Results 101 to 110 of about 844 (118)
Segmentation of Spine Computed Tomography Images Based on Three-Dimensional Recurrent Residual Convolution [PDF]
The automatic segmentation of spine Computed Tomography(CT) images can assist doctors in diagnosing related diseases. Compared to Three-Dimensional(3D) reconstruction after Two-Dimensional(2D) segmentation, the 3D segmentation method is more convenient ...
YANG Yudan, ZHANG Junhua, LIU Yunfeng
core +1 more source
Implicit Modeling Network of Human Keypoints Based on Attention Mechanism [PDF]
Human pose estimation necessitates the use of visual cues and anatomical joint relationships to pinpoint key points. Existing Convolutional Neural Network(CNN) methods falter in addressing long-range contextual cues and modeling dependencies among ...
Jiayuan ZHAO, Yuru ZHANG, Xiaodong SU, Hongyan XU, Shizhou LI, Yurong ZHANG
core +1 more source
智能科学与技术学报, 2020 近年来，结构性磁共振成像（sMRI）和功能性磁共振成像（fMRI）被广泛应用于抑郁症研究。从结构形态学、结构网络、功能网络3个角度探索抑郁症患者的大脑异常，了解其发病机制，辅助医生临床诊断、治疗和预后。目前大量研究发现抑郁症患者的海马体、杏仁核出现不同程度的萎缩，脑网络的连接强度、图论属性等均出现显著异常，且出现异常的脑区对应于人的情绪调节、注意力和认知控制等功能，异常的程度与抑郁的严重程度呈现高度相关性。从不同角度对抑郁症的研究现状进行综述，并对未来的研究提出了建议。
李姗 +6 more
doaj
Abstractive Text Summarization Method Incorporating Convolutional Shrinkage Gating [PDF]
Driven by deep learning techniques, Sequence to Sequence(Seq2Seq) model, based on an encoder-decoder architecture combined with an attention mechanism, is widely utilized in text summarization research, particularly for abstractive text summarization ...
Chenmin GAN, Hong TANG, Haolan YANG, Xiaojie LIU, Jie LIU
core +1 more source
Gaoya dianqi, 2020 动车组车载电压互感器被用来测量和传输动车组牵引电力系统的电压和频率,以保证其在运行中能够实施精确控制动车组牵引电机。由于地磁风暴、四象限斩波器在变流器中的应用、直流输电的单极运行、高空核电磁脉冲等原因,互感器运行过程中会产生直流偏磁现象,该现象会引起互感器谐波分量增加、无功损耗增加、铁心叠片的涡流损耗和铜损增加、铁心磁滞伸缩效应加剧以及振动和噪声加剧等,严重威胁动车组列车运行安全。总结了当前抑制电压互感器中的直流偏磁的措施主要包括注入反向电流法、中性点串联电容法、中性点串联电阻法、中性点串阻容法 ...
刘英 +4 more
doaj
Discussion on Deep-Learning Strategies for Diagnosis of Multiple Diseases in Fundus Diseases [PDF]
Deep-learning algorithms can achieve the precise diagnosis of fundus diseases, which is crucial for the early diagnosis and timely intervention of these diseases.
GONG Ajuan, PAN Tianrong
core +1 more source
Target-Level Implicit Sentiment Classification Based on Dual Multiview Representation [PDF]
Target-level implicit sentiment classification is a critical sentiment analysis task in natural language processing. Many existing studies mainly focused on modeling context-aware targets, and their modeling information source were relatively single ...
Mengmeng CUI, Jingping LIU, Tong RUAN, Yuqiu SONG, Wen DU
core +1 more source
Zhendong Ceshi yu Zhenduan针对燃气调压器故障识别中不平衡数据影响模型识别能力的问题，提出一种一维卷积神经网络（one‑dimensional convolutional neural network，简称1D‑CNN）与注意力机制（squeeze‑and‑excitation，简称SE）相结合的改进深度卷积神经网络（SE‑1DCNN）方法。首先，使用一维卷积核提取故障特征；其次，在交替的卷积层后添加SE模块用于通道加权，选择性地保留所需的重要信息特征，并抑制弱相关的特征；最后 ...
doaj +1 more source
基于多头注意力机制的CNN-BiLSTM高海拔多因素输电线路可听噪声预测
Gaoya dianqi为了研究考虑高海拔多环境因素影响下输电线路可听噪声的预测问题，在海拔2 400 m高度点的500 kV同塔双回线路下，搭建了边相外20、30、35 m三处可听噪声观测站，同时利用气象站进行多环境因素指标的数据采集。文中提出了一种基于多头注意力机制（multi-head attention，MHA）的卷积神经网络（convolutional neural network，CNN）—双向长短期记忆网络（bi-directional long short term memory，BiLSTM ...
黄悦华 +4 more
doaj
基于电流—磁场数据融合和交叉注意力的GIS母线电接触缺陷识别
Gaoya dianqi气体绝缘组合电器（GIS）母线触头的对接深度不足、对中度偏差和弹簧松弛等接触缺陷会显著增加接触电阻，引发过热甚至绝缘击穿事故。针对现有检测方法在复杂工况下灵敏度不足的问题，文中提出一种基于电流—磁场双模态数据融合与交叉注意力机制的缺陷识别算法。通过GIS原型试验平台同步采集4种典型工况下的瞬态电流信号与16通道空间磁场分布数据，构建多物理场数据集；采用Mel滤波器提取电流时频特征，通过对称点模式（SDP）表征磁场空间特性；进而设计双分支ResNet-18网络分别处理两类特征 ...
谢志杨, 彭涛, 敬磊
doaj