Shift-contagion in energy markets and global crisis

This paper presents an analysis of shift-contagion in energy markets, testing whether linkages between returns in energy markets increase during crisis periods. The research presented herein demonstrates how common movement between energy markets increases due to (i) shift-contagion across energy markets, reflected by structural transmission of shocks across markets and (ii) larger common shocks operating through standard cross-market interdependences. A regime-switching model was developed to detect shift-contagion across energy markets. In the approach adopted herein, the occurrence of shift-contagion is endogenously estimated rather than being exogenously assigned. The results show that shift-contagion has been a major feature of energy markets over the last decade. Evidence is presented which demonstrates that the linkages between energy markets do not appear to be stable. These results are remarkably accurate for forecasting Brent and natural gas for horizons for up to 50 days. Conversely, for WTI (West Texas Intermediate oil) and coal, the model performs well only for forecasting very short horizons (up to 20 days). For all products, the model shows significant biases for long horizons.     

Incorporating textual and management factors into financial distress prediction: A comparative study of machine learning methods

Financial distress prediction (FDP) has been widely considered as a promising approach to reducing financial losses. While financial information comprises the traditional factors involved in FDP, nonfinancial factors have also been examined in recent studies. In light of this, the purpose of this study is to explore the integrated factors and multiple models that can improve the predictive performance of FDP models. This study proposes an FDP framework to reveal the financial distress features of listed Chinese companies, incorporating financial, management, and textual factors, and evaluating the prediction performance of multiple models in different time spans. To develop this framework, this study employs the wrapper-based feature selection method to extract valuable features, and then constructs multiple single classifiers, ensemble classifiers, and deep learning models in order to predict financial distress. The experiment results indicate that management and textual factors can supplement traditional financial factors in FDP, especially textual ones. This study also discovers that integrated factors collected 4 years prior to the predicted benchmark year enable a more accurate prediction, and the ensemble classifiers and deep learning models developed can achieve satisfactory FDP performance. This study makes a novel contribution as it expands the predictive factors of financial distress and provides new findings that can have important implications for providing early warning signals of financial risk.     

The industrial asymmetry of the stock price prediction with investor sentiment: Based on the comparison of predictive effects with SVR

As a representative emerging financial market, the Chinese stock market is more prone to volatility because of investor sentiment. It is reasonable to use efficient predictive methods to analyze the influence of investor sentiment on stock price forecasting. This paper conducts a comparative study about the predictive performance of artificial neural network, support vector regression (SVR) and autoregressive integrated moving average and selects SVR to study the asymmetry effect of investor sentiment on different industry index predictions. After studying the relevant financial indicators, the results divide the Shenwan first-class industries into two types and show that the industries affected by investor sentiment are composed of young companies with high growth and high operative pressure and there are a great number of investment bubbles in those companies.     

基于光伏获能的WSNs节点能量管理策略

针对WSNs中基于预测算法的能量分配与管理机制的不足,研究太阳能可充电无线传感器网络中能耗管理,提出基于历史获能的能量中性管理机制。设计了一种自适应跟踪太阳光的节点获能模型,进而构建了一种基于历史获能的能量中性管理机制,根据当前操作周期中由太阳能转化而来的可用能量,调节下一操作周期中节点工作的占空比,以解决节点太阳能获取与节点能耗的优化问题。理论分析与实验结果表明,提出的基于历史获能的能量中性管理机制,实现了太阳能电池板大小与节点能耗的最佳匹配,为太阳能可充电无线传感器网络中的能量获取及能耗管理提供了值得借鉴的解决方案。     

轨道分析解的改进方法及其应用

主要介绍一种通过改进各类轨道摄动项的表达形式,以优化计算效率的轨道分析解改进方法。以低地球轨道为例,阐述了轨道分析解改进后的具体算法,并通过数值仿真分析验证了算法的有效性和实用性。算法以第一类无奇点根数作为轨道状态量,采用开普勒轨道根数计算各类摄动力的长期、长周期和短周期项,通过较简单的组合形式计算无奇点根数的对应摄动项,实现在保持分析解精度和消除小偏心率奇点的同时,提高计算效率。仿真结果表明,分析解算法的模型精度在1E-5量级,符合一阶分析解理论精度的预期;同时计算速度达到传统分析解算法的4倍左右,可有效提升空间碎片轨道预报的计算效率,具有较强的工程应用价值。     

