[Research on the application of convolution neural network in the diagnosis of Alzheimer's disease]. [PDF]
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, 2021 Xu B, Ding C, Xu G.
europepmc +1 more source
Research on Short term Traffic Flow Prediction on Highways Based on LC-Transformer Model
工程科学与技术随着城市经济的迅猛发展和私家车保有量的持续增加，城市交通流的准确预测对于缓解交通拥堵、提高出行效率以及保障交通安全有着重要意义。传统的交通流预测方法处理复杂的时空动态关系和天气、交通事故等外部因素影响时，往往依赖线性假设或静态模型，难以同时刻画交通流中非线性时空演化机制与多因素信息的融合特征，导致预测精度与泛化能力受限。为此，本文提出了一种基于改进Transformer模型，即LC-Transformer模型短时交通流预测方法。该模型结合了LSTM神经网络、CVAE条件变分自编码器以及交通历史事故数据 ...
Li ShuQing, Zhang Peizhe
doaj
[An autoencoder model based on one-dimensional neural network for epileptic EEG anomaly detection]. [PDF]
Nan Fang Yi Ke Da Xue Xue BaoOu J, Zhan C, Yang F.
europepmc +1 more source
[Research on computer aided diagnosis of otitis media based on faster region convolutional neural network]. [PDF]
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, 2021 Lu S +5 more
europepmc +1 more source
[Gesture accuracy recognition based on grayscale image of surface electromyogram signal and multi-view convolutional neural network]. [PDF]
Sheng Wu Yi Xue Gong Cheng Xue Za ZhiChen Q, Tao Q, Zhang X, Hu X, Zhang T.
europepmc +1 more source
[A three dimensional convolutional neural network pulmonary nodule detection algorithm based on the multi-scale attention mechanism]. [PDF]
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, 2022 Zhao Y, Peng Z, Ma J, Xia H, Wan H.
europepmc +1 more source
[Research on multi-scale convolutional neural network hand muscle strength prediction model improved based on convolutional attention module]. [PDF]
Sheng Wu Yi Xue Gong Cheng Xue Za ZhiDu Y, Sun M, Li J, Wang X, Cao T.
europepmc +1 more source
[Coronary artery segmentation based on Transformer and convolutional neural networks dual parallel branch encoder neural network]. [PDF]
Sheng Wu Yi Xue Gong Cheng Xue Za ZhiPan D, Luo G, Zeng A.
europepmc +1 more source
[Fetal electrocardiogram signal extraction and analysis method combining fast independent component analysis algorithm and convolutional neural network]. [PDF]
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, 2023 Yang Y, Hao J, Wu S.
europepmc +1 more source
Gaoya dianqi在电网建设过程中，电网基建档案是重要的过程资料，但其数量和类型繁杂，这给档案绿色数字化管理及预警带来巨大挑战。针对这一挑战，文中提出一种基于改进融合先验知识卷积神经网络（PKCNN）的电网基建档案电子化管理预警方法。首先，利用PKCNN卷积层对输入的电网基建档案进行特征提取，并引入先验知识辅助网络参数训练；然后，采用基于萤火虫算法（FA）优化的非线性SVM对PKCNN中分类函数进行改进，以提高电网基建档案电子化管理预警的精度；最后，建立基于改进PKCNN模型的电网基建档案电子化管理预警方法进行仿真验证 ...
陈然 +7 more
doaj