Visual Analytics Approach Research Articles

MADDPGViz: a visual analytics approach to understand multi-agent deep reinforcement learning

MADDPGViz: a visual analytics approach to understand multi-agent deep reinforcement learning

NetPrune: A sparklines visualization for network pruning

Current deep learning approaches are cutting-edge methods for solving classification tasks. Arising transfer learning techniques allows applying large generic model to simple tasks whereas simpler models could be used. Large models raise the major problem of their memory consumption and processor usage and lead to a prohibitive ecological footprint. In that paper, we present a novel visual analytics approach to interactively prune those networks and thus limit that issue. Our technique leverages a novel sparkline matrix visualization technique as well as a novel local metric which evaluates the discriminatory power of a filter to guide the pruning process and make it interpretable. We assess the well- founded of our approach through two realistic case studies and a user study. For both of them, the interactive refinement of the model led to a significantly smaller model having similar prediction accuracy than the original one.

Towards Progressively Detecting Faults in a Large Power System: A Visual Analytics Approach

Electricity serves as the foundation of everyday life. Grid operators are obliged to provide stable power supply to end users. However, given the scale and complexity of modern nationwide grids, it has become increasingly challenging to locate faults quickly and accurately during power failure. Previous locating techniques mainly focus on data analyzing methods, while little work is done using visual analytics approach. This paper presents a progressive visual analytics procedure (i.e., overview, detecting faulted bus candidates, locating buses, and looking into bus details) to detect fault location and figure out possible faulted buses. In particular, an efficient clustering algorithm associated with a novel visualization for time-varying series as well as multiple and coordinated views is developed to locate faulted buses intuitively and quickly. Case studies and expert feedback have indicated that our approach is contributing to real-world applications.

Visual Analytics for Innovation and R&D Intelligence

Overview: Innovation is critical to the growth and survival of companies across industries and geographies. Over time, however, sources of innovation have become much more diverse, and a systematic understanding of the complex and dynamic innovation landscape is challenging. This paper describes the value and impact of using a data-driven, visual analytic approach for innovation and R&D intelligence. I outline a methodology with which to approach visual analytic innovation and R&D intelligence, present illustrative mini-case studies, and frame the findings into key considerations and elements of the intelligence decision space. The paper contributes to practical and theoretical understanding of how emerging computational and analytical approaches can support innovation and R&D activities. It concludes with practical implications and future research directions.

High-dimensional spatiotemporal visual analysis of the air quality in China

Air quality is a significant environmental issue among the Chinese people and even the global population, and it affects both human health and the Earth’s long-term sustainability. In this study, we proposed a multiperspective, high-dimensional spatiotemporal data visualization and interactive analysis method, and we studied and analyzed the relationship between the air quality and several influencing factors, including meteorology, population, and economics. Six visualization methods were integrated in this study, each specifically designed and improved for visualization analysis purposes. To reveal the spatiotemporal distribution and potential impact of the air quality, we designed a comprehensive coupled visual interactive analysis approach visually express both high-dimensional and spatiotemporal attributes, reveal the overall situation and explain the relationship between attributes. We clarified the current spatiotemporal distribution, development trends, and influencing factors of the air quality in China through interactive visual analysis of a 25-dimensional dataset involving 31 Chinese provinces. We also verified the correctness and effectiveness of relevant policies and demonstrated the advantages of our method.

A visual analytics approach for multi-attribute decision making based on intuitionistic fuzzy AHP and UMAP

Multi-attribute decision making (MADM) has been extensively explored and applied in many real-world problems. However, comprehending the decision-making process and selecting a satisfactory choice from a large set of alternatives characterized by multiple conflicting attributes impose a significant cognitive burden on decision-makers. A visual analytics approach for MADM (MADM-VA) that integrates visual representations of alternatives with the decision-making analysis process is proposed to solve this problem. Firstly, to ensure the final decision meets the actual needs and expectations of decision-makers, an Intuitionistic Fuzzy Analytic Hierarchy Process based on Nonlinear Programming (IFAHP-NLP) is proposed. This approach directly determines the optimal crisp attribute weight vector according to the preferences of decision-makers and avoids information loss and distortion of attribute weights caused by defuzzification. Next, the Uniform Manifold Approximation and Projection (UMAP) is used to map the high-dimensional weighted normalized decision matrix to two-dimensional space, illustrating the distribution of alternatives. The concept of similarity to the ideal solution is introduced to enhance the interpretability of the generated space. Furthermore, the Voronoi diagram is innovatively adopted to assist decision-makers in gaining a better understanding of the decision-making process and help them visually identify the best choice, which is closest to the positive ideal solution and farthest from the negative ideal solution. Finally, experimental results from two case studies verify that MADM-VA is efficient and reliable.

