Results 91 to 100 of about 1,997 (147)

Application of high resolution computed tomography image assisted classification model of middle ear diseases based on 3D-convolutional neural network. [PDF]

Zhong Nan Da Xue Xue Bao Yi Xue Ban, 2022
Su R, Song J, Wang Z, Mao S, Mao Y, Wu X, Hou M.   +6 more
europepmc   +1 more source

[Automatic anatomical site recognition of laryngoscopic images using convolutional neural network]. [PDF]

Lin Chuang Er Bi Yan Hou Tou Jing Wai Ke Za Zhi, 2023
Wang M, Zhu J, Li Y, Tie C, Wang S, Zhang W, Wang G, Ni X.   +7 more
europepmc   +1 more source

[Atrial fibrillation diagnosis algorithm based on improved convolutional neural network]. [PDF]

Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, 2021
Pu Y, Zhu J, Zhang D, Yan T.
europepmc   +1 more source

基于CTGAN-CRS与改进卷积神经网络的变压器故障诊断方法

Gaoya dianqi
为了提升油中溶解气体数据不平衡场景下的电力变压器故障诊断性能，文中提出了一种基于数据增强与特征扩增结合卷积神经网络进行变压器故障诊断的方法。首先，建立一种基于条件式表格生成对抗网络（conditional tabular generative adversarial network，CTGAN）结合级联式拒绝采样（cascade reject sampling，CRS）的数据增强方法，以实现不平衡数据集的高质量均衡化；其次，构建了一种全类型气体比值结合随机森林算法（gas ratios and ...
阎对丰, 刘昌林, 李元超, 王纪儒, 孔宪光   +4 more
doaj  

[A protein complex recognition method based on spatial-temporal graph convolution neural network]. [PDF]

Nan Fang Yi Ke Da Xue Xue Bao, 2022
Sheng J, Xue J, Li P, Yi N.
europepmc   +1 more source

Unsupervised Learning Method for the Wave Equation Based on Finite Difference Residual Constraints Loss

The wave equation is an important physical partial differential equation, and in recent years, deep learning has shown promise in accelerating or replacing traditional numerical methods for solving it.
Deng, Xiao-Gang, Feng, Xin, Jiang, Yi, Qin, Jia-Xian, Zhang, Lai-Ping   +4 more
core  

[A multi-channel input convolutional neural network for artifact reduction in quantitative susceptibility mapping]. [PDF]

Nan Fang Yi Ke Da Xue Xue Bao, 2022
Si W, Feng Y.
europepmc   +1 more source

基于轻量级卷积神经网络的复合绝缘子憎水性诊断方法研究

Gaoya dianqi
复合绝缘子因其良好的性能在电网中普遍使用，为提高复合绝缘子带电憎水性检测的智能化和自动化水平，文中提出一种基于轻量级卷积神经网络的复合绝缘子憎水性诊断方法。文中使用EfficientNet算法对复合绝缘子不同憎水性等级对应的水迹图像数据进行特征提取训练，通过对模型准确率和参数量等方面的比较，并结合模型在边缘计算设备上的正向推理速度，确定EfficientNet-b3模型为本应用场景下的最优模型。该模型分类准确率为96.43%，在Jetson Xavier NX上的正向推理速度为57.16 FPS ...
马子儒, 刘云鹏, 裴少通, 张功浩, 杨家骏   +4 more
doaj  

[Research on inversion method of intravascular blood flow velocity based on convolutional neural network]. [PDF]

Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, 2022
Wang Y, Yang D, Xu B, Zhang X, Wang X.
europepmc   +1 more source

[CT and MRI fusion based on generative adversarial network and convolutional neural networks under image enhancement]. [PDF]

Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, 2023
Liu Y, Li J, Wang Y, Cai W, Chen F, Liu W, Mao X, Gan K, Wang R, Sun D, Qiu H, Liu B.   +11 more
europepmc   +1 more source