考虑车辆间交互作用的驾驶意图预测方法

准确的意图预测可以帮助智能车辆更好地了解周围环境并做出更加安全的决策，从而提高自动驾驶的安全性，促进人机协同驾驶。为了对驾驶员未来的意图做出更加精准的预测，提出了一种交互式意图预测方法。首先，通过将隐马尔可夫模型（HMM）与高斯混合模型（GMM）相结合，在充分考虑周围场景信息后建立了行为识别模型，用于对当前的驾驶行为做出准确的判断。然后，考虑到交通场景复杂多变的特点，提出基于意图的轨迹预测方法规划出一条最佳的行驶轨迹，并采用最大期望效用理论对未来的驾驶行为进行推理。由于行为识别和意图推理模型综合考虑了交通态势的演变过程和车辆之间的交互作用，所以将两个模型得到的结果相结合可得到车辆最终预测出的驾驶意图。最后，在NGSIM数据集对所提出的方法进行验证，结果表明提出的行为识别模型能够提前0.2~0.3 s识别出车辆的换道意图，结合未来意图推理模型，能够更加准确地预测出车辆未来的驾驶行为，由此可提高车辆驾驶的安全性。     

基于图注意力网络的案件罪名预测方法:CP-GAT

案件罪名预测任务是基于文本数据去预测案件所属罪名.针对现有方法在相似罪名和长尾数据集上表现不佳的问题，提出了一种基于图注意力网络的案件罪名预测方法CP-GAT(charge prediction based on graph attention network).该方法首先使用司法文书数据集中的案例事件描述文本和案例对应的法条信息建立异质图结构数据，构建后的异质图包含两种类型的节点(词节点、案例节点)，两种类型的边(词节点与词节点相连的边，词节点与案例节点相连的边).在基于法律文本构建后的异质图上使用图注意力网络进行图特征提取，最后将得到的特征向量输入到罪名预测的分类器中，得到案例所属的罪名.在CAIL2018法律数据集上的实验结果表明，基于图注意力网络的罪名预测方法优于对比实验使用的方法，准确率和宏观F1值分别达到了95.2%和66.1，验证了提出的方法有利于提升案件罪名预测任务的性能.     

能量转换量子系统的热力学特性及其研究进展

量子物理是理解微观粒子运动规律的现代物理学理论.它与信息、生命以及化学等学科相互联系日益紧密,引发了许多新技术革命,深刻影响着人类的生活,已成为社会经济发展的原动力之一.当前,量子物理和能源科学结合,正在产生新的学科生长点.本文主要概述多种类型能量转换量子系统的发展;结合国内外的研究现状,系统地阐明如何应用热力学理论研究量子体系的能量操控以及微观器件的优化设计;总结量子热力学循环、能量选择量子电子器件、量子点热管理器件等在理论和实验方面研究的代表性成果和进展;展望量子物理与能源科学交叉领域发展的新方向.     

基于注意力机制的GRU神经网络安全态势预测方法

传统的网络安全态势预测方法依赖于历史态势值的准确性,并且各种网络安全因素之间存在相关性和重要程度差异性。针对以上问题,提出一种基于注意力机制的循环门控单元(recurrent gate unit, GRU)编码预测方法,该方法利用GRU神经网络挖掘网络安全态势数据之间的时间相关性;引入注意力机制计算安全指标的分配权重并将其编码为网络安全态势值;利用改进的粒子群优化(particle swarm optimization, PSO)算法进行超参数寻优,以加速GRU神经网络的训练。仿真分析表明,所提方法具有更快的收敛速度和较低的复杂度,并且在不同的预测时长下具有较小的均方误差和平均绝对误差。     

可持续发展视角下提升我国钢铁行业能源利用率路径研究

工业发展过程中生产工艺与技术水平对资源利用率和可持续发展动力的培养会产生重要影响。作为我国传统资源消耗型工业的钢铁行业，在产量与能源消耗间存在长期协整关系和能源利用率不合理问题，这直接导致了高能耗、高CO2产出，并严重地破坏了环境。因此，积极地推广新型生产工艺、提高生产技术水平和发展规模经济是实现我国低碳经济目标和提升钢铁能源利用率的有效路径。