How to assess and improve the triple bottom line (TBL) in manufacturing processes: a real case in home appliance manufacturing

PurposeThis paper aims to propose a stepwise method to improve the sustainability of manufacturing processes.Design/methodology/approachThe proposed approach is based on an extensive literature review and research around the environmental, economic and social pillars of sustainability in manufacturing firms. Considering the lean approach, the manufacturing processes are mapped in a value stream and analyzed through the extensive identified sustainability criteria.FindingsThe findings reveal the consumption and waste of natural and nonrenewable resources, through going beyond the existing boundaries and focusing on relevant derived production pieces and tracing to their origins. The findings also present the effect of the time value of money on sustainability by using the cost–time profile as a sustainability criterion. This research finds out the employees’ impacts on sustainability improvement through an effective focus on technical, cultural and personal aspects.Practical implicationsThe research outcomes provide operations managers and decision-makers in the field of sustainability with a practical platform to comprehend and assess the factors contributing to the manufacturing process sustainability and to plan relevant corrective actions accordingly.Originality/valueThe extended view of sustainability criteria in this research as well as its visual-analytical approach will help practitioners to assess and improve sustainability in their operations in a more holistic way.

Analyzing Health Data Breaches: A Visual Analytics Approach

This research studies the occurrence of data breaches in healthcare provider settings regarding patient data. Using visual analytics and data visualization tools, we study the distribution of healthcare breaches by state. We review the main causes and types of breaches, as well as their impact on both providers and patients. The research shows a range of data breach victims. Network servers are the most popular location for common breaches, such as hacking and information technology (IT) incidents, unauthorized access, theft, loss, and improper disposal. We offer proactive recommendations to prepare for a breach. These include, but are not limited to, regulatory compliance, implementing policies and procedures, and monitoring network servers. Unfortunately, the results indicate that the probability of data breaches will continue to rise.

Visualization and Visual Analytics Approaches for Image and Video Datasets: A Survey

Image and video data analysis has become an increasingly important research area with applications in different domains such as security surveillance, healthcare, augmented and virtual reality, video and image editing, activity analysis and recognition, synthetic content generation, distance education, telepresence, remote sensing, sports analytics, art, non-photorealistic rendering, search engines, and social media. Recent advances in Artificial Intelligence (AI) and particularly deep learning have sparked new research challenges and led to significant advancements, especially in image and video analysis. These advancements have also resulted in significant research and development in other areas such as visualization and visual analytics, and have created new opportunities for future lines of research. In this survey article, we present the current state of the art at the intersection of visualization and visual analytics, and image and video data analysis. We categorize the visualization articles included in our survey based on different taxonomies used in visualization and visual analytics research. We review these articles in terms of task requirements, tools, datasets, and application areas. We also discuss insights based on our survey results, trends and patterns, the current focus of visualization research, and opportunities for future research.

Abortion and Democracy: Contentious Body Politics in Argentina, Chile, and Uruguay

In the chaos of 2020, with a backdrop of the global Corona Virus (CoVid19) pandemic, and in the midst of the unprecedented and historical political movements throughout south and central America centring abortion rights politics, ‘Abortion and Democracy: Contentious Body Politics in Argentina, Chile, and Uruguay’ came to be. Edited by Professor Barbara Sutton and Dr Nayla Luz Vacarezza, this important book astutely chronicles the struggles, challenges, and victories of recent abortion politics in Latin America. This edited collection is organized into four main parts examining abortion politics in Latin America’s Southern Cone of Argentina, Chile, and Uruguay. It explores how the demand for abortion rights shapes and has shaped political agendas in the region post-dictatorship and analyses how the issue, from the micro to the socio-political level, shapes individual experiences of abortion access, activism, and litigation. Chapters throughout the volume are based on qualitative interviews, ethnographic fieldwork, archival research, media analysis, statistical information, visual analysis, and historical-comparative approaches. The book concludes with reflections on where we can go from here with the lessons already learned from the successes and failures of what has come to be known as the ‘Green Tide’.

