结合深度学习与相关反馈的遥感图像检索

目的 针对基于内容的图像检索存在低层视觉特征与用户对图像理解的高层语义不一致、图像检索的精度较低以及传统的分类方法准确度低等问题，提出一种基于卷积神经网络和相关反馈支持向量机的遥感图像检索方法。方法 通过对比度受限直方图均衡化算法对遥感图像进行预处理，限制遥感图像噪声的放大，采用自学习能力良好的卷积神经网络对遥感图像进行多层神经网络的监督学习提取丰富的图像特征，并将支持向量机作为基分类器，根据测试样本数据到分类超平面的距离进行排序得到检索结果，最后采用相关反馈策略对检索结果进行重新调整。结果 在UC Merced Land-Use遥感图像数据集上进行图像检索实验，在mAP（mean average precision）精度指标上，当检索返回图像数为100时，本文方法比LSH（locality sensitive Hashing）方法提高了29.4%，比DSH（density sensitive Hashing）方法提高了37.2%，比EMR（efficient manifold ranking）方法提高了68.8%，比未添加反馈和训练集筛选的SVM（support vector machine）方法提高了3.5%，对于平均检索速度，本文方法比对比方法中mAP精度最高的方法提高了4倍，针对复杂的遥感图像数据，本文方法的检索效果较其他方法表现出色。结论 本文提出了一种以距离评价标准为核心的反馈策略，以提高检索精度，并采用多距离结合的Top-k排序方法合理筛选训练集，以提高检索速度，本文方法可以广泛应用于人脸识别和目标跟踪等领域，对提升检索性能具有重要意义。     

面向电信承载网的监控系统设计与实现

面对电信承载网连接的日益增长的海量终端设备，运营商需要结合网络拓扑对终端设备产生的数据进行高效的汇聚统计、异常分析、故障定位处理等操作。针对已有系统存在的操作困难、分析效率低等问题，设计与实现了一个面向电信承载网的高效监控系统，提供实时与离线数据分析和多维可视化分析的能力。对网管、认证、终端等系统及设备采集的数据进行结构化存储，对采集的数据进行拓扑相关性和时间序列方法分析，根据分析结果实现基于动态阈值控制的异常实时告警、定位等操作，并提供多维度可视化分析对网络状态进行实时监控。实际应用结果表明，该系统性能优异，具有良好交互性，能较好地满足承载网运维人员业务分析需求。     

Extended vertical lists for temporal pattern mining from multivariate time series

In this paper, the problem of mining complex temporal patterns in the context of multivariate time series is considered. A new method called the Fast Temporal Pattern Mining with Extended Vertical Lists is introduced. The method is based on an extension of the level‐wise property, which requires a more complex pattern to start at positions within a record where all of the subpatterns of the pattern start. The approach is built around a novel data structure called the Extended Vertical List that tracks positions of the first state of the pattern inside records and links them to appropriate positions of a specific subpattern of the pattern called the prefix. Extensive computational results indicate that the new method performs significantly faster than the previous version of the algorithm for Temporal Pattern Mining; however, the increase in speed comes at the expense of increased memory usage.     

Querying on large and complex databases by content: Challenges on variety and veracity regarding real applications

The amount and variety of digital data currently being generated, stored and analyzed, including images, videos, and time series, have brought challenges to data administrators, analysts and developers, who struggle to comply with the expectations of both data owners and end users. The majority of the applications demand searching complex data by taking advantage of queries that analyze different aspects of the data, and need the answers in a timely manner. Content-based similarity retrieval techniques are well-suited to handle large databases, because they enable performing queries and analyses using features automatically extracted from the data, without users’ intervention. In this paper, we review and discuss the challenges posed to the database and related communities in order to provide techniques and tools that can meet the variety and veracity characteristics of big and complex data, while also considering the aspects of semantical preservation and completeness of the data. Examples and results obtained over a two-decade-long experience with real applications are presented and discussed.     

Profiling of knowledge organisation systems for the annotation of Linked Data cultural resources

The importance of cultural heritage for supporting the knowledge economy has promoted its digitisation and online publication. Many cultural heritage repositories have published millions of digitised items using semantic web technologies and Linked Data approaches. These repositories frequently use knowledge organisation systems to classify the resources, but the domain heterogeneity makes it difficult to know if they are the most suitable ones. This paper describes the process used to discover and profile the knowledge organisation systems used in the cultural heritage domain. Additionally, for those knowledge organisation systems with a thesaurus-like structure, a detailed quality analysis is performed. The results of this analysis can be used as a key factor for the selection of knowledge organisation systems in classification tasks.     

