We present ManuKnowVis, the result of a design study, in which we contextualize data from multiple knowledge repositories of a manufacturing process for battery modules used in electric vehicles. In data-driven analyses of manufacturing data, we observed a discrepancy between two stakeholder groups involved in serial manufacturing processes: Knowledge providers (e.g., engineers) have domain knowledge about the manufacturing process but have difficulties in implementing data-driven analyses. Knowledge consumers (e.g., data scientists) have no first-hand domain knowledge but are highly skilled in performing data-driven analyses. ManuKnowVis bridges the gap between providers and consumers and enables the creation and completion of manufacturing knowledge. We contribute a multi-stakeholder design study, where we developed ManuKnowVis in three main iterations with consumers and providers from an automotive company. The iterative development led us to a multiple linked view tool, in which, on the one hand, providers can describe and connect individual entities (e.g., stations or produced parts) of the manufacturing process based on their domain knowledge. On the other hand, consumers can leverage this enhanced data to better understand complex domain problems, thus, performing data analyses more efficiently. As such, our approach directly impacts the success of data-driven analyses from manufacturing data. To demonstrate the usefulness of our approach, we carried out a case study with seven domain experts, which demonstrates how providers can externalize their knowledge and consumers can implement data-driven analyses more efficiently.

Abstract Random Forests (RFs) are a machine learning (ML) technique widely used across industries. The interpretation of a given RF usually relies on the analysis of statistical values and is often only possible for data analytics experts. To make RFs accessible to experts with no data analytics background, we present RfX, a Visual Analytics (VA) system for the analysis of a RF's decision‐making process. RfX allows to interactively analyse the properties of a forest and to explore and compare multiple trees in a RF. Thus, its users can identify relationships within a RF's feature subspace and detect hidden patterns in the model's underlying data. We contribute a design study in collaboration with an automotive company. A formative evaluation of RFX was carried out with two domain experts and a summative evaluation in the form of a field study with five domain experts. In this context, new hidden patterns such as increased eccentricities in an engine's rotor by observing secondary excitations of its bearings were detected using analyses made with RfX. Rules derived from analyses with the system led to a change in the company's testing procedures for electrical engines, which resulted in 80% reduced testing time for over 30% of all components.

Multiscale visualizations are typically used to analyze multiscale processes and data in various application domains, such as the visual exploration of hierarchical genome structures in molecular biology. However, creating such multiscale visualizations remains challenging due to the plethora of existing work and the expression ambiguity in visualization research. Up to today, there has been little work to compare and categorize multiscale visualizations to understand their design practices. In this article, we present a structured literature analysis to provide an overview of common design practices in multiscale visualization research. We systematically reviewed and categorized 122 published journal or conference articles between 1995 and 2020. We organized the reviewed articles in a taxonomy that reveals common design factors. Researchers and practitioners can use our taxonomy to explore existing work to create new multiscale navigation and visualization techniques. Based on the reviewed articles, we examine research trends and highlight open research challenges.

In this design study, we present IRVINE, a Visual Analytics (VA) system, which facilitates the analysis of acoustic data to detect and understand previously unknown errors in the manufacturing of electrical engines. In serial manufacturing processes, signatures from acoustic data provide valuable information on how the relationship between multiple produced engines serves to detect and understand previously unknown errors. To analyze such signatures, IRVINE leverages interactive clustering and data labeling techniques, allowing users to analyze clusters of engines with similar signatures, drill down to groups of engines, and select an engine of interest. Furthermore, IRVINE allows to assign labels to engines and clusters and annotate the cause of an error in the acoustic raw measurement of an engine. Since labels and annotations represent valuable knowledge, they are conserved in a knowledge database to be available for other stakeholders. We contribute a design study, where we developed IRVINE in four main iterations with engineers from a company in the automotive sector. To validate IRVINE, we conducted a field study with six domain experts. Our results suggest a high usability and usefulness of IRVINE as part of the improvement of a real-world manufacturing process. Specifically, with IRVINE domain experts were able to label and annotate produced electrical engines more than 30% faster.

