Results 61 to 70 of about 17,971 (165)
Research on self-training neural machine translation based on monolingual priority sampling [PDF]
To enhance the performance of neural machine translation (NMT) and ameliorate the detrimental impact of high uncertainty in monolingual data during the self-training process, a self-training NMT model based on priority sampling was proposed.
DU Xiaofeng +4 more
core +1 more source
Passive forensic based on spatio-temporal localization of video object removal tampering [PDF]
, 2020 To address the problem of identification of authenticity and integrity of video content and the location of video tampering area,a deep learning detection algorithm based on video noise flow was proposed.Firstly,based on SRM (spatial rich model) and C3D (
Guohua WU +5 more
core +1 more source
Wildlife Letters, Volume 4, Issue 1, Page 42-55, March 2026.This review summarizes the status of musk deer in China, highlighting severe population declines due to illegal hunting and habitat loss, and proposes integrated conservation strategies including habitat protection, captive breeding, and law enforcement to support the recovery and sustainable management of this ecologically and economically important ...
Feng Jiang +8 more
wiley +1 more source
Zhendong Ceshi yu Zhenduan针对动车组设备中滚动轴承故障预测实时性不强的问题，提出了基于增强节点更新的宽度神经网络方法。首先，采用宽度神经网络的方法对预处理之后的滚动轴承原始振动数据进行模型训练；其次，在训练过程中通过增加增强节点进行权值更新；最后，使用宽度网络对设置滑动窗口的数据进行预测并输出最终结果。动车组模拟实验台采集的滚动轴承故障数据的实验结果表明：模型训练时间得以缩短，预测时间控制在30 ms以内，达到实际工业设备预测要求；与传统深度学习相比，基于增强节点更新的宽度神经网络其预测准确性得以保障，且预测实时性优于其他方法。
doaj +1 more source
Gaoya dianqi, 2010 利用介质阻挡放电实验装置和测量系统研究了不同的介质层厚度、外加电压以及空气间隙距离的等离子体助燃（PAC）激励器放电特性,并在实验数据的基础上,根据介质阻挡放电等效电路对空气间隙上的两端电压、放电电流等参数进行了计算。结果表明,介质层的厚度对放电脉冲的次数的影响很大;随外加电压的增加,脉冲放电增加,放电的起始时刻不断提前;随着空气间隙距离的减小,激励器放电强度明显增强,放电更加均匀。
兰宇丹, 何立明, 丁伟
doaj
Wildlife Letters, Volume 4, Issue 1, Page 23-31, March 2026.American badgers, a medium‐sized carnivore occurring in much of North America, are important predators in prairie landscapes though our understanding of their habitat use requirements in these areas is unclear. We used a multi‐scale approach to understand American badger habitat use at both local and landscape scales.
Colleen W. Piper +5 more
wiley +1 more source
Zhejiang Daxue xuebao. Lixue banAiming at the problem of insufficient local feature extraction of general point cloud classification methods in fine-grained classification tasks, we propose a point cloud-oriented 3D model classification framework, HFE-Net.
白静(BAI Jing) +3 more
doaj +1 more source
Functional Ecology, Volume 40, Issue 3, Page 750-763, March 2026.Read the free Plain Language Summary for this article on the Journal blog. Abstract Forests worldwide are increasingly impacted by drought due to climate change, prompting plants to adapt through dehydration tolerance (DT) and avoidance (DA), two distinct physiological strategies.
Xingyun Liang +11 more
wiley +1 more source
智能科学与技术学报, 2019 首先提出了混合增强智能开放创新平台建设的总体目标以及面临的问题，提出了一种虚实系统互驱的平台架构方案。然后阐述了平台的基本形态，并详述了平台各层的模块机理和作用，以及涉及的关键技术，如人机交互技术、数据处理技术和数字虚拟工业技术。最后设计了开放创新的保障和激励机制，并探讨了区块链技术在混合增强智能开放创新平台数据安全方面的应用。
张俊 +7 more
doaj
Dianxin kexue随着元宇宙的兴起，扩展现实成为产业界重点关注的多媒体应用技术。为了逐步实现扩展现实，需要增强现有无线网络技术。首先介绍了扩展现实业务特点和在3GPP中的标准进展，探索了扩展现实业务对5G-Advanced网络提出的挑战，为了满足扩展现实业务的低功耗和高容量需求，研究了扩展现实业务感知技术、节能增强技术和容量增强技术，通过引入分组数据单元集参数、业务抖动等辅助信息实现业务感知，通过引入非整数周期、非连续接入播放器降低终端功耗，通过支持新缓冲状态表格、增强配置授权提升系统容量，通过仿真评估和性能分析 ...
肖扬
doaj +1 more source