The curse of dimensionality turns the high-dimensional data analysis a challenging task for data clustering techniques. In order to deal with highdimensional data, this paper presents a clustering approach that explores the combination of two strategies: semi-supervision and density estimation based on hubness scores. Initial experimental results show a good performance when applied on real dat...

Ant-based clustering is a nature-inspired technique whereas stochastic agents perform the task of clustering high-dimensional data. This paper analyzes the popular technique of Lumer/Faieta. It is shown that the Lumer/Faieta approach is strongly related to Kohonen’s SelfOrganizing Batch Map. A unifying basis is derived in order to assess strengths and weaknesses of both techniques. The behaviou...

Nowadays, most streaming data sources are becoming highdimensional. Accordingly, subspace stream clustering, which aims at finding evolving clusters within subgroups of dimensions, has gained a significant importance. However, existing subspace clustering evaluation measures are mainly designed for static data, and cannot reflect the quality of the evolving nature of data streams. On the other ...

In this paper we present Collaborative Low-Rank Subspace Clustering. Given multiple observations of a phenomenon we learn a unified representation matrix. This unified matrix incorporates the features from all the observations, thus increasing the discriminative power compared with learning the representation matrix on each observation separately. Experimental evaluation shows that our method o...

This paper presents the basic results for using the parallel coordinate representation as a high dimensional data analysis tool. Several alternatives are reviewed. The basic algorithm for parallel coordinates is laid out and a discussion of its properties as a projective transformation are shown. The several of the duality results are discussed along with their interpretations as data analysis ...

This is a difficult because: 1. Object appearance varies 2. Way of interacting with object vary among people 3. Both object and body parts of the interest might be occluded Contributions By using motion information alone, we propose an unsupervised framework for clustering and classifying videos of people interacting with objects. The method is based on [2]. We show that: 1. human-object intera...

A challenge involved in applying density-based clustering to categorical datasets is that the ‘cube’ of attribute values has no ordering defined. We propose the HIERDENC algorithm for hierarchical densitybased clustering of categorical data. HIERDENC offers a basis for designing simpler clustering algorithms that balance the tradeoff of accuracy and speed. The characteristics of HIERDENC includ...

Subspace clustering (also called projected clustering) addresses the problem that different sets of attributes may be relevant for different clusters in high dimensional feature spaces. In this paper, we propose the algorithm DiSH (Detecting Subspace cluster Hierarchies) that improves in the following points over existing approaches: First, DiSH can detect clusters in subspaces of significantly...

We establish the convergence of the fuzzy subspace clustering (FSC) algorithm by applying Zangwill’s convergence theorem. We show that the iteration sequence produced by the FSC algorithm terminates at a point in the solution set S or there is a subsequence converging to a point in S. In addition, we present experimental results that illustrate the convergence properties of the FSC algorithm in...

We propose a transformation method to circumvent the problems with high dimensional data. For each object in the data, we create an itemset of the k-nearest neighbors of that object, not just for one of the dimensions, but for many views of the data. On the resulting collection of sets, we can mine frequent itemsets; that is, sets of points that are frequently seen together in some of the views...