A new reverse reduce-error ensemble pruning algorithm

Although greedy algorithms possess high efficiency, they often receive suboptimal solutions of the ensemble pruning problem, since their exploration areas are limited in large extent. And another marked defect of almost all the currently existing ensemble pruning algorithms, including greedy ones, consists in: they simply abandon all of the classifiers which fail in the competition of ensemble selection, causing a considerable waste of useful resources and information. Inspired by these observations, an interesting greedy Reverse Reduce-Error (RRE) pruning algorithm incorporated with the operation of subtraction is proposed in this work. The RRE algorithm makes the best of the defeated candidate networks in a way that, the Worst Single Model (WSM) is chosen, and then, its votes are subtracted from the votes made by those selected components within the pruned ensemble. The reason is because, for most cases, the WSM might make mistakes in its estimation for the test samples. And, different from the classical RE, the near-optimal solution is produced based on the pruned error of all the available sequential subensembles. Besides, the backfitting step of RE algorithm is replaced with the selection step of a WSM in RRE. Moreover, the problem of ties might be solved more naturally with RRE. Finally, soft voting approach is employed in the testing to RRE algorithm. The performances of RE and RRE algorithms, and two baseline methods, i.e., the method which selects the Best Single Model (BSM) in the initial ensemble, and the method which retains all member networks of the initial ensemble (ALL), are evaluated on seven benchmark classification tasks under different initial ensemble setups. The results of the empirical investigation show the superiority of RRE over the other three ensemble pruning algorithms.     

基于模式间混淆关系自适应构建层次化分类器

为了解决层次化分类器的设计难点——子分类器的层属关系及其内部组成的确定,本文首先定义了模式间混淆关系,用于描述不同模式在判决域中的相互作用;进而提出了基于混淆矩阵度量模式间混淆关系的方法。设计并实现了多模式混淆关系分析机MPCRAM,将有师指派和无师自组两种常用的模式重组方法有机结合,遵循Fisher准则,自适应地产生层次化分类器结构。大量综合测试证实了该方法有效、实用,可显著提高分类器的识别性能和稳健性。     

Employing optimized combinations of one-class classifiers for automated currency validation

Automated currency validation requires a decision to be made regarding the authenticity of a banknote presented to the validation system. This decision often has to be made with little or no information regarding the characteristics of possible counterfeits as is the case for issues of new currency. A method for automated currency validation is presented which segments the whole banknote into different regions, builds individual classifiers on each region and then combines a small subset of the region specific classifiers to provide an overall decision. The segmentation and combination of region specific classifiers to provide optimized false positive and false negative rates is achieved by employing a genetic algorithm. Experiments based on high value notes of Sterling currency were carried out to assess the effectiveness of the proposed solution.     

Information-Based Evaluation Criterion for Classifier's Performance

In the past few years many systems for learning decision rules from examples were developed. As different systems allow different types of answers when classifying new instances, it is difficult to appropriately evaluate the systems' classification power in comparison with other classification systems or in comparison with human experts. Classification accuracy is usually used as a measure of classification performance. This measure is, however, known to have several defects. A fair evaluation criterion should exclude the influence of the class probabilities which may enable a completely uninformed classifier to trivially achieve high classification accuracy. In this paper a method for evaluating the information score of a classifier's answers is proposed. It excludes the influence of prior probabilities, deals with various types of imperfect or probabilistic answers and can be used also for comparing the performance in different domains.     

Predictive modeling of mercury speciation in combustion flue gases using GMDH-based abductive networks

Modeling mercury speciation is an important requirement for estimating harmful emissions from coal-fired power plants and developing strategies to reduce them. First-principle models based on chemical, kinetic, and thermodynamic aspects exist, but these are complex and difficult to develop. The use of modern data-based machine learning techniques has been recently introduced, including neural networks. Here we propose an alternative approach using abductive networks based on the group method of data handling (GMDH) algorithm, with the advantages of simplified and more automated model synthesis, automatic selection of significant inputs, and more transparent input–output model relationships. Models were developed for predicting three types of mercury speciation (elemental, oxidized, and particulate) using a small dataset containing six inputs parameters on the composition of the coal used and boiler operating conditions. Prediction performance compares favourably with neural network models developed using the same dataset, with correlation coefficients as high as 0.97 for training data. Network committees (ensembles) are proposed as a means of improving prediction accuracy, and suggestions are made for future work to further improve performance.     

FuzzyBagging: A novel ensemble of classifiers

In this work, a new method for the creation of classifier ensembles is introduced. The patterns are partitioned into clusters to group together similar patterns, a training set is built using the patterns that belong to a cluster. Each of the new sets is used to train a classifier. We show that the approach here presented, called FuzzyBagging, obtains performance better than Bagging.     

基于特征选择的集成分类器抗噪性能分析

特征选择有助于增强集成分类器成员间的随机差异性,从而提高泛化精度。研究了随机子空间法（RandomSub-space）和旋转森林法（RotationForest）两种基于特征选择的集成分类器构造算法,分析讨论了两算法特征选择的方式与随机差异程度之间的关系。通过对UCI数据集引入噪声,比较两者在噪声环境下的分类精度。实验结果表明：当噪声增加及特征关联度下降时,基本学习算法及噪声程度对集成效果均有影响,当噪声增强到一定程度后。集成效果和单分类器的性能趋于一致。     

基于神经网络集成的软件故障预测及实验分析

软件系统故障预测是软件测试过程中软件可靠性研究的重点之一。利用软件系统测试过程中前期的故障相关信息进行建模,预测后期的软件故障信息,以便于后期测试和验证资源的合理分配。根据软件测试过程中已知的软件故障时间序列,利用非齐次泊松分布过程、神经网络、神经网络集成等方法对其进行建模。通过对三个实例分别建模,其预测平均相对误差G-O模型依次为3.02%、5.88%和6.58%,而神经网络集成模型为0.19%、1.88%和1.455%,实验结果表明神经网络集成模型具有更精确的预测能力。     

Linear reconstruction measure steered nearest neighbor classification framework

The linear reconstruction measure (LRM), which determines the nearest neighbors of the query sample in all known training samples by sorting the minimum L₂-norm error linear reconstruction coefficients, is introduced in this paper. The intuitive interpretation and mathematical proofs are presented to reveal the efficient working mechanism of LRM. Through analyzing the physical meaning of coefficients and regularization items, we find that LRM provides more useful information and advantages than the conventional similarity measure model which calculates the distance between two entities (i.e. conventional point-to-point, C-PtP). Inspired by the advantages of LRM, the linear reconstruction measure steered nearest neighbor classification framework (LRM-NNCF) is designed with eight classifiers according to different decision rules and models of LRM. Evaluation on several face databases and the experimental results demonstrate that these proposed classifiers can achieve greater performance than the C-PtP based 1-NNs and competitive recognition accuracy and robustness compared with the state-of-the-art classifiers.     

水泥微细分级的试验研究

用新开发的新型旋风式微细分级机进行水泥微细分级试验.结果表明.当原动中10μm以下的颗粒含量52.6%,经分级后的细粉中小于10μm的颗粒含量达88.9%,平均粒径为4.06μm.分级切割粒径为11.8μm分级精度d_(75)/d_(25)<1.5.