结合受限玻尔兹曼机的递归神经网络电力系统短期负荷预测

短期负荷预测的重要性随着电力企业的发展不断提高。传统的负荷预测虽然已经发展相对成熟,但现阶段对负荷预测的准确性要求逐渐提高。为满足发展需要,则要对现有的方法进行改进或建立新的预测方法。通过分析负荷预测数据周期性及周期内的特征,结合递归神经网络在分析时间序列数据的独特优势和受限玻尔兹曼机的强大的无监督学习能力,对结合受限玻尔兹曼机的递归神经网络的工作原理及训练过程进行了阐述。利用该网络进行了电力负荷数据预测实验验证并与其他神经网络进行了比较性实验。结果表明,所提出的神经网络较其他网络在电力短期负荷预测实验中有更高的准确性。     

基于变分模式分解和深度门控循环网络的风速短期预测模型

考虑到风速时间序列非平稳特性和时序关联难以建模的问题,提出一种基于变分模态分解和深度门控循环网络的风速短期预测模型。该模型首先使用变分模态分解非递归地将原始风速序列分解为预先设定层数的子分量,以期降低原始序列的不平稳度,使用深度门控网络分别对各子分量建模预测,最后叠加各分量的预测结果,得到风速的预测结果。实例研究表明所提模型能够有效地跟踪风速的变化,具有较高的短期预测精度。     

The Instability of Terahertz Plasma Waves in Two Dimensional Gated and Ungated Quantum Electron Gas

The instability of terahertz(THz)plasma waves in two-dimensional(2D)quantum electron gas in a nanometer field effect transistor(FET)with asymmetrical boundary conditions has been investigated.We analyze THz plasma waves of two parts of the 2D quantum electron gas:gated and ungated regions.The results show that the radiation frequency and the increment(radiation power)in 2D ungated quantum electron gas are much higher than that in 2D gated quantum electron gas.The quantum effects always enhance the radiation power and enlarge the region of instability in both cases.This allows us to conclude that 2D quantum electron gas in the transistor channel is important for the emission and detection process and both gated and ungated parts take part in that process.     

Engset multi‐rate state‐dependent loss models with QoS guarantee

We consider a single link loss system of quasi‐random input, described by the Engset multirate loss model (EnMLM). Blocked calls may once reattempt to be connected to the system requiring less bandwidth; then the system is described by the single retry model for finite sources (f‐SRM). The EnMLM and the f‐SRM are extended with the single threshold finite source model (f‐STM), where calls may attempt to be connected to the system with less bandwidth requirements, according to the link occupancy, before blocking occurs. We focus on CBP equalization in the EnMLM, f‐SRM and f‐STM, under the bandwidth reservation (BR) policy. For this analysis, we apply two approximate methods, the Roberts' method and the method of reverse transition rates (RTR), which lead to a recursive CBP calculation. We evaluate the accuracy of the above models under the BR policy by comparing the analytical with simulation CBP results, based on the relative approximation errors (RAE). The results are highly satisfactory because they show that the proposed models (formulas) lead to small RAE. Copyright © 2005 John Wiley & Sons, Ltd.     

Context-gated knowledge partitioning in categorization.

According to the knowledge partitioning framework, people sometimes master complex tasks by creating multiple independent parcels of partial knowledge. Research has shown that knowledge parcels may contain mutually contradictory information, and that each parcel may be used without regard to knowledge that is demonstrably present in other parcels. This article reports 4 experiments that investigated knowledge partitioning in categorization. When component boundaries of a complex categorization were identified by a context cue, a significant proportion of participants learned partial and independent categorization strategies that were chosen on the basis of context. For those participants, a strategy used in one context was unaffected by knowledge demonstrably present in other contexts, suggesting that knowledge partitioning in categorization can be complete. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

激光水下成像技术及其进展

介绍了近年发展起来的三种主要的激光水下成像方法，即常规水下激光成像、高分辨率水下激光三维成像和偏振激光成像，分析了它们各自的工作原理、特点以及各自的发展状况。     

New delay-dependent criterion for the stability of recurrent neural networks with time-varying delay

