基于类区分度的高维不平衡特征选择算法

传统特征选择算法没有考虑特征之间的关联性,并且基于类别平衡假设,在不平衡问题上偏向多数类而忽略少数类。针对以上不足,本文综合考虑特征相关性与不平衡性,提出一种基于类区分度的高维不平衡特征选择算法CDHI,该算法通过k-means进行特征聚类,并计算簇中每个特征的类区分度,利用类区分度对聚类簇中特征进行重要性排序,然后选择各簇中类区分度较高的特征组成特征子集,达到去除高维特征冗余与处理不平衡数据的双重目的。实验结果表明,与传统特征选择方法相比,CDHI算法有效降低了特征空间的维度,提高了少数类的识别率。

基于类间区分度的属性约简方法

属性约简是粗糙集理论中最重要的研究问题之一。近年来,粗糙集理论下的属性约简问题引发了学者们广泛的关注。然而,大多数属性约简方法都是基于不可分辨或可分辨关系所提出的,属性约简的性能仅仅取决于等价类或近似集的变化,却忽略了不具有等价关系的对象所在的不同类簇间关系的变化情况。因此,引入了类间区分度的概念,相较于等价类和上下近似集而言,它可以反映类簇区分程度随属性变化而变化的情况。对类间重合度和类间区分度进行了解释及定义,并结合启发式搜索策略,提出了一种基于类间区分度的属性约简方法,实验验证了所提方法的有效性。

基于随机森林的电网GIS数据分布式存储方法

内部电网地理信息系统(Geographic Information Systern,GIS)数据体量增加,对电网数据存储性能造成了极大的困难,为此,提出一种基于随机森林的电网GIS数据分布式存储方法。以跨域资源共享(Cross-Origin Resource Sharing,CORS)技术在电网GIS空间信息服务平台中获取的电网GIS数据为基础,根据类区分度数值选择电网GIS数据特征,引入随机森林算法分类处理电网GIS数据,将其合理分发给不同的服务器,采用并行处理手段存储分类数据,从而实现了电网GIS数据的分布式存储。实验数据显示:应用所提方法后,电网GIS数据分类精度达到了96.8%,电网GIS数据分布式存储时间最小值为5.2 s,充分证实了所提方法数据存储性能更佳。

基于对象立方体结构的类描述规则挖掘

在类描述规则中,特征规则用于描述目标类中对象的特征,区分规则用于区分一个类及其对比类。研究基于对象立方体结构的类描述规则表示及其发现方法。通过实验验证该方法的可行性,得到用高层概念表示的类描述规则,该规则有助于用户对特定类进行识别。

一种大规模高维数据快速聚类算法

提出了一种面向大规模高维数据的自组织映射聚类算法.算法通过压缩神经元的特征集合,仅选择与神经元代表的文档类相关的特征构造神经元的特征向量,从而减少了聚类时间.同时由于选取的特征能够将映射到不同神经元的文档类进行有效区分,避免了无关特征的干扰,因而提升了聚类的精度.实验结果表明该方法能够有效加快聚类的速度,提升聚类的准确度,达到比较理想的聚类效果.

文本分类中一种改进的特征项权重计算方法

TF-IDF方法是文本向量化过程中一种常用的特征项权重计算方法,衡量的是特征项在整个文档集中的重要性.针对文本分类过程中TF-IDF方法未能体现特征项对类别的区分能力和对类别的代表性问题,基于文档类别,结合特征项的类间区分度和类内贡献度,提出一种改进的TF-IDF权重计算方法,并采用KNN和SVM模型对改进后算法的分类性能进行了验证.实验结果表明,与传统的TF-IDF方法相比,改进后的权重计算方法不仅在整个测试数据集上能够取得较高的宏平均精确率、宏平均召回率和宏平均F1,而且使测试数据集绝大部分类别的分类性能得到了较大提升.因此,改进后的TF-IDF权重计算方法是有效且可行的.

