Prediction of COVID-19 - Pneumonia based on Selected Deep Features and One Class Kernel Extreme Learning Machine.

Prediction of COVID-19 - Pneumonia based on Selected Deep Features and One Class Kernel Extreme Learning Machine.
复制标题

基于选择深度特征和一类核极限学习机的COVID-19肺炎预测。

DOI:
10.1016/j.compeleceng.2020.106960
复制
发表时间:
2021-03
期刊:
Computers & electrical engineering : an international journal
影响因子:
--
通讯作者:
Saba T
Saba T
中科院分区:
其他
文献类型:
--
作者:
Khan MA;Kadry S;Zhang YD;Akram T;Sharif M;Rehman A;Saba T

文献摘要

参考文献

被引文献

相似文献

在这项工作中,我们提出了一个深度学习框架,用于从正常胸部CT扫描中分类COVID-19肺炎感染。在这方面,开发了一个15层卷积神经网络架构,它从从Radiopedia收集的选定图像样本中提取深度特征。从两个不同的层,全局平均池和全连接层,收集深度特征,然后使用最大层细节(MLD)方法组合。随后,在主设计中嵌入相关熵技术,以从特征池中选择最具鉴别力的特征。最后采用单类核极端学习机器分类器进行分类,平均准确率为95.1%,灵敏度、特异度和精确度分别为95.1%、95%和94%。为了进一步验证我们的说法,详细的统计分析的基础上,标准误差均值(SEM),这证明了我们提出的预测设计的有效性。
In this work, we propose a deep learning framework for the classification of COVID-19 pneumonia infection from normal chest CT scans. In this regard, a 15-layered convolutional neural network architecture is developed which extracts deep features from the selected image samples – collected from the Radiopeadia. Deep features are collected from two different layers, global average pool and fully connected layers, which are later combined using the max-layer detail (MLD) approach. Subsequently, a Correntropy technique is embedded in the main design to select the most discriminant features from the pool of features. One-class kernel extreme learning machine classifier is utilized for the final classification to achieving an average accuracy of 95.1%, and the sensitivity, specificity & precision rate of 95.1%, 95%, & 94% respectively. To further verify our claims, detailed statistical analyses based on standard error mean (SEM) is also provided, which proves the effectiveness of our proposed prediction design.
DOI: 10.1002/jemt.23447
发表时间: 2020-01-27
影响因子: 2.5
作者:
Majid, Abdul;Khan, Muhammad Attique;Tariq, Usman
通讯作者: Tariq, Usman
DOI: 10.1002/jemt.23275
发表时间: 2019-08-01
影响因子: 2.5
作者:
Khan, Sajid A.;Nazir, Muhammad;Awais, Muhammad
通讯作者: Awais, Muhammad
DOI: 10.1148/radiol.2020200905
发表时间: 2020-08-01
期刊: RADIOLOGY
影响因子: 19.7
作者:
Li, Lin;Qin, Lixin;Xia, Jun
通讯作者: Xia, Jun
DOI: 10.1079/9781789246070.0001
发表时间: 2021-02-24
期刊: EUROPEAN RADIOLOGY
影响因子: 5.9
作者:
Wang, Shuai;Kang, Bo;Xu, Bo
通讯作者: Xu, Bo
使用极限学习机进行一类分类
DOI: 10.1155/2015/412957
发表时间: 2015-01-01
影响因子: --
作者:
Leng, Qian;Qi, Honggang;Su, Guiping
通讯作者: Su, Guiping