共查询到20条相似文献,搜索用时 15 毫秒
1.
2.
3.
4.
5.
6.
根据细胞神经网络(CNN)数学模型,提出一种新的彩色图像边缘检测方法。新方法继承了CNN的优点,解决了CNN现有算法不能直接检测彩色图像边缘的问题。该方法充分利用图像中的颜色信息,通过欧几里得距离度量像素之间的差异,使CNN方程可以在RGB彩色空间中进行运算。对CNN模板进行理论分析和鲁棒性研究,提出一个实现彩色图像边缘检测功能要求的CNN鲁棒性定理,为设计相应的CNN模板参数提供了解析判据。实验结果表明,该方法可以对彩色图像进行有效的边缘提取,定量评价验证了CNN边缘检测定位准确的优点。 相似文献
7.
8.
With the spreading of radar emitter technology, it is more difficult for traditional methods to recognize radar emitter signals. In this article, a new method is proposed to establish a novel radial basis function (RBF) neural network for radar emitter recognition based on Rough Sets theory. First of all, radar emitter signals describing words are processed by Rough Sets, and the importance weight of each attribute is obtained and the classification rules are extracted. The classification rules are the basis of initial centers of Rough k-means. These initial centers can reduce the computational complexity of Rough k-means efficiently because of a priori knowledge from Rough Sets. In addition, basis functions of neural units of an RBF neural network are improved with attribute importance weights based on Rough Sets theory. The novel network structure makes the RBF neural network more effective. The simulation results show that novel RBF neural network radar emitter recognition can recognize radar emitter signals more effectively than a traditional RBF neural network, because of the improved Rough k-means and the network structure with attribute importance weights. 相似文献
9.
Liangliang Li Yujuan Si Zhenhong Jia 《International journal of imaging systems and technology》2018,28(2):124-131
In this article, a novel brain image enhancement approach based on nonsubsampled contourlet transform (NSCT) is proposed. First, the image is decomposed into a low‐frequency component and several high‐frequency components by the NSCT; Second, the gamma correction is applied to deal with the low‐frequency sub‐band coefficients, and the adaptive threshold is used to remove the noise of the high‐frequency sub‐bands coefficients; Third, the inverse nonsubsampled contourlet transform is adopted to reconstruct the processed coefficients; Finally, the unsharp filter is used to enhance the reconstructed image. The experimental results demonstrate that the performance of the proposed method is superior to the state‐of‐the‐art algorithms in terms of brain image enhancement. 相似文献
10.
Yaochen Sheng LuFang Zhang Feng Li Xinyu Chen Zhijian Xie Haiyan Nan Zihan Xu David Wei Zhang Jianhao Chen Yong Pu Shaoqing Xiao Wenzhong Bao 《材料科学技术学报》2021,69(10):15-19
Contact engineering is of critical importance for two-dimensional (2D) transition metal dichalcogenide(TMD)-based devices. However, there are only a few solutions to overcome this obstacle because of the complexity of the TMD-contact interface. In this work, we propose a novel method using a soft plasma treatment followed by the seamless deposition of a metal electrode to reduce the contact resistance of MoS_2 field effect transistors(FETs). The treated FETs exhibit three times higher mobility than the control FETs without plasma treatment. The soft plasma treatment can remove the facial sulfur atoms and expose the middle Mo atoms so that they come into direct contact with the metal electrode, thus greatly improving the contact behavior. First-principles calculation is also performed to support the experimental results. Our potentially scalable strategy can be extended to the whole family of TMD based FETs to provide a possible route of device processsing technology for 2D device application. 相似文献
11.
12.
研究了利用特殊的正弦扫频技术识别非线性参数的方法。该方法利用目前线性系统成熟的模态分析技术,并结合等效线性化理论,通过振动测试识别结构的非线性参数,可以建立一个更加准确的模型来反映非线性结构的动力学特性,从而提高模型的预测精度。该方法包括两部分:(1)常位移测试识别非线性刚度;(2)常速度测试识别非线性阻尼。常位移测试是在一次正弦扫频过程中,通过调整各频率下的激励力幅值使得位移响应的幅值为常数,获得一组频响函数,通过模态分析获得等效刚度;改变位移响应的幅值进行多次测试,获得多组等效刚度;对获得的一系列恒定位移响应下的等效刚度进行曲线拟合,即可获得所有线性和非线性刚度参数。常速度测试与其类似。以三自由度非线性系统为例,进行了常位移测试和 相似文献
13.
