Providing guidance during a Visual Analytics session can support analysts in pursuing their goals more efficiently. However, the effectiveness of guidance depends on many factors: Determining the right timing to provide it is one of them. Although in complex analysis scenarios choosing the right timing could make the difference between a dependable and a superfluous guidance, an analysis of the literature suggests that this problem did not receive enough attention. In this paper, we describe a methodology to determine moments in which guidance is needed. Our assumption is that the need of guidance would influence the user state-of-mind, as in distress situations during the analytical process, and we hypothesize that such moments could be identified by analyzing the user's facial expressions. We propose a framework composed by a facial recognition software and a machine learning model trained to detect when to provide guidance according to changes of the user facial expressions. We trained the model by interviewing eight analysts during their work and ranked multiple facial features based on their relative importance in determining the need of guidance. Finally, we show that by applying only minor modifications to its architecture, our prototype was able to detect a need of guidance on the fly and made our methodology well suited also for real-time analysis sessions. The results of our evaluations show that our methodology is indeed effective in determining when a need of guidance is present, which constitutes a prerequisite to providing timely and effective guidance in VA.

Temporal Blind Source Separation (TBSS) is used to obtain the true underlying processes from noisy temporal multivariate data, such as electrocardiograms. TBSS has similarities to Principal Component Analysis (PCA) as it separates the input data into univariate components and is applicable to suitable datasets from various domains, such as medicine, finance, or civil engineering. Despite TBSS’s broad applicability, the involved tasks are not well supported in current tools, which offer only text-based interactions and single static images. Analysts are limited in analyzing and comparing obtained results, which consist of diverse data such as matrices and sets of time series. Additionally, parameter settings have a big impact on separation performance, but as a consequence of improper tooling, analysts currently do not consider the whole parameter space. We propose to solve these problems by applying visual analytics (VA) principles. Our primary contribution is a design study for TBSS, which so far has not been explored by the visualization community. We developed a task abstraction and visualization design in a user-centered design process. Task-specific assembling of well-established visualization techniques and algorithms to gain insights in the TBSS processes is our secondary contribution. We present TBSSvis, an interactive web-based VA prototype, which we evaluated extensively in two interviews with five TBSS experts. Feedback and observations from these interviews show that TBSSvis supports the actual workflow and combination of interactive visualizations that facilitate the tasks involved in analyzing TBSS results.

A typical problem in Visual Analytics (VA) is that users are highly trained experts in their application domains, but have mostly no experience in using VA systems. Thus, users often have difficulties interpreting and working with visual representations. To overcome these problems, user assistance can be incorporated into VA systems to guide experts through the analysis while closing their knowledge gaps. Different types of user assistance can be applied to extend the power of VA, enhance the user’s experience, and broaden the audience for VA. Although different approaches to visualization onboarding and guidance in VA already exist, there is a lack of research on how to design and integrate them in effective and efficient ways. Therefore, we aim at putting together the pieces of the mosaic to form a coherent whole. Based on the Knowledge-Assisted Visual Analytics model, we contribute a conceptual model of user assistance for VA by integrating the process of visualization onboarding and guidance as the two main approaches in this direction. As a result, we clarify and discuss the commonalities and differences between visualization onboarding and guidance, and discuss how they benefit from the integration of knowledge extraction and exploration. Finally, we discuss our descriptive model by applying it to VA tools integrating visualization onboarding and guidance, and showing how they should be utilized in different phases of the analysis in order to be effective and accepted by the user.

Guidance is an emerging topic in the field of visual analytics. Guidance can support users in pursuing their analytical goals more efficiently and help in making the analysis successful. However, it is not clear how guidance approaches should be designed and what specific factors should be considered for effective support. In this paper, we approach this problem from the perspective of guidance designers. We present a framework comprising requirements and a set of specific phases designers should go through when designing guidance for visual analytics. We relate this process with a set of quality criteria we aim to support with our framework, that are necessary for obtaining a suitable and effective guidance solution. To demonstrate the practical usability of our methodology, we apply our framework to the design of guidance in three analysis scenarios and a design walk-through session. Moreover, we list the emerging challenges and report how the framework can be used to design guidance solutions that mitigate these issues.

Trust-ability, reputation, security and quality are the main concerns for public and private financial institutions. To detect fraudulent behaviour, several techniques are applied pursuing different goals. For well-defined problems, analytical methods are applicable to examine the history of customer transactions. However, fraudulent behaviour is constantly changing, which results in ill-defined problems. Furthermore, analysing the behaviour of individual customers is not sufficient to detect more complex structures such as networks of fraudulent actors. We propose NEVA (Network dEtection with Visual Analytics), a Visual Analytics exploration environment to support the analysis of customer networks in order to reduce false-negative and false-positive alarms of frauds. Multiple coordinated views allow for exploring complex relations and dependencies of the data. A guidance-enriched component for network pattern generation, detection and filtering support exploring and analysing the relationships of nodes on different levels of complexity. In six expert interviews, we illustrate the applicability and usability of NEVA.

