Results 71 to 80 of about 380 (97)
Computer Vision-assisted Wireless Channel Simulation for Millimeter Wave Human Motion Recognition [PDF]
This study proposes a computer vision-assisted millimeter wave wireless channel simulation method incorporating the scattering characteristics of human motions.
Chao YU +4 more
core +1 more source
Zhendong Ceshi yu Zhenduan针对高转速、高温升、大载荷等持续复杂的工况波动引起的航空发动机高速轴承故障诊断问题，提出了一种新型的深度图迁移学习算法，以及波动工况下基于图迁移卷积网络（graph transfer convolutional networks， 简称GTCNs）的航空发动机高速轴承故障智能诊断方法。首先，利用阶比分析对波动工况下航空发动机高速轴承振动信号进行重采样，将其转化为阶次谱信号作为目标域与源域数据集；其次，采用训练好的一维图卷积网络（one⁃dimensional graph convolutional ...
doaj +1 more source
Kongjian kexue xuebao不同等级耀斑发生的频次存在数量级上的差别, 使基于常规卷积神经网络的耀斑预报模型通常难以捕捉M和X类耀斑先兆特征, 导致高等级耀斑预报精度低的问题. 本文对于这种耀斑预报中的长尾分布问题, 通过控制变量法讨论不同深度长尾学习方法对于耀斑预报精度提升. 尝试从训练集优化、损失函数优化、网络权重优化等角度改进模型对于M和X类耀斑的预报性能.
周 俊 +3 more
doaj +1 more source
Key method of digitization of power distribution panel with artificial intelligence identification for power communication network [PDF]
To enhance the operational management efficiency of the power communication network, artificial intelligence technology was utilized to develop a digitalization method for distribution panels within the communication power system.
CHEN Yitong +4 more
core +1 more source
Gaoya dianqi针对实际高压断路器故障发生的时空不确定性和暂态过程的随机性引发新增类别的未知故障类型，且其样本分布呈现长尾特性，导致现有故障识别模型出现误判的问题，提出了一种基于改进迁移学习的高压断路器新增类别故障精准识别方法。首先，提取实际在运高压断路器振动信号的多维特征参数，构建具有强特征提取能力的故障识别模型。其次，通过计算Mahalanobis距离和置信度辨识新增类别的未知故障。最后，采用伪标签和迁移学习将长尾分布的未知故障类别纳入模型训练，更新后的模型能够准确预测运行数据的故障类型。结果表明 ...
王兴华 +3 more
doaj
Dynamic Adaptive Cross-Domain Mean Approximation [PDF]
Cross-domain mean approximation (CDMA) is an efficient measure of distributional differences between domains. It measures the sample distribution difference between domains by calculating the distance from a sample in one domain to the sample mean in ...
LI Huimin, MA Jianwei, ZANG Shaofei, SONG Yanbing
core +1 more source
Weight Adaptive Multi-view Spectral Clustering Algorithm Based on Consistent Graphs [PDF]
With the popularity of mobile devices and the Internet, it has become easier to collect and share multi-view data. Multi-view data can describe data from multiple views more accurately.
Lijuan WANG, Jinping XING, Ming YIN, Zhifeng HAO, Ruichu CAI, Wen WEN
core +1 more source
Deep learning model for co-seismic response detection of fixed-point deformation data [PDF]
Co-seismic response identification of fixed-point deformation data currently relies on manual selection, and no automatic co-seismic response detection method has yet been applied.
Liming Zhao +4 more
core +1 more source
Zhongguo cuzhong zazhi目的 本研究旨在构建并研发一种基于低成本惯性测量单元（inertial measurement unit，IMU）信号的上肢多关节运动状态识别系统，用于快速、可靠地解码人类活动中的上肢多关节（前臂、肘关节、肩关节）运动状态，为卒中后上肢康复评估中的运动模式识别和日常运动监测提供支持。 方法 本研究纳入4名健康受试者，通过部署于手腕和上臂的IMU采集受试者的6维（3轴加速度+3轴角速度）运动信号，每名受试者重复10次。基于Fugl-Meyer运动功能评定量表上肢部分的屈肌协同运动，设计8个子任务 ...
程相鑫1，张烁1，杜松骏1，刘子阳1，周宏宇2，3，贾伟丽2，3，李子孝2，3，刘涛1 (CHENG Xiangxin1, ZHANG Shuo1, DU Songjun1, LIU Ziyang1, ZHOU Hongyu2,3, JIA Weili2,3, LI Zixiao2,3, LIU Tao1 )
doaj +1 more source
Image data-driven intelligent recognition of permafrost strength and feature visualization based analysis [PDF]
Ensuring the stability of the frozen wall is critical in freezing construction, but traditional onsite detection methods, due to their intermittent nature, fail to provide real-time monitoring, limiting timely responses to potential catastrophic events ...
Hang WEI +3 more
core +1 more source