SOMFlow: Guided Exploratory Cluster Analysis with Self-Organizing Maps and Analytic Provenance

Abstract

Clustering is a core building block for data analysis, aiming to extract otherwise hidden structures and relations from raw datasets, such as particular groups that can be effectively related, compared, and interpreted. A plethora of visual-interactive cluster analysis techniques has been proposed to date, however, arriving at useful clusterings often requires several rounds of user interactions to fine-tune the data preprocessing and algorithms. We present a multi-stage Visual Analytics (VA) approach for iterative cluster refinement together with an implementation (SOMFlow) that uses Self-Organizing Maps (SOM) to analyze time series data. It supports exploration by offering the analyst a visual platform to analyze intermediate results, adapt the underlying computations, iteratively partition the data, and to reflect previous analytical activities. The history of previous decisions is explicitly visualized within a flow graph, allowing to compare earlier cluster refinements and to explore relations. We further leverage quality and interestingness measures to guide the analyst in the discovery of useful patterns, relations, and data partitions. We conducted two pair analytics experiments together with a subject matter expert in speech intonation research to demonstrate that the approach is effective for interactive data analysis, supporting enhanced understanding of clustering results as well as the interactive process itself.

FDive: Learning Relevance Models Using Pattern-based Similarity Measures

“…We layout the SOM-based relevance model in a tree structure, because it is explainable and an intuitive way of reading a classifier. Techniques introduced by Sacha et al [53] can be used to enhance its descriptive ability. This addition can lead to novel SOM interactions focused on classification rather than exploratory cluster analysis.…”

“…Visual interactive approaches for cluster evaluation and understanding were presented by Nam et al for general high-dimensional data [46] and by Ruppert et al [52] for the clustering of text documents. Sacha et al present SOMFlow [53], an exploration system that uses Self-Organizing Maps (SOM) to guide the user through an iterative cluster refinement task, leveraging the proximity-preserving property of SOMs [7,59] for clustering and data partitioning tasks. In a model creation task, the user needs to be guided towards areas of high uncertainty.…”

“…We resolve this by proposing a hierarchical SOMs that allows for the expression of fine-grained differences in the user's notion of relevance. For this reason, we merge the concept of a tree with the concept of child SOMs presented by Sacha et al [53], where a new SOM is calculated only with a subset of the dataset determined by the cell selection of a parent SOM. However, our algorithm creates a classifier automatically without any user interaction other than supplied labels.…”

A User‐based Visual Analytics Workflow for Exploratory Model Analysis

“…Sedlmair et al [SHB∗14] provide a comprehensive survey of visual analytics tools for analyzing the parameter space of models. Example types of models used by these visual analytics tools include regression [MP13], clustering [NHM∗07, CD19, KEV∗18, SKB∗18], classification [VDEvW11, CLKP10], dimension reduction [CLL∗13, JZF∗09, NM13, AWD12, LWT∗15], and domain‐specific modeling approaches including climate models [WLSL17]. In these examples, the user directly constructs or modifies the parameters of the model through the interaction of sliders or interactive visual elements within the visualization.…”

Multistage Dynamic Packet Access Mechanism of Internet of Things

“…SOM not only includes an input layer but also contains a competitive layer, and the input layer is the status of full mesh with the competitive layer through each neuron which refers to one category [39]. According to the rules of learning, the objective of capturing the feature of each of the input models can be attained by repeated learning, and the self-organizing clustering will be carried out in these features.…”