以问题的疑问词、句法结构、疑问意向词、疑问意向词在知网中的首义原作为分类特征。
We choose the interrogative words, syntax structure, question focus words and its first sememes as classification feature.
该方法以问题的疑问词、句法结构、疑问意向词、疑问意向词在知网中的首义原作为分类特征。
We choose the interrogative words , syntax structure , question focus words and their first sememes as classification feature.
盒维数的简单统计结果可以作为PQ神经网络分类器的输入特征量。
After simple statistics, the dimension can act as the input vector of ANN for PQ classification.
将其作为分类器的输入特征量，提出了一种基于极化合成的目标分类算法，并对实测极化SAR数据进行了分类实验。
Algorithm of target classification based on polarization synthesis is proposed, when it is acted as input value of classifier. Then, polarimetric SAR data is applied to classification experiment.
在植物不同的器官中，叶表面的气孔分布特征可以作为植物分类的佐证。
In the plant organs, the stomatic distribution characteristics of leaf epidermis may be taken as an evidence of plant classification.
作为输入的FTIR特征谱峰不同时，则网络的平均分类识别正确率也不同。
The mean accurate rate of recognition of the LVQ neural network would be different, as the input vectors comtained different kind of FTIR characteristic frequencies.
本文提出了全局上下文属性和局部上下文属性两类属性作为分类模型的特征属性。
Two kinds of features, global context feature and local context feature, are proposed as the classification features.
根据构建概念格过程中概念聚类的特性，本文引出了概念格图形的近似自相似性这一特征作为信息分类的评估系数。
Based on the characteristics of conceptual cluster during the construction of concept lattices, this paper gave a characteristic of approximate self-similarity to value the information classification.
通常把词义消歧作为模式分类问题进行研究，其中特征选择是一个重要的环节。
WSD is usually considered as an issue about pattern classification to study, which feature selection, is an important component.
该结果说明：不同尺度下复杂性的差异可以作为图像分类的新方法或者作为现有分类器的特征。
The test shows that multi-scale Lempel-Ziv complexity can be used as an image classification method or as a feature of image classifier.
根据太白山自然保护区立地特征，以生态学作为立地分类理论依据，制定出一套较为完整的立地分类系统。
According to the site characteristics of Taibai Mountain conservation area, using ecology as theoretical bases, an integrated site classification system is established.
该方法将振动信号小波包分解后的频带能量作为特征向量，输入到由多个支持向量机构成的多故障分类器中进行故障识别和分类。
According to the method, the energy of different frequency bands after wavelet packet decomposition constitutes the input vectors of support vector machine as feature vectors.
在进行分类时，首先以色度矩作为特征向量，然后将支持向量机分类方法应用于黄瓜病害的识别。
At first, extracting features of chromaticity moments is done, then classification method of SVM for recognition of cucumber disease is discussed.
通过分析采样数据和比较各车型波形后，采用实际采样波形的幅值作为车型分类判据标准，整条波形的采样值作为模式匹配的特征参数。
After analyzing data and comparing automobile type of data ware, the max-data as criterion of vehicle classification, whole sample's data as character parameter of pattern matching.
然后，以特征系数作为识别特征量，采用最小距离分类法，实现了自动目标识别。
Then, the feature coefficients are classified by the minimum distance criterion to recognize the target automatically.
实例计算表明，分维作为描述土体粒度成分特征的参数，能较好反映了各种粒径大小在土体中的组成特点，可将其作为土体工程分类的一个综合性定量指标。
A case study indicates that fractional dimension can be used as a typical parameter to exactly reflect the structural characteristics of various soil grain sizes.
该方法应用小波包变换提取信号各子空间的能量，以能量分类距离标准选取最佳小波包基，最佳小波包基上距离系数大的能量作为特征值。
It applies WP translate to get energy from subspace and select the best WP bases with classification distance criterion. The energy has bigger distance coefficient in best WP bases is the feature.
重点探索了以不同特征作为输入的组合多分类器方法。
This article has summarized current methods of combining multiple classifiers, and investigated on embodying different features as input vectors.
通过将对分类有相同贡献的文本特征词聚合，使用它们共同的分类贡献向量特征模式作为文本特征向量的基本维；
Multiple discriminating features with similar contribution to classification are combined into one pattern, which is used as the basic feature dimension.
表皮的特征作为压型化石枝叶标本细胞信息的重要来源，甚至是惟一来源，一直作为杉科植物化石分类鉴定的主要依据。
Epidermal structures of leaves, the source of cellular information of fossil plants, provide the important evidence to separate the similar leaves of these genera in Taxodiaceous fossil plants.
三种目标提取方法在对空中目标声信号的特征提取均具有较高的可靠性，可作为分类器的输入。
The three methods have the high reliability to the airborne sound target, may as the sorter input.
子图像的特征奇异值组成整个图像的局部奇异值向量，作为分类器的输入。
With the data of characteristic singular values of sub-images, the Local Singular Value Vector of the whole image are combined, and are used as the input of the classifier.
确定了物体对称轴的取向后，可使用坐标变换方法，将轴对称物体的对称轴旋转到某一特定的取向，便于使用特征面积分布作为特征参数进行快速的目标分类识。
By rotating the symmetry axis of a target into a defined orientation, it is efficient for target recognition to use the feature area distribution as a parameter.
算法从位平面相关性的角度出发提取特征值，使用支持向量机作为分类器，对LSB匹配算法进行隐写分析。
From the perspective of bit plane correlation, this algorithm extracts features, USES support vector machine as a classifier to detect LSB matching.
研究了模式识别中的特征选择方法，采用最近邻分类正确率作为特征选择的性能评价函数。
The paper studies the methods of feature selection in pattern recognition, and USES nearest neighbor classification accuracy as the evaluation criteria for feature selection.
本文选用辨识参数作为模型聚类分析的特征向量，分别用HCM算法和FCM算法进行了分类研究。
In this paper, the identified parameter is used as feature vector of the load model cluster analysis; HCM and FCM are used as the classification algorithm.
不同种类昆虫的触角感器形态、结构、分布、数量等特征存在差异，可以作为昆虫分类的依据。
The morphological structure, composition, distribution and quantitative characteristics of antennal sensilla may serve as taxonomic characters.
海岸带作为海洋、陆地和大气共同作用的地带，其地物混杂度大，变化频繁，单纯利用光谱特征分类难以取得理想的精度。
Influenced jointly by such factors as ocean, land and atmosphere, the coastal zone is characterized by the mixing of various land types with high extent of variation.
海岸带作为海洋、陆地和大气共同作用的地带，其地物混杂度大，变化频繁，单纯利用光谱特征分类难以取得理想的精度。
Influenced jointly by such factors as ocean, land and atmosphere, the coastal zone is characterized by the mixing of various land types with high extent of variation.
应用推荐