Detecting positional vertigo using an ensemble of 2D convolutional neural networks.
Detecting positional vertigo using an ensemble of 2D convolutional neural networks.
复制标题
DOI：
10.1016/j.bspc.2021.102708
复制
发表时间：
2021-07
影响因子：
5.1
通讯作者：
Cox SJ
中科院分区：
文献类型：
--
作者：
Newman JL;Phillips JS;Cox SJ
我们训练了深度神经网络来检测运动引起的头晕。2D卷积深度神经网络优于1D网络架构。最好的结果提供了输入功能相结合的眼睛和头部运动。五个网络的整体表现优于每个单独的网络。这里提出的工作的目的是开发一个系统，可以自动识别发生在患有位置性眩晕的患者中的头晕发作，当患者将头部移动到某些位置时会发生这种情况。我们使用我们的新型医疗设备CAVA连续记录被诊断患有良性阵发性位置性眩晕的患者的眼球和头部运动数据长达30天。在我们以前的工作的基础上，我们描述了一个新的五个2D卷积神经网络的集合，使用复合识别功能，包括眼动数据和三通道加速度计数据。我们在11倍交叉验证实验中获得了0.63的1分，表明该系统可以从超过100小时的正常眼动数据中检测到几秒钟的运动引起的头晕。我们表明，该系统优于我们以前的一维神经网络方法，我们的集成分类器是上级的每个单独的网络，它包含。我们还证明，我们的复合识别功能提供了改进的性能，使用单独的数据源独立获得的结果。
We trained Deep Neural Networks to detect attacks of motion provoked dizziness. 2D Convolutional Deep Neural Networks outperform 1D network architectures. Best results were provided by input features combining eye- and head-movement. An ensemble of five networks outperformed each individual network alone. The aim of the work presented here was to develop a system that can automatically identify attacks of dizziness occurring in patients suffering from positional vertigo, which occurs when sufferers move their head into certain positions. We used our novel medical device, CAVA, to record eye- and head-movement data continually for up to 30 days in patients diagnosed with a disorder called Benign Paroxysmal Positional Vertigo. Building upon our previous work, we describe a novel ensemble of five 2D Convolutional Neural Networks, using composite recognition features, including eye-movement data and three-channel accelerometer data. We achieve an 1 score of 0.63 across an 11-fold cross-fold validation experiment, demonstrating that the system can detect a few seconds of motion provoked dizziness from within over a 100 h of normal eye-movement data. We show that the system outperforms our previous 1D Neural Network approach, and that our ensemble classifier is superior to each of the individual networks it contains. We also demonstrate that our composite recognition features provide improved performance over results obtained using the individual data sources independently.
登录
查看更多内容
影响因子：
9.9
作者：
Oh, Hui Jong;Kim, Ji Soo;Lim, Jeong Geun
通讯作者：
Lim, Jeong Geun
影响因子：
4.7
作者：
Chin, Seong
通讯作者：
Chin, Seong
影响因子：
6.1
作者：
Erdenebayar, Urtnasan;Kim, Yoon Ji;Lee, Kyoung-Joung
通讯作者：
Lee, Kyoung-Joung
DOI：
10.1080/21681163.2019.1699165
发表时间：
2019-12-07
影响因子：
1.6
作者：
Ben Slama, Amine;Mouelhi, Aymen;Trabelsi, Hedi
通讯作者：
Trabelsi, Hedi
影响因子：
5
作者：
Chawla, NV;Bowyer, KW;Kegelmeyer, WP
通讯作者：
Kegelmeyer, WP