Leveraging industrial statistics in the data revolution: The Youden Memorial Address at the 63rd Annual Fall Technical Conference

We are in the midst of a “Data Revolution” that is transforming our economy. This revolution is as large and profound as other major economic shifts from the introduction of the printing press to the Industrial Revolution. In this article, we compare the development of the field of Industrial Statistics as an outgrowth of the Machine Age to the development of the field of Data Science as an outgrowth of the Information Age. It is shown how the knowledge, skills, and abilities required for “Data Scientists” have evolved to support companies as they try to differentiate themselves in the Information Age. It is discussed how the unique skills that Industrial Statisticians possess can provide a transformative advantage to Data Scientists working in the Information Age. Advice is given on how to leverage Industrial Statistics in the midst of the Data Revolution so that we ethically and responsibly implement the tools of Data Science, address important problems, and inclusively educate future generations.     

Comprehensive Analysis of Secure Data Aggregation Scheme for Industrial Wireless Sensor Network

As an Industrial Wireless Sensor Network (IWSN) is usually deployed in a harsh or unattended environment, the privacy security of data aggregation is facing more and more challenges. Currently, the data aggregation protocols mainly focus on improving the efficiency of data transmitting and aggregating, alternately, the aim at enhancing the security of data. The performances of the secure data aggregation protocols are the trade-off of several metrics, which involves the transmission/fusion, the energy efficiency and the security in Wireless Sensor Network (WSN). Unfortunately, there is no paper in systematic analysis about the performance of the secure data aggregation protocols whether in IWSN or in WSN. In consideration of IWSN, we firstly review the security requirements and techniques in WSN data aggregation in this paper. Then, we give a holistic overview of the classical secure data aggregation protocols, which are divided into three categories: hop-by-hop encrypted data aggregation, end-to-end encrypted data aggregation and unencrypted secure data aggregation. Along this way, combining with the characteristics of industrial applications, we analyze the pros and cons of the existing security schemes in each category qualitatively, and realize that the security and the energy efficiency are suitable for IWSN. Finally, we make the conclusion about the techniques and approach in these categories, and highlight the future research directions of privacy preserving data aggregation in IWSN.     

航空物探遥感地质资料定密工作初探与实践

在地质调查信息化与地质资料社会化服务工作不断发展的背景下,航空物探遥感地质资料的开发利用与保密管理工作矛盾日益凸显。本文以航空物探遥感资料定密为研究重点,总结了地质、测绘地理信息、海洋等工作领域的定密工作情况,基于对航空物探遥感地质资料分类结果提取了共性资料涉密要素/事项,根据保密法规的相关规定与要求,初步建立了以比例尺/空间精度、测绘地理信息要素、航空物探遥感专业要素为主的定密判定要素集,提出了航空物探遥感地质资料的定密工作原则与参考准则,以期为航空物探遥感地质信息共享服务提供必要的工作支撑。     

模型驱动的大数据流水线框架PiFlow

复杂流程的大数据处理多依托于流水线系统，但大数据处理的流水线系统在易用性、功能复用性、扩展性以及处理性能等方面存在不足。针对上述问题，为提高大数据处理环境的构建与开发效率,优化处理流程，提出了一种模型驱动的大数据流水线框架PiFlow。首先，将大数据处理过程抽象为有向无环图；然后，开发一系列组件用于构建数据处理流水线，并设计了流水线任务执行机制。同时，为规范和简化流水线框架的描述，设计了基于模型驱动的大数据流水线描述语言——PiFlowDL，该语言以模块化、层次化的方式对大数据处理任务进行描述。PiFlow以所见即所得(WYSIWYG)的方式配置流水线，集成了状态监控、模板配置、组件集成等功能，与Apache NiFi相比有2~7倍的性能提升。     

基于决策树的堆芯物理参数预测研究

反应堆堆芯核设计涉及大量方案的搜索与详细计算，缩短方案搜索时间有利于提高核设计效率。数据挖掘技术通过对大量数据进行学习与模式识别，可实现核设计方案物理参数的快速预测，更快地筛选出可行的备选堆芯方案。本文基于数据挖掘的决策树4种算法：C4.5、RepTree、Random Forest及Random Tree，在计算时以燃料富集度、含可燃毒物燃料棒数量及含量作为自变量，以寿期内k_eff不均匀系数偏差（KUCD）、径向功率不均匀系数偏差（RPNCD）、径向中子通量不均匀系数偏差（RFNCD）、堆芯寿期（CL）作为目标函数，构成目标函数符合度（CPF），利用大量已知核设计参数的组件及堆芯设计方案作为数据挖掘训练集，构建数据挖掘模型，并用于对未知核设计参数的组件方案集合（测试集）进行CPF快速预测。结果表明，4种算法利用训练集构建数据挖掘模型的时间在0.6 s以内，各算法的交叉验证精度均在0.7以上，其中C4.5算法对CPF预测精度最高；对测试集方案的核设计参数预测中，单个方案的预测时间均在0.9 s以内，而Random Forest算法对CPF等于4的预测效果最好。