Radiolarians from the British North‐Polar Expedition (1875–1876): re‐examination of the H. B. Brady (1878) collection

The earliest report on radiolarians from the Arctic Ocean (north of the Arctic Circle) was provided by H. B. Brady (1878 Brady, H. B. 1878. On the reticularian and radiolarian Rhizopoda (Foraminifera and Polycystina) of the North‐Polar Expedition of 1875–76.. Annals and Magazine of Natural History, Series 5, 1: 425–440. [Taylor & Francis Online] , [Google Scholar]). He documented the occurrences of 10 genera from soundings in northern Baffin Bay and north of Greenland, but he did not illustrate any specimens in his report. We have re‐examined Brady's original slide collection, housed at the Natural History Museum, London (NHM), in order to refine his radiolarian identifications to species level. We have identified 11 radiolarian taxa in his slides, but some are definitely more characteristic of tropical oceans rather than high northern latitudes. We conclude that this is most likely due to sample contamination or misidentification of samples. Therefore, the actual occurrence of tropically affiliated radiolarians recorded from the Arctic is uncertain and should be regarded with suspicion.     

Microhabitat use and feeding habits of Crossodactylus bokermanni Caramaschi and Sazima, 1985 (Anura,Hylodidae) at a site in south‐eastern Brazil

We studied a population of Crossodactylus bokermanni in a stream at the Reserva Particular do Patrimônio Natural, Santuário do Caraça, south‐eastern Brazil, with respect to microhabitat use and diet. We characterized microhabitats based on substrate, distance to water and exposure level of the occupying individual (exposed or sheltered), and adjacent aquatic microhabitats (evaluated as potential nesting sites based on observed nests), according to water current (absent, slow or fast), substrate and depth. Calling males, silent males, ovigerous females, non‐ovigerous females and juveniles showed spatial niche overlap higher than that expected by chance, with calling males showing the strongest preference for microhabitats close to potential nesting sites (with intermediate depths, fast current and sandy bottom). Only 14 males out of 48 individuals examined for stomach contents had prey in their stomachs. The food items with the highest electivity values were Coleoptera and Diptera, but preys with both high and low mobility were exploited.     

Forecasting regional house price inflation: a comparison between dynamic factor models and vector autoregressive models

This paper uses the dynamic factor model framework, which accommodates a large cross‐section of macroeconomic time series, for forecasting regional house price inflation. In this study, we forecast house price inflation for five metropolitan areas of South Africa using principal components obtained from 282 quarterly macroeconomic time series in the period 1980:1 to 2006:4. The results, based on the root mean square errors of one to four quarters ahead out‐of‐sample forecasts over the period 2001:1 to 2006:4 indicate that, in the majority of the cases, the Dynamic Factor Model statistically outperforms the vector autoregressive models, using both the classical and the Bayesian treatments. We also consider spatial and non‐spatial specifications. Our results indicate that macroeconomic fundamentals in forecasting house price inflation are important. Copyright © 2010 John Wiley & Sons, Ltd.     

基于支持向量机的轰炸机敏感性权衡优化

生存力中敏感性方案的设计及改进是一个效益和代价不断权衡的过程。针对轰炸机敏感性权衡中的效益-费用优化问题,研究了基于支持向量机的轰炸机敏感性权衡方法。建立支持向量机代理模型,简化了敏感性的计算,并利用交叉验证和网格搜索对模型参数进行优化;拟合了轰炸机敏感性参数与增加费用的函数关系,将灵敏度理论引入敏感性权衡中,从最优效费比的角度出发,确定敏感性参数的取值范围。最后通过仿真验证了方法的可行性。结果表明,该权衡优化方法能够在费用约束条件下对敏感性参数的取值范围进行优化,在保证精度的同时提升了计算效率。     

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.     

一种基于视频图像的挖掘机工作状态识别方法

为了实现违法用地现象的实时监测,对土地间的挖掘机等施工机械的工作状态识别是非常重要的.实际场景下,因随机噪声和光照变化的影响,给挖掘机工作状态识别带来极大的挑战.本文提出一种基于视频图像的挖掘机工作状态识别方法,首先,对同一品牌挖掘机工作装置的各种姿态建立混合local binary features (LBF)形状回归模型并进行离线训练;其次,利用上述模型预测输入视频帧中挖掘机工作装置的形状信息,构建挖掘机的工作状态特征描述子;最后,利用support vector machine (SVM)分类器自动判别挖掘机的工作状态—-工作状态或非工作状态.实验结果表明,该方法很好地克服了多姿态导致形状变化的影响,对挖掘机工作状态识别准确率达到了93.53%.     

大入射余角CFAR检测器

雷达在大入射余角高分辨率海杂波背景下检测时,等效后向散射面积增大,大部分海杂波能量投射到少数距离单元,能量分布不均,出现功率突然增大的杂波“异常单元”,导致检测器参考窗口所处的背景环境复杂多变,传统检测器检测概率降低,虚警率及误检率增加。为解决此问题,通过参考滑窗单元的协方差矩阵构造正定矩阵,求解其矩阵范数用以估计杂波功率水平,并采用支持向量机改进传统恒虚警率(constant false alarm rate,CFAR)检测器,得到基于正定矩阵杂波功率估计训练支持向量机的改进CFAR检测器。实验结果表明,新检测器在均匀杂波、多目标环境下检测性能稳定,在杂波边缘的虚警控制能力良好。     

空中目标辐射源的个体识别方法

针对传统的辐射源个体识别方法在低信噪比环境下识别性能不佳的问题,提出了一种空中目标辐射源的个体识别方法,该方法利用经验模态分解和变分模态分解得到信号不同频率的模态分量,将各模态分量的多尺度排列熵作为特征,利用主成分分析对数据进行降维,并采用支持向量机分类器进行辐射源个体识别。仿真结果表明,该方法对相位噪声、频率漂移以及谐波失真等细微特征的识别性能明显优于传统方法,并具有良好的抗噪性。     

Forecasting the Daily Time‐Varying Beta of European Banks During the Crisis Period: Comparison Between GARCH Models and the Kalman Filter

This intention of this paper is to empirically forecast the daily betas of a few European banks by means of four generalized autoregressive conditional heteroscedasticity (GARCH) models and the Kalman filter method during the pre‐global financial crisis period and the crisis period. The four GARCH models employed are BEKK GARCH, DCC GARCH, DCC‐MIDAS GARCH and Gaussian‐copula GARCH. The data consist of daily stock prices from 2001 to 2013 from two large banks each from Austria, Belgium, Greece, Holland, Ireland, Italy, Portugal and Spain. We apply the rolling forecasting method and the model confidence sets (MCS) to compare the daily forecasting ability of the five models during one month of the pre‐crisis (January 2007) and the crisis (January 2013) periods. Based on the MCS results, the BEKK proves the best model in the January 2007 period, and the Kalman filter overly outperforms the other models during the January 2013 period. Results have implications regarding the choice of model during different periods by practitioners and academics. Copyright © 2016 John Wiley & Sons, Ltd.     

Forecasting Ability of a Periodic Component Extracted from Large‐Cap Index Time Series

We develop a method to extract periodic variations in a time series that are hidden in large non‐periodic and stochastic variations. This method relies on folding the time series many times and allows direct visualization of a hidden periodic component without resorting to any fitting procedure. Applying this method to several large‐cap stock time series in Europe, Japan and the USA yields a component with periodicity of 1 year. Out‐of‐sample tests on these large‐cap time series indicate that this periodic component is able to forecast long‐term (decade) behavior for large‐cap time series. Copyright © 2016 John Wiley & Sons, Ltd.