A Data Complexity Analysis of Comparative Advantages of Decision Forest Constructors

Using a number of measures for characterising the complexity of classification problems, we studied the comparative advantages of two methods for constructing decision forests – bootstrapping and random subspaces. We investigated a collection of 392 two-class problems from the UCI depository, and observed that there are strong correlations between the classifier accuracies and measures of length of class boundaries, thickness of the class manifolds, and nonlinearities of decision boundaries. We found characteristics of both difficult and easy cases where combination methods are no better than single classifiers. Also, we observed that the bootstrapping method is better when the training samples are sparse, and the subspace method is better when the classes are compact and the boundaries are smooth. Received: 03 November 2000, Received in revised form: 25 October 2001, Accepted: 04 January 2002     

多分类器组合研究

文章提出了一种多分类器的组合方法,它利用了参与组合的分类器提供的度量层次上的两类信息:对训练样本的决策信息;对待识样本的决策信息。首先对这两类信息进行集成,进而给出了组合分类器的判定规则。用该方法对手写体汉字作分类识别,实验结果显示,较之其它几种方法,它有更高的正确识别率。     

Improved k-nearest neighbor classification

k-nearest neighbor (k-NN) classification is a well-known decision rule that is widely used in pattern classification. However, the traditional implementation of this method is computationally expensive. In this paper we develop two effective techniques, namely, template condensing and preprocessing, to significantly speed up k-NN classification while maintaining the level of accuracy. Our template condensing technique aims at “sparsifying” dense homogeneous clusters of prototypes of any single class. This is implemented by iteratively eliminating patterns which exhibit high attractive capacities. Our preprocessing technique filters a large portion of prototypes which are unlikely to match against the unknown pattern. This again accelerates the classification procedure considerably, especially in cases where the dimensionality of the feature space is high. One of our case studies shows that the incorporation of these two techniques to k-NN rule achieves a seven-fold speed-up without sacrificing accuracy.     

基于主动学习的分类器融合算法

本文提出了基于主动学习的分类融合算法,将度量层输出的分类器融合问题看作二级分类器的设计问题，将SVM主动学习引入二级分类器设计。该算法在有效减少标注代价的同时获得了较高的分类性能。实验证明该算法在分类性能和标注代价两方面都优于传统分类器融合方法。     

PAV and the ROC convex hull

Classifier calibration is the process of converting classifier scores into reliable probability estimates. Recently, a calibration technique based on isotonic regression has gained attention within machine learning as a flexible and effective way to calibrate classifiers. We show that, surprisingly, isotonic regression based calibration using the Pool Adjacent Violators algorithm is equivalent to the ROC convex hull method. Editor: Johannes Fürnkranz.     

一种双目标排序层分类器融合方法

最近 Melnik 提出了一种新的排序层分类器融合思想, 指出在分类器融合过程中既要调节对不同分类器的侧重程度, 又要利用不同序号值提供的置信度信息. 但是在 Melnik 提出的融合方法中, 参数数量随着分类器数量的增加呈指数级增长, 在分类器数目增加时会产生维数灾难问题. 在 Melnik 的思想启发下, 本文提出了一种新的融合方法, 该方法将对序号的变换与分类器的加权组合协调起来, 能够更好地实现 Melnik 提出的目标. 另外, 本文给出了一种用连续可微函数表示的分类错误率表达式, 设计了基于梯度下降的参数调节方法. 在实验中本文设计了融合掌纹图像数据和手指图像数据的多模态身份识别系统, 观察了不同数目分类器条件下的融合效果. 实验结果表明本文方法的分类正确率高于传统方法和 Melnik 的方法.     

带预分离装置的旋转煤粉分离器主要结构尺寸的确定及转子驱动气粉流耗功的理论计算

本文采用理论与实验相结合的方法，探讨了组合式旋转分离器的设计方法。确定了分离器中各主要的结构尺寸。从理论上导出了转子旋转功耗及气粉流产生的阻力矩计算公式，并进行了实例计算。本文的设计方法对于改善我国配ＭＰＳ磨煤机的组合式旋转分离器的设计具有重要的实际和理论价值。     

Influence of nozzle angle and classifier height on the performance of a spiral air jet mill

We study the effect of varying air jet mill design parameters, the nozzle angle and the classifier tube height, on the performance of the mill, operated in the semi-batch mode, using quartz and limestone particles as feed. Particle size distributions of the product and the material in the mill are measured along with the mass in the mill. The product size distribution and the specific mass flux are found to be constant with time. The breakage rate is found to increase with nozzle angle. The efficiency of classification, characterized by the fraction of coarse particles larger than the cut size, increases with nozzle angle and classifier tube height. The energy for grinding per unit mass of the product decreases with nozzle angle and increases with classifier tube height and optimal values of the parameters, at which the specific energy is minimized, are obtained.     

单导心电监护中不同电极模式的自动识别方法

电极脱落、电极混用等不正常电极模式会影响采集的心电信号的质量,导致误诊。人工判断电极模式是否正常过于依赖人的经验。为此对单导心电采集中4种电极模式的自动识别方法进行研究,定义了表征不同电极模式的心电信号的数字特征,结合基于LDA的特征降维和最近邻分类器来实现自动识别。实验表明,所提出的自动识别方法对单导心电设备4种电极模式的自动识别有效,对电极脱落的正确识别率可达到100%。     

基于平均奖赏强化学习算法的零阶分类元系统

零阶学习分类元系统ZCS（Zeroth-level Classifier System）作为一种基于遗传的机器学习技术（Genetics-Based Machine Learning）,在解决多步学习问题上,已展现出应用价值。然而标准的ZCS系统采用折扣奖赏强化学习技术,难于适应更为广泛的应用领域。基于ZCS的现有框架,提出了一种采用平均奖赏强化学习技术（R-学习算法）的分类元系统,将ZCS中的折扣奖赏强化学习方法替换为R-学习算法,从而使ZCS一方面可应用于需要优化平均奖赏的问题领域,另一方面则可求解规模较大、需要动作长链支持的多步学习问题。实验显示,在多步学习问题中,该系统可给出满意解,且在维持动作长链,以及克服过泛化问题方面,具有更优的特性。