基于联合损失胶囊网络的换衣行人重识别

目前的行人重识别（Re-ID）研究主要集中在短时间情形,即一个人的衣着不太可能发生改变的情况。然而现实中更常见的是长时间的情况,这时一个人有很大的机会更换衣服,Re-ID模型应该考虑这种情况。为此,研究了一种基于联合损失胶囊网络的换衣行人重识别方法。所提方法基于换衣行人重识别胶囊网络ReIDCaps,使用与传统的标量神经元相比包含更多信息的矢量胶囊,用其长度表示行人身份信息,用其方向表示行人衣着信息;采用软嵌入注意力（SEA）防止模型过拟合;使用特征稀疏表示（FSR）机制提取具有判别性的特征;增加标签平滑正则化交叉熵损失与Circle Loss的联合损失以提高模型的泛化能力和鲁棒性。在三个换衣行人重识别数据集Celeb-reID、Celeb-reID-light和NKUP上进行实验,实验结果表明所提方法与目前已有的Re-ID方法相比具有一定优势。     

改进在线词对主题模型的微博热点话题演化

话题演化分析是舆情监控的研究热点之一,面向微博热点话题进行演化分析,对于网络用户以及网络监管部门都有很重要的现实意义。针对在线词对主题模型（On-line Biterm Topic Model,OBTM）新旧主题混合、冗余词概率相对较高的问题,对OBTM进行改进,提出基于话题标签和先验参数的OBTM模型（Topic Labels and Prior Parameters OBTM,LPOBTM）。根据微博热点话题的话题标签,将微博文本集区分为含话题标签和不含话题标签的两类数据集,并设置不同的文档-主题先验参数;在前一时间片文档-主题概率分布的基础上,借鉴Sigmod函数对所有主题进行强度排名,从而优化当前时间片上主题-词分布的先验参数计算方法。实验结果表明,LPOBTM能够更准确地描述话题的内容演化情况,并且有更低的模型困惑度。     

极值-I型风速预测的Bayes方法

为提高极值-I型风速预测精度,在Jeffreys准则的基础上,采用Bayes估计中的Lindley近似方法推导极值-I型风速预测表达式.采用Monte Carlo法产生服从极值-I型分布的伪风速母样,基于伪风速母样分别采用基于Bayes理论和最大似然估计理论的极值-I型风速预测方法进行风速预测,并与伪风速母样的理论值进行对比分析.结果表明:与最大似然估计法相比,采用基于Bayes理论建立的极值-I型风速预测模型进行风速预测的精度更高,且精度随着伪风速母样样本量的增加而提高,位置参数先验样本数量的增加以及先验方差的增大对计算精度没有影响.     

Robust registration based compensation method based on sparse recovery

The loss of the degree of system freedom and mismatch of prior information based on the registration based compensation (RBC) method will result in a decline in computational performance. In order to solve above problems, a robust method named SRBC is proposed where the sparse recovery method is applied instead of the sub-aperture smoothing operation. First, the SRBC utilizes the sparse recovery to get the super resolution clutter space-time spectrum. Then the transition covariance matrix is calculated. Finally, the clutter covariance matrix is reconstructed by the Capon spectrum. Compared with the traditional RBC method, the SRBC proposed does not depend on sub-aperture smoothing operation and prior information and maintains the performance of clutter range-dependence. In addition, it is also steadier when the sensor error exists. Experimental simulation demonstrates the correctness and feasibility of this method.     

Novel Apriori-Based Multi-Label Learning Algorithm by Exploiting Coupled Label Relationship

It is a key challenge to exploit the label coupling relationship in multi-label classification (MLC) problems. Most previous work focused on label pairwise relations, in which generally only global statistical information is used to analyze the coupled label relationship. In this work, firstly Bayesian and hypothesis testing methods are applied to predict the label set size of testing samples within their k nearest neighbor samples, which combines global and local statistical information, and then apriori algorithm is used to mine the label coupling relationship among multiple labels rather than pairwise labels, which can exploit the label coupling relations more accurately and comprehensively. The experimental results on text, biology and audio datasets shown that, compared with the state-of-the-art algorithm, the proposed algorithm can obtain better performance on 5 common criteria.     

