K-means clustering is widely used, but its iterative and initialization-sensitive nature makes results hard to interpret, compare, and debug, especially when multiple runs are needed to obtain a reliable solution. This paper presents VISPEK, a visual interactive system for progressive ensemble k-means clustering that helps users understand how clustering results evolve and how agreement emerges across runs. By combining Progressive Visual Analytics with an ensemble-based strategy, VISPEK exposes intermediate results, stability and quality metrics, and similarities among runs, enabling users to inspect, explain, and steer the clustering process before convergence. In this way, VISPEK supports the interpretation of consensus formation, highlights uncertainty, and helps users identify promising results early. We validate the approach through two usage scenarios and an expert study with data science and machine learning experts, showing that VISPEK improves analysis transparency while reducing time and computational effort.

RadViz contributes to multidimensional analysis by using 2D points for encoding data elements and interpreting them along the original data dimensions. For these characteristics it is used in different application domains, like clustering, anomaly detection, and software visualization. However, it is likely that using the dimension arrangement that comes with the data will produce a plot that leads users to make inaccurate conclusions about points values and data distribution. This article attacks this problem without altering the original RadViz design: It defines, for both a single point and a set of points, the metric of effectiveness error, and uses it to define the objective function of a dimension arrangement strategy, arguing that minimizing it increases the overall RadViz visual quality. This article investigated the intuition that reducing the effectiveness error is beneficial for other well-known RadViz problems, like points clumping toward the center, many-to-one plotting of non-proportional points, and cluster separation. It presents an algorithm that reduces to zero the effectiveness error for a single point and a heuristic that approximates the dimension arrangement minimizing the effectiveness error for an arbitrary set of points. A set of experiments based on 21 real datasets has been performed, with the goals of analyzing the advantages of reducing the effectiveness error, comparing the proposed dimension arrangement strategy with other related proposals, and investigating the heuristic accuracy. The Effectiveness Error metric, the algorithm, and the heuristic presented in this article have been made available in a d3.js plugin at https://aware-diag-sapienza.github.io/d3-radviz.

Analyzing and mitigating the threats that cyber-attacks pose on the services of a critical infrastructure is not a trivial activity. Research solutions have been developed using data about the devices used for implementing the services, services dependencies, network topology, and the vulnerabilities that can be exploited to attack the network. However, most of the proposed solutions fail to consider these aspects in an integrated fashion, allowing the user to understand global dependencies and weaknesses. This paper contributes this issue with BUCEPHALUS, a Visual Analytics solution providing a) a visual overview of the existing relationships among business functions, devices, and vulnerabilities, and b) a what-if analysis scenario, in which the user is supported on making decisions on which vulnerabilities are more appropriate to fix. BUCEPHALUS has been developed and validated within a user-centered design process involving security professionals.

Filtering is one of the basic interaction techniques in Information Visualization, with the main objective of limiting the amount of displayed information using constraints on attribute values. Research focused on direct manipulation selection means or on simple interactors like sliders or check-boxes: while the interaction with a single attribute is, in principle, straightforward, getting an understanding of the relationship between multiple attribute constraints and the actual selection might be a complex task. To cope with this problem, usually referred as cross-filtering, the paper provides a general definition of the structure of a filter, based on domain values and data distribution, the identification of visual feedbacks on the relationship between filters status and the current selection, and guidance means to help in fulfilling the requested selection. Then, leveraging on the definition of these design elements, the paper proposes CrossWidgets, modular attribute selectors that provide the user with feedback and guidance during complex interaction with multiple attributes. An initial controlled experiment demonstrates the benefits that CrossWidgets provide to cross-filtering activities.

Visual environment techniques can support an easy exploration of large datasets. A visual environment has been developed to explore the breeding data of a monogamous and nest-site faithful seabird, the Scopoli's shearwater. The aim was to provide a tool, easy-to-use for ornithologists, to examine the history of the nests, and the relationships of the various factors affecting the variability in the breeding success during a four year time period. The tool is based on four coordinated views, linked to each other and to the dataset, each showing a different grouping of data according with spatial, temporal, and categorical criteria. This tool can help the ornithologists to pick up easily the similarities and differences between the nests and offers a new instrument for the first exploration of data.