A window-based sequence-to-one approach with dynamic voting for nurse care activity recognition using acceleration-based wearable sensor
A window-based sequence-to-one approach with dynamic voting for nurse care activity recognition using acceleration-based wearable sensor
复制标题
一种基于窗口的序列对一方法，使用基于加速度的可穿戴传感器进行护士护理活动识别的动态投票
DOI：
10.1145/3410530.3414336
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Mirshekari, Mostafa
中科院分区：
文献类型：
--
作者：
Dong, Yiwen;Liu, Jingxiao;Gao, Yitao;Sarkar, Sulagna;Hu, Zhizhang;Fagert, Jonathon;Pan, Shijia;Zhang, Pei;Noh, Hae Young;Mirshekari, Mostafa
本文介绍了一种基于窗口的顺序到一的方法与动态投票的护士护理活动识别使用基于加速度的可穿戴传感器。护士护理活动的认可是确保高质量的病人护理和提供建设性的和具体的反馈给护理团队的重要组成部分。用于活动识别的当前感测方法中的一些包括基于视觉的感测和非可穿戴RF感测。然而，由于诸如感知隐私和对特定乘员路径的敏感性等限制性因素，它们的应用在现实生活场景中受到限制。为了克服这些限制，在最近的工作中引入了基于加速度的可穿戴传感。然而，护理活动实例的持续时间分布是有偏差和偏斜的。这种偏斜导致不平衡的数据集，这将导致常见预测模型的性能低下。此外，诸如环境噪声和环境因素的不确定性影响信号，并且因此可能潜在地降低活动识别性能。为了克服第一个挑战，我们将信号分成具有不同长度的活动实例的自适应重叠比率的短窗口，这平衡了由于事件长度变化引起的标签分布。此外，我们使用多层长短期记忆（LSTM）模型来预测每个滑动窗口的护理活动，并引入基于投票的方案来补充信号窗口的预测并解决不确定性挑战。我们通过参与“第二届护士护理活动识别挑战赛使用实验室和现场数据”作为团队HealthyVibes来验证我们的方法。在挑战数据集上，我们的模型在训练和验证方面分别达到了97.4%和43.9%的准确率。
This paper introduces a window-based sequence-to-one approach with dynamic voting for nurse care activity recognition using acceleration-based wearable sensors. Nurse care activity recognition is an essential part of ensuring high quality patient care and providing constructive and concrete feedback to the care team. Some of the current sensing approaches for activity recognition include vision-based sensing and non-wearable RF sensing. However, their application is limited in real-life scenarios due to restrictive factors such as perceived privacy and sensitivity to specific occupant paths. To overcome these limitations, acceleration-based wearable sensing have been introduced in recent works. However, the duration distribution of nursing activity instances are biased and skewed. This skewness leads to imbalanced datasets which will result in low performance for the common predictive models. Further, uncertainties such as ambient noise and environmental factors affect the signals and thus can potentially reduce the activity recognition performance. To overcome the first challenge, we separate the signals into short windows with adaptive overlapping ratios for activity instances having different lengths, which balances the label distribution due to event length variations. Further, we use a multi-layer Long Short-Term Memory (LSTM) model to predict nursing activities of each sliding window and introduce a voting-based scheme for complementing the predictions across the signal windows and addressing the uncertainty challenge. We validate our approach through participation in "The 2nd Nurse Care Activity Recognition Challenge Using Lab and Field Data" as team HealthyVibes. On the challenge dataset our model achieves 97.4% and 43.9% accuracy for training and validation, respectively.
登录
查看更多内容
活动识别对基于手机的护理文档的好处：绿野仙踪研究
DOI：
--
发表时间：
2010
期刊：
International Semantic Web Conference
影响因子：
--
作者：
Bashar Altakrouri;Gerd Kortuem;Agnes Grünerbl;K. Kunze;P. Lukowicz
通讯作者：
P. Lukowicz
影响因子：
2.5
作者：
Y. Takebe;M. Kanai-Pak;N. Kuwahara;J. Maeda;Miwa Hirata;Y. Kitajima;J. Ota
通讯作者：
Y. Takebe;M. Kanai-Pak;N. Kuwahara;J. Maeda;Miwa Hirata;Y. Kitajima;J. Ota
简单的方法可以识别复杂的护士护理活动吗？
DOI：
--
发表时间：
2019
期刊：
UbiComp/ISWC Adjunct
影响因子：
--
作者：
Md. Eusha Kadir;Pritom Saha Akash;S. Sharmin;A. Ali;M. Shoyaib
通讯作者：
M. Shoyaib
使用实验室和现场数据进行的第二届护士护理活动识别挑战摘要
DOI：
--
发表时间：
2020
期刊：
UbiComp/ISWC Adjunct
影响因子：
--
作者：
S. S. Alia;P. Lago;Kohei Adachi;Tahera Hossain;H. Goto;Tsuyoshi Okita;Sozo Inoue
通讯作者：
Sozo Inoue
DOI：
10.1061/(asce)em.1943-7889.0001719
发表时间：
2020-03
期刊：
Journal of Engineering Mechanics-asce
影响因子：
--
作者：
Mostafa Mirshekari;Jonathon Fagert;Shijia Pan;Pei Zhang;H. Noh
通讯作者：
Mostafa Mirshekari;Jonathon Fagert;Shijia Pan;Pei Zhang;H. Noh