Results 81 to 90 of about 17,971 (165)
TCGCL: Complex Network Traffic Classification Algorithm Based on Graph Contrastive Learning [PDF]
Network traffic classification technology plays a crucial role in the field of network security. Modern network architecture is highly complex, and various abnormal situations will inevitably be encountered during network traffic transmission.
HU Zhongze, QIN Hongchao, LI Zhenjun, LI Yanhui, LI Ronghua, WANG Guoren
core +1 more source
Dianci bileiqi, 1973 电力系统配电装置位于强烈雷电活动地区。以雷日和雷时表示的雷电强度列于表1。考虑强的雷电活动,所有的逐年增多的电力系统配电装置都用阀式避雷器来防护架空线路的大气过电压波。避雷器数量,正如图1所示,亦是逐年在增长。220、110和35仟伏避雷器通常装于变电站母线上和电力变压器与断路器之间。它们的动作数据如下:
汪仁根
doaj
[Epilepsy detection and analysis method for specific patient based on data augmentation and deep learning]. [PDF]
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, 2022 Yang Y, Qin X, Lin X, Wen H, Peng Y.
europepmc +1 more source
Shuitu Baochi Xuebao, 2017 利用遂宁水土保持试验站5个径流小区1984—2015年次降雨和径流输沙数据，基于降雨过程定量划分出4种雨型，分析了雨型对不同坡度坡耕地产流产沙的作用。结果表明：径流深与各时段最大雨强均呈极显著相关（p＜0.01），随着坡度的增加，最大相关系数所对应的雨强时段越短；冲刷量均与I平均呈极显著相关，且相关系数最大。径流深、冲刷量与雨强拟合关系均为幂函数，分别为“凸型”和“凹型”增函数，且拟合度区间分别为[0.79，0.88]和[0.90，0.97]，说明冲刷量和雨强的关系更密切 ...
马, 陈, 单志杰, 郎登潇, 廖
doaj
Backdoor defense method in federated learning based on contrastive training [PDF]
In response to the inadequacy of existing defense methods for backdoor attacks in federated learning to effectively remove embedded backdoor features from models, while simultaneously reducing the accuracy of the primary task, a federated learning ...
Bing CHEN +4 more
core +1 more source
Dizhen xuebao依据 《中国震例》 （1966—2017年）对1966年以来中国大陆东部MS＞6.0、西部MS＞7.0强震前地震活动增强的异常现象特征进行了系统的梳理，并试图总结不同活动构造地块周缘强震前地震活动增强的异常时空演化特征。结果显示：① 我国大陆大震前普遍存在地震活动增强现象，33个震例中有21个震例存在震前地震活动增强异常，占比达64%；② 西部地区大多数震例的地震活动增强空间范围表现为中间尺度或构造尺度，且主震震级越大，越有可能出现大范围的地震活动增强；③ 西部地区出现中强地震活动增强的概率高于东部地区，
Nan Hu +7 more
doaj +1 more source
Spectroscopic Method for Detection of Soluble Solid Content in Cherry Tomato Using Deep Convolutional Generative Adversarial Network-Based Data Augmentation [PDF]
Considering insufficient sample numbers in the practical detection of soluble solid content (SSC) in cherry tomato, we proposed a deep convolutional generation adversarial network (DCGAN) model to expand spectral data and SSC label data, and established ...
WU Zhijing, LIU Fuqiang, LI Zhigang, CHEN Hui
core +1 more source
Detection Method of X-ray Fuel Rod End Plug Defect Based on Deep Learning [PDF]
Amidst the global expansion of nuclear power generation, ensuring the integrity of nuclear fuel rods is crucial for the safe operation of nuclear power plants.
ZHANG Xiaogang, YU Dongbao, TANG Hui, ZHU Yongli
core +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 +4 more
doaj
Jianzhu Gangjiegou Jinzhan, 2022 设计了10个高强钢T形件的单向拉伸试验，分别研究了螺栓直径、螺栓线距、螺栓端距和钢材强度对T形件受拉力学性能的影响，试验结果表明：在试验参数范围内，T形件共产生螺栓破坏、联合屈服和翼缘屈服三种破坏模式；增大螺栓直径会显著提高T形件的初始刚度、屈服荷载、极限承载力和极限变形；增大螺栓线距有利于提高T形件的变形能力，但初始刚度、屈服荷载和极限承载力会有所降低；增加螺栓端距能小幅提高T形件的屈服荷载、极限承载力和极限位移，但对初始刚度影响不大；钢材强度对T形件的屈服荷载和极限承载力影响较大。另外 ...
陈潘 +4 more
doaj