ID	原文	译文
53827	本文首先对单用户多基站计算卸载问题，采用拉格朗日乘子法对其进行求解;	We start from the single user multi-cell computation offloading problem solved by the Lagrange multiplier method.
53828	然后针对多用户多基站场景，考虑用户的基站选择以及边缘服务器计算资源的竞争，基于定义的选择函数对接入基站进行选择，采用次优的迭代启发式算法对单用户场景下的卸载决策做出动态修正，获得卸载决策和边缘服务器资源分配。	Secondly, for the multi-user multi-base station scenario, considering the user's selection of base station and the competition of computing resources of edge server, the access base station is selected based on the defined selection function, and the suboptimal iterative heuristic algorithm is adopted to make the dynamic correction for the offloading decision in the single-user scenario, so as to obtain the offloading decision and resource allocation of the edge server.
53829	仿真结果表明，提出的计算卸载及资源分配算法能有效的降低任务完成的时延与终端的能耗。	Simulation results show that the proposed algorithm can effectively reduce the task completion delay and terminal energy consumption.
53830	网络社交的流行与普及，使得微博等短文本区别于以往传统文章，具有了独有的文学表达形式和情感发泄方式，导致基于短文本的机器学习情感分析工作难度逐渐增大。	Online social networks have gradually become popular and popularization. A number of social networks such as microblog have formed a unique form of literary and emotional expression. Because the expression of microblog is different from the expression of traditional articles, the sentiment analysis research based on short-text machine learning has become more and more difficult.
53831	针对微博短文本的语言表达新特性，爬取收集大量无情感标记微博数据，建立微博短文本语料库，基于全局语料库构建词与短文本的全局关系图，使用BERT(Bidirectional Encoder Representations from Transformers)文档嵌入作为图节点的特征值，采用图卷积进行节点间的特征传递和特征提取。	Aiming at the new features of Microblog short text language expression, we crawl and collect a large amount of non-emotionally labeled Microblog data, and build a Microblog short text corpus to create a global relationship graph between words and short texts. The BERT(Bidirectional Encoder Representations from Transformers) document embedding is used as the feature value of the graph node, and graph convolution is used for feature transfer and feature extraction between nodes. We manually annotate non-emotionally labeled Microblog data which sample from the whole Microblog short text corpus.
53832	采样部分无情感标记微博数据进行人工标注，采用半监督机器学习方法结合全局关系图提高情感分类器的性能，实验表明通过无情感标记数据比例的增加，该方法可以更好地捕捉全局特征，提高情感分类的精度。	A semi-supervised machine learning method combined with global relationship graph is proposed to improve the performance of sentiment classifier. Experiments show that by increasing the proportion of unmarked data, the method can better capture global features and improve the accuracy of sentiment classification.
53833	在自建人工标记数据、COAE2014数据集和NLP&CC2014数据集上进行了对比实验，实验结果表明该方法在精确率和召回率上均具有很好的表现。	Comparative experiments are carried out on self-built artificial labeling data, COAE2014 data set and NLP&CC2014 data set. The experimental results show that the method has a good performance in accuracy and recall.
53834	传统基于单机的合成孔径雷达(Synthetic Aperture Radar，SAR)图像舰船目标检测需要在本地计算机上进行数据下载、处理和分析，这极大受限于本地计算机的性能，只能对少量SAR图像进行检测。	The traditional ship target detection in Synthetic Aperture Radar image based on stand-alone computer requires data download, processing and analysis on the local computer, which is greatly limited by the performance of the local computer and can only be detected in a small number of SAR images.
53835	本文利用Google Earth Engine(GEE)遥感云计算平台的海量数据存储和强大运算能力，通过在云端部署SAR卫星数据、模型算法和计算机算力，在GEE平台上进行了大范围海域的海量舰船目标SAR图像处理应用研究，	This paper makes use of the Google Earth Engine remote sensing cloud computing platform of massive data storage and powerful computing power, through the deployment of SAR satellite data, model algorithms and computer computing power in the cloud, carried out the SAR image processing application research of massive ship targets in a large range of sea areas on the GEE platform.
53836	实现了舰船目标检测同时还可以获取舰船目标信息、统计舰船目标数量、批量下载目标检测结果图像等。	It realizes ship target detection and can also obtain ship target information, count the number of ship targets, and download target detection result images in batches.