This paper is concerned with the global asymptotic stability of a class of recurrent neural networks with interval time-varying delay. By constructing a suitable Lyapunov functional, a new criterion is established to ensure the global asymptotic stability of the concerned neural networks, which can be expressed in the form of linear matrix inequality and independent of the size of derivative of time varying delay. Two numerical examples show the effectiveness of the obtained results. Supported by the National Natural Science Foundation of China (Grant Nos. 60534010, 60728307, 60774048, 60774093), the Program for Cheung Kong Scholars and Innovative Research Groups of China (Grant No. 60521003) and the National High-Tech Research & Development Program of China (Grant No. 2006AA04Z183), China Postdoctoral Sciencer Foundation (Grant No. 20080431150), and the Specialized Research Fund for the Doctoral Program of Higher Education of China (Grant No. 200801451096)     

The effect of recurrent episodes of clinical mastitis caused by gram-positive and gram-negative bacteria and other organisms on mortality and culling in Holstein dairy cows

The objective of this study was to estimate the effects of recurrent episodes of different types of clinical mastitis (CM) caused by gram-positive (Streptococcus spp., Staphylococcus aureus, Staphylococcus spp.) and gram-negative (Escherichia coli, Klebsiella, Citrobacter, Enterobacter, Pseudomonas) bacteria, and other organisms (Arcanobacterium pyogenes, Mycoplasma, Corynebacterium bovis, yeast, miscellaneous) on the probability of mortality and culling in Holstein dairy cows. Data from 30,233 lactations in cows of 7 dairy farms in New York State were analyzed. Cows were followed for the first 10 mo in lactation, or until death or culling occurred, or until the end of our study period. Generalized linear mixed models with a Poisson error distribution were used to study the effects of recurrent cases of the different types of CM and several other factors (herd, parity, month of lactation, current year and season, profitability, net replacement cost, other diseases) on cows’ probability of death (model 1) or being culled (model 2). Primiparous and multiparous cows were modeled separately because they had different risks of mortality and culling and potentially different CM effects on mortality and culling. Approximately 30% of multiparous cows had at least one case of CM in lactation compared with 16.6% of primiparous cows. Multipara also had higher lactational incidence risks of second (10.7%) and third (4.4%) cases than primipara (3.7% and 1.1%, respectively). For primipara, CM increased the probability of death, with each successive case occurring in a month being increasingly lethal. In multipara, gram-negative CM increased the probability of death, especially when the gram-negative case was the first or second CM case in lactation. Primiparous cows with CM were more likely to be culled after CM than if they did not have CM, particularly after a second or third case. In multipara, any type of CM increased the probability of being culled. Gram-negative CM cases were associated with the numerically highest risk of culling.     

模糊优选递归神经网络模型及其在水利水电投资项目评价中的应用

在模糊优选BP神经网络模型上,加入反馈信号及偏差单元,生成递归神经网络.其基本思想是通过对前馈神经网络中加入附加的、内部的反馈通道来增加网络本身处理动态信息的能力.将该模型用于水电投资项目的评价,所得结果与其它方法所得结果相比较,对该方法用于水利水电投资项目的评价的有效性进行了说明.     

求解广义特征根问题的反馈神经网络方法

研究了广义特征根问题求解的神经网络方法,给出了求解该问题的一个时间连续性反馈网络模型,利用LaSalle不变原理分析并证明了该网络的拟全局收敛性,这是网络能够确切的求解广义特征根问题的保证．同时,该网络解决了已有的基于罚函数方法构造的特征根问题的神经网络存在的一些基本缺陷:其一,基于罚函数的网络模型所得到的解可能不是真解,甚至可能都不是可行解;其二,它们的共同缺陷是有一个需要调节的参数,但是参数的选择并没有一个可供参考的准则;其三,这些模型的稳定性无法保证．本文所提出的网络模型解决了这些问题,并且,此网络具有一个很好的特征就是在初始点选定在问题的可行解集的话,网络轨线将永远是可行的并收敛到一个广义特征向量．最后,数值模拟也表明这里所提出的网络的可靠性能,进一步证明了此网络可以很好地求解广义特征根问题．