A clustering comparison measure using density profiles and its application to the discovery of alternate clusterings

Abstract

Data clustering is a fundamental and very popular method of data analysis. Its subjective nature, however, means that different clustering algorithms or different parameter settings can produce widely varying and sometimes conflicting results. This has led to the use of clustering comparison measures to quantify the degree of similarity between alternative clusterings. Existing measures, though, can be limited in their ability to assess similarity and sometimes generate unintuitive results. They also cannot be applied to compare clusterings which contain different data points, an activity which is important for scenarios such as data stream analysis.In this paper, we introduce a new clustering similarity measure, known as ADCO, which aims to address some limitations of existing measures, by allowing greater flexibility of comparison via the use of density profiles to characterize a clustering. In particular, it adopts a 'data mining style' philosophy to clustering comparison, whereby two clusterings are considered to be more similar, if they are likely to give rise to similar types of prediction models.Furthermore, we show that this new measure can be applied as a highly effective objective function within a new algorithm, known as MAXIMUS, for generating alternate clusterings.

Structure-Aware Distance Measures for Comparing Clusterings in Graphs

“…In traditional clustering of points, it was found that clusterings could be similar in memberships, but their points are distributed very differently. This could lead to counter-intuitive situations where such clusterings were considered similar [5] [6]. We show the same scenario occurs when comparing graph clusterings.…”

A Study on the Conduction Mechanism and Evaluation of the Comprehensive Efficiency of Photovoltaic Power Generation in China

“…Hierarchical cluster analysis is a type of technology with a multivariate numerical analytical method, by measuring the distances between the samples to confirm their similarities [38]. It uses the fact that the samples that are close to each other cluster more quickly than those that are far away from each other.…”

Artificial metaplasticity prediction model for cognitive rehabilitation outcome in acquired brain injury patients

“…Data mining has been applied with success in different fields of knowledge and in the last few years, it has been increasingly used in medical literature [10,11]. One of the objectives of data mining in clinical medicine is to create models that can use specific patient information to predict the outcome of interest and to support clinical decision-making or form the basis of hypotheses for future experiments.…”

“…If s,j, ieN are the MLP layer, node and input counters respectively, for each W(t) component, w j, s '(t) e R, an d being ijgR* the learning rate, then the weight reinforcement in each iteration is given by: (11) So, as the pdf weighting function proposed is the distribution of the input patterns that does not depend on the network parameters, the AMMLP algorithm can then be summarized as a weighting operation for updating each weight in each MLP learning iteration A*w = w*(x)Aw (12) being Aw = w(t + 1) -w{t) the weight updating value obtained by usual BPA and w*(x) the realization of the described weighting function w*(x) for each input training pattern x.…”