基于数据质量评价的目标估计

针对目标估计过程需要大量人工参与、自动化程度低的问题，提出了基于数据质量评价的目标估计方法。利用目标数据质量评价方法，对不同传感器得到的目标数据质量进行科学、有效的测度和评价，并根据质量得分动态调整各数据源在目标估计过程中所占的权重，从而减少人工干预，提高目标估计效能。仿真试验结果证明了该方法的有效性。     

Mutual information maximizing GAN inversion for real face with identity preservation

Recent generative adversarial networks (GANs) have yielded remarkable performance in face image synthesis. GAN inversion embeds an image into the latent space of a pretrained generator, enabling it to be used for real face manipulation. However, current inversion approaches for real faces suffer the dilemma of initialization collapse and identity loss. In this paper, we propose a hierarchical GAN inversion for real faces with identity preservation based on mutual information maximization. We first use a facial domain guaranteed initialization to avoid the initialization collapse. Furthermore, we prove that maximizing the mutual information between inverted faces and their identities is equivalent to minimizing the distance between identity features from inverted and original faces. Optimization for real face inversion with identity preservation is implemented on this mutual information-maximizing constraint. Extensive experimental results show that our approach outperforms state-of-the-art solutions for inverting and editing real faces, particularly in terms of face identity preservation.     

控制爆破法处理卡钻事故

介绍了在包头市某工程实施管道穿越黄河施工中,采用爆破法处理卡钻的经验。针对深水环境条件及钻杆内径小不宜采用集团装药的条件,确定采用"小直径爆破筒,钻杆内部装药"的爆破方案,阐述了爆破设计及施工注意事项。可供类似工程参考。     

机器翻译译文质量估计综述

机器翻译译文质量估计(Quality Estimation,QE)是指在不需要人工参考译文的条件下,估计机器翻译系统产生的译文的质量,对机器翻译研究和应用具有很重要的价值。机器翻译译文质量估计经过最近几年的发展,取得了丰富的研究成果。该文首先介绍了机器翻译译文质量估计的背景与意义;然后详细介绍了句子级QE、单词级QE、文档级QE的具体任务目标、评价指标等内容,进一步概括了QE方法发展的三个阶段: 基于特征工程和机器学习的QE方法阶段,基于深度学习的QE方法阶段,融入预训练模型的QE方法阶段,并介绍了每一阶段中的代表性研究工作;最后分析了目前的研究现状及不足,并对未来QE方法的研究及发展方向进行了展望。     

IRS辅助的SWIPT系统中基于能效优先的波束成形设计与优化

以智能反射面(intelligent reflecting surface,IRS)辅助的无线携能通信(simultaneous wireless information and power transfer,SWIPT)系统为背景,研究了该系统中基于能效优先的多天线发送端有源波束成形与IRS无源波束成形联合设计与优化方法。以最大化接收端的最小能效为优化目标,构造在发送端功率、接收端能量阈值、IRS相移等多约束下的非线性优化问题,用交替方向乘子法(alternating direction method of multipliers,ADMM)求解。采用Dinkelbach算法转化目标函数,通过奇异值分解(singular value decomposition,SVD)和半定松弛(semi-definite relaxation,SDR)得到发送端有源波束成形向量。采用SDR得到IRS相移矩阵与反射波束成形向量。结果表明,该系统显著降低了系统能量收集(energy harvesting,EH)接收端的能量阈值。当系统总电路功耗为?15 dBm时,所提方案的用户能效为300 KB/J。当IRS反射阵源数与发送天线数均为最大值时,系统可达最大能效。     

Locating wind farm for power and hydrogen production based on Geographic information system and multi-criteria decision making method: An application

