RSFM网络及其在信号滤波中的应用

介绍了一种适用于模式识别的新型神经网络模型--局部有监督特征映射（Reglonal Supervised Feature Mapping,RSFM）网络,描述了该网络的拓扑结构和学习算法,研究了网络的基本性能,最后将其应用到了信号滤波中.理论研究和仿真实验表明,该网络结构简单、算法简洁,收敛速度快、识别精度高,适用于需要大样本训练、随机干扰严重的复杂模式的分类与识别.     

A pattern recognition-based approach for phylogenetic network construction with constrained recombination

The tree representation of evolutionary relationship oversimplifies the view of the process of evolution as it cannot take into account the events such as horizontal gene transfer, hybridization, homoplasy and genetic recombination. Several algorithms exist for constructing phylogenetic networks which result from events such as horizontal gene transfer, hybridization and homoplasy. Very little work has been published on the algorithmic detail of phylogenetic networks with constrained recombination. The problem of minimizing the number of recombinations in a phylogenetic network, constructed using binary DNA sequences, is NP-hard. In this paper, we propose a pattern recognition-based O(n²) time approach for constructing the phylogenetic network, where n is the number of nodes or sequences in the input data. The network is constructed with the restriction that no two cycles in the network share a common node.     

降雨空间分布模式识别

以广东省内186个站点的年降雨量分布为基础，把模式识别的聚类分析理论方法引入降雨空间特征分类研究中，进行降雨特征空间分布模式识别，以预测无雨量站点的降雨模式，从而分析水资源的空间分布模式，以便制订有效的水资源利用方案。结果表明，广东省年降雨量在空间上的分布可划分为6类模式；同时基于BP人工神经网络算法，建立了以高程、气温、蒸发量为主要参数的可判别和预测无雨量测站区域的降雨空间分布模式所属类别的模型，经过模型的学习和验证，效果较好。     

Directional features in online handwriting recognition

The selection of valuable features is crucial in pattern recognition. In this paper we deal with the issue that part of features originate from directional instead of common linear data. Both for directional and linear data a theory for a statistical modeling exists. However, none of these theories gives an integrated solution to problems, where linear and directional variables are to be combined in a single, multivariate probability density function. We describe a general approach for a unified statistical modeling, given the constraint that variances of the circular variables are small. The method is practically evaluated in the context of our online handwriting recognition system frog on hand and the so-called tangent slope angle feature. Recognition results are compared with two alternative modeling approaches. The proposed solution gives significant improvements in recognition accuracy, computational speed and memory requirements.     

Remarks on different reviews of Chinese character recognition

This paper gives an introduction and remarks on two review papers for Chinese character recognition. One review is made by Chinese authors, another is from American scientists. They investigate Chinese character from different language environments; they do the research from different points of view. Thus, a more comprehensive view on Chinese character recognition, which is an important branch of pattern recognition, can be provided to the readers. Meantime, one article pays attention to online process, and other paper deals with offline recognition, which complement each other. The author is the Associate Editor-in-Chief of Frontiers of Computer Science in China     

Generation and context memory.

Generation enhances memory for occurrence but may not enhance other aspects of memory. The present study further delineates the negative generation effect in context memory reported in N. W. Mulligan (2004). First, the negative generation effect occurred for perceptual attributes of the target item (its color and font) but not for extratarget aspects of context (location and background color). Second, nonvisual generation tasks with either semantic or nonsemantic generation rules (antonym and rhyme generation, respectively) produced the same pattern of results. In contrast, a visual (or data-driven) generation task (letter transposition) did not disrupt context memory for color. Third, generating nonwords produced no effect on item memory but persisted in producing a negative effect on context memory for target attributes, implying that (a) the negative generation effect in context memory is not mediated by semantic encoding, and (b) the negative effect on context memory can be dissociated from the positive effect on item memory. The results are interpreted in terms of the processing account of generation. The original, perceptual-conceptual version of this account is too narrow, but a modified processing account, based on a more generic visual versus nonvisual processing distinction, accommodates the results. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

组织协同进化分类算法用于雷达目标一维像识别

针对雷达目标一维像识别问题，提出了一种基于组织协同进化分类算法的识别方法．该方法与现有进化分类方法的不同之处在于它的进化操作直接作用于样本而不是规则，采用了一种自下而上的搜索机制，即先使若干样本的集合得到进化，再从进化结果中提取规则．这样有利于避免在进化过程中产生无意义的规则．该方法不需要进行特征提取；对于高维数据，不需要预先进行降维处理；没有复杂的运算，训练和识别的速度都很快．对3种飞机微波暗室实测数据的识别实验表明，该方法性能稳定，优于基于支撑矢量机与子波核函数的方法，识别率均达到了96％以上．实验中还对算法的抗噪能力进行了测试，获得了良好的效果．     

Symbolic control of visual attention: The role of working memory and attentional control settings.

This study examined how 1 symbol is selected to control the allocation of attention when several symbols appear in the visual field. In Experiments 1-3, the critical target feature was color, and it was found that uninformative central arrows that matched the color of the target were selected and produced unintentional shifts of attention (i.e., involuntary, initiated slowly, producing long-lasting facilitatory effects). Experiment 4 tested whether such selection is the result of an attentional filter or of a competition bias due to a match of incoming information against integrated object representations stored in working memory. Here, the critical feature was shape and color was irrelevant, but matching color arrows were still selected. Thus, features of objects in working memory will bias the selection of symbols in the visual field, and such selected symbols are capable of producing unintentional shifts of attention. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Simultaneous translation of lectures and speeches

With increasing globalization, communication across language and cultural boundaries is becoming an essential requirement of doing business, delivering education, and providing public services. Due to the considerable cost of human translation services, only a small fraction of text documents and an even smaller percentage of spoken encounters, such as international meetings and conferences, are translated, with most resorting to the use of a common language (e.g. English) or not taking place at all. Technology may provide a potentially revolutionary way out if real-time, domain-independent, simultaneous speech translation can be realized. In this paper, we present a simultaneous speech translation system based on statistical recognition and translation technology. We discuss the technology, various system improvements and propose mechanisms for user-friendly delivery of the result. Over extensive component and end-to-end system evaluations and comparisons with human translation performance, we conclude that machines can already deliver comprehensible simultaneous translation output. Moreover, while machine performance is affected by recognition errors (and thus can be improved), human performance is limited by the cognitive challenge of performing the task in real time.