For the dislribulion if mean error under independent but not identicallydislribuled conditions. its approximating dislribution whose precision reachO is obtained.
A new threshold secret sharing scheme is constructed by introducing the concept of share vector, in which the number of shareholders can be adjusted by randomly changing the weights of them. This kind of scheme overco...A new threshold secret sharing scheme is constructed by introducing the concept of share vector, in which the number of shareholders can be adjusted by randomly changing the weights of them. This kind of scheme overcomes the limitation of the static weighted secret sharing schemes that cannot change the weights in the process of carrying out and the deficiency of low efficiency of the ordinary dynamic weighted sharing schemes for its resending process. Thus, this scheme is more suitable to the case that the number of shareholders needs to be changed randomly during the scheme is carrying out.展开更多
文摘目的针对用于SAR(synthetic aperture radar)目标识别的深度卷积神经网络模型结构的优化设计难题,在分析卷积核宽度对分类性能影响基础上,设计了一种适用于SAR目标识别的深度卷积神经网络结构。方法首先基于二维随机卷积特征和具有单个隐层的神经网络模型-超限学习机分析了卷积核宽度对SAR图像目标分类性能的影响;然后,基于上述分析结果,在实现空间特征提取的卷积层中采用多个具有不同宽度的卷积核提取目标的多尺度局部特征,设计了一种适用于SAR图像目标识别的深度模型结构;最后,在对MSTAR(moving and stationary target acquisition and recognition)数据集中的训练样本进行样本扩充基础上,设定了深度模型训练的超参数,进行了深度模型参数训练与分类性能验证。结果实验结果表明,对于具有较强相干斑噪声的SAR图像而言,采用宽度更大的卷积核能够提取目标的局部特征,提出的模型因能从输入图像提取目标的多尺度局部特征,对于10类目标的分类结果(包含非变形目标和变形目标两种情况)接近或优于已知文献的最优分类结果,目标总体分类精度分别达到了98.39%和97.69%,验证了提出模型结构的有效性。结论对于SAR图像目标识别,由于与可见光图像具有不同的成像机理,应采用更大的卷积核来提取目标的空间特征用于分类,通过对深度模型进行优化设计能够提高SAR图像目标识别的精度。
文摘For the dislribulion if mean error under independent but not identicallydislribuled conditions. its approximating dislribution whose precision reachO is obtained.
基金supported by the National Preeminent Youth Foundation(70225002)the Doctor Foundation of North China Electric Power University(200822029).
文摘A new threshold secret sharing scheme is constructed by introducing the concept of share vector, in which the number of shareholders can be adjusted by randomly changing the weights of them. This kind of scheme overcomes the limitation of the static weighted secret sharing schemes that cannot change the weights in the process of carrying out and the deficiency of low efficiency of the ordinary dynamic weighted sharing schemes for its resending process. Thus, this scheme is more suitable to the case that the number of shareholders needs to be changed randomly during the scheme is carrying out.
