Interactive and iterative visual clustering

Abstract

This article proposes a semi-interactive system for visual data exploration using an iterative clustering that combines an automatic approach with an interactive one. We propose a framework to improve the interactivity between the user and the data analysis process, allowing him or her to participate actively in the iterative clustering tasks using a two-dimensional projection. Defining a cluster by its seed (center) and its limit, the proposed approach allows the user to modify the automated values or to define new seeds and the associated cluster limit himself or herself. The user can perform the clustering according to his or her visual perception manually and can also choose to let the automated approach find optimal seeds and then interact with the process to iterate the clustering process according to his or her visual perception and domain knowledge. Most of the evaluation criteria for clustering evaluate the complete clustering and not each cluster separately. In this article, we propose to adapt evaluation criteria to single clusters, allowing the users to evaluate their own clusters and perform the clustering iteratively until satisfaction. To evaluate our proposed approach, we conduct a user evaluation, where the users are asked to perform clustering interactively according to their visual perception and with the semi-interactive one. We also compare the obtained results with those of automated clustering. The quantitative results have shown that the cooperative approach can improve the clustering results in terms of accuracy.

MCLEAN: Multilevel Clustering Exploration As Network

“…As Boudjeloud-Assala et al (2016) state, ''the clustering process is not complete until it is evaluated, validated, and accepted by the user. As such, visual validation and exploration can improve understanding of clustering structure, and can be very effective in revealing trends, highlighting outliers, and showing clusters''.…”

“…In other words: clustering is used generally to analyze the data, not to explore it (Boudjeloud-Assala et al, 2016). The integration of visualization and algorithm into the same model is a possible solution to make the clustering process dynamic.…”

“…The integration of visualization and algorithm into the same model is a possible solution to make the clustering process dynamic. The framework to perform interactive visual clustering (IVC) presented by Boudjeloud-Assala et al (2016) demonstrated a significant advantage in data mining since it allows users to participate in the clustering process by leveraging their visual perception and domain knowledge. As recommended by Keim, Mansmann & Thomas (2010), we believe that if we adapt the visualization environment and combine it with the clustering approach, this combined approach can be used to provide a very natural way for users to explore datasets.…”

Γ-stochastic neighbour embedding for feed-forward data visualization

“…This methodology was extended using t-distributions over dissimilarities for the visualization space in t-SNE [29] which forms a part of the visualization framework in [3]. It was found that mismatching the neighbourhood distributions allowed for better local clustering, with examples given in the supplementary material of [29].…”

“…A further issue is the optimisation of the cost function in equation (3). In order to avoid achieving poor local-minima in the optimisation process a momentum-based gradient descent process is required.…”