ID 原文 译文
19045 最后，利用相邻超像素间的色彩差异对过分割的超像素进行合并。 Finally, the over-segmented super pixels are merged based on the color differences between adjacent super pixels.
19046 为验证方法的有效性，该文采用Berkeley, Pascal VOC和3Dircadb公共数据库作为实验数据集，并与其他多种超像素分割方法进行了比较。实验结果表明，该文提出的超像素分割方法能更精确贴合图像目标边界，有效抑制图像过分割和欠分割。 Experiments on Berkeley, Pascal VOC and 3Dircadb databases, as well as comparison with other methods indicate that the proposed method can adhere to image boundaries more accurately, and can prevent over- and under- segmentations more effectively.
19047 相比于传统高阶时域有限差分算法(FDTD)而言，该文提出了一种改进的高阶FDTD的优化方法， Compared with the traditional high-order Finite Difference Time Domain(FDTD) Method, animproved high-order FDTD optimization method is proposed in this paper.
19048 该算法基于安培环路定律，通过计算机技术寻找到一组最优的系数使得FDTD方法的全局色散误差达到最小， This algorithm is based on Ampere’s law of circuits and finds a set of optimal coefficients through computer technology to minimize the global dispersion error of the FDTD method.
19049 通过不同分辨率下的点源辐射模拟证明了该方法在较低分辨率的情况下仍然具有极低的相位误差，对于解决电大尺寸结构建模中的数值色散等问题提供了有效的解决方案。 The simulation of point source radiation with different resolutions shows that this method still has very low phase error in the case of lower resolution. It provides an effective solutionto the problem of numerical dispersion in the modeling of large size structures.
19050 针对异构网络中D2D通信复用蜂窝用户频谱时存在的频谱分配问题，该文提出一种基于改进离散鸽群优化(PIO)算法的D2D通信资源分配机制。 For the problem of spectrum allocation in the multiplexing of cellular user spectrum resources byDevice-to-Device (D2D) communication in heterogeneous networks, a D2D communication resource allocation mechanism based on improved discrete Pigeon-Inspired Optimization(PIO) algorithm is proposed.
19051 通过设置信干噪比(SINR)门限值来保证用户的通信服务质量(QoS)，采用功率控制算法为用户设置发射功率，使用基于运动权值的二进制离散鸽群优化(MWBPIO)算法为D2D用户进行资源分配，并将D2D通信技术与中继技术进行有效结合，为边缘用户建立D2D中继链路，保证边缘用户的通信质量，最大化系统性能目标。 The user'sQuality of Service (QoS) is guaranteed by setting the Signal-to-Interference plus Noise Ratio (SINR) threshold,the transmitting power is set for users by power control algorithms. To allocate resources for D2D users, theBinary discrete PIO based on Motion Weight (MWBPIO) algorithm is used. To ensure the communicationquality of edge users, the D2D communication technology and relay technology are used to establish D2D relaylinks, so then the performance of system can be maximized.
19052 仿真结果表明，该方案有效抑制了异构通信系统中引入D2D用户后导致的干扰问题，提高了边缘用户的通信质量和系统的频谱利用率以及系统的能效。 Simulation results show that the proposed scheme can effectively suppress the interference caused by the introduction of D2D users in heterogeneous communication systems. Moreover, the proposed scheme can effectively improve the communication quality of edge users, and improve the utilization of spectrum resources and the performance of the system.
19053 在极限学习机(ELM)网络结构和训练模式的基础上，该文提出了相关熵融合极限学习机(CF-ELM)。 Based on the network structure and training methods of the Extreme Learning Machine (ELM),Correntropy-based Fusion Extreme Learning Machine (CF-ELM) is proposed.
19054 针对多数分类方法中表示级特征融合不充分的问题，该文将核映射与系数加权相结合，提出了能够有效融合表示级特征的融合极限学习机(F-ELM)。 Considering the problem that the fusion of representation level features is insufficient in most classification methods, the kernel mapping and coefficient weighting are combined to propose a Fusion Extreme Learning Machine (F-ELM), which can effectively fuse the representation level features.