Learning Classifier System Ensembles With Rule-Sharing

This paper presents an investigation into exploiting the population-based nature of learning classifier systems (LCSs) for their use within highly parallel systems. In particular, the use of simple payoff and accuracy-based LCSs within the ensemble machine approach is examined. Results indicate that inclusion of a rule migration mechanism inspired by parallel genetic algorithms is an effective way to improve learning speed in comparison to equivalent single systems. Presentation of a mechanism which exploits the underlying niche-based generalization mechanism of accuracy-based systems is then shown to further improve their performance, particularly, as task complexity increases. This is not found to be the case for payoff-based systems. Finally, considerably better than linear speedup is demonstrated with the accuracy-based systems on a version of the well-known Boolean logic benchmark task used throughout.     

Analysis of a Classifier with Random Thresholds

A neural classifier with random thresholds is considered. Probabilistic analysis of functional characteristics depending on the classifier parameters is performed, and recommendations for their selection are made. The classifier structure optimization is proposed for input data distribution.     

Multi-step Training of a Generalized Linear Classifier

Neural Processing Letters - We propose a multi-step training method for designing generalized linear classifiers. First, an initial multi-class linear classifier is found through regression. Then...     

Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy

Diversity among the members of a team of classifiers is deemed to be a key issue in classifier combination. However, measuring diversity is not straightforward because there is no generally accepted formal definition. We have found and studied ten statistics which can measure diversity among binary classifier outputs (correct or incorrect vote for the class label): four averaged pairwise measures (the Q statistic, the correlation, the disagreement and the double fault) and six non-pairwise measures (the entropy of the votes, the difficulty index, the Kohavi-Wolpert variance, the interrater agreement, the generalized diversity, and the coincident failure diversity). Four experiments have been designed to examine the relationship between the accuracy of the team and the measures of diversity, and among the measures themselves. Although there are proven connections between diversity and accuracy in some special cases, our results raise some doubts about the usefulness of diversity measures in building classifier ensembles in real-life pattern recognition problems.     

Feature representation selection based on Classifier Projection Space and Oracle analysis

One of the main problems in pattern recognition is obtaining the best set of features to represent the data. In recent years, several feature extraction algorithms have been proposed. However, due to the high degree of variability of the patterns, it is difficult to design a single representation that can capture the complex structure of the data. One possible solution to this problem is to use a multiple-classifier system (MCS) based on multiple feature representations. Unfortunately, still missing in the literature is a methodology for comparing and selecting feature extraction techniques based on the dissimilarity of the feature representations. In this paper, we propose a framework based on dissimilarity metrics and the intersection of errors, in order to analyze the relationships among feature representations. Each representation is used to train a classifier, and the results are compared by means of a dissimilarity metric. Then, with the aid of Multidimensional Scaling, visual representations are obtained of each of the dissimilarities and used as a guide to identify those that are either complementary or redundant. We applied the proposed framework to the problem of handwritten character and digit recognition. The analysis is followed by the use of an MCS built on the assumption that combining dissimilar feature representations can greatly improve the performance of the system. Experimental results demonstrate that a significant improvement in classification accuracy is achieved due to the complementary nature of the representations. Moreover, the proposed MCS obtained the best results to date for both the MNIST handwritten digit dataset and the Cursive Character Challenge (C-Cube) dataset.     

对抗环境下的线性分类器对抗性比较

机器学习算法为很多安全应用提供了良好的解决方案,然而机器学习算法本身却面临被敌手攻击的威胁。为分析敌手攻击对机器学习算法造成的影响,本文提出符合某些特定场合的敌手攻击模型,并在该模型下比较几种线性分类器的对抗性。最后在垃圾邮件过滤公开数据库上进行测试,实验结果表明,支持向量分类器具有相对较好的对抗性。     

GCD of Random Linear Combinations

We show that for arbitrary positive integers with probability the gcd of two linear combinations of these integers with rather small random integer coefficients coincides with This naturally leads to a probabilistic algorithm for computing the gcd of several integers, with probability via just one gcd of two numbers with about the same size as the initial data (namely the above linear combinations). This algorithm can be repeated to achieve any desired confidence level.     

一种基于线性的朴素贝叶斯分类器知识库的组织方法

提出一种基于线性的朴素贝叶斯分类器知识库组织方法.该方法按照朴素贝叶斯分类算法对所有条件概率进行统一计算,最后把计算结果储存在以枚举类型为下标的线性表当中,以便于快捷查找条件概率并结合先验概率来预测未知类属的样本.该方法具有可扩展性.     

基于局部加权表示的线性回归分类器及人脸识别

线性回归分类器(Linear Regression Classifier,LRC)是一种有效的图像分类算法,然而LRC未关注数据的局部结构信息,忽略了类内样本之间的差异性,因此当人脸图像存在表情、光照、角度、遮挡等变化时分类性能不佳.针对此问题,文中提出了一种基于局部加权表示的线性回归分类器(Local WeightedRepresentation based Linear Regression Classifier,LWR-LRC).LWR-LRC首先以测试样本与所有样本的相似性为度量,构建每类样本的加权代表样本;然后将测试样本分解为加权代表样本的线性组合;最后将测试样本分类到重构系数最大的类别.LWR-LRC考虑了样本的局部结构,构建了每类样本的最优代表样本,使用代表样本进行计算,在提高鲁棒性同时,大幅缩短了计算时间.在AR,CMU PIE,FERET和GT数据集上的实验的结果表明,LWR-LRC与NNC,SRC,LRC,CRC,MRC,LMRC等算法相比,在性能上有很强的优越性.     