一种基于时频原子特征的雷达辐射源信号识别方法

提出了一种全新的基于时频原子特征的雷达辐射源信号识别方法.训练阶段,在过完备时频原子库的基础上,以类区分度为度量,提取少数最能区分不同类别信号的时频原子作为一组固定的特征;识别阶段,以原子和信号的内积的绝对值作为分类器的输入特征,采用有监督模糊自适应共振网络进行辐射源的自动识别.对5类典型雷达辐射源信号的实验结果表明,该方法大大减小了识别过程中特征提取的计算量,输入特征具有类内聚集性强、类间区分度大的特点,在信噪比大于3 dB时可以获得高的识别正确率.

艺术院校教材建设之我见

教材建设是培养人才的基础,搞好教材建设,直接关系到培养人才的质量,尤其是艺术院校显得更为突出,因为艺术院校的艺术门类区分细,专业性强,学生人数少,教师品味不同,教材难以固定。就拿广西艺术学院来说,只有五个系,就有114门课程,其中需订购的教材有75种,任课老师自编的13种,还有部分课程是由任课老师临场发挥教学的,并无课本。在订购教材中,最多的有300册,最少的才有10册,可见教材的订购难度是比较大的。在这种情况下,作为教材管理部门,应该如何抓好教材建设?笔者认为,主要是做好以下三个方面的工作。

一种新的鲁棒声纹特征提取与融合方法

为提高说话人确认系统在噪声环境下的鲁棒性,在利用听觉外周模型改进Mel频率倒谱系数(Mel Frequency Cepstral Coefficient,MFCC)的基础上,结合感知线性预测系数(Perceptual Linear Predictive Coefficient,PLPC),以类间区分度为依据,在特征域对两种声纹特征进行融合,提出一种新的声纹特征提取方法,并对基于该特征的说话人确认系统的噪声鲁棒性进行研究。针对不同信噪比的语音信号进行了融合特征与原始特征的对比实验,结果表明,融合特征在模拟餐厅噪声环境中的错误率更低,较MFCC与PLPC分别降低了2.2%和3.1%,说话人确认系统在噪声中的鲁棒性得到提升。

一种改进的ID3算法

决策树是数据挖掘的一种重要方法,通常用来形成分类器和预测模型。ID3算法作为决策树的核心算法,由于它的简单与高效而得到了广泛的应用,然而它倾向于选择属性值较多的属性作为分支属性,从而可能错过分类能力强的属性。对ID3算法的分支策略进行改进,增加了对属性的类区分度的考量。经实验比较,新方法能提高决策树的精度,简化决策树。

A Scheme of Vegetation Classification of Taiwan, China

The complexity of natural conditions leads to the complexity of vegetation types of Taiwan of China, which has both tropical and cold-temperate vegetation types, and could be depicted as the vegetation miniature of China or even for the world. The physiognomic-floristic principle was adopted for the vegetation classification of Taiwan. The units of rank from top to bottom are: class of vegetation-type, order of vegetation-type, vegetation-type, alliance group, alliance and association. The high-rank units (class, order and vegetation-type) are classified by ecological physiognomy, while the median and lower units by the species composition of community. At the same time the role of dominant species and character species will also be considered. The dominant species are the major factor concerned with the median ranks (alliance group, and alliance) because they are the chief components of community, additionally their remarkable appearance is easy to identify; the character species (or diagnostic species) are for relatively low ranks (association) because they will clearly show the interspecies relation-ship and the characteristics of community. According to this principle, vegetation of Taiwan is classi-fied into five classes of vegetation-types (forests, thickets, herbaceous vegetation, rock fields vegetation, swamps and aquatic vegetation), 29 orders of vegetation-types (cold-temperate needle-leaved forests, cool-temperate needle-leaved forests, warm-temperate needle-leaved forests, warm needle-leaved forests, deciduous broad-leaved forests, mixed evergreen and deciduous broad-leaved forests, evergreen mossy forests, evergreen sclerophyllous forests, evergreen broad-leaved forests, tropical rain forests, tropical monsoon forests, coastal forests, warm bamboo forests, evergreen needle-leaved thickets, sclerophyllous thickets, deciduous broad-leaved thickets, evergreen broad-leaved thickets, xerothermic thorn-succulent thickets, bamboo thickets, meadows, sparse shrub grasslands, savannahic grasslands, sparse scree communities, chasmophytic vegetation, woody swamps, herbaceous swamps, moss bogs, fresh water aquatic vegetation, salt water aquatic vegetation) and 53 vegetation-types. The main alliances of each vegetation-type are described.

