Towards Incremental Fuzzy Classifiers

Fuzzy classification systems (FCS) are traditionally built from observations (data points) in an off-line one shot-experiment. Once the learning phase is exhausted, the classifier is no more capable to learn further knowledge from new observations nor is it able to update itself in the future. This paper investigates the problem of incremental learning in the context of FCS. It shows how, in contrast to off-line or batch learning, incremental learning infers knowledge in the form of fuzzy rules from data that evolves over time. To accommodate incremental learning, appropriate mechanisms are applied in all steps of the FCS construction: (1) Incremental supervised clustering to generate granules in a progressive manner, (2) Systematic and automatic update of fuzzy partitions, (3) Incremental feature selection using an incremental version of Fisher’s interclass separability criterion. The effect of incrementality on various aspects is demonstrated via a numerical evaluation.     

A scalable, incremental learning algorithm for classification problems

In this paper a novel data mining algorithm, Clustering and Classification Algorithm-Supervised (CCA-S), is introduced. CCA-S enables the scalable, incremental learning of a non-hierarchical cluster structure from training data. This cluster structure serves as a function to map the attribute values of new data to the target class of these data, that is, classify new data. CCA-S utilizes both the distance and the target class of training data points to derive the cluster structure. In this paper, we first present problems with many existing data mining algorithms for classification problems, such as decision trees, artificial neural networks, in scalable and incremental learning. We then describe CCA-S and discuss its advantages in scalable, incremental learning. The testing results of applying CCA-S to several common data sets for classification problems are presented. The testing results show that the classification performance of CCA-S is comparable to the other data mining algorithms such as decision trees, artificial neural networks and discriminant analysis.     

Multirelational classification: a multiple view approach

Multirelational classification aims at discovering useful patterns across multiple inter-connected tables (relations) in a relational database. Many traditional learning techniques, however, assume a single table or a flat file as input (the so-called propositional algorithms). Existing multirelational classification approaches either “upgrade” mature propositional learning methods to deal with relational presentation or extensively “flatten” multiple tables into a single flat file, which is then solved by propositional algorithms. This article reports a multiple view strategy—where neither “upgrading” nor “flattening” is required—for mining in relational databases. Our approach learns from multiple views (feature set) of a relational databases, and then integrates the information acquired by individual view learners to construct a final model. Our empirical studies show that the method compares well in comparison with the classifiers induced by the majority of multirelational mining systems, in terms of accuracy obtained and running time needed. The paper explores the implications of this finding for multirelational research and applications. In addition, the method has practical significance: it is appropriate for directly mining many real-world databases.

Incremental learning with multi-level adaptation

Self-adaptation is an inherent part of any natural and intelligent system. Specifically, it is about the ability of a system to reconcile its requirements or goal of existence with the environment it is interacting with, by adopting an optimal behavior. Self-adaptation becomes crucial when the environment changes dynamically over time. In this paper, we investigate self-adaptation of classification systems at three levels: (1) natural adaptation of the base learners to change in the environment, (2) contributive adaptation when combining the base learners in an ensemble, and (3) structural adaptation of the combination as a form of dynamic ensemble. The present study focuses on neural network classification systems to handle a special facet of self-adaptation, that is, incremental learning (IL). With IL, the system self-adjusts to accommodate new and possibly non-stationary data samples arriving over time. The paper discusses various IL algorithms and shows how the three adaptation levels are inherent in the system's architecture proposed and how this architecture is efficient in dealing with dynamic change in the presence of various types of data drift when applying these IL algorithms.     

A nonparametric classification scheme with mean squared error criterion

A statistical classification scheme for a given set of data requires knowledge of the probability distribution of the observations. Traditional approaches to this problem have revolved around chosen various parametric forms for the probability distribution and evaluating these by goodness of fit methods. Among the difficulties with this method are that it is time consuming, it may not lead to satisfactory results and it may lie beyond the statistical expertise of many practitioners. In this paper, the author's consider the use of a recently developed nonparametric probability density estimator in classification schemes with mean squared error loss criterion. Classical parametric approaches are compared to the nonparametric method on simulated data on the basis of the misclassification probability. Real data from the medical and biological sciences are also used to illustrate the usefulness of the nonparametric method.     

