Study on Recognition Method of Similar Weather Scenes in Terminal Area

Weather is a key factor affecting the control of air traffic. Accurate recognition and classification of similar weather scenes in the terminal area is helpful for rapid decision-making in air traffic flow management. Current researches mostly use traditional machine learning methods to extract features of weather scenes, and clustering algorithms to divide similar scenes. Inspired by the excellent performance of deep learning in image recognition, this paper proposes a terminal area similar weather scene classification method based on improved deep convolution embedded clustering (IDCEC), which uses the combination of the encoding layer and the decoding layer to reduce the dimensionality of the weather image, retaining useful information to the greatest extent, and then uses the combination of the pre-trained encoding layer and the clustering layer to train the clustering model of the similar scenes in the terminal area. Finally, terminal area of Guangzhou Airport is selected as the research object, the method proposed in this article is used to classify historical weather data in similar scenes, and the performance is compared with other state-of-the-art methods. The experimental results show that the proposed IDCEC method can identify similar scenes more accurately based on the spatial distribution characteristics and severity of weather; at the same time, compared with the actual flight volume in the Guangzhou terminal area, IDCEC's recognition results of similar weather scenes are consistent with the recognition of experts in the field.     

Asymptotic switched composite adaptive control with application to robotic interaction tasks

This article proposes a new switched adaptive control design for uncertain switched systems with composite (time-driven and state-dependent) switching and shows its applicability in switched impedance control. A composite switched adaptive control design, consisting of the direct switched adaptive control and the indirect switched adaptive control counterpart, is developed to improve the control performance. Specifically, a new stability condition for composite switching is proposed by making use of differential matrix equations and Sylvester matrix equations, which are a generalization of Lyapunov matrix equations. The design results in a time-varying multiple Lyapunov function that is decreasing at the switching instants. From the theoretical point of view, the relevance of this work is the construction of the adaptive laws that guarantee asymptotic tracking error and asymptotic estimation for the direct and indirect switched adaptive control loops, respectively. From the practical point of view, the relevance of this work is validated in a new switched impedance control for the robot interaction with uncertain and discontinuous environments.     

Robust integrated sequential covariance intersection fusion Kalman filters and their convergence and stability for networked sensor systems with five uncertainties

For networked sensor systems (NSSs) with hard and soft sensors including five uncertainties, two universal approaches of solving the robust fusion estimation problems are presented. It includes an integrated sequential covariance intersection (SCI) fusion minimax robust Kalman filtering approach with cross-covariance information and a generalized Lyapunov equation approach with four pairs of Lyapunov equations. Applying them, the robust local and SCI fused time-varying and steady-state Kalman filters are presented in the sense that their actual estimation error variances are guaranteed to have the corresponding minimal upper bounds. The equivalent batch SCI fusers are also presented. Their robustness and accuracy relations are proved, and the sensitivity of the SCI fuser with respect to the fused orders of sensors is analyzed. Applying the dynamic error system analysis method and the dynamic variance error system analysis method, a new convergence and absolute asymptotic stability theory of robust fusion Kalman filtering is presented. The classical Kalman filtering convergence and stability theory is developed. Compared with the original covariance intersection fuser, they significantly reduced the computational complexity and burden. Compared with the optimal and conservative SCI fusers, they significantly improved the robust accuracies. They are suitable to deal with asynchronous or random delayed data and are suitable for real-time applications. A simulation applied to the two-mass spring damper mechanical system shows their effectiveness.     

面向Kubernetes的容器立体化监控系统

容器监控是保证容器基础设施正常运行的核心要素之一,然而当前容器监控角度较为单一,尚缺少直观有效的方法协助运维人员快速定位业务容器异常原因.本文设计并实现了一个面向Kubernetes的容器立体化监控系统,通过监控指标相关性分析,把相关性较强的指标作为立体化监控的核心指标提供给运维人员,更好地实现对容器的全局统筹监控.     

基于之字形解码算法优化的高效低存储ZD码

ZD码(ZigZag-decodable codes)是基于之字形解码算法设计生成的一类纠删码, 它仅需要少量的计算即可修复存储系统中的故障数据, 但需要存储相对其他纠删码更多的冗余数据以保证系统的高可靠性. 为了降低ZD码产生的存储开销, 本文通过分析当前在存储系统中使用的之字形解码的思想, 提出了一种优化的之字形解码算法. 新的解码算法能够更充分利用校验数据中的信息来完成数据修复. 基于新的解码算法, 本文相应的提出了一种新的ZD码编码方案, 由于新算法更高的信息利用率, 新的编码方案能够用更少的存储开销来满足存储系统的高可靠性. 实验结果表明, 本文提出的ZD码编码方案具有最优的存储开销, 且编解码性能远高于目前广泛使用的RS码.     