Discussions on taxonomy of genus Betula in northeast China

Many researches have been carried out on the taxonomy of Betula in northeast of China, but the classification of species and subdivision of species had some divergences at all times, which led to a disorder for developing and utilizing resources of Betula. In this paper, species and subdivision of Betula were classified not only according to the wax sample of Betula but also the comprehensive taxonomy of population characters, geographical distribution, and the habitat. Theconclusion supported the Fu Pei-yuns?(1995) viewpoint of the taxonomy of Betula in the northeast of China. But B. mandshurica (Regel) Nakai should be considered as one single species, the name of B. platyphyla Suk.var phellodendroidesTung should be the synonym of B. platyphyla var platyphyla, and B. ermanii Cham.var.yingkiliensis liou et Wang should be incorporated into B. ermanii Cham. B. ovalifolia Rupr should not be regarded as a variety of B. fruticosa Pall. but as one single species.

Division of forest fuel type areas of Heilongjiang Province by using GIS

Eight factors, including forest coverage, fuel load, species composition, elevation, monthly mean temperature, monthly mean relative humidity, monthly mean wind velocity, and monthly mean precipitation of fire season, were considered and the methods of weight, the cumulative probability, ARC/INFO technique, and raster-to-vector conversion were adopted in division of forest fuel type area. Firstly, the electronic maps of forest distribution and administrative divisions were built, then overlaid and transformed to the real-world coordinates. Finally, the forest fuel type areas of Heilongjiang Province including 81 counties were divided into five grades, accounting for 16%, 17%, 17%, 11%, and 38% respectively. The grade Ⅰ fuel type areas with highest fire danger rating mainly distributed on Daxinganling Mountains, Xiaoxinganling Mountains, and Zhangguangcailing Mountains, the grade Ⅴ fuel type areas mainly centralized on Songnen Plain, Sanjiang Plain, and other Plains, and other forest fuel type areas (grades Ⅱ, Ⅲ, and Ⅳ) were situated between plains and mountainous areas.

Characteristics,classification and ordination of riparian plant communities in the Three-Gorges areas

Sixteen different vegetation types of grassland and shrubland were selected to study the component and diversity of plant species of riparian plant communities along main channel in the Three-Gorges areas. Species richness (s), Simpson index (D), and Shannon-Weiner index (H) were used to study the biodiversity and the hierarchical classification was carried out by the methods of TWINSPAN and DCA ordination. The results showed that the components of flora were complex and dominated by the temperate type in the riparian plant communities. Species diversity was not different between the communities, but Shannon-Weiner indexes of different layers in some grassland were significantly different. TWINSPAN and DCA indicated that riparian plant communities distributed along the gradient of moisture.

Preliminary Studies on the Zoogeographic Divisions of Chinese Ground Spiders(Araneae:Gnaphosidae)

This paper aims to carry out the preliminary study on the zoogeographic distributions of 166 species within Gnaphosidae by clustering method,and analyze and compare the similarities of 15 subregions in seven zoogeographic regions in China.The results suggested that the division of Northern China was coincident with the distribution pattern of Chinese ground spiders,but there was subregion recombination between the other regions.There was aggregation between Da Hinggan Mountains subregion in the Northeast,east plain subregion in Mengxin area and west hungriness subregion,between Tianshan mountainous subregion in Mengxin area,Qiangtang altiplano subregion and the southwest mountainous region subregion in Southwest,and between east hill plain subregion in central China,west mountainous region altiplano subregion,Min and Guang coastal subregion in south of China and south Dian mountainous region subregion.The other two subregions in the Northeast formed a region.Qinghai and south Xizang subregion in Qinghai-Xizang Region formed a branch independently.

