Xiaodong Yue

Hierarchical attribute reduction algorithms for big data using MapReduce

Attribute reduction is one of the important research issues in rough set theory. Most existing attribute reduction algorithms are now faced with two challenging problems. On one hand, they have seldom taken granular computing into consideration. On the other hand, they still cannot deal with big data. To address these issues, the hierarchical encoded decision table is first defined. The relationships of hierarchical decision tables are then discussed under different levels of granularity. The parallel computations of the equivalence classes and the attribute significance are further designed for attribute reduction. Finally, hierarchical attribute reduction algorithms are proposed in data and task parallel using MapReduce. Experimental results demonstrate that the proposed algorithms can scale well and efficiently process big data.

Parallel attribute reduction algorithms using MapReduce

Abstract Attribute reduction is the key technique for knowledge acquisition in rough set theory. However, it is still a challenging task to perform attribute reduction on massive data. During the process of attribute reduction on massive data, the key to improving the reduction efficiency is the effective computation of equivalence classes and attribute significance. Aiming at this problem, we propose several parallel attribute reduction algorithms in this paper. Specifically, we design a novel structure of 〈 key , value 〉 pair to speed up the computation of equivalence classes and attribute significance and parallelize the traditional attribute reduction process based on MapReduce mechanism. The different parallelization strategies of attribute reduction are also compared and analyzed from the theoretic view. Abundant experimental results demonstrate the proposed parallel attribute reduction algorithms can perform efficiently and scale well on massive data.

A clustering ensemble

The aim of clustering ensemble is to combine multiple base partitions into a robust, stable and accurate partition. One of the key problems of clustering ensemble is how to exploit the cluster structure information in each base partition. Evidence accumulation is an effective framework which can convert the base partitions into a co-association matrix. This matrix describes the frequency of a pair of points partitioned into the same cluster, but ignores some hidden information in the base partitions. In this paper, we reveal some of those information by refining the co-association matrix from data point and base cluster level. From the data point level, as pairs of points in the same base cluster may have varied similarities, their contributions to the co-association matrix can be different. From the cluster level, since the base clusters may have diversified qualities, the contribution of a base cluster as a whole can also be different from those of others. After being refined, the co-association matrix is transformed into a path-based similarity matrix so that more global information of the cluster structure is incorporated into the matrix. Finally, spectral clustering is applied to the matrix to generate the final clustering result. Experimental results on 8 synthetic and 8 real data sets demonstrate that the clustering ensemble based on the refined co-association matrix outperforms some state-of-the-art clustering ensemble schemes. HighlightsA two-level-refined co-association matrix for cluster ensemble is proposed.The refined co-association matrix is transformed by path-based measure.A theoretical background of the refinement is given.The proposed method outperforms some state-of-the-art ensemble methods.

Multiscale roughness measure for color image segmentation

Color image segmentation is always an important technique in image processing system. Highly precise segmentation with low computation complexity can be achieved through roughness measurement which approximate the color histogram based on rough set theory. However, due to the imprecise description of neighborhood similarity, the existing roughness measure tends to over-focus on the trivial homogeneous regions but is not accurate enough to measure the color homogeneity. This paper aims to construct a multiscale roughness measure through simulating the human vision. We apply the theories of linear scale-space and rough sets to generate the hierarchical roughness of color distribution under multiple scales. This multiscale roughness can tolerate the disturbance of trivial regions and also can provide the multilevel homogeneity representation in vision, which therefore produces precise and intuitive segmentation results. Furthermore, we propose roughness entropy for scale selection. The optimal scale for segmentation is decided by the entropy variation. The proposed method shows the encouraging performance in the experiments based on Berkeley segmentation database.

Attribute reduction for sequential three-way decisions under dynamic granulation

Abstract In real-world decision making, sequential three-way decisions are an effective way of human problem solving under multiple levels of granularity. Making the right decision at the most optimal level is a crucial issue. To this end, we address the attribute reduction problem for sequential three-way decisions under dynamic granulation. By reviewing the existing definitions of attribute reducts, a new attribute reduct for sequential three-way decisions is defined, and a corresponding monotonic attribute significance measure is designed. An attribute reduction algorithm satisfying the monotonicity of the probabilistic positive region is developed. The relationships of the different attribute reducts, the probabilistic positive regions and the probabilistic positive rules for decision-theoretic rough set models are further discussed under global view, local view and sequential three-way decisions. Experimental results demonstrate that our method is effective. This study will provide a new insight into the attribute reduction problem of sequential three-way decisions.