LightGuider is a novel guidance-based approach to interactive lighting design, which typically consists of interleaved 3D modeling operations and light transport simulations. Rather than having designers use a trial-and-error approach to match their illumination constraints and aesthetic goals, LightGuider supports the process by simulating potential next modeling steps that can deliver the most significant improvements. LightGuider takes predefined quality criteria and the current focus of the designer into account to visualize suggestions for lighting-design improvements via a specialized provenance tree. This provenance tree integrates snapshot visualizations of how well a design meets the given quality criteria weighted by the designer's preferences. This integration facilitates the analysis of quality improvements over the course of a modeling workflow as well as the comparison of alternative design solutions. We evaluate our approach with three lighting designers to illustrate its usefulness.

The economy of a country can be modeled as a complex system in which several players buy and sell goods from each other. By analyzing the investment flows, it is possible to reconstruct the supply chain for the production of most goods, whose understanding is important to analysts and public officials interested in creating and evaluating strategies for informed and strategic decision making, for instance, adjusting tax policies. Those networks of players and investments, however, tend to be complex and very dense, which leads to over-plotted visualizations that obfuscate precious information such as the dependencies between productive sectors and regions. In this paper, we propose Hermes, a guidance-enriched Visual Analytics environment (named after the Greek God of Commerce) for the exploration of complex economic networks, to uncover supply chains, regions’ productivity, and sector-to-sector relationships. With practical knowledge regarding guidance, we designed and implemented a visual sub-graph querying approach to extract patterns from such complex investment graphs obtained from real-world data. We present a three-fold evaluation of the system: we perform a qualitative evaluation of our approach with three domain experts, a separate assessment of the proposed guidance features with an expert researcher in this field, and a case study of Hermes using a bank account network dataset to demonstrate the generalizability of our approach.

Abstract Visual data analysis can be envisioned as a collaboration of the user and the computational system with the aim of completing a given task. Pursuing an effective system‐user integration, in which the system actively helps the user to reach his/her analysis goal has been focus of visualization research for quite some time. However, this problem is still largely unsolved. As a result, users might be overwhelmed by powerful but complex visual analysis systems which also limits their ability to produce insightful results. In this context, guidance is a promising step towards enabling an effective mixed‐initiative collaboration to promote the visual analysis. However, the way how guidance should be put into practice is still to be unravelled. Thus, we conducted a comprehensive literature research and provide an overview of how guidance is tackled by different approaches in visual analysis systems. We distinguish between guidance that is provided by the system to support the user, and guidance that is provided by the user to support the system. By identifying open problems, we highlight promising research directions and point to missing factors that are needed to enable the envisioned human‐computer collaboration, and thus, promote a more effective visual data analysis.

Since it can be challenging for users to effectively utilize interactive visualizations, guidance is usually provided to assist users in solving tasks. Guidance is mentioned as an effective mean to overcome stall situations occurring during the analysis. However, the effectiveness of a peculiar guidance solution usually varies for different analysis scenarios. The same guidance may have different effects on users with (1) different levels of expertise. The choice of the appropriate (2) degree of guidance and the type of (3) task under consideration also affect the positive or negative outcome of providing guidance. Considering these three factors, we conducted a user study to investigate the effectiveness of variable degrees of guidance with respect to the user’s previous knowledge in different analysis scenarios. Our results shed light on the appropriateness of certain degrees of guidance in relation to different tasks, and the overall influence of guidance on the analysis outcome in terms of user’s mental state and analysis performance.

Sensible data analysis requires data quality control. An essential part of this is data profiling, which is the identification and assessment of data quality problems as a prerequisite for adequately handling these problems. Differentiating between actual quality problems and unusual, but valid data values requires the "human-in-the-loop" through the use of visual analytics. Unfortunately, existing approaches for data profiling do not adequately support the special characteristics of time, which is imperative to identify quality problems in time series data - a data type prevalent in a multitude of disciplines. In this design study paper, we outline the design, implementation, and evaluation of "Know Your Enemy" (KYE) - a visual analytics approach to assess the quality of time series data. KYE supports the task of data profiling with (1) predefined data quality checks, (2) user-definable, customized quality checks, (3) interactive visualization to explore and reason about automatically detected problems, and (4) the visual identification of hidden quality problems.

Financial institutions are interested in ensuring security and quality for their customers. Banks, for instance, need to identify and stop harmful transactions in a timely manner. In order to detect fraudulent operations, data mining techniques and customer profile analysis are commonly used. However, these approaches are not supported by Visual Analytics techniques yet. Visual Analytics techniques have potential to considerably enhance the knowledge discovery process and increase the detection and prediction accuracy of financial fraud detection systems. Thus, we propose EVA, a Visual Analytics approach for supporting fraud investigation, fine-tuning fraud detection algorithms, and thus, reducing false positive alarms.

