基于深度学习的秀丽隐杆线虫显微图像分割方法

利用计算机实现自动、准确的秀丽隐杆线虫(C.elegans)的各项形态学参数分析,至关重要的是从显微图像上分割出线虫体态,但由于显微镜下的图像噪声较多,线虫边缘像素与周围环境相似,而且线虫的体态具有鞭毛和其他附着物需要分离,多方面因素导致设计一个鲁棒性的C.elegans分割算法仍然面临着挑战。针对这些问题,提出了一种基于深度学习的线虫分割方法,通过训练掩模区域卷积神经网络(Mask R-CNN)学习线虫形态特征实现自动分割。首先,通过改进多级特征池化将高级语义特征与低级边缘特征融合,结合大幅度软最大损失(LMSL)损失算法改进损失计算;然后,改进非极大值抑制;最后,引入全连接融合分支等方法对分割结果进行进一步优化。实验结果表明,相比原始的Mask R-CNN,该方法平均精确率(AP)提升了4.3个百分点,平均交并比(mIOU)提升了4个百分点。表明所提出的深度学习分割方法能够有效提高分割准确率,在显微图像中更加精确地分割出线虫体。     

DCS分布式冷却系统在通信基站的应用研究

针对基站柜式空调耗电量大的问题,创造性地使用基站分布式冷却的方式,达到精确送风,节能高效的目的.在应用实践中检验了分布式冷却系统实际节能量和应用效果,总结出分布式冷却系统应用场景和范围,为更大范围推广应用DCS分布式冷却系统提供实践依据.     

东兴铝业嘉峪关分公司铝灰渣循环利用研究

铝灰渣是铝熔铸过程中产生的废弃物。本文主要介绍了酒钢东兴铝业嘉峪关分公司铝灰渣的产生量、排放、利用情况、化学成分及表面特征,并简要介绍了铝灰渣、铝灰的循环利用途径。     

Fundamental Evaluation of Power Supply and Rectifiers for Wireless Power Transfer Using Magnetic Resonant Coupling

This paper provides a fundamental analysis of a power supply and rectifiers for wireless power transfer using magnetic resonant coupling (MRC). MRC enables efficient wireless power transfer over middle‐range transfer distances. MRC for wireless power transfer should operate at a high frequency in the industry science medical band, such as 13.56 MHz, because the size of the transfer device decreases at higher transfer frequencies. Therefore, the output frequency of the power supply on the transmitting side should be 13.56 MHz. In addition, the rectifier on the receiving side is operated at a high frequency. This paper focuses on the reflected power in the power supply and rectifiers. Thus, the parametric design method is clarified for the power supply, including a low‐pass filter to match the output, the impedance of the power supply with the characteristic impedance of the transmission line. In addition, the effects on the rectifiers of silicon carbide and gallium nitride diodes are confirmed by performing an experiment and a loss analysis.     

基于SoC的多轴驱控一体化平台设计

随着FPGA技术和电力电机技术的发展,FPGA+ARM的集成方式已经成为FPGA的发展方向.针对一体化多轴运动控制与驱动的特点,选用了集成双核ARM CPU与FPGA结合的Xilinx Zynq-7020全可编程System-on-chip(SoC)作为硬件平台,一个ARM CPU完成多轴的位置环、速度环和电流环的算法以及多轴轨迹生成,能同时完成伺服高级算法如谐振等,另一个ARM CPU完成交互功能,发挥FPGA高速运算的功能,完成6轴电流环流水线控制以及双采样双更新电流环算法.提高了系统整体带宽,实现多轴ns级同步精度以实现更精确的位置轨迹,驱控一体内部数据通过共享内存以及高速内部总线的方式进行交换,其传输速度更快、传输信息更加丰富.     

A practical reliability assessment approach and its application for pile-stabilized slopes using FORM and support vector machine

Bulletin of Engineering Geology and the Environment - Many uncertainties exist in pile-stabilized slopes which make their design substantially complicated. In this paper, a first-order reliability...     

A Student's t-based density peaks clustering with superpixel segmentation (tDPCSS) method for image color clustering

Image color clustering is a basic technique in image processing and computer vision, which is often applied in image segmentation, color transfer, contrast enhancement, object detection, skin color capture, and so forth. Various clustering algorithms have been employed for image color clustering in recent years. However, most of the algorithms require a large amount of memory or a predetermined number of clusters. In addition, some of the existing algorithms are sensitive to the parameter configurations. In order to tackle the above problems, we propose an image color clustering method named Student's t-based density peaks clustering with superpixel segmentation (tDPCSS), which can automatically obtain clustering results, without requiring a large amount of memory, and is not dependent on the parameters of the algorithm or the number of clusters. In tDPCSS, superpixels are obtained based on automatic and constrained simple non-iterative clustering, to automatically decrease the image data volume. A Student's t kernel function and a cluster center selection method are adopted to eliminate the dependence of the density peak clustering on parameters and the number of clusters, respectively. The experiments undertaken in this study confirmed that the proposed approach outperforms k-means, fuzzy c-means, mean-shift clustering, and density peak clustering with superpixel segmentation in the accuracy of the cluster centers and the validity of the clustering results.