视频侦查中人像智能分析应用及算法优化

人像智能分析指的是对视频或录像中的人像进行结构化和可视化分析,对目标人物进行性别、年龄、发型等特征的智能识别,这项技术在视频侦查中有极高的应用价值。人像识别早期的算法是通过人工提取特征,通过学习低级视觉特征来针对不同属性进行分类学习,这种基于传统方法的模型表现常常不尽如人意。在计算机视觉领域,通过海量图像数据学习的神经网络比传统方法有更丰富的信息量和特征可以被提取。文章尝试通过深度学习技术训练神经网络模型对行人进行检测和识别,对于衣着不同的行人进行智能识别,具有更好的鲁棒性,提升了视频人像识别的准确率,拓展了人工智能技术在身份识别领域的应用。     

无源光网络标准发展及关键技术研究

无源光网络(Passive Optical Network,PON)作为当今接入网的主要技术解决方案,具有带宽使用效率高、传输距离远、抗干扰能力强等特点.通过研究PON技术的发展动态,本文首先归纳了各种PON技术的产生背景和应用特点,整理出各技术间的连接关系及主要标准;其次介绍了PON技术的帧结构,并对带宽、波长、传输模式等PON技术的主要参数进行了汇总;然后将国内外研究热点进行划分,围绕媒体访问控制协议、帧结构、动态带宽分配算法、节能机制等关键技术,阐述了其研究现状及在PON中的重要作用;最后对PON技术的发展趋势进行了展望.     

基于特征融合的中文简历解析方法研究

针对基于规则和统计的传统中文简历解析方法效率低、成本高、泛化能力差的缺点，提出一种基于特征融合的中文简历解析方法，即级联Word2Vec生成的词向量和用BLSTM（Bidirectional Long Short-Term Memory）建模字序列生成的词向量，然后再结合BLSTM和CRF（Conditional Random Fields）对中文简历进行解析（BLSTM-CRF）。为了提高中文简历解析的效率，级联包含字序列信息的词向量和用Word2Vec生成的词向量，融合成一个新的词向量表示；再由BLSTM强大的学习能力融合词的上下文信息，输出所有可能标签序列的分值给CRF层；再由CRF引入标签之间约束关系求解最优序列。利用梯度下降算法训练神经网络，使用预先训练的词向量和Dropout优化神经网络，最终完成对中文简历的解析工作。实验结果表明，所提的特征融合方法优于传统的简历解析方法。     

Sequence-Dependent Nanofiber Structures of Phenylalanine and Isoleucine Tripeptides

The molecular design of short peptides to achieve a tailor-made functional architecture has attracted attention during the past decade but remains challenging as a result of insufficient understanding of the relationship between peptide sequence and assembled supramolecular structures. We report a hybrid-resolution model to computationally explore the sequence–structure relationship of self-assembly for tripeptides containing only phenylalanine and isoleucine. We found that all these tripeptides have a tendency to assemble into nanofibers composed of laterally associated filaments. Molecular arrangements within the assemblies are diverse and vary depending on the sequences. This structural diversity originates from (1) distinct conformations of peptide building blocks that lead to different surface geometries of the filaments and (2) unique sidechain arrangements at the filament interfaces for each sequence. Many conformations are available for tripeptides in solution, but only an extended β-strand and another resembling a right-handed turn are observed in assemblies. It was found that the sequence dependence of these conformations and the packing of resulting filaments are determined by multiple competing noncovalent forces, with hydrophobic interactions involving Phe being particularly important. The sequence pattern for each type of assembly conformation and packing has been identified. These results highlight the importance of the interplay between conformation, molecular packing, and sequences for determining detailed nanostructures of peptides and provide a detailed insight to support a more precise design of peptide-based nanomaterials.     

金属配合物与核酸作用机理的理论计算

通过计算机模拟金属配合物与核酸作用机理,对其理论模型能量计算和结构优化。在不同的化学环境条件下得到不同的实验模拟结果,对真实的化学反应过程有重要的指导意义和参考意义。通过Gaussian03,Gauss View等软件的结合应用,分别应用于优化计算和理论建模,熟悉了对化学软件操作应用。     

Detection of correlation characteristics between financial time series based on multi-resolution analysis