VizOPTICS: Getting insights into OPTICS via interactive visual analysis

Ordering points to identify the clustering structure (OPTICS) is a density-based clustering algorithm that allows the exploration of the cluster structure in the dataset by outputting an ordered queue called cluster ordering. However, this nonexplicit output makes it greatly more difficult for practitioners to identify cluster patterns and obtain high-quality clusters. In this paper, we firstly investigate OPTICS in depth and identify the challenges facing users of OPTICS for cluster analysis through a pilot user study. Then, integrating human intelligence deeply with the machine intelligence of OPTICS, a visual analytics approach, VizOPTICS, is proposed to support practitioners in understanding and applying OPTICS to extract meaningful clustering results. It includes an ordered lattice plot for observing the generation process of cluster ordering, a density scatter plot for analyzing the cluster structure in datasets, and a dynamic reachability plot for optimizing clustering results, and also provides several interaction modes, such as selecting and highlighting, to help users analyze the cluster formation and algorithm operation processes interactively. Finally, we assess our approach through four case studies and a user evaluation study. The results demonstrate the effectiveness and efficiency of the system.

Data Analytics and Visualization of Adaptive Collaboration Simulations

Role-based collaboration (RBC) is an adaptive computational methodology that uses roles as underlying mechanisms to facilitate and analyze system behavior for entities that collaborate and coordinate their activities with or within these systems. In dynamic environments, including those that occur in large-scale simulations, visualization provides insights into complex systems behaviors. This article presents a visual analytics (VA) approach to studying dynamics involved in adaptive collaboration (AC) for large, multiagent simulation model using new open-source tools. The results show that time-varying systems can be steered for optimal performance and assessing adaptations using VA dashboards.

PDViz: A Visual Analytics Approach for State Policy Data

AbstractSub‐national governments across the United States implement a variety of policies to address large societal problems and needs. Many policies are picked up or adopted in other states. This process is called policy diffusion and allows researchers to analyse and compare the social, political, and contextual characteristics that lead to adopting certain policies, as well as the efficacy of these policies once adopted. In this paper, we introduce PDViz, a visual analytics approach that allows social scientists to dynamically analyse the policy diffusion history and underlying patterns. It is designed for analysing and answering a list of research questions and tasks posed by social scientists in prior work. To evaluate our system, we present two usage scenarios and conduct interviews with domain experts in political science. The interviews highlight that PDViz provides the result of policy diffusion patterns that align with their domain knowledge as well as the potential to be a learning tool for students to understand the concept of policy diffusion.

Decision-making based on an improved visual analytics approach for emotion prediction

Visual Analytics approach allows driving informed and effective decision-making. It assists decision-makers to visually interact with large amount of data and to computationally learn valuable hidden patterns in that data, which improve the decision quality. In this article, we introduce an enhanced visual analytics model combining cognitive-based visual analysis to data mining-based automatic analysis. As emotions are strongly related to human behaviour and society, emotion prediction is widely considered by decision making activities. Unlike speech and facial expressions modalities, EEG (electroencephalogram) has the advantage of being able to record information about the internal emotional state that is not always translated by perceptible external manifestations. For this reason, we applied the proposed cognitive approach on EEG data to demonstrate its efficiency for predicting emotional reaction to films. For automatic analysis, we developed the Echo State Network (ESN) technique considered as an efficient machine learning solution due to its straightforward training procedure and high modelling ability for handling time-series problems. Finally, utility and usability tests were performed to evaluate the developed prototype.

A visual analytics approach for national intangible cultural heritage in Heilongjiang province

The work of traditional intangible cultural heritage analyzes the intangible cultural works in restricted scales way. So, it is difficult to multi-scale understand the closely related to intangible cultural heritage. In this paper, visual analytics approaches are proposed for the preserve and protection those historic cultural heritages, which include multi-dimensional visualization, temporal visualization, and geospatial visualization. We take national intangible cultural heritage in Heilongjiang province as an example. Through visual analysis of intangible cultural heritage in Heilongjiang province, experts can form multi-dimensional understanding the culture of Heilongjiang province, including the categories, numbers and distributions. Furthermore, those methods we proposed can effective help experts make an in-depth analysis of those intangible cultural heritage, and provide them a new insight in a comparative way.

