Results 31 to 40 of about 5,293 (164)
Risk, Hazards &Crisis in Public Policy, Volume 15, Issue 2, Page 203-235, June 2024.Abstract Misinformation presents a challenge to democracies, particularly in times of crisis. One way in which misinformation is spread is through voice messages sent via messenger groups, which enable members to share information on a larger scale. Gaining user perspectives on digital misinformation interventions as countermeasure after detection is ...
Katrin Hartwig +2 more
wiley +1 more source
Gaoya dianqi, 2023 高压断路器分合闸操作伴随的电流、振动信号特征与电气和机械状态息息相关。提出一种线圈电流和振动信号联合分析的断路器操动机构故障诊断方法，针对线圈电流“双峰状”特点，提取关键时序特征和刻画波形畸变的波形特征。为捕捉振动信号细节变化，对振动信号进行自适应噪声集合经验模态分解CEEMDAN后，进一步计算各分量的时频分布，得到时间、频率边缘特征。将电流和振动特征组成的高维特征由因子分析进行降维处理，作为支持向量机SVM的输入进行故障诊断。实验表明，该方法能够有效提升断路器典型故障诊断准确率，且时间开销较少 ...
包伟川 +4 more
doaj
Deep Learning-based Marine Target Detection Method with Multiple Feature Fusion [PDF]
Considering the problem of radar target detection in the sea clutter environment, this paper proposes a deep learning-based marine target detector.
Chuanfei ZANG +4 more
core +1 more source
Challenges in humanitarian response implementation: a large‐scale review of aid worker perspectives
Disasters, Volume 48, Issue 2, April 2024.Aid workers offer important perspectives for understanding better the most pervasive challenges that arise when implementing emergency response programming in humanitarian settings. This large sample study provides a global review of these perspectives, derived from 4,679 applications to the National NGO Program on Humanitarian Leadership, in which aid
Vincenzo Bollettino +6 more
wiley +1 more source
, 2018 针对航天器传动链机械零部件发生故障时训练数据稀缺以及信号的强非平稳\非线性特点,提出了动态数据驱动的子空间稀疏多分类智能故障诊断算法。首先对采集的单一传感器动态信号进行分形小波变换,生成常规和非常规二进小波尺度。然后对生成的各子空间提出基于故障能量指标的稀疏多分类器,以监测部件的故障特征频率为搜索目标,在子空间的包络解调谱上计算特征频率及其倍频附近的能量峰值,导出特定故障模式的稀疏评价指标,以各种故障模式的最大值识别和判定故障类型。所提出的算法完全实现了无人工监督的智能故障诊断 ...
何昱超 +4 more
core
Dianci bileiqi, 2016 绝缘子发生污秽放电时的声信号中含有大量能够体现绝缘子污秽程度的信息量,利用傅里叶变换（FFT）将声信号分解为时域和频域两部分,研究在不同污秽度下声信号的时频特性,发现声信号的时域的平均值和频域的频谱特性两方面含有4个特征量,这4个特征量充分体现了绝缘子污秽放电的发展特征。分析得出,声信号时域的均值、最大值、标准差及FFT实部幅值这4个特征量与绝缘子污秽度具有很好的关联性,但是4个特征值对污秽预测结果的影响不尽相同。试验结果表明,绝缘子污秽放电声信号的4个特征量可以作为新的污闪预警特征量。
王洪坤, 聂晶
doaj
Sequential image deep learning-based Wi-Fi human activity recognition method [PDF]
, 2020 For the problems existing in most of the researches,such as weak anti-noise ability,incompatible signal size and insufficient feature extraction of deep-learning-based Wi-Fi human activity recognition,a kind of sequential image deep learning-based ...
Deshuai HAN +3 more
core +1 more source
Gaoya dianqi, 2018 根据目前基于100 MS/s超宽带检测实现多局放源识别和干扰抑制依据的局部放电波形特征提取及分类,指出实现此系统的关键技术为脉冲群波形的快速特征提取。其一般通过对脉冲群时、频域波形进行非线性映射,形成特征参数的2D平面或3D空间,再进行无监督聚类分析即可实现局放源间和噪声源的分离。针对目前应用较多的等效时频法,提出了时频自相法和时频熵法,基于指数模型和蒙特卡洛法产生仿真脉冲群,对上述3种时频算子进行了特征参数2D平面和3D空间的可分类性评定。可分类性测度值表明 ...
魏本刚, 姚周飞, 贺林, 李悦
doaj
Radar Intelligent Processing Technology and Application for Weak Target [PDF]
Weak target signal processing is the cornerstone and prerequisite for radar to achieve excellent detection performance. In complex practical applications, due to strong clutter interference, weak target signals, unclear image features, and difficult ...
Jian GUAN +7 more
core +1 more source
基于时频分布图像纹理特征的局部放电特高频信号的特征参数提取方法
Gaoya dianqi, 2017 针对局部放电特高频（ultra-high frequency,UHF）信号畸变导致模式识别准确率下降的问题,提出了基于时频分布图像纹理特征的特征参数提取方法。首先对局部放电UHF信号进行s变换得到时频分布图像,然后采用灰度共生矩阵（gray-level co-occurrence matrix,CLCM）算法,从时频分布图像中提取出纹理特征参数。采用主成分分析（principal component analysis,PCA）法对由纹理特征参数构成的特征向量进行降维处理 ...
田妍 +5 more
doaj