Abstract We evaluate visualization concepts to represent missing values in parallel coordinates. We focus on the trade‐off between the ability to perceive missing values and the concept's impact on common tasks. For this purpose, we identified three missing value representation concepts: removing line segments where values are missing, adding a separate, horizontal axis onto which missing values are projected, and using imputed values as a replacement for missing values. For the missing values axis and imputed values concepts, we additionally add downplay and highlight variations. We performed a crowd‐sourced, quantitative user study with 732 participants comparing the concepts and their variations using five real‐world datasets. Based on our findings, we provide suggestions regarding which visual encoding to employ depending on the task at focus.

This article contributes a novel visualization method, Missingness Glyph, for analysis and exploration of missing values in data. Missing values are a common challenge in most data generating domains and may cause a range of analysis issues. Missingness in data may indicate potential problems in data collection and pre-processing, or highlight important data characteristics. While the development and improvement of statistical methods for dealing with missing data is a research area in its own right, mainly focussing on replacing missing values with estimated values, considerably less focus has been put on visualization of missing values. Nonetheless, visualization and explorative analysis has great potential to support understanding of missingness in data, and to enable gaining of novel insights into patterns of missingness in a way that statistical methods are unable to. The Missingness Glyph supports identification of relevant missingness patterns in data, and is evaluated and compared to two other visualization methods in context of the missingness patterns. The results are promising and confirms that the Missingness Glyph in several cases perform better than the alternative visualization methods.

In visually demanding environments like working positions in air traffic control, there is a risk of missing important information. Attention support might help to reduce this, but there is a risk that it introduces new issues in the form of distractions or increased visual load. The work presented in this paper explores the concept of Soft Visual Cues, with the aim to make the operator aware of missing information, but doing it discreetly enough only to be noticed when the operator is scanning the area where the information is present, thereby complementing the concepts of attention guidance, alarms, and subtle gaze direction. The qualitative evaluation performed aimed primarily at catching the operators' (air traffic controllers) first impressions. Focus was on air traffic control, but was complemented with vessel traffic service and train control environments and operators. The results from air traffic control showed a preference for symbol property changes related to geometry rather than for colour or opacity changes as soft visual cues. The comparison to the other domains highlighted the contextual dependence, visual context and process context, of the concept.

Parallel coordinates are commonly used for non-temporal multivariate data, but there is little support for their usability for displaying temporal multivariate data. In this paper, we introduce a study evaluating the usability of 2D and 3D parallel coordinates for pattern identification in temporal multivariate data. The results indicate that 3D parallel coordinates have higher usability, as measured with higher accuracy and faster response time as well as subjective ratings, compared to 2D.

Eye-tracking has become an invaluable tool for the analysis of working practices in many technological fields of activity. Typically studies focus on short tasks and use static expected areas of interest (AoI) in the display to explore subjects' behaviour, making the analyst's task quite straightforward. In long-duration studies, where the observations may last several hours over a complete work session, the AoIs may change over time in response to altering workload, emergencies or other variables making the analysis more difficult. This work puts forward a novel method to automatically identify spatial AoIs changing over time through a combination of clustering and cluster merging in the temporal domain. A visual analysis system based on the proposed methods is also presented. Finally, we illustrate our approach within the domain of air traffic control, a complex task sensitive to prevailing conditions over long durations, though it is applicable to other domains such as monitoring of complex systems.

The parallel coordinates technique is widely used for the analysis of multivariate data. During recent decades significant research efforts have been devoted to exploring the applicability of the technique and to expand upon it, resulting in a variety of extensions. Of these many research activities, a surprisingly small number concerns user-centred evaluations investigating actual use and usability issues for different tasks, data and domains. The result is a clear lack of convincing evidence to support and guide uptake by users as well as future research directions. To address these issues this paper contributes a thorough literature survey of what has been done in the area of user-centred evaluation of parallel coordinates. These evaluations are divided into four categories based on characterization of use, derived from the survey. Based on the data from the survey and the categorization combined with the authors' experience of working with parallel coordinates, a set of guidelines for future research directions is proposed.

Findings from field studies in power system control rooms show that overview displays are needed to aid operators to achieve shared situation awareness. The existing overview displays are often cluttered, with a lot of detailed information and with overuse of colors. There is no "best practice'' in the field and it is up to power system utilities to design their own displays. This work presents a survey of previously proposed mappings of power system data to visual representations and based on this analysis a set of alternative mappings are demonstrated.

