基于神经网络的图像描述方法研究

自动识别和描述图像的内容是人工智能中一个重要的研究方向,它涉及计算机视觉和自然语言处理技术。针对这一难题,提出了一种由深层神经网络模型生成自然语言句子来描述图像内容的方法。该方法提出的模型由卷积神经网络(Convolution Neural Network,CNN)和循环神经网络(Recurrent Neural Network,RNN)组成,其中,CNN用来提取输入图像的特征生成固定长度的特征向量,该特征向量初始化RNN来生成句子。在MSCOCO图像描述数据集上的实验结果表明了该模型所生成句子的语法准确性和语义准确性,且优于先前的基线模型。     

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.     

基于深度残差适配网络的通信辐射源个体识别

为解决通信辐射源识别中传统的人工特征提取方法鲁棒性不足和深度学习方法需要大量带标签目标域数据的问题,提出一种基于深度残差适配网络的通信辐射源个体识别方法.应用深度学习技术实现从源域到目标域上的迁移识别,只需要将带标签的源域数据和无标签的目标域数据进行训练.原始通信辐射源信号经过预处理后输入网络训练,将源域和目标域的分布...     

国际临界带研究发展回顾与美国临界带研究进展介绍

基于对临界带国际发展态势的分析,梳理了临界带的概念;回顾了国际临界带研究的发展历程;并重点对美国在临界带研究方面的进展及其已经部署的6个临界带观测站进行了详细的介绍。     

深部岩体传热机理的研究现状与进展

基于国内外深部工程普遍面临的高温状况,探讨了深部高温的形成机制与影响因素。围绕岩体导热性质研究、水热耦合迁移问题和工程环境对传热的影响三个方面阐述了深部岩体传热机理的研究现状,目前的研究成果主要体现在建立了深部工程的热交换理论体系、矿山地热学的理论体系和地下工程制冷降温系统的热力学基础。在总结分析的基础上,确立了深部岩体流固耦合传热问题的研究思路：开展深部工程区域的的渗流场监测和开展岩体的流固耦合传热实验和建立岩体在应力-渗流-温度耦合条件下的传热模型,揭示深部岩体的传热机理。     

An ensemble of LSTM neural networks for high‐frequency stock market classification

We propose an ensemble of long–short‐term memory (LSTM) neural networks for intraday stock predictions, using a large variety of technical analysis indicators as network inputs. The proposed ensemble operates in an online way, weighting the individual models proportionally to their recent performance, which allows us to deal with possible nonstationarities in an innovative way. The performance of the models is measured by area under the curve of the receiver operating characteristic. We evaluate the predictive power of our model on several US large‐cap stocks and benchmark it against lasso and ridge logistic classifiers. The proposed model is found to perform better than the benchmark models or equally weighted ensembles.     

基于背景插值的空空导弹攻击区在线模拟方法

针对空战态势迅速变化对空空导弹攻击区模拟实时性的需求,提出基于背景插值的攻击区在线模拟方法。首先预测下一采样时刻态势,并针对预测态势模拟解算攻击区信息;当下一采样时刻到来时,利用攻击区预测值和先前两次攻击区模拟信息及相应的态势记录插值估计攻击区真实值。背景插值方法将攻击区模拟解算放到先前计算周期中,实时性高。理论分析证明了背景插值误差随着采样时间的减小收敛于零。仿真结果表明,背景插值模拟方法的误差与传统攻击区模拟方法相当,而前者平均可在7.16×10^-6s内给出结果,后者平均计算耗时为0.290 s。     

The landing zone – Ground for model transfer in chemistry

This essay proposes a new notion - the landing zone - in order to identify conceptual features that allow modelers to transfer mathematical tools across disciplinary borders. This discussion refers to the transferable models as ‘templates’. Templates are functions, equations, or computational methods that are capable of being generalized from a particular subject matter. There are formal and conceptual prerequisites for the transfer of a template to a new domain. A landing zone is an ontology that contributes to the satisfaction of these conditions for successful transfer. This paper presents a case study on a model in chemistry - the Quantum Theory of Atoms in Molecules (QTAIM) - that makes use of transferred templates from physics - the virial theorem and the wave function. The landing zone in this case is a new ontological notion, that of the topological atom, which prepares ground for the use of the virial theorem and the wave function in chemistry. The virial theorem requires that there exists in-principle stability to the system that it represents, and the wave function requires transformation in its representation that is justified. The ontology of QTAIM - the landing zone for these templates - grounds the scientific use of these templates in the context of chemistry.     

Three noteworthy mirine plant bugs inhabiting subalpine zones of the Nepalese Himalayas (Hemiptera: Heteroptera: Miridae: Mirinae)

Three unique mirine plant bugs inhabiting typical subalpine vegetation in the Nepalese Himalayas are documented, with their confirmed plant associations. A new genus and new species, Khumbumiris schwartzi, is diagnosed and described, based on a male specimen collected from Abies spectabilis; two additional new species, Lygocoris laligurans (associated with Rhododendron shrubs) and Phytocoris sagarmathanus (Abies spectabilis), are also described. Images of the habitats and live individuals are also provided. The tribal placement of Khumbumiris is discussed in detail.

http:/zoobank.org/urn:lsid:zoobank.org:pub:54E31614-3262-4BF8-8BBB-F81893AF41D2