一种使用shapelets的增量式时间序列分类

根据时间序列数据维度高、实值有序、数据间存在自相关性等特点,对时间序列分类过程进行研究。研究了当前比较流行的时间序列分类方法;从图像处理的角度出发,提出了一种将图片信息转化为时间序列数据的ITTS方法。shapelets作为最能够表示一条时间序列的子序列,随着时间的推移,这个特征序列可能会动态地发生变化。基于这样的思想,提出了一种基于动态发现shapelets的增量式时间序列分类算法IPST。该算法能够较好地动态发现当前最优的k个shapelets,从而提高时间序列分类的准确度。 得到 的shapelets集合还可以与多个传统的分类器结合,从而获得更佳的分类效果。     

An experimental comparison of the new goal programming and the linear programming approaches in the two-group discriminant problems

The aim of this article is to consider a new linear programming and two goal programming models for two-group classification problems. When these approaches are applied to the data of real life or of simulation, our proposed new models perform well both in separating the groups and the group–membership predictions of new objects. In discriminant analysis some linear programming models determine the attribute weights and the cut-off value in two steps, but our models determine simultaneously all of these values in one step. Moreover, the results of simulation experiments show that our proposed models outperform significantly than existing linear programming and statistical approaches in attaining higher average hit-ratios.     

Divide: a fortran IV program for segmenting multivariate one-dimensional spatial series

DIVIDE is a FORTRAN IV computer program for dividing a multivariate sequence of observations into relatively homogeneous segments. A window, split about its midpoint, is moved along the sequence from one end to the other. At each position the two halves are compared, and either Mahalanobis D² or squared Euclidean distance calculated. Maxima in the criterion indicate the division points.     

Learning a locality discriminating projection for classification

This paper introduces a new algorithm called locality discriminating projection (LDP) for subspace learning, which provides a new scheme for discriminant analysis by considering both the manifold structure and the prior class information. In the LDP algorithm, the overlap among the class-specific manifolds is approximated by an invader graph, and a locality discriminant criterion is proposed to find the projections that best preserve the within-class local structures while decrease the between-class overlap. The feasibility of the LDP algorithm has been successfully tested in text data and visual recognition experiments. Experiment results show it is an effective technique for data modeling and classification comparing to linear discriminant analysis, locality preserving projection, and marginal Fisher analysis.     

基于多视角多标签学习的读者情绪分类

传统的读者情绪分类主要从情感分析的角度出发,着重考量读者评论中体现出来的情感极性。然而现实中,读者评论的缺失有可能影响情绪分类的有效性和及时性。如何融合包括新闻文本和评论在内的多视角信息,对读者情绪进行更加准确的研判,成为了一个具有挑战性的问题。针对这一问题,构建了一种融合多视角信息的多标签隐语义映射模型(Multi-view Multi-label Latent Indexing,MV-MLSI),将不同视角下的文本特征映射到低维语义空间,同时建立特征和标签之间的映射函数,通过最小化重构误差对模型进行求解,并设计了相关算法,从而实现对读者情绪的有效预测。相比于传统模型,该模型不仅可以充分利用多视角的信息,而且考虑了标签之间的相关性。在新闻文本数据集上的实验表明,该方法可以获得更高的准确率和稳定性。     

基于块对角化表示的多视角字典对学习

字典学习作为一种高效的特征学习技术被广泛应用于多视角分类中.现有的多视角字典学习方法大多只利用多视角数据的部分信息,且只学习一种类型的字典.实际上,多视角数据的相关性信息和多样性信息同样重要,且仅考虑一种合成型字典或解析型字典的学习算法不能同时满足处理速度、可解释性以及应用范围的要求.针对上述问题,提出了一种基于块对角...     

