Chung;C. C. Hu-C.;John Paul Shen;Pei Zhang;H. Noh
影响因子：
8.4
作者：
Mirshekari, Mostafa;Pan, Shijia;Noh, Hae Young
通讯作者：
Noh, Hae Young