基于动态组合残差修正的预测方法

本文建立了一种基于残差修正的组合预测方法,并基于该方法证明了针对多个单一的预测方法根据其在某个时间段的相对预测误差的大小选择组合选项可以进一步提高预测精度.提出了针对不同时间段可根据各种单项预测模型的相对预测误差的大小动态选取相对预测误差最小的两种模型构成组合残差来修正基本方法的预测误差,以提高预测精度.最后通过实际空调负荷预测对其进行了验证,结果表明这种动态组合残差修正的预测方法相对于基于多个固定单一预测方法的组合预测方法,可以进一步改善预测效果.     

The impact of parameter and model uncertainty on market risk predictions from GARCH‐type models

We study the effect of parameter and model uncertainty on the left‐tail of predictive densities and in particular on VaR forecasts. To this end, we evaluate the predictive performance of several GARCH‐type models estimated via Bayesian and maximum likelihood techniques. In addition to individual models, several combination methods are considered, such as Bayesian model averaging and (censored) optimal pooling for linear, log or beta linear pools. Daily returns for a set of stock market indexes are predicted over about 13 years from the early 2000s. We find that Bayesian predictive densities improve the VaR backtest at the 1% risk level for single models and for linear and log pools. We also find that the robust VaR backtest exhibited by linear and log pools is better than the backtest of single models at the 5% risk level. Finally, the equally weighted linear pool of Bayesian predictives tends to be the best VaR forecaster in a set of 42 forecasting techniques.     

体域网中基于特征组合的步态行为识别

物联网(internet of things,IOT)拥有无处不在的识别、传感和通信能力,体域网(body area network,BAN)属于物联网中和人体相关的领域,其应用广泛,可以在日常生活中对人们进行监测及提供帮助.行走是许多日常活动的基本环节,因而步态分析能为体域网应用提供重要的生理行为信息.现有的步态分析已取得一定的研究成果,但仍存在一些问题,例如大多数步态特征提取是对加速度信号进行6重以上的变换,使得特征达到了45维以上,最后需要通过降维或优化来简化特征,较为复杂.本文设计一种灵活便捷的数据采集系统,并利用小波变换、傅里叶变换和四分位差提取出加速度信号中比较简单、低维度但能反应运动特征的步态参数,之后通过模式识别算法进行步态行为识别验证.实验结果表明该系统使用方便,特征提取方法简单实用,识别精确度为97%,EER(equal error rate)最小可到0.9%.     

Forecast Combination and Bayesian Model Averaging: A Prior Sensitivity Analysis

In this study we evaluate the forecast performance of model‐averaged forecasts based on the predictive likelihood carrying out a prior sensitivity analysis regarding Zellner's g prior. The main results are fourfold. First, the predictive likelihood does always better than the traditionally employed ‘marginal’ likelihood in settings where the true model is not part of the model space. Secondly, forecast accuracy as measured by the root mean square error (RMSE) is maximized for the median probability model. On the other hand, model averaging excels in predicting direction of changes. Lastly, g should be set according to Laud and Ibrahim (1995: Predictive model selection. Journal of the Royal Statistical Society B 57 : 247–262) with a hold‐out sample size of 25% to minimize the RMSE (median model) and 75% to optimize direction of change forecasts (model averaging). We finally apply the aforementioned recommendations to forecast the monthly industrial production output of six countries, beating for almost all countries the AR(1) benchmark model. Copyright © 2011 John Wiley & Sons, Ltd.     

Revision of the genus Mimopodabrus Wittmer (Coleoptera,Cantharidae)

The genus Mimopodabrus Wittmer is reviewed, and the genus diagnosis is re-described. Three new species are described, M. multidentatus sp. nov. (Guangdong, China), M. variabilis sp. nov. (Yunnan, China) and M. diversefoveolatus sp. nov. (Lao Cai, Vietnam), with illustrations of habitus, antennae and aedeagus. A species is transferred from Micropodabrus to this genus, M. bicoloriceps (Wittmer, 1989 Wittmer, W. 1989. 42. Beitrag zur Kenntnis der indo-malaiischen Cantharidae und Malachiidae (Coleoptera). Entomol Basil., 13: 209–237.  [Google Scholar]) comb. nov. A species is synonymized, M. bicoloriceps (Wittmer, 1989 Wittmer, W. 1989. 42. Beitrag zur Kenntnis der indo-malaiischen Cantharidae und Malachiidae (Coleoptera). Entomol Basil., 13: 209–237.  [Google Scholar]) comb. nov.?=?M. bicoloriceps Wittmer, 1997 syn. nov. and the definition of M. yunnanus (Wittmer, 1993 Wittmer, W. 1993. Zur Kenntnis der palaearktischen und indo-malaiischen Cantharidae (Coleoptera). Entomol Basil., 16: 203–253.  [Google Scholar]) is restricted. A key to all known species of this genus is provided.     

