改进主题模型的短文本评论情感分析

使用传统的主题模型方法对医疗服务平台中的评论等短文本语料进行主题模型的情感分析时,会出现上下文依赖性差的问题。提出基于词嵌入的WLDA算法,使用Skip-Gram模型训练出的词w*替换传统的LDA模型中吉布斯采样算法里的词w`,同时引入参数λ,控制吉布斯采样时词的重采样的概率.实验结果证明,与同类的主题模型相比,该主题模型的主题一致性高.     

FUZZY RELATIONAL EQUATIONS: BRIDGING THEORY,METHODOLOGY AND PRACTICE

This study delivers a general overview of the theory and practice of fuzzy relational equations. We discuss various methods leading to the solutions of these equations starting from analytical approaches, moving through semi-analytic methods and finally elaborating on the neural-like style of finding solutions to relational constructs. The paper addresses important aspects of knowledge representation worked out by these equations and proposes a number of structural enhancements of the existing relational architectures.     

A single chart with supplementary runs rules for monitoring the mean vector and the covariance matrix of multivariate processes

The MRMAX chart is a single chart based on the standardized sample means and sample ranges for monitoring the mean vector and the covariance matrix of multivariate processes. User’s familiarity with the computation of these statistics is a point in favor of the MRMAX chart. As a single chart, the recently proposed MRMAX chart is very appropriate for supplementary runs rules. In this article, we compare the supplemented MRMAX chart and the synthetic MRMAX chart with the standard MRMAX chart. The supplementary and the synthetic runs rules enhance the performance of the MRMAX chart.     

An analysis of specialist and non-specialist user requirements for geographic climate change information

The EU EuroClim project developed a system to monitor and record climate change indicator data based on satellite observations of snow cover, sea ice and glaciers in Northern Europe and the Arctic. It also contained projection data for temperature, rainfall and average wind speed for Europe. These were all stored as data sets in a GIS database for users to download. The process of gathering requirements for a user population including scientists, researchers, policy makers, educationalists and the general public is described. Using an iterative design methodology, a user survey was administered to obtain initial feedback on the system concept followed by panel sessions where users were presented with the system concept and a demonstrator to interact with it. The requirements of both specialist and non-specialist users is summarised together with strategies for the effective communication of geographic climate change information.     

关于D.W.Etherington的扩充产生算法的一个注记

Ｄ．Ｗ．Ｅｔｈｅｒｉｎｇｔｏｎ提出了一类总是有扩充的缺省理论，即有限有序缺省理论，同时使用接连近似的方法给出产生这类缺省理论的所有扩充的算法，并证明该算法对有限有序网络缺省理论总是收敛到一扩充。本文首先举例说明Ｄ．Ｗ．Ｅｔｈｅｒｉｎｇｔｏｎｄ的算法对一般的有限有序缺省理论并非总是收敛，然后给出了该算法对
对一般的有限有序缺省理论收敛的一个充分条件。     

Stable growing neural gas: A topology learning algorithm based on player tracking in video games

Characters in video games usually use a manually-defined topology of the environment to navigate. To evolve in an open, unknown and dynamic world, characters should not have pre-existing representations of their environment. In this paper, characters learn this representation by imitating human players. We here put forward a modified version of the growing neural gas model (GNG) called stable growing neural gas (SGNG). The algorithm is able to learn how to use the environment from one or more teachers (players) by representing it with a graph. Unlike GNG, SGNG learning is in-line, reflecting the dynamic nature of the environment. The evaluation of the quality of the learned representations are detailed.     

基于组合矩特征的舰船目标识别

针对采用一维距离像特征进行舰船目标识别时,大样本需要、算法复杂和效率较低的问题,提出一种利用组合矩特征进行舰船目标识别的方法.首先提取目标距离像的变换不变矩及小波不变矩特征,并且在考虑算法效率及分类器设计的基础上,最终选取共6维特征构造组合矩,作为分类器输入,并利用实测数据对特征进行简化.分析结果表明:经过实测舰船数据验证,所提取的特征克服了姿态、幅度敏感性等特点,能够较好地表征不同类型舰船的差异.算法分类正确率较高,具有较好的工程应用前景.     

Effect of solution representations on Tabu search in scheduling applications

This research investigates the application of meta-heuristic algorithms to a scheduling problem called permutation manufacturing-cell flow shop (PMFS) from two perspectives. First, we examine the effect of using different solution representations (S_new and S_old) while applying Tabu-search algorithm. Experimental results reveal that Tabu_S_new outperforms Tabu_S_old. The rationale why Tabu_S_new is superior is further examined by characterizing the intermediate outcomes of the evolutionary processes in these two algorithms. We find that the superiority of S_new is due to its relatively higher degree of freedom in modeling Tabu neighborhood. Second, we propose a new algorithm GA_Tabu_S_new, which empirically outperforms the state-of-the-art meta-heuristic algorithms in solving the PMFS problem. This research highlights the importance of solution representation in the application of meta-heuristic algorithm, and establishes a significant milestone in solving the PMFS problem.     

用于一维图像识别的支撑矢量机方法

研究了支撑矢量机的分类机理,并利用支撑矢量机对雷达目标一维像进行了识别.识别的结果表明了该方法的优越性,并显示它可以对残缺不全的样本进行识别.     

基于Trace变换的人脸特征提取技术研究*

为了提高人脸特征的稳定性和区分度,提出了一种基于Trace变换的人脸特征提取算法。算法通过几种不同的泛函函数对预处理后的人脸图像进行组合作用,得到该图像的一个Trace特征向量,从而建立了一种新的人脸特征表达方式。基于ORL人脸数据库的实验结果表明,该算法所提出的人脸特征对同一个人不同表情、不同光照条件下的图像变化能够保持较好的稳定性,同时对不同人的人脸图像具有较高的区分能力,在人脸识别的实际应用中是一种可行的方法。