目的 精确估计热带气旋的强度有助于提升天气预报和预警的准确性。随着深度学习技术的不断发展，基于卷积神经网络（convolutional neural network，CNN）的方法已应用于强度估计任务中。然而，现有方法仍存在许多问题，例如无法充分利用不同波段的卫星图像信息、输入图像以热带气旋的定位为中心等限制，从而产生较大误差，影响实时估计的结果。针对以上问题，本文提出一种融合定位信息的强度估计网络IEFL（intensity estimation fusing location），提升强度估计的准确率。方法 模型采用双分支结构，能有效融合不同波段的图像特征，同时可以同步优化两个任务，达到互相促进的效果。此外，模型对强度估计任务做了定位的特征融合，将得到的定位特征图与强度特征图进行拼接，共同输出最后的强度结果，通过利用定位信息达到提升强度估计精度的目的。结果 本文在完成热带气旋强度估...

Abstract—Keyword Search is known as a user-friendly alternative for structured languages to retrieve information from graph-structured data. Efficient retrieving of relevant answers to a keyword query and effective ranking of these answers according to their relevance are two main challenges in the keyword search over graph-structured data. In this paper, a novel scoring function is proposed, w...

We discuss how the wireless-mobile revolution will change the notion of relevance in information retrieval. We distinguish between classical relevance (e-relevance) and relevance for wireless/mobile information retrieval (w-relevance). Starting from a fourdimensional model of e-relevance previously developed by one of us, we discuss how, in an ubiquitous computing environment, much more informa...