一种Winnow线性分类器及其在TREC Novelty任务中的应用

文本检索会议(TextREtrievalConference,TREC)是目前国际上信息检索领域最重要的学术交流与国际评测活动。笔者等人代表中科院计算所参加了2003年TREC的Novelty任务。在该任务中,实现了Winnow线性分类器在检测relevant句子和novel句子中的应用。实验表明,这种简单的分类方法表现了较好的性能。     

Long Random Linear Programs Do Not Generalize

The chance of solving a problem by random search of long linear programs tends to a limit as their size increases. When all outputs are equally used this limit is no more than 2^{–|test set|}. The chance of randomly finding a long linear general solution is exponentially small.     

RTCS: a Reactive with Tags Classifier System

In this work, a new Classifier System is proposed (CS). The system, a Reactive with Tags Classifier System (RTCS), is able to take into account environmental situations in intermediate decisions. CSs are special production systems, where conditions and actions are codified in order to learn new rules by means of Genetic Algorithms (GA). The RTCS has been designed to generate sequences of actions like the traditional classifier systems, but RTCS also has the capability of chaining rules among different time instants and reacting to new environmental situations, considering the last environmental situation to take a decision. In addition to the capability to react and generate sequences of actions, the design of a new rule codification allows the evolution of groups of specialized rules. This new codification is based on the inclusion of several bits, named tags, in conditions and actions, which evolve by means of GA. RTCS has been tested in robotic navigation. Results show the suitability of this approximation to the navigation problem and the coherence of tag values in rules classification.     

任意切换时间下的二维线性混合系统的滑模控制

由于混合系统的复杂性,设计出能保证混合系统在任意切换时间下都能稳定的控制是比较困难的。为了突出滑模控制设计的思想,文章针对一类二维线性混合系统,提出通过确保混合系统实现滑动模的充分条件来保证系统的稳定性,并得到相应的控制律。仿真结果表明了该控制律的有效性。     

随机线性网络编码的一种差错控制方法

针对随机线性网络编码,提出点-点检错和端-端重传相结合的差错控制方法.借助于随机线性网络编码的鲁棒性,对信道的突发性错误和随机错误,采用三维奇偶校验码进行检错,让有错的数据包不参与编码;当宿点不能解出源点播出的信息时,通过反馈重传策略让源点重传信息,理论分析和仿真测试结果表明,在伽罗华域较大且数据包较长时,提出的方法能以较大的概率消除信道的传输错误,并解决了全局编码向量出错的问题,且以较低的重传率实现宿点完整地接收源点的信息.     

Priority Random Linear Codes in Distributed Storage Systems

Node churn and failures exist as fundamental characteristics in both peer-to-peer (P2P) and sensor networks. Peers in P2P networks are highly dynamic, whereas sensors are not dependable. As such, maintaining the persistence of periodically measured data in a scalable fashion has become a critical challenge in such systems, without the use of centralized servers. To better cope with node dynamics and failures, we propose priority random linear codes (RLCs), as well as their affiliated predistribution protocols, to maintain measurement data in different priorities, such that critical data have a higher opportunity to survive node failures than data of less importance. A salient feature of priority RLCs is the ability to partially recover more important subsets of the original data with higher priorities, when it is not feasible to recover all of them due to node dynamics. We present extensive analytical and experimental results to show the effectiveness of priority RLCs.     

线性分类器与BP网络联合诊断变压器故障

油中溶解气体分析(DGA)是目前电力充油设备潜伏性故障诊断的重要手段。为了克服传统BP网络及其改进诊断算法所具有的隐层节点数多、收敛时间长的缺陷,减少算法运算量及提高变压器故障诊断的正确率,提出了一种新的诊断算法:线性分类器-BP神经网络(LC-BP)故障辨识方法。通过对变压器大量过热和放电两类典型故障数据的研究,发现其DGA故障数据的特征空间线性可分且分离度较好。基于以上特性,先用线性分类器诊断过热和放电故障,然后利用两个小型BP网络分别进行进一步诊断,得到最终诊断结果。实验结果表明,提出的LC-BP算法具有良好的分类能力,故障诊断的正确率达到94%,且网络结构简单,运算量小,从而为变压器的故障诊断提供了一条新的有效途径。     

Classifier fusion with interval-valued weights

The article presents a new approach of calculating the weight of base classifiers from a committee of classifiers. The obtained weights are interpreted in the context of the interval-valued sets. The work proposes four different ways of calculating weights which consider both the correctness and incorrectness of the classification. The proposed weights have been used in the algorithms which combine the outputs of base classifiers. In this work we use both the outputs, represented by rank and measure level. Research experiments have involved several bases available in the UCI repository and two data sets that have generated distributions. The performed experiments compare algorithms which are based on calculating the weights according to the resubstitution and algorithms proposed in the work. The ensemble of classifiers has also been compared with the base classifiers entering the committee.