The detection of anomalous events in huge amounts of data is sought in many domains. For instance, in the context of financial data, the detection of suspicious events is a prerequisite to identify and prevent attempts to defraud. Hence, various financial fraud detection approaches have started to exploit Visual Analytics techniques. However, there is no study available giving a systematic outline of the different approaches in this field to understand common strategies but also differences. Thus, we present a survey of existing approaches of visual fraud detection in order to classify different tasks and solutions, to identify and to propose further research opportunities. In this work, fraud detection solutions are explored through five main domains: banks, the stock market, telecommunication companies, insurance companies, and internal frauds. The selected domains explored in this survey were chosen for sharing similar time-oriented and multivariate data characteristics. In this survey, we (1) analyze the current state of the art in this field; (2) define a categorization scheme covering different application domains, visualization methods, interaction techniques, and analytical methods which are used in the context of fraud detection; (3) describe and discuss each approach according to the proposed scheme; and (4) identify challenges and future research topics.

Preprocessing is a mandatory first step to make data usable for analysis. While in time series analysis many established methods require data that are sampled in regular time intervals, in practice sensors may sample data at varying interval lengths. Time series rastering is the process of aggregating unequally spaced time series into equal interval lengths. In this paper we discuss critical aspects in the context of time series rastering, and we present a visual design which supports the parametrization of the rastering transformation, communicates the introduced uncertainties and quality issues, and facilitates the comparison of alternative rastering outcomes to achieve optimal results.

Abstract The cycle plot is an established and effective visualization technique for identifying and comprehending patterns in periodic time series, like trends and seasonal cycles. It also allows to visually identify and contextualize extreme values and outliers from a different perspective. Unfortunately, it is limited to univariate data. For multivariate time series, patterns that exist across several dimensions are much harder or impossible to explore. We propose a modified cycle plot using a distance‐based abstraction (Mahalanobis distance) to reduce multiple dimensions to one overview dimension and retain a representation similar to the original. Utilizing this distance‐based cycle plot in an interactive exploration environment, we enhance the Visual Analytics capacity of cycle plots for multivariate outlier detection. To enable interactive exploration and interpretation of outliers, we employ coordinated multiple views that juxtapose a distance‐based cycle plot with Cleveland's original cycle plots of the underlying dimensions. With our approach it is possible to judge the outlyingness regarding the seasonal cycle in multivariate periodic time series.

Visual analytics (VA) is typically applied in scenarios where complex data has to be analyzed. Unfortunately, there is a natural correlation between the complexity of the data and the complexity of the tools to study them. An adverse effect of complicated tools is that analytical goals are more difficult to reach. Therefore, it makes sense to consider methods that guide or assist users in the visual analysis process. Several such methods already exist in the literature, yet we are lacking a general model that facilitates in-depth reasoning about guidance. We establish such a model by extending van Wijk's model of visualization with the fundamental components of guidance. Guidance is defined as a process that gradually narrows the gap that hinders effective continuation of the data analysis. We describe diverse inputs based on which guidance can be generated and discuss different degrees of guidance and means to incorporate guidance into VA tools. We use existing guidance approaches from the literature to illustrate the various aspects of our model. As a conclusion, we identify research challenges and suggest directions for future studies. With our work we take a necessary step to pave the way to a systematic development of guidance techniques that effectively support users in the context of VA.

A number of studies have investigated different ways of visualizing uncertainty. However, in the temporal dimension, it is still an open question how to best represent uncertainty, since the special characteristics of time require special visual encodings and may provoke different interpretations. Thus, we have conducted a comprehensive study comparing alternative visual encodings of intervals with uncertain start and end times: gradient plots, violin plots, accumulated probability plots, error bars, centered error bars, and ambiguation. Our results reveal significant differences in error rates and completion time for these different visualization types and different tasks. We recommend using ambiguation - using a lighter color value to represent uncertain regions - or error bars for judging durations and temporal bounds, and gradient plots - using fading color or transparency - for judging probability values.

In recent years, sophisticated visualization methods have been developed to support both, the logical structure and the time-oriented aspects of computer-executable clinical treatment plans. However, visualizing the effects of applying treatment plans as well as supporting the exploration of effects on the patient's condition are still largely unresolved tasks. To fill this gap, we have developed a prototype that enhances known visualization methods to communicate the processes of treatment plan application together with their effects on a patient's condition in an easily understandable way. Our prototype combines the advantages of enhanced visual recognition of patterns with traditional information of parameters' development. Thus, it provides means (1) to assess success or failure of previously applied treatment plans, (2) to explore the effects of each applied clinical action on the patient's condition, and (3) to identify sub-optimal treatment choices. These means help physicians to optimize their treatment choices and enable developers of clinical practice guidelines (CPGs) to investigate and readjust these treatment plans.

Mapping concepts from medical terminologies, such as the UMLS, to medical documents is a prerequisite for many tasks of (automatically) processing documents. Due to the nature of the UMLS and the tools to accomplish the mapping, it is not always possible to achieve a correct and unambiguous mapping. This drawback led us to the development of an editor for correcting the obtained information. Our editor, MapFace, visualizes information received by the MetaMap Transfer (MMTx) program and enables users to edit and correct this information on both a conceptual and a syntactical level. By means of this functionality we are able to provide further processing steps with correct and appropriate input. Furthermore, the visualization features enable users to validate or even generate hypotheses, as well as support the better understanding of medical text. 1.