读《中国文法论》

何容《中国文法论》写于1937年,1942年才由开明书店出版。1948年作者对该书作了一些修改,1957年由新知识出版社重印。1985年《中国文法论》被选入《汉语语法丛书》,由商务印书馆重版。

Studies on the Calyptratae in Ningbo City

[Objective] The aim was to master the distribution of Calyptratae in Ning-bo. [Method] The species and distribution of the Calyptratae in Ningbo were studied using the cage trap and butterfly nets method from 2010 to 2013. [Result] The re-sults showed that Calyptratae of 82 species, 45 genera, 6 families were recognized in Ningbo. The characters of the faunistic distribution were discussed. [Conclusion] The research indicated that the species of Calyptratae are diversified in Ningbo.

Analysis on Chemical Compositions in Chinese Wolfberry from Different Producing Areas

[Objective] This study aimed to conduct correspondence cluster analysis of the trace elements in Chinese wolfberry from Qinghai and Ningxia regions, and to investigate the relationship among the quality of the wolfberry samples, the composition of trace elements and the sample sources. [Method] The determined contents of trace elements and ratios of zinc to copper （Zn/Cu） of wolfberry from 11 different producing areas of Qinghai and Ningxia regions were adopted to construct the raw measurement data matrix, to analyze the distribution characteristics of the trace ele- ments in wolfberry from Qinghai and Ningxia by using the corresponding cluster analysis method. [Result] The quality of wolfberry samples in 7hongning County, Zhongwei City, Pingluo County, Shizuishan City, Heicheng Town of Ningxia Hui Au-tonomous Region and Hehuang Valley, Golmud City of Qinghai Province is mainly related to the contents of Zn and Mn; Zn/Cu greatly affects the quality of Chinese wolfberry in Dulan County of Qinghai Province; Fe has great effect on the quality of Chinese wolfberry in Yinchuan City of Ningxia Hui Autonomous Region; Cu greatly affects the quality of Chinese wolfberry in Nuomuhong Village of Qinghai Province and a wolfberry research institute in Ningxia. [Conclusion] The relationship between the quality of wolfberry from different producing areas and the trace elements was investigated, which provides theoretical and practical basis for the cultivation, har- vesting, processing, and further development and utilization of Chinese wolfberry resources from different producing areas.

《基础写作》摭谈(下)

说明说明是运用简洁明了的文字对事物做清楚的解说。对事理做明白的剖释,以使读者对说明对象有客观正确的认识。说明,有对实体事物的说明和对抽象事理的说明两种。说明的要求,一是正确把握说明对象,二是要解说的容易为读者所理解。正确地把握说明对象,首先必须明确说明的问题点,即明确要说明什么问题及明确要回答的疑问之点;其次则是科学地把握问题点。这要求作者有问题意识,对所要说明的问题仔细观察、分析、研究;对说明对象深入了解、认识;力求解说得客观、科学。科学地把握问题点,是说明的前提。客观问题的说明点是很多的,如内容、结构、形式、规则、规律等。所谓"科学地把握",指的是概念的准确,判断的正确,种类区分清楚的界说,事物间内部联系的同异分明……因此种种,都要恰如其理、恰如其分。

再版、再印的文学名著著录探讨

我国文学名著的版本形式复杂多样,如何使不同版本的同种文学名著集中在同一个类号下,对不同版本的文学名著取号;如何进一步再区分及文学名著其它方面的著录作了一些粗浅的论述。