排序方式: 共有14条查询结果,搜索用时 15 毫秒
1.
为对光学薄膜缺陷图像进行准确识别分类,提出一种基于改进的卷积神经网络光学薄膜缺陷图像识别方法。为突出输入图像中的缺陷信息,采用改进的LBP算法对图像进行预处理。从三个方面对传统的卷积神经网络进行改进:为了解决单通道卷积神经网络对图像特征提取不充分的问题,构建双通道卷积神经网络;改进传统的ReLU激活函数,避免模型出现欠拟合现象;使用支持向量机(SVM)代替Softmax分类器,提高计算效率和准确率。光学薄膜缺陷图像仿真识别实验表明,所提方法分类平均准确率高达93.2%,训练时间为964 s,充分验证了所提方法的鲁棒性和有效性。 相似文献
2.
We propose an Interactive Message Authentication Protocol (IMAP) using two channels; an insecure broadband channel and an
authenticated narrow-band channel. We consider the problem in the context of ad hoc networks, where it is assumed that there
is neither a secret key shared among the two parties, nor a public-key infrastructure in place. The security of our IMAP is
based on the existence of Interactive-Collision Resistant (ICR) hash functions, a new notion of hash function security. Our
IMAP is based on the computational assumption that ICR hash functions exist. It performs better than message authentication
protocols that are based on computational assumptions. That is, while achieving the same level of security, the amount of
information sent over the authenticated channel in our IMAP is smaller than the most secure IMAP and Non-interactive Message
Authentication Protocol (NIMAP) in the literature. In other words, if we send the same amount of information over the authenticated
channel, we can allow much stronger adversaries compared to the existing protocols in the literature. Moreover, our IMAP benefits
from a simple structure and works under fewer security assumptions compared to other IMAPs in the literature. The efficient
and easy-to-use structure of our IMAP makes it very practical in real world ad hoc network scenarios. 相似文献
3.
最优PI控制器整定需要传递函数模型,且强调模型-90°在相位处的准确性。满足这种要求的模型化方法是应用PI控制器最优整定的关键步骤。为此,本文提出了一种基于双通道继电测试TRFT的相位相关闭环频域辨识策略。在该方法中,首先通过TRFT以闭环方式提取在指定相位的多点频率特性;其次,采用所提出的RNLS频域辨识算法估计过程对象的带有时滞的传递函数模型。最后的仿真取得了令人满意的结果,验证了所提出方法的有效性。本文所提出的建模方法与最优整定相结合构成了一个完整的工业应用框架。 相似文献
4.
本文研制了一种用来同时检测环境水中的阴、阳离子含量的全自动离子色谱仪。本文首先介绍了仪器的结构和电控系统,接着对仪器的性能进行了测试。应用该仪器对阴离子(F-、Cl-、NO2-、Br-、NO3-、H2PO4-、SO42-)和阳离子(Na+、NH4+、K+、Mg2+、Ca2+)的含量进行测定,各种离子的检出限(S/N=3)和相对标准偏差分别为0.0005 mg/L和1.20%,0.0007 mg/L和1.02%,0.0032 mg/L和0.98%,0.0023 mg/L和0.95%,0.0804 mg/L和0.78%,0.0051 mg/L和0.77%,0.0016 mg/L和0.75%,0.0021 mg/L和0.28%,0.0073 mg/L和0.33%,0.0229 mg/L和0.92%,0.0161 mg/L和0.17%,0.0190 mg/L和0.93%;样品的加标回收率在91.6%~104.0%之间。使用配对t检验,将自动进样法和手动进样法测定结果进行对比,结果显示没有显著差异。 相似文献
5.
An iterative approach for minimax design of multidimensional quadrature mirror filters 总被引:1,自引:0,他引:1
In this paper, a nest of iterative techniques is proposed for the minimax design of quadrature mirror filter (QMF) banks. The method can be generalized such that multidimensional QMF banks can be designed by the proposed algorithm. For a given weighting function, an iterative method is used to minimize the objective error function in the inner iterations. To further reduce the peak error of overall magnitude response, an iterative weighting-updated technique is adopted in the outer iterations. Comparing with the existing works concern the design of perfect-reconstruction QMF banks, only one of the filters is needed to be designed under the cost of magnitude distortion, but the system complexity can be reduced drastically. Several examples, including design of 2-D and 3-D QMF banks, will be presented to demonstrate the effectiveness of the proposed method. 相似文献
6.
本文介绍了一种适用于舰船航行速度测试的微波多普勒雷达方案。本方案采用连续波发射,零中频接收,使得组件前端电路简易,信号处理简单,并且采用IQ 正交双通道接收机方式保留了目标运动方向信息。另外,利用加速度测量芯片跟踪舰船由于海浪起伏引起的天线角度变化,从而可以精确测量舰船的即时水平行进速度。 相似文献
7.
基于双路AOTF的宽光谱成像技术在偏振成像光谱仪中得到应用,其成像质量受AOTF衍射效率、光谱带宽等影响。其核心部件超声换能器阻抗失配时导致驱动功率无法最大限度的传递给换能器,使AOTF光谱衍射效率降低,3dB光谱带宽变窄,影响光谱图像有用信息的获取。采用压缩回波损耗技术,设计了一种基于LC拓扑结构及组合臂的宽频带、光谱衍射效率高的新型匹配网络。最终测得AOTF的光谱衍射效率最高达94%,光谱带宽小于5nm,提高了在420~1150nm波段范围内的光谱衍射效率及分辨率,实测目标的成像质量得到明显改善。 相似文献
8.
9.
M. A. Mojumder 《Journal of Superconductivity and Novel Magnetism》2009,22(4):417-425
We have calculated the planar magnetoresistance of the doped cuprate superconductor in the ‘normal’ state; the results are
in agreement with the divergence of the magnetoresistance near T
c
, and other unexplained data. Argument and evidence have been known for assuming that the ‘normal’ state in the doped cuprate
is mainly a two-channel Kondo lattice. In the common moderately disordered nonstoichiometrically doped cuprate, in contrast with the fully ordered crystal, the two-channel Kondo fixed point is effectively stable.
相似文献
10.
This paper presents modeling and blind identification of human cardiovascular system. In contrast to the population-based methods widespread in current practice, the proposed method does not require any a priori knowledge of the cardiovascular system. This paper develops a human cardiovascular system model, analyzes its identifiability, and identifies the model using two diametric blood pressure measurements. The aortic blood pressure reconstructed using the identified model can eliminate the use of invasive aortic blood pressure measurement for cardiovascular monitoring. Results based on the data from a realistic human cardiovascular system simulator demonstrate the validity of the proposed model and identification method. 相似文献