子结构拟动力试验平台NetSLabOSR开发与试验应用

为推进拟动力试验方法的研究与应用,开发了子结构拟动力混合试验平台Net SLab OSR,可用于结构工程体系抗震性能的评估.Net SLab OSR试验平台包括3个模块:Control Ctr OSR,Tester和Control Eq DAQ.通过动态数据链接库开发的Active X控件方式实现各主模块与试验设备系统的连接,完成子结构拟动力试验试验数据之间的传递、转换.利用Net SLab OSR试验平台对子结构取倒V型防屈曲耗能支撑和钢管混凝土底柱的试验模型,进行子结构拟动力试验研究,试验结果验证了Net SLab OSR试验平台的可靠性和稳定性.     

Polarimetric super-resolution algorithm for radar range imaging via spatial smoothing processing

A full-polarimetric super-resolution algorithm with spatial smoothing processing is presented for one-dimensional (1-D) radar imaging. The coherence between scattering centers is minimized by using spatial smoothing processing (SSP). Then the range and polarimetric scattering matrix of the scattering centers are estimated. The impact of different lengths of the smoothing window on the imaging quality is mainly analyzed with different signal-to-noise ratios (SNR). Simulation and experimental results show that an improved radar super-resolution range profile and more precise estimation can be obtained by adjusting the length of the smoothing window under different SNR conditions.     

基于改进加权空间平滑的凸优化协方差估计

针对相干信号受到非均匀噪声的干扰,在低信噪比环境中常规DOA估计存在估计效果较差甚至失效的情况,基于改进加权空间平滑,提出一种使用凸优化构造最优权重矩阵的方法。改进加权空间平滑算法解相干的同时构造权重矩阵,再用凸优化重构无噪声权重矩阵,将平滑过的协方差矩阵加权,并用MUSIC算法进行DOA估计。仿真结果证实,所提方法相对于空间平滑（spatial smoothing,SS）、基于特征空间MUSIC的空间平滑估计（spatial smoothing and eigen space based MUSIC,SS-ESMUSIC）以及接收信号协方差矩阵秩最小化（spatial smoothing based covariance rank minimization,SS-CRM）算法能更好地抑制非均匀噪声和解相干,且减少了低信噪比的干扰,展现出更优良的分辨力和准确性。     

刚性连体位置对非对称双塔连体结构动力可靠度的影响

考虑地震动的非平稳性,变化连体位置,对非对称双塔连体结构运用虚拟激励法进行非平稳随机激励下的动力可靠度研究。采用刚度退化的Bouc-Wen模型模拟塔楼各楼层的滞变特性,建立非线性化动力方程。运用混合精细积分法对每一时刻的响应进行求解,得到连体位置变化时非对称连体结构在非平稳随机激励下的时变方差。基于首次超越破坏准则与Markov假定,研究非平稳随机地震激励下连体结构的动力可靠度。运用上述理论,在8度罕遇地震作用下对某非对称双塔连体结构进行随机地震响应与动力可靠度分析。研究结果表明,地震作用下结构的层间位移响应呈现强烈的非平稳性,变化连体位置对连体结构的随机地震响应与动力可靠度将产生显著影响。     

预制钢桁架加固钢筋混凝土框架试验

目的验证一种新的框架结构整体抗震加固方法的可行性.方法对已损伤的一榀框架做预制钢桁架加固,并对加固后的试件进行水平低周反复荷载试验,分析其力学性能、变形能力、抗侧力体系的破坏特征,与理论值进行比较判断两个框架的抗震能力.结果加固后试件表现了较强的耗能能力,骨架曲线的平行段较长,其滞回曲线形状饱满,充分体现了预制钢桁架加固钢筋混凝土的优越性.加固后原框架承载力约提高了16%,框架的延性系数是原来的1.2倍,提高了框架结构的变形能力.结论预制钢桁架加固钢筋混凝土的方法可提高试件的承载力、耗能能力以及变形能力.