Organising and optimising production in small and medium enterprises with batch production and many different products can be very difficult due to high complexity of possible solutions. The paper presents a method of fine layout planning that rearranges production resources and minimises work and material flow transfer between production cells. The method is based on self-organising map clustering which organises the production cells into groups sharing similar product properties. The proposed method improves the internal layout of each cell with respect to a material flow diagram and a from-to matrix, and fine workspace positioning also considers various restrictions on placement, specifications and types of transportation. The method is particularly suitable for improving the existing layouts. The method was applied in the Slovenian company KGL d.o.o. and promising results were achieved. A reduction by more than 40% in the total transport length with respect to the current production layout was observed. 相似文献
14.
针对现有的产品结构模块划分方法的不足,将复杂网络理论中的社团结构发现方法应用于产品结构模块的划分,提出了一种新的结构模块划分方法.产品的结构单元作为网络的节点,有关联的结构单元对应的节点之间为网络的边,从而构建产品结构的网络图,使用复杂网路理论中的社团结构发现方法——GN算法实现结构模块的划分.论文阐述了基于GN算法的模块划分的方法与步骤,在此基础上以汽车发动机的结构模块划分为例验证了该方法的有效性和实用性,并对模块划分结果进行了分析,最后指出了今后进一步研究的内容与方法. 相似文献
15.
16.
《成像科学杂志》2013,61(7):529-540
AbstractMedical image fusion plays an important role in clinical applications, such as image-guided surgery, image-guided radiotherapy, non-invasive diagnosis and treatment planning. Shearlet is a novel multi-scale geometric analysis (MGA) tool proposed recently. In order to overcome the drawback of the shearlet-based fusion methods that the pseudo-Gibbs phenomenon is easily caused around the singularities of the fused image, a new multi-modal medical image fusion method is proposed in shift-invariant shearlet transform domain. First, the original images are decomposed into lowpass sub-bands and highpass sub-bands; then, the lowpass sub-bands and high sub-bands are combined according to the fusion rules, respectively. All the operations are performed in shift-invariant shearlet domain. The final fused image is obtained by directly applying inverse shift-invariant shearlet transform to the fused lowpass sub-bands and highpass sub-bands. Experimental results demonstrate that the proposed method can not only suppress the pseudo-Gibbs phenomenon efficiently, but perform better than the popular wavelet transform-based method, contourlet transform-based method and non-subsampled contourlet transform-based method. 相似文献
17.
18.
水声目标智能识别是水声装备智能化的重要组成部分,深度学习则是实现水声目标智能识别的重要技术手段之一。当前水声目标智能识别经常面临数据集较小带来的训练样本量不足的情况,针对小数据集识别中存在的因过拟合导致模型泛化能力不足,以及输入的水声信号二维谱图样式不统一的问题,文章提出了一种基于VGGish神经网络模型的水声目标识别方法。该方法以VGGish网络作为特征提取器,并在VGGish网络前部加入了信号预处理模块,同时设计了一种基于传统机器学习算法的联合分类器,通过以上措施解决了过拟合问题和二维谱图样式不统一问题。实验结果显示,该方法应用在ShipsEar数据集上得到了94.397%的识别准确率,高于传统预训练-微调法得到的最高90.977%的准确率,并且在相同条件下该方法的模型训练耗时仅为传统预训练-微调方法的0.5%左右,有效提高了识别准确率和模型训练速度。 相似文献
19.
20.
An opportunistic replacement policy for a multi-unit system with various failure rates is developed. The objective function is to minimize the total maintenance cost due to preventive and failure replacement. Failure rate is used as replacement criterion for each unit. Units are replaced at failure or at a failure rate limit, L, whichever occurs first. A unit is also replaced at replacement time of another unit if its failure rate falls in a preventive replacement interval, (L-u, L). A solution method to obtain the value of and u is presented. The solution procedure is demonstrated through an algorithm followed by a numerical example. 相似文献