Interactions between financial time series are complex and changeable in both time and frequency domains. To reveal the evolution characteristics of the time-varying relations between bivariate time series from a multi-resolution perspective, this study introduces an approach combining wavelet analysis and complex networks. In addition, to reduce the influence the phase lag between the time series has on the correlations, we propose dynamic time-warping (DTW) correlation coefficients to reflect the correlation degree between bivariate time series. Unlike previous studies that symbolized the time series only based on the correlation strength, the second-level symbol is set according to the correlation length during the coarse-graining process. This study presents a novel method to analyze bivariate time series and provides more information for investors and decision makers when investing in the stock market. We choose the closing prices of two stocks in China’s market as the sample and explore the evolutionary behavior of correlation modes from different resolutions. Furthermore, we perform experiments to discover the critical correlation modes between the bull market and the bear market on the high-resolution scale, the clustering effect during the financial crisis on the middle-resolution scale, and the potential pseudo period on the low-resolution scale. The experimental results exactly match reality, which provides powerful evidence to prove that our method is effective in financial time series analysis.     

采油树平板闸阀柔性密封圈结构优化设计

为了提高采油树平板闸阀密封圈的密封性能,在泛塞封的基础上,设计一种密封圈本体唇边开有锯齿状凸起的新型柔性密封结构;运用有限元分析方法模拟密封圈的工作状况,分析柔性密封结构特性参数对密封圈密封性能的影响,获得不同柔性密封圈结构参数下密封面间接触应力分布规律,并对新型密封结构进行优化。结果表明:密封面间最大接触应力随唇边锯齿数量、唇边夹角度数的增大而增大,随唇谷夹角度数的增大而减小;新型密封结构选择锯齿数量为3、唇边夹角为20°、唇谷夹角为30°的特性参数时,其最大接触应力比常规Y形密封圈提高了15倍;新型柔性密封结构的密封圈与阀杆、阀盖壁面间接触应力比常规Y形密封圈有显著提高,提高了密封圈的密封性能。     

The origin of the modulated structure in Sr2CuO3+δ (δ = 0.4): [CuO2] in-plane oxygen vacancy or apical oxygen vacancy?

We propose the question of the modulated structures of copper oxide is caused by the [CuO₂] in-plane oxygen vacancy or apical oxygen vacancy. Sr₂CuO_3+δ single-crystal samples were prepared using high-temperature and high-pressure methods. The major phase of Sr₂CuO_3+δ (δ = 0.4) single-crystal system is found to be constituted by the 5 a modulated structure with the Fmmm space group, which originates from the [CuO₂] in-plane oxygen vacancy appearing in octahedral Cu-O. Besides, the presence of the [CuO₂] in-plane oxygen vacancy may obliterate the superconductivity of the system. Experimental results deduce that the oxygen vacancy may appear in the apical oxygen sites in high-temperature copper oxide superconductors.     

基于注意力机制与文本信息的用户关系抽取

随着社交媒体的发展,用户之间的关系网络对于社交媒体的分析有很大的帮助。因此,该文主要研究用户好友关系检测。以往的关于用户好友关系抽取的研究主要基于社交媒体上的结构化信息,比如其他好友关系,用户的不同属性等。但是,很多时候用户本身并没有大量的好友信息存在,同时也不一定有很多确定的属性。因此,我们希望基于用户发表的文本信息来对用户关系进行预测。不同于以往的潜在好友推荐算法,该文提出了一种基于注意力机制以及长短时记忆网络(long short-term memory,LSTM)的好友关系预测模型,将好友之间的评论分开处理,通过分析用户之间的评论来判断是否具备一定的好友关系。该模型将好友双方信息拼接后的结果作为输入,并将注意力机制应用于LSTM的输出。实验表明,用户之间的评论对于好友关系预测确实有较大的实际意义,该文提出的模型较之于多个基准系统的效果,取得了明显的提升。在不加入任何其它非文本特征的情况下,实验结果的准确率达到了77%。     

Food recognition using neural network classifier and multiple hypotheses image segmentation

ABSTRACT

This paper proposes the multiple-hypotheses image segmentation and feed-forward neural network classifier for food recognition to improve the performance. Initially, the food or meal image is given as input. Then, the segmentation is applied to identify the regions, where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the features of every food item are extracted by the global feature and local feature extraction. After the features are obtained, the classification is performed for each segmented region using a feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food volume and (ii) calorie and nutrition measure based on mass value. The experimental results and performance evaluation are validated. The outcome of the proposed method attains 0.947 for Macro Average Accuracy (MAA) and 0.959 for Standard Accuracy (SA), which provides better classification performance.