Visual comparison is an intrinsic part of interactive data exploration and analysis. The literature provides a large body of existing solutions that help users accomplish comparison tasks. These solutions are mostly of visual nature and custom-made for specific data. We ask the question if a more general support is possible by focusing on the interaction aspect of comparison tasks. As an answer to this question, we propose a novel interaction concept that is inspired by real-world behavior of people comparing information printed on paper. In line with real-world interaction, our approach supports users (1) in interactively specifying pieces of graphical information to be compared, (2) in flexibly arranging these pieces on the screen, and (3) in performing the actual comparison of side-by-side and overlapping arrangements of the graphical information. Complementary visual cues and add-ons further assist users in carrying out comparison tasks. Our concept and the integrated interaction techniques are generally applicable and can be coupled with different visualization techniques. We implemented an interactive prototype and conducted a qualitative user study to assess the concept's usefulness in the context of three different visualization techniques. The obtained feedback indicates that our interaction techniques mimic the natural behavior quite well, can be learned quickly, and are easy to apply to visual comparison tasks.

Categorical data is common within many areas and efficient methods for analysis are needed. It is, however, often difficult to analyse categorical data since no general measure of similarity exists. One approach is to represent the categories with numerical values (quantification) prior to visualization using methods for numerical data. Another is to use visual representations specifically designed for categorical data. Although commonly used, very little guidance is available as to which method may be most useful for different analysis tasks. This paper presents an evaluation comparing the performance of employing quantification prior to visualization and visualization using a method designed for categorical data. It also provides a guidance as to which visualization approach is most useful in the context of two basic data analysis tasks: one related to similarity structures and one related to category frequency. The results strongly indicate that the quantification approach is most efficient for the similarity related task, whereas the visual representation designed for categorical data is most efficient for the task related to category frequency.

Today weather forecasts assist in the preparation of roads during the winter season to avoid accidents resulting from snow, rain and slipperiness. As with any weather forecast there is always a search for improvement. One way to do this is by verifying the forecasted parameters with the actual weather observed in the forecasted area. To facilitate identification of significant trends and patterns within weather data we have developed an application based on interactive information visualization techniques. The application was created in close collaboration with domain experts from the Swedish Meteorological and Hydrological Institute and initial feedback from a performed user study shows that interactive visualization speeds up the analysis process as well as increases flexibility compared to currently used manual methods.

Operators of power grid supervisory control systems have to gather information from a wide variety of views to build situation awareness. Findings from a conducted field study show that this task is challenging and cognitively demanding. Visualization research for power grid supervisory control systems has focused on developing new visualization techniques for representing one aspect of the power system data. Little work has been done to demonstrate how information visualization techniques can support the operator in the sense making process to achieve situation awareness. To fill this gap, and with support from a field study, we propose solutions based on multiple and coordinated views, visual interactive filtering and parallel coordinates.

Evaluation is a key research challenge within the international Information Visualization (InfoVis) community, and Heuristic Evaluation is one recognized method. Various sets of heuristics have been proposed but there remains no consensus as to which heuristics are most useful for addressing aspects specific to the complex interactive visual displays used in modern InfoVis systems. This paper presents a first effort to empirically determine a new set of such general heuristics tailored for Heuristic Evaluation of common and important usability problems in InfoVis techniques. Participants in the study rated how well a total of 63 heuristics from 6 earlier published heuristic sets could explain a collection of 74 usability problems derived from earlier InfoVis evaluations. The results were used to synthesize 10 heuristics that, as a set, provided the highest explanatory coverage. The paper also stresses the challenges for future research to validate and further improve upon this set.

To meet the growing demand of communicating climate science and policy research, the interdisciplinary field of climate visualization has increasingly extended its traditional use of 2D representations and techniques from the field of scientific visualization to include information visualization for the creation of highly interactive tools for both spatial and abstract data. This paper provides an initial discussion on the need and design of evaluations for climate visualization. We report on previous experiences and identify how evaluation methods commonly used in information visualization can be used in climate visualization to increase our understanding of visualization techniques and tools.

The complex nature of multivariate data sets calls for high interactive performance and intuitive metaphors. A specific type of multivariate data is where the variables sum up to a constant, here defined as multicomponent data. This application paper presents an interactive application for analysis of modeled multicomponent data. The aim is to find high performance variable combinations that fulfill some requested properties. The application is based on coordinated views that include parallel coordinates, a ternary diagram, a 2D scatter plot and a line plot. It supports numerous interaction techniques enabling fast analysis of complex patterns in multicomponent data sets. The application is developed in collaboration with researchers within the fields of statistics and chemistry. An informal usability evaluation indicates that the interactive nature of the application clearly facilitates the analysis process.

An interesting property of the commonly used parallel coordinates display is the distinct overall pattern formed by the totality of lines between adjacent axes. These patterns have a direct correspondence to the type of relationship existing between the variables mapped onto the axes in question as well as a salient visual appearance. Parallel coordinates displays can therefore be used to visually investigate relationships between variables as well as investigating individual objects/lines. The problem with this approach is that, whereas each object is mapped in its entirety in a standard parallel coordinates display, only a small subset of the interrelations between variables is shown as the number of variables increase. To show all possible relations between variables multiple parallel coordinates displays are needed. In turn this means that each variable is duplicated several times, once per extra parallel coordinates display. To a viewer this increases the visual complexity and most probably the mental load. To aid users we have devised a new configuration of the axes in multiple parallel coordinates displays. Through an experiment we have also started to investigate the usability of this new configuration and the results are promising.