数字孪生技术在智慧水利工程中的应用

水利工程是我国促进经济发展的重要设施,应重视水利工程的稳定以及运行安全。数字孪生技术能够为智慧水利工程建设中存在的问题提供解决方案,有助于相关部门更科学、精准地进行防洪、减灾、洪水调度等水安全处理工作,主动防范灾害对城市经济、人民生命财产产生影响,促进智慧水利工程的高质量发展。基于此,文中主要介绍了数字孪生技术,及其在智慧水利工程中应用的必要性,并对其在智慧水利工程中的应用进行了深入分析,以期为智慧水利工程的发展提供参考。     

Lithiation-Induced Defect Engineering to Promote Oxygen Evolution Reaction

Exploring efficient electrocatalysts for oxygen evolution reaction (OER) is an urgent need to advance the development of sustainable energy conversion. Though defect engineering is considered an effective strategy to regulate catalyst activity for enhanced OER performance, the controllable synthesis of defective oxides electrocatalysts remains challenging. Here, oxygen defects are introduced into NiCo₂O₄ nanorods by an electrochemical lithiation strategy. By tuning in situ lithiation potentials, the concentration of oxygen defects and the corresponding catalytic activity can be feasibly regulated. In addition, the relationship between the changes in the defect density and electronic structure and the lithiation cut-off voltages is revealed. The results show that NiCo₂O₄ nanorods undertook intercalation and two-step conversion reaction, in which the lithiation-induced conversion reaction gives rise to a CoO@NiO-based structure with higher defect density and lower oxidation states. As a result, the defective CoO@NiO-based catalyst exhibits exceptional OER activity with an overpotential of 270 mV at 10 mA cm⁻², which is about 74 mV below the pristine nanomaterials. This research proposes a novel strategy to explore high-performance catalysts with structural stability and defect control.     

基于两阶段分布鲁棒优化的列车停站方案与时刻表协同研究

列车停站方案与列车时刻表协同优化能够克服两者单独优化难以实现系统最优的弊端,从而可以得到旅客满意和企业期望的运营方案.首先,针对多场景不确定旅客需求概率分布信息已知的情形,综合考虑轨道与车站站线占用等约束,以极小化列车总行程时间、各场景未被满足旅客需求以及列车冗余之和为目标,构建列车停站方案与时刻表两阶段随机规划模型.在此基础上,进一步考虑旅客需求场景概率分布信息部分已知的情形,构建与之相对应的两阶段分布鲁棒优化模型.其次,借助L∞范数非精确集,将所构建的列车停站方案与时刻表两阶段分布鲁棒协同优化模型转换为等价的混合整数线性规划模型,并利用Visual C++平台调用GUROBI进行求解.最后,将所构建模型应用到武汉-广州高速铁路走廊上验证其有效性,结果表明,相比于随机优化模型,分布鲁棒优化模型只需付出较小的代价,即可抵御旅客需求概率分布不确定性带来的影响,且可以改善最坏情形下解的质量,为得到鲁棒性较强的铁路列车停站方案与时刻表提供一定的理论依据.     

Rumor detection with self-supervised learning on texts and social graph

Rumor detection has become an emerging and active research field in recent years. At the core is to model the rumor characteristics inherent in rich information, such as propagation patterns in social network and semantic patterns in post content, and differentiate them from the truth. However, existing works on rumor detection fall short in modeling heterogeneous information, either using one single information source only (e.g., social network, or post content) or ignoring the relations among multiple sources (e.g., fusing social and content features via simple concatenation).Therefore, they possibly have drawbacks in comprehensively understanding the rumors, and detecting them accurately. In this work, we explore contrastive self-supervised learning on heterogeneous information sources, so as to reveal their relations and characterize rumors better. Technically, we supplement the main supervised task of detection with an auxiliary self-supervised task, which enriches post representations via post self-discrimination.Specifically, given two heterogeneous views of a post (i.e., representations encoding social patterns and semantic patterns), the discrimination is done by maximizing the mutual information between different views of the same post compared to that of other posts. We devise cluster-wise and instance-wise approaches to generate the views and conduct the discrimination, considering different relations of information sources. We term this framework as self-supervised rumor detection (SRD). Extensive experiments on three real-world datasets validate the effectiveness of SRD for automatic rumor detection on social media.     

一种针对TomcatFilter型的MemShell检测技术研究

近些年来,随着计算机技术的不断发展和应用,Web应用技术也在快速更迭,与其一起发展的还有木马后门技术,但传统的木马后门技术已经不能满足攻击者的需求,因而基于内存攻击的方式不断涌现,包括powershell内存载入攻击、.NET assembly托管代码注入攻击以及内存马(Memory WebShell,MemShell)攻击等,这些攻击方式为现有的安全防御检测机制带来了极大的挑战。因而业界对面向解决基于内存的攻击尤其是内存马的攻击展现出了强烈的需求。但当前业内针对内存马的检测能力较弱,学术界也缺乏对该领域的研究工作,所以本文提出了一种针对Tomcat Filter型的内存马检测方法。通过研究发现,内存马其最核心技术便是无文件(Fileless)及不落地(Living off the Land),但尽管如此,内存马最终会在内存中展现其功能并执行命令,所以内存是所有威胁的交汇点,因此本文将Java虚拟机(Java Virtual Machine,JVM)作为起始点,首先利用JVM内存扫描技术遍历出JVM内存中加载的所有Filter类型对象,但需要注意的是这些对象并非都是有威胁的,并且每一个对象都具有一定的特征,所以可以对这些特征通过人工经验进行分类并且筛选出具有代表性的特征向量,然后获取每一个Filter类型对象的所有代表特征向量,并根据特征向量的值梳理出异常表现序列;最后,利用朴素贝叶斯算法将大量正常和异常的Filter对象的异常表现序列作为训练样本,计算出对应项的条件概率并形成贝叶斯分类器。利用训练出的贝叶斯分类器就可以构建出一个内存马检测模型,该模型能够有效得针对该类型的内存马进行检测。实验结果表明,本文提出的方法针对Tomcat Filter型内存马的检测,实现了零误报率和94.07%的召回率。