Ensembles of classifier models typically deliver superior performance and can outperform single classifier models given a dataset and classification task at hand. However, the gain in performance comes together with the lack of comprehensibility, posing a challenge to understand how each model affects the classification outputs and from where the errors come. We propose a tight visual integration of the data and the model space for exploring and combining classifier models. We introduce an interactive workflow that builds upon the visual integration and enables the effective exploration of classification outputs and models. The involvement of the user is key to our approach. Therefore, we elaborate on the role of the human and connect our approach to theoretical frameworks on human-centered machine learning. We showcase the usefulness of our approach and the integration of the user via binary and multiclass classification problems. Based on ensembles automatically selected by a standard ensemble selection algorithm, the user can manipulate models and alternative combinations.

The overview-driven visual analysis of large-scale dynamic graphs poses a major challenge. We propose Multiscale Snapshots, a visual analytics approach to analyze temporal summaries of dynamic graphs at multiple temporal scales. First, we recursively generate temporal summaries to abstract overlapping sequences of graphs into compact snapshots. Second, we apply graph embeddings to the snapshots to learn low-dimensional representations of each sequence of graphs to speed up specific analytical tasks (e.g., similarity search). Third, we visualize the evolving data from a coarse to fine-granular snapshots to semi-automatically analyze temporal states, trends, and outliers. The approach enables us to discover similar temporal summaries (e.g., reoccurring states), reduces the temporal data to speed up automatic analysis, and to explore both structural and temporal properties of a dynamic graph. We demonstrate the usefulness of our approach by a quantitative evaluation and the application to a real-world dataset.

Tennis players and coaches of all proficiency levels seek to understand and improve their play. Summary statistics alone are inadequate to provide the insights players need to improve their games. Spatio-temporal data capturing player and ball movements is likely to provide the actionable insights needed to identify player strengths, weaknesses, and strategies. To fully utilize this spatio-temporal data, we need to integrate it with domain-relevant context meta-data. In this paper, we propose CourtTime, a novel approach to perform data-driven visual analysis of individual tennis matches. Our visual approach introduces a novel visual metaphor, namely 1-D Space-Time Charts that enable the analysis of single points at a glance based on small multiples. We also employ user-driven sorting and clustering techniques and a layout technique that aligns the last few shots in a point to facilitate shot pattern discovery. We discuss the usefulness of CourtTime via an extensive case study and report on feedback from an amateur tennis player and three tennis coaches.

Understanding the movement patterns of collectives, such as flocks of birds or fish swarms, is an interesting open research question. The collectives are driven by mutual objectives or react to individual direction changes and external influence factors and stimuli. The challenge in visualizing collective movement data is to show space and time of hundreds of movements at the same time to enable the detection of spatiotemporal patterns. In this paper, we propose MotionRugs, a novel space efficient technique for visualizing moving groups of entities. Building upon established space-partitioning strategies, our approach reduces the spatial dimensions in each time step to a one-dimensional ordered representation of the individual entities. By design, MotionRugs provides an overlap-free, compact overview of the development of group movements over time and thus, enables analysts to visually identify and explore group-specific temporal patterns. We demonstrate the usefulness of our approach in the field of fish swarm analysis and report on initial feedback of domain experts from the field of collective behavior.

Multivariate time series data can be found in many application domains. Examples include data from computer networks, healthcare, social networks, or financial markets. Often, patterns in such data evolve over time among multiple dimensions and are hard to detect. Dimensionality reduction methods such as PCA and MDS allow analysis and visualization of multivariate data, but per se do not provide means to explore multivariate patterns over time. We propose Temporal Multidimensional Scaling (TMDS), a novel visualization technique that computes temporal one-dimensional MDS plots for multivariate data which evolve over time. Using a sliding window approach, MDS is computed for each data window separately, and the results are plotted sequentially along the time axis, taking care of plot alignment. Our TMDS plots enable visual identification of patterns based on multidimensional similarity of the data evolving over time. We demonstrate the usefulness of our approach in the field of network security and show in two case studies how users can iteratively explore the data to identify previously unknown, temporally evolving patterns.