Assessing the cognition of movement trajectory visualizations: interpreting speed and direction

ABSTRACT This paper evaluates cognitively plausible geovisualization techniques for mapping movement data. With the widespread increase in the availability and quality of space-time data capturing movement trajectories of individuals, meaningful representations are needed to properly visualize and communicate trajectory data and complex movement patterns using geographic displays. Many visualization and visual analytics approaches have been proposed to map movement trajectories (e.g. space-time paths, animations, trajectory lines, etc.). However, little is known about how effective these complex visualizations are in capturing important aspects of movement data. Given the complexity of movement data which involves space, time, and context dimensions, it is essential to evaluate the communicative efficiency and efficacy of various visualization forms in helping people understand movement data. This study assesses the effectiveness of static and dynamic movement displays as well as visual variables in communicating movement parameters along trajectories, such as speed and direction. To do so, a web-based survey is conducted to evaluate the understanding of movement visualizations by a nonspecialist audience. This and future studies contribute fundamental insights into the cognition of movement visualizations and inspire new methods for the empirical evaluation of geovisualizations.

Intelligent visualization and visual analytics

Intelligent visualization and visual analytics

Visual Analytics for Understanding Draco's Knowledge Base.

Draco has been developed as an automated visualization recommendation system formalizing design knowledge as logical constraints in ASP (Answer-Set Programming). With an increasing set of constraints and incorporated design knowledge, even visualization experts lose overview in Draco and struggle to retrace the automated recommendation decisions made by the system. Our paper proposes an Visual Analytics (VA) approach to visualize and analyze Draco's constraints. Our VA approach is supposed to enable visualization experts to accomplish identified tasks regarding the knowledge base and support them in better understanding Draco. We extend the existing data extraction strategy of Draco with a data processing architecture capable of extracting features of interest from the knowledge base. A revised version of the ASP grammar provides the basis for this data processing strategy. The resulting incorporated and shared features of the constraints are then visualized using a hypergraph structure inside the radial-arranged constraints of the elaborated visualization. The hierarchical categories of the constraints are indicated by arcs surrounding the constraints. Our approach is supposed to enable visualization experts to interactively explore the design rules' violations based on highlighting respective constraints or recommendations. A qualitative and quantitative evaluation of the prototype confirms the prototype's effectiveness and value in acquiring insights into Draco's recommendation process and design constraints.

FSLens: A Visual Analytics Approach to Evaluating and Optimizing the Spatial Layout of Fire Stations.

The provision of fire services plays a vital role in ensuring the safety of residents' lives and property. The spatial layout of fire stations is closely linked to the efficiency of fire rescue operations. Traditional approaches have primarily relied on mathematical planning models to generate appropriate layouts by summarizing relevant evaluation criteria. However, this optimization process presents significant challenges due to the extensive decision space, inherent conflicts among criteria, and decision-makers' preferences. To address these challenges, we propose FSLens, an interactive visual analytics system that enables in-depth evaluation and rational optimization of fire station layout. Our approach integrates fire records and correlation features to reveal fire occurrence patterns and influencing factors using spatiotemporal sequence forecasting. We design an interactive visualization method to explore areas within the city that are potentially under-resourced for fire service based on the fire distribution and existing fire station layout. Moreover, we develop a collaborative human-computer multi-criteria decision model that generates multiple candidate solutions for optimizing firefighting resources within these areas. We simulate and compare the impact of different solutions on the original layout through well-designed visualizations, providing decision-makers with the most satisfactory solution. We demonstrate the effectiveness of our approach through one case study with real-world datasets. The feedback from domain experts indicates that our system helps them to better identify and improve potential gaps in the current fire station layout.

Marjorie: Visualizing Type 1 Diabetes Data to Support Pattern Exploration.

In this work we propose Marjorie, a visual analytics approach to address the challenge of analyzing patients' diabetes data during brief regular appointments with their diabetologists. Designed in consultation with diabetologists, Marjorie uses a combination of visual and algorithmic methods to support the exploration of patterns in the data. Patterns of interest include seasonal variations of the glucose profiles, and non-periodic patterns such as fluctuations around mealtimes or periods of hypoglycemia (i.e., glucose levels below the normal range). We introduce a unique representation of glucose data based on modified horizon graphs and hierarchical clustering of adjacent carbohydrate or insulin entries. Semantic zooming allows the exploration of patterns on different levels of temporal detail. We evaluated our solution in a case study, which demonstrated Marjorie's potential to provide valuable insights into therapy parameters and unfavorable eating habits, among others. The study results and informal feedback collected from target users suggest that Marjorie effectively supports patients and diabetologists in the joint exploration of patterns in diabetes data, potentially enabling more informed treatment decisions. A free copy of this paper and all supplemental materials are available at https://osf.io/34t8c/.