A study of Platyplectrus Ferrière (Hymenoptera: Eulophidae) in mainland China

This paper reviews the Chinese species of Platyplectrus Ferrière. Twelve valid species are recognized from mainland China and a key to species is provided. Trichoplectrus Erdös (1951 Erdös, J, 1951. "Eulophidae novae. Acta Biologica". 1951, Academiae Scientiarum Hungaricae, 2(1–3), 169–237. [Google Scholar]) is newly synonymized with Metaplectrus Ferrière (1941 Ferrière, C, 1941. New species of Euplectrini (Hym. Chalcidoidea) from Europe, Africa and Asia, Bulletin of Entomological Research 32 (1941), pp. 17–48.[Crossref] , [Google Scholar]) and three new combinations are proposed: Metaplectrus szepligetii (Erdös) from Platyplectrus, Platyplectrus bussy (Crawford) from Euplectrus and P. politus (Lin) from Metaplectrus. Four species of Platyplectrus were known previously from China: P. politus (Lin), P. odontogaster (Lin), P. papillata Lin and P. medius Zhu and Huang. Six species, P. bussyi (Crawford), P. laeviscuta (Thomson), P. natadae Ferrière, P. orthocraspedae Ferrière, P. pannonica (Erdös) and P. viridiceps (Ferrière) are newly recorded from China and re-described. Five new species, P. pulcher, P. setulosus, P. peculiaris, P. obtusiclavatus and P. variflagellum are described and compared with related species. Several species are also newly recorded from other regions: P. orthocraspedae Ferrière from the Afrotropical region, P. bussyi (Crawford) and P. laeviscuta (Thomson) from the Australian/Pacific region, P. laeviscuta (Thomson) from the Oriental region and P. viridiceps from the Palearctic region.     

7种化学杀菌剂和拮抗菌代谢物对苹果斑点落叶病菌的抑制活性及增效组合筛选

目的 为苹果斑点落叶病的防控提供新颖的杀菌剂及其增效组合。方法 采用菌丝生长速率法测定了7种化学杀菌剂、拮抗菌发酵代谢物及其复配剂对苹果斑点落叶病菌的抑制活性。结果 7种化学杀菌剂均对病菌有较强的抑制活性,其中戊唑醇、苯醚甲环唑和丙环唑3种药剂对病菌抑制效果最佳,EC₅₀分别达0.21、0.30和0.81 μg/mL,其次为吡唑醚菌酯、代森锰锌和嘧菌酯。多菌灵的抑菌效果最差,EC₅₀为15.03 μg/mL。生防菌发酵上清液和发酵上清粗提物对病菌的EC₅₀分别为2.38 μL/mL和0.53 μL/mL。发酵上清液粗提物和代森锰锌、吡唑醚菌酯的复配均表现为增效作用,其中体积比6∶4和7∶3达最大毒性比,分别为1.39和1.41。结论 戊唑醇、苯醚甲环唑和丙环唑对苹果斑点落叶病菌的毒力最大。解淀粉芽孢杆菌SJ1606所产粗提物对化学杀菌剂代森锰锌和吡唑醚菌酯具有增效作用,为后续农药新制剂研发提供了参考数据。     

关联交叉口短时交通流可预测性分析及组合预测算法

文中首先根据交叉口交通流参数时间序列的相关性对关联交叉口进行定义,给出关联交叉口短时交通流可预测分析的几个定量指标,以及交通流时间序列最大Lya-punov指数的计算方法;然后提出在短时交通流时间序列的可预测分析基础上,选取一组预测模型并建立基于RBF网络的非线性组合预测模型,提出了关联交叉口短时交通流的组合预测算法;最后对实测短时交通流进行仿真试验,结果表明组合预测方法相对于单项预测方法具有更好的预测性能.     

二维方柱光子晶体的波导特性

具有缺陷的光子晶体,光子频率带隙内将出现局域模,而线缺陷相应地形成一个传输效率很高的光波导.计算了空气中Al材料的旋转四边形直柱光子晶体存在线缺陷时的带结构和态密度,给出了二维方形光子晶体的波导的TM模的电场分布,并讨论了波导耦合的传输效率.     

跳频抗干扰通信系统中LDPC码的编码优化设计

为进一步提升低密度奇偶校验(low-density parity-check, LDPC)编码跳频通信系统抗干扰能力,提出一种对抗部分频带干扰样式的LDPC编码构造方法。首先针对不同干扰因子参数优化了LDPC码字在干扰环境下的度分布序列,然后通过基于渐进边增长和近似环外信息算法构造基矩阵,最后采用改进部分分割移位系数矩阵扩展得到校验矩阵,并结合不等差错保护特性应用到信息位的干扰保护上。该构造方法兼顾优化的度分布和准循环结构。仿真结果表明,所构造的码字性能良好,相同条件下,抗干扰性能优于现行主流类型码字的抗干扰性能。