Search

Nonlinear clustering has attracted an increasing amount of attention recently. In this paper, we propose a new nonlinear clustering method based on crowd movement and selection (CCMS). Different from most of the existing clustering methods that concentrate on cluster centers, our method focuses on the data points themselves and the data distribution of their neighborhood. Based on this novel idea, some useful rules are designed to transform the original nonlinearly separable datasets into linearly separable datasets. Finally, a new clustering phase is designed to partition the transformed data. Extensive experiments have been conducted to evaluate the effectiveness of the proposed CCMS method. [ABSTRACT FROM AUTHOR]

Abstract: Web Usage Mining (WUM) is the application of data mining techniques over Web server logs in order to extract navigation usage patterns. The analysis of mining patterns for assessing the knowledge they reveal is a critical phase in WUM. The main challenges are: (a) mining algorithms yield a huge number of patterns and (b) there is a significant semantic gap between URLs and events performed by users. In this paper, we describe the pattern analysis mechanisms integrated in O3R (Ontology-based Rules Retrieval and Rummaging), a human-centered environment for the analysis of navigation rules. O3R explores the synergy of mechanisms for retrieving and analyzing patterns. Filtering and clustering allow users to retrieve subsets of patterns with specific characteristics, in order to deal with the large volume of patterns. Rummaging mechanisms are targeted at assessing the meaning and relevance of pattern with regard to the domain, and it is particularly suitable for exploratory analysis. The distinctive feature of O3R is that is dynamically associates meaning to patterns using the concepts and relationships of a domain ontology, as a means of reducing the gap between syntactic URLs and semantic events performed by users. The paper describes the mechanisms in detail, and explores their synergic integration in the O3R prototype. It also reports two case studies that evaluate the use of O3R for the analysis of navigation patterns of a learning site. [Copyright &y& Elsevier]

Abstract: Feature selection methods have been extensively applied in machine learning tasks, such as computer vision, pattern recognition, and data mining. These methods aim to identify a subset of the original features with high discriminating power. Among them, the feature selection technique for unsupervised tasks is more attractive since the cost to obtain the labels of the data and/or the information between classes is often high. On the other hand, the low-dimensional manifold of the “same” class data is usually revealed by considering the local invariance of the data structure, it may not be adequate to deal with unsupervised tasks where the class information is completely absent. In this paper, a novel feature selection method, called Minimum–maximum local structure information Laplacian Score (MMLS), is proposed to minimize the within-locality information (i.e., preserving the manifold structure of the “same” class data) and to maximize the between-locality information (i.e., maximizing the information between the manifold structures of the “different” class data) at the same time. The effectiveness of the proposed algorithm is demonstrated with experiments on classification and clustering. [Copyright &y& Elsevier]

Abstract: The present paper considers the problem of partitioning a dataset into a known number of clusters using the sum of squared errors criterion (SSE). A new clustering method, called DE-KM, which combines differential evolution algorithm (DE) with the well known K-means procedure is described. In the method, the K-means algorithm is used to fine-tune each candidate solution obtained by mutation and crossover operators of DE. Additionally, a reordering procedure which allows the evolutionary algorithm to tackle the redundant representation problem is proposed. The performance of the DE-KM clustering method is compared to the performance of differential evolution, global K-means method, genetic K-means algorithm and two variants of the K-means algorithm. The experimental results show that if the number of clusters K is sufficiently large, DE-KM obtains solutions with lower SSE values than the other five algorithms. [Copyright &y& Elsevier]

Abstract: KNN (k nearest neighbor) is widely discussed and applied in pattern recognition and data mining, however, as a similar outlier detection method using local information for mining a new outlier, neighborhood outlier detection, few literatures are reported on. In this paper, we introduce neighborhood model as a uniform framework to understand and implement neighborhood outlier detection. Furthermore, a neighborhood-based outlier detection algorithm is also given. This algorithm integrates rough set granular technique with outlier detecting. We propose a neighborhood-based metric on outlier detection, and compare neighborhood outlier detection with DIS, KNN and RNN. The experimental results show that neighborhood-based metric is able to measure the local information for outlier detection. The detected accuracies based on neighborhood outlier detection are superior to DIS, KNN for mixed dataset, and a litter better than RNN for discrete dataset. [ABSTRACT FROM AUTHOR]