Hydrogen generation from renewable energy resources is considered as a suitable solution to solve the problems related to the energy sector and the reduction of greenhouse gases. The aim of this study is to provide an integrated framework for identifying suitable areas for the construction of wind farms to produce hydrogen. For this purpose, a combined method of Geographic Information System (GIS) and multi-criteria decision making (MCDM) has been used to locate the power plant in Yazd province. The GIS method in the present study consisted of two parts: constraints and criteria. The constraint section included areas that were unsuitable for the construction of wind farms to produce power and hydrogen. In the present study, various aspects such as physical, economic and environmental had been considered as constraints. In the criteria section, eight different criteria from technical aspects (including average wind speed, hydrogen production potential, land slope) and economic aspects (including distance to electricity grid, distance to urban areas, distance to road, distance to railway and distance to centers of High hydrogen consumption) had been investigated. The MCDM tool had been used to weigh the criteria and identify suitable areas. Analytic Hierarchy Process (AHP) technique was used for weighting the criteria. The results of AHP weighting method showed that economic criteria had the highest importance with a value of 0.681. The most significant sub-criterion was the distance to urban areas and the least significant sub-criterion was the distance to power transmission lines. The results of GIS-MCDM analysis had shown that the most proper areas were in the southern and central sectors of Yazd province. In addition, the feasibility of hydrogen production from wind energy had shown that this province had the capacity to generate hydrogen at the rate of 53.6–128.6 tons per year.     

基于CiteSpace的资源型产业研究知识图谱分析

资源型产业发展为推进国家经济增长和工业化进程提供了重要保障。为深入了解资源型产业的研究情况，以CNKI数据库为数据源，搜集2000—2020年关于资源型产业的核心及以上期刊论文，利用CiteSpace软件从发文作者与研究机构分布、关键词共现网络和时区图谱等方面，绘制知识图谱，进行可视化分析。研究发现：资源型产业领域的研究成果愈加丰富，但研究群体间联系合作较少，且现有的合作研究主要集中在所处地域资源富集和具有学科优势的研究机构及学者；资源型产业领域的研究热点可概括为产业发展、资源型城市、产业集群、产业结构、产业链和产业集聚等方面；针对资源型产业领域未来可从资源型产业相关理论研究、创新发展模式和可持续发展等方面深入展开。     

A Tradeoff Between Accuracy and Speed for K-Means Seed Determination

With a sharp increase in the information volume, analyzing and retrieving this vast data volume is much more essential than ever. One of the main techniques that would be beneficial in this regard is called the Clustering method. Clustering aims to classify objects so that all objects within a cluster have similar features while other objects in different clusters are as distinct as possible. One of the most widely used clustering algorithms with the well and approved performance in different applications is the k-means algorithm. The main problem of the k-means algorithm is its performance which can be directly affected by the selection in the primary clusters. Lack of attention to this crucial issue has consequences such as creating empty clusters and decreasing the convergence time. Besides, the selection of appropriate initial seeds can reduce the cluster’s inconsistency. In this paper, we present a new method to determine the initial seeds of the k-mean algorithm to improve the accuracy and decrease the number of iterations of the algorithm. For this purpose, a new method is proposed considering the average distance between objects to determine the initial seeds. Our method attempts to provide a proper tradeoff between the accuracy and speed of the clustering algorithm. The experimental results showed that our proposed approach outperforms the Chithra with 1.7% and 2.1% in terms of clustering accuracy for Wine and Abalone detection data, respectively. Furthermore, achieved results indicate that comparing with the Reverse Nearest Neighbor (RNN) search approach, the proposed method has a higher convergence speed.     

基于条件信息卷积生成对抗网络的图像识别

传统的图像识别方法需要大量有标签样本进行训练，且模型训练难以达到稳定。针对这些问题，结合条件生成网络和信息最大化生成网络的结构优势建立了条件信息卷积生成网络（C-Info-DCGAN）。模型增加图像的类别信息和潜在信息作为输入数据，然后利用Q网络去更好地发挥类别信息和潜在信息对训练的引导作用，并且利用深度卷积网络来加强对图像特征的提取能力。实验结果表明，该方法能够加快模型训练收敛速度，并有效提高图像识别的准确率。     

结合边缘特征先验引导的深度卷积显著性检测

针对当前基于深度学习的显著性检测算法缺少利用先验特征和边缘信息，且在复杂场景中难以检测出鲁棒性强的显著性区域的问题，提出了一种结合边缘特征，利用先验信息引导的全卷积神经网络显著性检测算法。该算法利用三种被经常用到的先验知识结合边缘信息形成先验图，通过注意力机制将提取的先验特征与深度特征有效融合，最终通过提出的循环卷积反馈优化策略迭代地学习改进显著性区域，从而产生更可靠的最终显著图预测。经过实验定性定量分析，对比证明了算法的可靠性。