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。     

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.     

Critical state model for structured soil

Structure is an evident determinant for macroscopic behaviors of soils. However, this is not taken into account in most constitutive models, as structure is a rather complex issue in models. For this, it is important to develop and implement simple models that can reflect this important aspect of soil behavior. This paper tried to model structured soils based on well-established concepts, such as critical state and sub-loading. Critical state is the core of the classic Cam Clay model. The sub-loading concept implies adoption of an inner (sub-loading) yield surface, according to specific hardening rules for some internal strain-like state variables. Nakai and co-workers proposed such internal variables for controlling density (ρ) and structure (ω), using a modified stress space, called t_ij. Herein, similar variables are used in the context of the better-known invariants (p and q) of the Cam Clay model. This change requires explicit adoption of a non-associated flow rule for the sub-loading surface. This is accomplished by modifying the dilatancy ratio of the Cam Clay model, as a function of the new internal variables. These modifications are described and implemented under three-dimensional (3D) conditions. The model is then applied to simulating laboratory tests under different stress paths and the results are compared to experiments reported for different types of structured soils. The good agreements show the capacity and potential of the proposed model.     

A Distribution‐freeCUSUMChart for Monitoring Variability of AutocorrelatedProcesses

We present a distribution‐free tabular cumulative sum chart for monitoring the variability of an autocorrelated process. A quantity known as the asymptotic variance parameter is employed as a measure of the variability, and a distribution‐free tabular cumulative sum chart is applied to variance estimates calculated from batches of nonoverlapping samples. The proposed chart is applicable to a stationary process with a general marginal distribution and a general autocorrelation structure. It also determines control limits analytically without trial‐and‐error simulations. The performance of the proposed chart is tested on stationary processes with both normal and nonnormal marginals with various autocorrelation structures. Copyright © 2014 John Wiley & Sons, Ltd.     

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%。     

因素空间理论下基点分类算法研究

目前，基于因素空间理论的背景基提取算法计算过程复杂，初始化必须依赖各因素极值，基点数量提取冗余等原因，未能在应用中取得很好效果。为此，结合内点判别法和知识可继承、可扩展的思想，提出一种计算简单、初始化独立、基点数量小的改进的背景基提取算法。然后，利用改进的背景基提取算法构造出一种全新的数据分类算法-基点分类算法，基点分类算法以提取每一类样本的背景基为预测模型，再通过新定义的λ-背景基，优化预测模型。数值实验表明:基点分类算法原理简单、构造难度小、分类模型泛化能力强，预测能力准确率高，同时严格的模型限定区域又能为识别新类别提供新方法。     

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.     

基于密集神经网络的灰度图像着色算法

针对在灰度图像着色领域中，传统算法信息提取率不高、着色效果不理想的问题，提出了基于密集神经网络的灰度图像着色算法，以实现改善着色效果，让人眼更好地观察图片信息的目的。利用密集神经网络的信息提取高效性，构建并训练了一个端到端的深度学习模型，对图像中的各类信息及特征进行提取。训练网络时与原图像进行对比，以逐渐减小网络输出结果的信息、分类等各类型的损失。训练完成后，只需向网络输入一张灰度图片，即可生成一张颜色饱满、鲜明逼真的彩色图片。实验结果表明，引入密集网络后，可有效改善着色过程中的漏色、细节信息损失、对比度低等问题，所提算法着色效果较基于VGG网络及U-Net、双流网络结构、残差网络（ResNet）等性能优异的先进着色算法而言取得了显著的改进。     

1,5-己二烯交联烯烃聚合物的合成及其抗剪切稳定性

以金属配合物为催化剂、1,5-己二烯为交联剂,采用本体聚合法合成了交联超高相对分子质量烯烃类聚合物(简称交联聚合物)。用傅里叶变换红外光谱、核磁共振、凝胶渗透色潜表征交联聚合物的结构和相对分子质量。用旋转黏度计和超声波仪研究了1,5-己二烯用量对交联聚合物溶液表观黏度的影响及交联聚合物的相对分子质量对交联聚合物溶液抗剪切稳定性的影响。实验结果表明,在最佳聚合条件(单体80mL、助催化剂0．4mL、CS-1催化剂0．090g、1,5-己二烯0．40mL、0℃、24 b)下所合成的交联聚合物的重均相对分子质量为7．7×106,数均相对分子质量3．6×106。加入少量1,5-己二烯能提高交联聚合物的抗剪切能力,同时也能提高交联聚合物的相对分子质量。交联聚合物的相对分子质量越大,抗剪切稳定性越好。1,5-己二烯用量约为0．1 mL时(单体40 mL),交联聚合物溶液的表观黏度达到最大值(16．8 mPa·s)。