Explore the vast range of titles available.

为了使数据驱动模型能够实现降雨径流过程的高精度连续模拟,本文提出了新型耦合数据驱动模型（基于偏互信息的输入变量选择、基于新型集成神经网络模型的出流量预测和基于K最近邻算法的出流量误差预测-PBK模型）.PBK模型有以下4个特点.

随着全球气候变化和城市化进程的加剧，暴雨-洪涝灾害呈现出突发性强、预见期短的特征，其时空变化的复杂性和不确定性日益突出，暴雨-洪涝灾害的模拟预警已经成为国际学术研究的热点前沿。大量已有研究基于稳定环境的理论假设，采用静态数据驱动的被动式模拟方法导致“数据滞后、分析滞后和决策滞后”的问题日益突出。

大洋钻探资料证实,现代海底多金属硫化物分布范围广泛、储量大,是具有巨大开发潜力和远景的海底矿产资源。根据水深、地质构造、扩张速率、地球物理以及火山地震等区域性调查数据,分析了印度洋中脊多金属硫化物成矿地质条件、控矿因素和地球物理异常信息,提取了9项找矿证据因子,建立了区域找矿有利条件组合模型。运用证据权重法,对印度洋中脊多金属硫化物资源进行了基于数据驱动的定量预测与评价。研究认为,最有利区(Ⅰ类)占工区面积的29.77%,比较有利区(Ⅱ类)占18.12%。

Obtaining the real-time fatigue crack length of a metallic structure is the prerequisite of the fatigue life monitoring and residual life estimation for an aircraft. This paper proposed a metallic structure's fatigue crack prediction model using strain monitoring data based on deep learning method. A cycle consistent adversarial network was developed to map the strain monitoring data from experimental measurement with those from finite element modeling. A crack size classification model and a crack length quantification model were proposed to classify the crack size range and identify the exact crack length, respectively. The proposed model was applied to predict the fatigue crack growth in centeral hole metallic plates subjected to random loading spectrum. The results showed that the prediction is effective and accurate. 实时获取金属结构的疲劳裂纹长度是开展飞机单机寿命监控和剩余寿命估算的基础。采用深度学习方法, 提出了一种基于应变监控数据的金属结构疲劳裂纹长度预测模型, 通过构造循环对抗网络模型、裂纹尺寸的分类模型和裂纹长度的量化模型, 分别实现了含裂纹结构的应变试验数据与有限元模型数据的映射、裂纹尺寸范围的准确分类、裂纹长度的精确量化。将上述方法应用于中心带孔金属板在随机载荷谱下的疲劳裂纹监测, 有效实现了疲劳裂纹长度的实时预测。与试验结果对比表明, 单孔板的孔边疲劳裂纹长度预测误差小于1 mm, 满足工程实际的需求。

The objective of this study is to quantitatively evaluate Tropical Rainfall Measuring Mission （TRMM） data with rain gauge data and further to use this TRMM data to drive a Dis- tributed Time-Variant Gain Model （DTVGM） to perform hydrological simulations in the semi-humid Weihe River catchment in China. Before the simulations, a comparison with a 10-year （2001-2010） daily rain gauge data set reveals that, at daily time step, TRMM rainfall data are better at capturing rain occurrence and mean values than rainfall extremes. On a monthly time scale, good linear relationships between TRMM and rain gauge rainfall data are found, with determination coefficients R2 varying between 0.78 and 0.89 for the individual stations. Subsequent simulation results of seven years （2001-2007） of data on daily hydro- logical processes confirm that the DTVGM when calibrated by rain gauge data performs better than when calibrated by TRMM data, but the performance of the simulation driven by TRMM data is better than that driven by gauge data on a monthly time scale. The results thus suggest that TRMM rainfall data are more suitable for monthly streamfiow simulation in the study area, and that, when the effects of recalibration and the results for water balance components are also taken into account, the TRMM 3B42-V7 product has the potential to perform well in similar basins.

The paper by Fang et al. proposes a data-driven approach based on a bootstrapping framework to jointly extract feature and opinion words with weak supervision. This is very important for fine granular sentiment analysis. Experiments on two different datasets （Dianping and Douban） demonstrate the advantage of the proposed method.

Today＇s ubiquitous online social networks serve multiple purposes, including social communication （Face- book, Renren）, and news dissemination （Twitter）. But how does a social network＇s design define its functionality？ An- swering this would need social network providers to take a proactive role in defining and guiding user behavior. In this paper, we first take a step to answer this question with a data-driven approach, through measurement and anal- ysis of the Sina Weibo microblogging service. Often com- pared to Twitter because of its format, Weibo is interesting for our analysis because it serves as a social communication tool and a platform for news dissemination, too. While similar to Twitter in functionality, Weibo provides a distinguishing feature, comments, allowing users to form threaded con- versations around a single tweet. Our study focuses on this feature, and how it contributes to interactions and improves social engagement. We use analysis of comment interactions to uncover their role in social interactivity, and use comment graphs to demonstrate the structure of Weibo users interac- tions. Finally, we present a case study that shows the impact of comments in malicious user detection, a key application on microblogging systems. That is, using properties of com- ments significantly improves the accuracy in both modeling and detection of malicious users.

Software systems have played critical roles in scientific research, business, and society. Research on software systems focuses on construction, operation, maintenance, and assessment of software systems. This special section is an effort to encourage and promote research to address challenges from the perspective of software systems. The goal of this special section is to present state-of-the-art and high-quality original research in the area of software systems. This special section includes two major themes： software testing and analysis, and data-driven software engi- neering. Software Testing and Analysis. The theme of software testing and analysis encompasses all the research chal- lenges that concern software quality achieved through software testing and analysis techniques that contribute in detecting/fixing defects in the end-product software. The ever increasing diversity, ubiquity, and dynamism of modern software systems are making such software testing and analysis more challenging.

A kind of adaptive sliding model control algorithm is developed to solve and improve the mathematical model dependency and un-modeled dynamics of a controlled system. The control strategy derived from a kind of data-driven control method in essence, thereby the input and output data are utilized by the controller with no information about the control system model. Theoretical analysis proves that this proposed control algorithm can improve the utilization of the estimated pseudo partial derivative information and accelerate the velocity of the convergence. The stability of the control system is further verified by rigorous mathematical analysis. This new discrete-time nonlinear systems model-free control algorithm obtained better control performance through the simulations for the linear motor position and the information tracking speed, which also achieved robust and accurate traceability.