Tri-partition neighborhood covering reduction for robust classification

Neighborhood Covering Reduction extracts rules for classification through formulating the covering of data space with neighborhoods. The covering of neighborhoods is constructed based on distance measure and strictly constrained to be homogeneous. However, this strategy over-focuses on individual samples and thus makes the neighborhood covering model sensitive to noise and outliers. To tackle this problem, we construct a flexible Tri-partition Neighborhood for robust classification. This novel neighborhood originates from Three-way Decision theory and is partitioned into the regions of certain neighborhood, neighborhood boundary and non-neighborhood. The neighborhood boundary consists of uncertain neighbors and is helpful to tolerate noise. Besides the neighborhood construction, we also proposed complete and partial strategies to reduce redundant neighborhoods to optimize the neighborhood covering for classification. The reduction process preserves lower and upper approximations of neighborhood covering and thereby provides a flexible way to handle uncertain samples and noise. Experiments verify the classification based on tri-partition neighborhood covering is robust and achieves precise and stable results on noisy data. Propose Tri-partition Neighborhood Covering Reduction for robust classification.Extend neighborhoods to form covering approximations of data space.Propose three reduction strategies for tri-partition neighborhood covering.Investigate the properties of tri-partition neighborhood covering reduction.Design a classifier based on neighborhood covering models.

Knowledge reduction in interval-valued information systems

In this paper, the concept of α -maximal consistent blocks is proposed to formulate the new rough approximations to an arbitrary object set in interval-valued information systems. The a -maximal consistent blocks can provide the simpler discernibility matrices and discernibility functions in reduction of interval-valued information systems. This means that they can provide a more efficient computation for knowledge acquisitions. Numerical examples are employed to substantiate the conceptual arguments.

Three-way decision support for diagnosis on focal liver lesions

Malignant Focal Liver Lesion (FLL) is a main cause of primary liver cancer. In most existing Computer-Aided Diagnosis (CAD) systems of FLLs, machine learning and data mining methods have been widely applied to classify liver CT images for diagnostic decision making. However, these strategies of automatic decision support depend on data-driven classification methods and may lead to risky diagnosis on uncertain medical cases. To tackle the drawback, we expect to integrate the objective judgments from classification algorithms and the subjective judgments from human expert experiences, and propose a data-human-driven Three-way Decision Support for FLL diagnosis. The methodology of three-way decision support is motivated by Three-way Decision (3WD) theory. It tri-partitions the FLL medical records into certain benign, certain malignant and uncertain cases. The certain cases are automatically classified by decision rules and the challenging uncertain cases will be carefully diagnosed by human experts. Therefore, the method of three-way decision support can balance well the risk and efficiency of decision making. The workflow of three-way decision support for FLL diagnosis includes the stages of semantic feature extraction, three-way rule mining and decision cost optimization. Abundant experiments demonstrate that the proposed three-way decision support method is effective to handle the uncertain medical cases, and in the meantime achieves precise classification of FLLs to support liver cancer diagnosis.

An efficient color quantization based on generic roughness measure

Color quantization is a process to compress image color space while minimizing visual distortion. The quantization based on preclustering has low computational complexity but cannot guarantee quantization precision. The quantization based on postclustering can produce high quality quantization results. However, it has to traverse image pixels iteratively and suffers heavy computational burden. Its computational complexity was not reduced although the revised versions have improved the precision. In the work of color quantization, balancing quantization quality and quantization complexity is always a challenging point. In this paper, a two-stage quantization framework is proposed to achieve this balance. In the first stage, high-resolution color space is initially compressed to a condensed color space by thresholding roughness indices. Instead of linear compression, we propose generic roughness measure to generate the delicate segmentation of image color. In this way, it causes less distortion to the image. In the second stage, the initially compressed colors are further clustered to a palette using Weighted Rough K-means to obtain final quantization results. Our objective is to design a postclustering quantization strategy at the color space level rather than the pixel level. Applying the quantization in the precisely compressed color space, the computational cost is greatly reduced; meanwhile, the quantization quality is maintained. The substantial experimental results validate the high efficiency of the proposed quantization method, which produces high quality color quantization while possessing low computational complexity.

Multi-view attribute reduction model for traffic bottleneck analysis

In the field of traffic bottleneck analysis, it is expected to discover traffic congestion patterns from the reports of road conditions. However, data patterns mined by existing KDD algorithms may not coincide with the real application requirements. Different from academic researchers, traffic management officers do not pursue the most frequent patterns but always hold multiple views for mining task to facilitate traffic planning. They expect to study the correlation between traffic congestion and various kinds of road properties, especially the road properties easily to be improved. In this multi-view analysis, each view actually denotes a kind of user preference of road properties. Thus it is required to integrate user-defined attribute preferences into pattern mining process. To tackle this problem, we propose a multi-view attribute reduction model to discover the patterns of user interests. In this model, user views are expressed with attribute preferences and formally represented by attribute orders. Based on this, we implement a workflow of multi-view traffic bottleneck analysis, which consists of data preprocessing, preference representation and congestion pattern mining. We validate our approach based on the reports of road conditions from Shanghai. Experimental results show that the resultant multi-view mining outcomes are effective for analyzing congestion causes and traffic management.