基于GFU和分层LSTM的组群行为识别研究方法

提出一种以"关键人物"为核心，使用门控融合单元（GFU，Gated Fusion Unit）进行特征融合的组群行为识别框架，旨在解决两个问题：①组群行为信息冗余，重点关注关键人物行为特征，忽略无关人员对组群行为的影响；②组群内部交互行为复杂，使用GFU有效融合以关键人物为核心的交互特征，再通过LSTM时序建模成为表征能力更强的组群特征.最终，通过softmax分类器进行组群行为类别分类.该算法在排球数据集上取得了86.7%的平均识别率.     

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。     

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)     

复合栅控二极管新技术提取热载流子诱生的NMOS/SOI器件界面陷阱的横向分布

提出了用复合栅控二极管新技术提取MOS/SOI器件界面陷阱沿沟道横向分布的原理,给出了具体的测试步骤和方法.在此基础上,对具有体接触的NMOS/SOI器件进行了具体的测试和分析,给出了不同的累积应力时间下的界面陷阱沿沟道方向的横向分布.结果表明:随累积应力时间的增加,不仅漏端边界的界面陷阱峰值上升,而且沿沟道方向,界面陷阱从漏端不断向源端增生.     

面向WSI的乳腺病理亚型分类研究

为实现乳腺病理WSI图像的精准分类,提出了一种基于混合连接的门控卷积神经网络分类方法。搭建了局部残差连接和全局稠密连接的混合模块,将压缩激活门控单元嵌入混合模块,建立了混合模块与过渡层交替连接的骨干网络。结合基于四叉树分割的图像数据增强方法训练模型,基于BreastSet临床数据集的实验结果得出,该方法的图像级、患者级和病理级准确率分别达到92.24%、92.83%和92.18%,相较其他方法,其准确率提高,参数量和计算量降低,更具有临床应用价值。     

基于门控循环单元与误差修正的短期负荷预测

针对负荷预测模型迭代训练过程中存在误差积累的问题,提出结合叠式双向门控循环单元（SBiGRU）、完整自适应噪声集成经验模态分解（CEEMDAN）和误差修正的组合预测模型. 建立SBiGRU模型学习在气温、日期类型影响下负荷序列的时序特征,误差特征体现在SBiGRU模型预测产生的误差序列中;使用CEEMDAN算法将误差序列分解为数个本征模态函数（IMF）分量与趋势分量,对每项分量再次建立SBiGRU模型进行学习与预测,并对各分量的预测值进行序列重构,得到误差的预测结果;对预测结果进行求和以修正误差. 模型评估结果表明,组合模型的预测准确精度为98.86%,与SBiGRU、BiRNN、支持向量回归等方法相比,该模型具有更好的精度.     

基于VMD与改进QRGRU的超短期风电功率概率预测

风电功率概率预测是分析未来风电功率不确定性的有效方法之一。为提高风电功率概率预测精度,文中提出基于变分模态分解(VMD)与改进门控循环单元分位数回归(QRGRU)的超短期风电功率概率预测方法。首先,采用VMD将原始风电功率序列分解成不同特征的模态函数;然后,对每个模态函数分别建立基于QRGRU的概率预测模型,并将变量间的网络结构约束作为目标函数的惩罚项,改进QRGRU权重在迭代修正过程中的平稳性;最后,在不同分位数条件下叠加各个模态函数预测值,并采用非参数核密度估计方法得到未来风电功率的概率密度函数。结合某风电场实测数据开展具体算例分析,结果表明所提方法能够兼顾区间覆盖率,减少区间宽度,在不同预测步长中均能表现较好的预测效果。     

Quantitative determination of castor oil in edible and heat-abused oils by13C nuclear magnetic resonance spectroscopy

Application of¹³C nuclear magnetic resonance (NMR) spectroscopy for detection of castor oil (CO) in various edible oils, such as coconut oil, palm oil, groundnut oil and mustard oil, is described. Characteristic signals observed at δ 132.4, δ 125.6, δ 71.3, δ 36.8 and δ 35.4 ppm, due to C10, C9, C12, C13 and C11 carbons of ricinoleic acid (RA) in CO, were selected for distinguishing it from edible oils. Quantitative¹³C NMR spectra of oils were recorded in CDCl₃ with a gated decoupling technique. The minimum detection limits for qualitative and quantitative analyses were 2.0 and 3.0%, respectively. The proposed method is simple, nondestructive and requires no sample pretreatment. Its application to heat-abused oils has also been demonstrated successfully without any of the interferences observed in most other methods.     

REVERSED RESIDUALS IN AUTOREGRESSIVE TIME SERIES ANALYSIS

Abstract. Both linear and non-linear time series can have directional features which can be used to enhance the modelling and investigation of linear or non-linear autoregressive statistical models. For this purpose, reversed p th-order residuals are introduced. Cross-correlations of residuals and squared reversed residuals allow extensions of current model identification ideas. Quadratic types of partial autocorrelation functions are introduced to assess dependence associated with non-linear models which nevertheless have linear autoregressive correlation structures. The use of these residuals and their cross-correlation functions is exemplified empirically on some deseasonalized river flow data for which a first-order autoregressive model is a satisfactory second-order fit. Parallel theoretical computations are undertaken for the non-linear first-order random coefficient autoregressive model and comparisons are made. While the data are shown to be strongly non-linear, their correlational signatures are found to be convincingly different from those of a first-order autoregressive model with random coefficients.     

安克锰锌在荔枝树上施用的残留代谢消解规律与安全性评价

安克锰锌是烯酰吗啉两个异构体和代森锰锌组成的多元混合制剂。试样经粉碎、溶剂浸泡提取、混合柱净化,用气相色谱测定烯酰吗啉和代森锰锌母体(CS2),液相色谱测定代谢物乙撑硫脲(ETU)。仪器最低检出量:烯酰吗啉为1.436×10-12g,代森锰锌母体1.326×10-10g,ETU2.5×10-10g,最低检出浓度依次为0.02、0.025、0.02mg/kg,方法回收率依次为86.4%～90.8%、89.2%～95.9%、89.10%～95.13%;标准偏差为0.53～4.34;变异系数为0.58%～4.62%。安克锰锌在果皮中的消解方程广西和广东分别为C=1.2719e-0.1975T和C=1.045e-0.1972T,半衰期(T/2)均为3.5d;土壤中分别为C=0.8734e-0.1187T和C=0.6171e-0.1146T,半衰期(T/2)=6d;最高剂量250倍、最多施3次,最短距收期7d,在果肉中均未检出,果皮和土壤中的残留仅分别为0.1385～0.1745mg/kg和0.3105～0.3415mg/kg,均低于欧共体规定代森锰锌MRL值0.5mg/kg。