基于半监督学习的增量图像分类方法

为有效使用大量未标注的图像进行分类,提出一种基于半监督学习的图像分类方法。通过共同的隐含话题桥接少量已标注的图像和大量未标注的图像,利用已标注图像的Must-link约束和Cannot-link约束提高未标注图像分类的精度。实验结果表明,该方法有效提高Caltech-101数据集和7类图像集约10%的分类精度。此外,针对目前绝大部分半监督图像分类方法不具备增量学习能力这一缺点,提出该方法的增量学习模型。实验结果表明,增量学习模型相比无增量学习模型提高近90%的计算效率。关键词半监督学习,图像分类,增量学习中图法分类号TP391。41IncrementalImageClassificationMethodBasedonSemi-SupervisedLearningLIANGPeng^1,2,LIShao-Fa²,QINJiang-Wei²,LUOJian-Gao³¹(SchoolofComputerScienceandEngineering,GuangdongPolytechnicNormalUniversity,Guangzhou510665)²(SchoolofComputerScienceandEngineering,SouthChinaUniversityofTechnology,Guangzhou510006)³(DepartmentofComputer,GuangdongAIBPolytechnicCollege,Guangzhou510507)ABSTRACTInordertouselargenumbersofunlabeledimageseffectively,animageclassificationmethodisproposedbasedonsemi-supervisedlearning。Theproposedmethodbridgesalargeamountofunlabeledimagesandlimitednumbersoflabeledimagesbyexploitingthecommontopics。Theclassificationaccuracyisimprovedbyusingthemust-linkconstraintandcannot-linkconstraintoflabeledimages。TheexperimentalresultsonCaltech-101and7-classesimagedatasetdemonstratethattheclassificationaccuracyimprovesabout10%bytheproposedmethod。Furthermore,duetothepresentsemi-supervisedimageclassificationmethodslackingofincrementallearningability,anincrementalimplementationofourmethodisproposed。Comparingwithnon-incrementallearningmodelinliterature,theincrementallearningmethodimprovesthecomputationefficiencyofnearly90%。     

Regularized discriminant entropy analysis

In this paper, we propose the regularized discriminant entropy (RDE) which considers both class information and scatter information on original data. Based on the results of maximizing the RDE, we develop a supervised feature extraction algorithm called regularized discriminant entropy analysis (RDEA). RDEA is quite simple and requires no approximation in theoretical derivation. The experiments with several publicly available data sets show the feasibility and effectiveness of the proposed algorithm with encouraging results.     

一种半监督协同训练的正则化算法

半监督学习是机器学习领域的研究热点。协同训练研究数据有多个特征集时的半监督学习问题。从正则化角度研究协同训练,利用假设空间的度量结构定义学习函数的光滑性和一致性,在每个视图内的学习过程中以函数光滑性为约束条件,在多个视图的协同学习过程中以函数一致性为约束条件,创新性地提出一种两个层次的正则化算法,同时使用函数的光滑性和一致性进行正则化。实验表明,该算法较仅使用光滑性或仅使用一致性的正则化方法在预测性能上有显著提高。     

一种用于构建用户画像的多视角融合框架

电网公司的电费敏感客户往往对由用电引发的电量、电价、电费、缴费、欠费等电力服务具有强烈反应。快速定位电费敏感客户,对降低客户投诉率、提升客户满意度、树立供电企业良好的服务形象具有重要的作用。基于电网用户数据,提出了一种用于构建用户画像的多视角融合框架,该框架能够快速、准确地识别出电费敏感客户。首先,对电网用户进行了分析研究,利用双通道对不同特性的用户分别建模预测;其次,提出了多种特征萃取方法,用于构建用户多源特征体系;最后,为了充分利用多源特征,进一步提出了基于双层Xgboost的多视角融合模型。该框架在2016CCF大数据与计算智能大赛“客户画像”竞赛中获得了F1值为0.90379(第一名)的成绩,其有效性得到了验证。