The identification of significant sequences in large and complex event-based temporal data is a challenging problem with applications in many areas of today's information intensive society. Pure visual representations can be used for the analysis, but are constrained to small data sets. Algorithmic search mechanisms used for larger data sets become expensive as the data size increases and typically focus on frequency of occurrence to reduce the computational complexity, often overlooking important infrequent sequences and outliers. In this paper we introduce an interactive visual data mining approach based on an adaptation of techniques developed for web searching, combined with an intuitive visual interface, to facilitate user-centred exploration of the data and identification of sequences significant to that user. The search algorithm used in the exploration executes in negligible time, even for large data, and so no pre-processing of the selected data is required, making this a completely interactive experience for the user. Our particular application area is social science diary data but the technique is applicable across many other disciplines.

Multivariate data sets including hundreds of variables are increasingly common in many application areas. Most multivariate visualization techniques are unable to display such data effectively, and a common approach is to employ dimensionality reduction prior to visualization. Most existing dimensionality reduction systems focus on preserving one or a few significant structures in data. For many analysis tasks, however, several types of structures can be of high significance and the importance of a certain structure compared to the importance of another is often task-dependent. This paper introduces a system for dimensionality reduction by combining user-defined quality metrics using weight functions to preserve as many important structures as possible. The system aims at effective visualization and exploration of structures within large multivariate data sets and provides enhancement of diverse structures by supplying a range of automatic variable orderings. Furthermore it enables a quality-guided reduction of variables through an interactive display facilitating investigation of trade-offs between loss of structure and the number of variables to keep. The generality and interactivity of the system is demonstrated through a case scenario.

Data sets containing a combination of categorical and continuous variables (mixed data sets) are difficult to analyse since no generalized similarity measure exists for categorical variables. Quantification of categorical variables makes it possible to represent this type of data using techniques designed for numerical data. This paper presents a quantification process of categorical variables in mixed data sets that incorporates information on relationships among the continuous variables into the process, as well as utilizing the domain knowledge of a user. An interactive visualization environment using parallel coordinates as a visual interface is provided, where the user is able to control the quantification process and analyse the result. The efficiency of the approach is demonstrated using two mixed data sets.

Abstract The rendering of large data sets can result in cluttered displays and non‐interactive update rates, leading to time consuming analyses. A straightforward solution is to reduce the number of items, thereby producing an abstraction of the data set. For the visual analysis to remain accurate, the graphical representation of the abstraction must preserve the significant features present in the original data. This paper presents a screen space quality method, based on distance transforms, that measures the visual quality of a data abstraction. This screen space measure is shown to better capture significant visual structures in data, compared with data space measures. The presented method is implemented on the GPU, allowing interactive creation of high quality graphical representations of multivariate data sets containing tens of thousands of items.

This paper introduces Temporal Density Parallel Coordinates (TDPC) and Depth Cue Parallel Coordinates (DCPC) which extend the standard 2D parallel coordinates technique to capture time-varying dynamics. The proposed techniques can be used to analyse temporal positions of data items as well as temporal positions of changes occurring using 2D displays. To represent temporal changes, polygons (instead of traditional lines) are rendered in parallel coordinates. The results presented show that rendering polygons is superior at revealing large temporal changes. Both TDPC and DCPC have been efficiently implemented on the GPU allowing the visualization of thousands of data items over thousands of time steps at interactive frame rates.

Analysing multivariate data is a difficult task. Extensive interaction with the data is often necessary and, hence, the analysis can be quite time consuming. In this paper, we introduce a method to allow the user to simultaneously examine the relationships of a single dimension with many others in the data. The single dimension can then be interactively changed to allow the user to quickly examine all possible combinations. This method is achieved by extending the standard parallel coordinate approach to a 3D clustered multi-relational parallel coordinate representation (CMRPC). To aid this method, we use a technique called relation spacing which is used to position the axes according to how 'interesting' the different relations are. We also propose a number of interaction techniques to further facilitate the analysis process.

Parallel coordinates are widely used in many applications for visualization of multivariate data. Because of the nature of parallel coordinates, the visualization technique is often used for data overview. However, when the number of tuples to be visualized becomes very large, this technique makes it difficult to distinguish the overall structure. In This work we present a novel technique which uses a classification approach, the self-organizing map (an unsupervised learning algorithm), to solve this problem by creating an initial clustering of the data. By initially only visualizing the resulting representational clusters, the inherited global structure can be shown. Using linked views and allowing the user to perform drill-down and filtering on these representations reveals the single data items without loss of context.

Extracting actionable insight from large high dimensional data sets, and its use for more effective decision-making, has become a pervasive problem across many fields in research and industry. We describe an investigation of the application of tightly coupled statistical and visual analysis techniques to this task. The approach we choose is "unsupervised learning" where we investigate the advantages offered by close coupling of the self-organizing map algorithm with new combinations of visualization components and techniques for interactivity.