[论文解读] Abnormal respiratory patterns classifier may contribute to large-scale screening of people infected with COVID-19 in an accurate and unobtrusive manner

Yunlu Wang, Menghan Hu+4 more|arXiv (Cornell University)|Feb 12, 2020

Anomaly Detection Techniques and Applications参考文献 22被引用 197

一句话总结

本论文提出带有 BI-AT-GRU 与呼吸模拟模型的系统，以非接触深度相机数据对六种呼吸模式进行分类，在真实世界数据上达到 94.5% 的准确率。

ABSTRACT

Research significance: The extended version of this paper has been accepted by IEEE Internet of Things journal (DOI: 10.1109/JIOT.2020.2991456), please cite the journal version. During the epidemic prevention and control period, our study can be helpful in prognosis, diagnosis and screening for the patients infected with COVID-19 (the novel coronavirus) based on breathing characteristics. According to the latest clinical research, the respiratory pattern of COVID-19 is different from the respiratory patterns of flu and the common cold. One significant symptom that occurs in the COVID-19 is Tachypnea. People infected with COVID-19 have more rapid respiration. Our study can be utilized to distinguish various respiratory patterns and our device can be preliminarily put to practical use. Demo videos of this method working in situations of one subject and two subjects can be downloaded online. Research details: Accurate detection of the unexpected abnormal respiratory pattern of people in a remote and unobtrusive manner has great significance. In this work, we innovatively capitalize on depth camera and deep learning to achieve this goal. The challenges in this task are twofold: the amount of real-world data is not enough for training to get the deep model; and the intra-class variation of different types of respiratory patterns is large and the outer-class variation is small. In this paper, considering the characteristics of actual respiratory signals, a novel and efficient Respiratory Simulation Model (RSM) is first proposed to fill the gap between the large amount of training data and scarce real-world data. The proposed deep model and the modeling ideas have the great potential to be extended to large scale applications such as public places, sleep scenario, and office environment.

研究动机与目标

• 推动与 COVID-19 筛查相关的异常呼吸模式的远程、无干扰检测。
• 通过使用呼吸模拟模型（RSM）生成大量合成训练数据来解决数据稀缺问题。
• 开发并验证一个针对呼吸波形特征定制的深度学习分类器。

提出的方法

• 引入呼吸模拟模型（RSM）以生成具有参数 a_i、b_i、c_i、d_i 和噪声的多样化合成呼吸波形。
• 从 20 名受试者获取使用 Kinect v2 与基于 ROI 的深度信号模仿六种模式的真实世界深度相机数据。
• 提出 BI-AT-GRU，即具注意力机制的双向 GRU，用于从时间序列数据分类六种呼吸模式。
• 训练中使用 RSM 生成的数据；测试中在深度相机测量数据上进行评估。
• 训练 BI-AT-GRU，并与 BI-AT-LSTM、GRU 和 LSTM 进行比较，以评估性能。

实验结果

研究问题

• RQ1 在深度相机信号下，使用对模拟呼吸数据进行训练的深度神经网络，是否能够准确分类真实世界的呼吸模式？
• RQ2 双向和注意力机制是否相较于标准的 GRU/LSTM 模型提升呼吸模式分类的性能？
• RQ3 在真实世界深度相机数据上，所提出的 BI-AT-GRU 针对六种模式的分类准确率是多少？

主要发现

• BI-AT-GRU 在真实世界数据上达到 94.5% 的准确率、94.4% 的精确率、95.1% 的召回率，以及 94.8% 的 F1。
• BI-AT-GRU 在同一测试集上优于 BI-AT-LSTM、GRU 和 LSTM。
• 双向与注意力机制相较于非双向/非注意力的对照模型，提升了性能。
• 在分辨 Cheyne-Stokes 与 Central-Apnea 时，分类错误主要发生，原因是振幅相关的变异性和运动。
• 该方法展示了远程、无干扰呼吸模式分类的可行性，并具有大规模应用潜力。