Abstract: It is desirable to find unusual data objects by Ramaswamy et al.’s distance-based outlier definition, because only a metric distance function between two objects is required. This definition does not need any neighborhood distance threshold required by many existing algorithms based on the definition of Knorr and Ng. Bay and Schwabacher proposed an efficient algorithm ORCA, which can give near linear time performance, for this task. To further reduce the running time, we propose in this paper two algorithms RC and RS using the following two techniques, respectively: (i) faster cutoff update, and (ii) space utilization after pruning. We tested RC, RS, and RCS (a hybrid approach combining both RC and RS) on several large and high-dimensional real data sets with millions of objects. The experiments show that the speed of RCS is as fast as 1.4–2.3 times that of ORCA, and the improvement of RCS is relatively insensitive to the increase in the data size. [Copyright &y& Elsevier]

Abstract: Image mining is an important task to discover interesting and meaningful patterns form large image databases. In this paper, we introduce the spatial co-orientation patterns in image databases. Spatial co-orientation patterns refer to objects that frequently occur with the same spatial orientation, e.g. left, right, below, etc. among images. For example, an object P is frequently left to an object Q among images. We utilize the data structure, 2D string, to represent the spatial orientation of objects in an image. Two approaches, Apriori-based and pattern-growth approaches, are proposed for mining co-orientation patterns. An experimental evaluation with synthetic datasets shows the advantage and disadvantage between these two algorithms. [Copyright &y& Elsevier]

Abstract: In this paper, we proposed an efficient algorithm, called PCP-Miner (Pointset Closed Pattern Miner), for mining frequent closed patterns from a pointset database, where a pointset contains a set of points. Our proposed algorithm consists of two phases. First, we find all frequent patterns of length two in the database. Second, for each pattern found in the first phase, we recursively generate frequent closed patterns by a frequent pattern tree in a depth-first search manner. Since the PCP-Miner does not generate unnecessary candidates, it is more efficient and scalable than the modified Apriori, SASMiner and MaxGeo. The experimental results show that the PCP-Miner algorithm outperforms the comparing algorithms by more than one order of magnitude. [Copyright &y& Elsevier]

Abstract: Algorithms for feature selection in predictive data mining for classification problems attempt to select those features that are relevant, and are not redundant for the classification task. A relevant feature is defined as one which is highly correlated with the target function. One problem with the definition of feature relevance is that there is no universally accepted definition of what it means for a feature to be ‘highly correlated with the target function or highly correlated with the other features’. A new feature selection algorithm which incorporates domain specific definitions of high, medium and low correlations is proposed in this paper. The proposed algorithm conducts a heuristic search for the most relevant features for the prediction task. [Copyright &y& Elsevier]

Abstract: This paper proposes a flexible sequence alignment approach for pattern mining and matching in the recognition of human activities. During pattern mining, the proposed sequence alignment algorithm is invoked to extract out the representative patterns which denote specific activities of a person from the training patterns. It features high performance and robustness on pattern diversity. Besides, the algorithm evaluates the appearance probability of each pattern as weight and allows adapting pattern length to various human activities. Both of them are able to improve the accuracy of activity recognition. In pattern matching, the proposed algorithm adopts a dynamic programming based strategy to evaluate the correlation degree between each representative activity pattern and the observed activity sequence. It can avoid the trouble on segmenting the observed sequence. Moreover, we are able to obtain recognition results continuously. Besides, the proposed matching algorithm favors recognition of concurrent human activities with parallel matching. The experimental result confirms the high accuracy of human activity recognition by the proposed approach. [Copyright &y& Elsevier]

Abstract: In real world situations, explanations for the same observations may be different depending on perceptions or contexts. They may change with time especially when concept drift occurs. This phenomenon incurs ambiguities. It is useful if an algorithm can learn to reflect ambiguities and select the best decision according to context or situation. Based on this viewpoint, we study the problem of deriving ambiguous decision trees from data streams to cope with concept drift. CVFDT (Concept-adapting Very Fast Decision Tree) is one of the most well-known streaming data mining methods that can learn decision trees incrementally. In this paper, we establish a method called ambiguous CVFDT (aCVFDT), which integrates ambiguities into CVFDT by exploring multiple options at each node whenever a node is to be split. When aCVFDT is used to make class predictions, it is guaranteed that the best and newest knowledge is used. When old concepts recur, aCVFDT can immediately relearn them by using the corresponding options recorded at each node. Furthermore, CVFDT does not automatically detect occurrences of concept drift and only scans trees periodically, whereas an automatic concept drift detecting mechanism is used in aCVFDT. In our experiments, hyperplane problem and two benchmark problems from the UCI KDD Archive, namely Network Intrusion and Forest CoverType, are used to validate the performance of aCVFDT. The experimental results show that aCVFDT obtains significantly improved results over traditional CVFDT. [Copyright &y& Elsevier]