Search

We present RCMVis, a visual analytics system to support interactive Route Choice Modeling analysis. It aims to model which characteristics of routes, such as distance and the number of traffic lights, affect travelers' route choice behaviors and how much they affect the choice during their trips. Through close collaboration with domain experts, we designed a visual analytics framework for Route Choice Modeling. The framework supports three interactive analysis stages: exploration, modeling, and reasoning. In the exploration stage, we help analysts interactively explore trip data from multiple origin-destination (OD) pairs and choose a subset of data they want to focus on. To this end, we provide coordinated multiple OD views with different foci that allow analysts to inspect, rank, and compare OD pairs in terms of their multidimensional attributes. In the modeling stage, we integrate a k-medoids clustering method and a path-size logit model into our system to enable analysts to model route choice behaviors from trips with support for feature selection, hyperparameter tuning, and model comparison. Finally, in the reasoning stage, we help analysts rationalize and refine the model by selectively inspecting the trips that strongly support the modeling result. For evaluation, we conducted a case study and interviews with domain experts. The domain experts discovered unexpected insights from numerous modeling results, allowing them to explore the hyperparameter space more effectively to gain better results. In addition, they gained OD- and road-level insights into which data mainly supported the modeling result, enabling further discussion of the model.

Varied edge bundling methods have been used to reduce visual clutter in parallel coordinates plots (PCP). However, existing edge-bundled PCP do not scale well for visual analysis of multidimensional big data and often overplot the bundles in the area near the axes. In this study, we propose a scalable lightweight bundling method to support visual analysis of multidimensional big data in PCP. It helps the users discover trends and detect outliers in the data by bundling the edges between each two adjacent axes independently. We integrate human judgments into the two-dimensional data binning by novel interactions to accelerate the clustering process of the data. We use the frequency-based representation to render the clusters as histogram-like bundles to reveal the distribution of the data and eliminate the overplotting of the bundles. Based on our method, we build a lightweight web-based visual analytics system for exploring multidimensional big data in PCP. The scalability analysis of our method shows that its clustering time increases linearly with the size of the data. Its rendering time is independent of the size of the data. We conduct two case studies and a user study to compare our method with classic PCP and two state-of-the-art edge-bundled PCP.

Projection techniques are often used to visualize high-dimensional data, allowing users to better understand the overall structure of multi-dimensional spaces on a 2D screen. Although many such methods exist, comparably little work has been done on generalizable methods of inverse-projection -- the process of mapping the projected points, or more generally, the projection space back to the original high-dimensional space. In this paper we present NNInv, a deep learning technique with the ability to approximate the inverse of any projection or mapping. NNInv learns to reconstruct high-dimensional data from any arbitrary point on a 2D projection space, giving users the ability to interact with the learned high-dimensional representation in a visual analytics system. We provide an analysis of the parameter space of NNInv, and offer guidance in selecting these parameters. We extend validation of the effectiveness of NNInv through a series of quantitative and qualitative analyses. We then demonstrate the method's utility by applying it to three visualization tasks: interactive instance interpolation, classifier agreement, and gradient visualization.

The analysis of variance in complex text traditions is an arduous task when carried out manually. Text alignment algorithms provide domain experts with a robust alternative to such repetitive tasks. Existing white-box approaches allow the digital humanities to establish syntax-based metrics taking into account the spelling, morphology and order of words. However, they produce limited results, as semantic meanings are typically not taken into account. Our interdisciplinary collaboration between visualization and digital humanities combined a semi-supervised text alignment approach based on word embeddings that take not only syntactic but also semantic text features into account, thereby improving the overall quality of the alignment. In our collaboration, we developed different visual interfaces that communicate the word distribution in high-dimensional vector space generated by the underlying neural network for increased transparency, assessment of the tool's reliability and overall improved hypothesis generation. We further offer visual means to enable the expert reader to feed domain knowledge into the system at multiple levels with the aim of improving both the product and the process of text alignment. This ultimately illustrates how visualization can engage with and augment complex modes of reading in the humanities.

Extracting and analyzing crime patterns in big cities is a challenging spatiotemporal problem. The hardness of the problem is linked to two main factors, the sparse nature of the crime activity and its spread in large spatial areas. Sparseness hampers most time series (crime time series) comparison methods from working properly, while the handling of large urban areas tends to render the computational costs of such methods impractical. Visualizing different patterns hidden in crime time series data is another issue in this context, mainly due to the number of patterns that can show up in the time series analysis. In this article, we present a new methodology to deal with the issues above, enabling the analysis of spatiotemporal crime patterns in a street-level of detail. Our approach is made up of two main components designed to handle the spatial sparsity and spreading of crimes in large areas of the city. The first component relies on a stochastic mechanism from which one can visually analyze probable×intensive crime hotspots. Such analysis reveals important patterns that can not be observed in the typical intensity-based hotspot visualization. The second component builds upon a deep learning mechanism to embed crime time series in Cartesian space. From the embedding, one can identify spatial locations where the crime time series have similar behavior. The two components have been integrated into a web-based analytical tool called CriPAV (Crime Pattern Analysis and Visualization), which enables global as well as a street-level view of crime patterns. Developed in close collaboration with domain experts, CriPAV has been validated through a set of case studies with real crime data in São Paulo - Brazil. The provided experiments and case studies reveal the effectiveness of CriPAV in identifying patterns such as locations where crimes are not intense but highly probable to occur as well as locations that are far apart from each other but bear similar crime patterns.

Visually identifying effective bio-markers from human brain networks poses non-trivial challenges to the field of data visualization and analysis. Existing methods in the literature and neuroscience practice are generally limited to the study of individual connectivity features in the brain (e.g., the strength of neural connection among brain regions). Pairwise comparisons between contrasting subject groups (e.g., the diseased and the healthy controls) are normally performed. The underlying neuroimaging and brain network construction process is assumed to have 100% fidelity. Yet, real-world user requirements on brain network visual comparison lean against these assumptions. In this work, we present MV^2Net, a visual analytics system that tightly integrates multi-variate multi-view visualization for brain network comparison with an interactive wrangling mechanism to deal with data uncertainty. On the analysis side, the system integrates multiple extraction methods on diffusion and geometric connectivity features of brain networks, an anomaly detection algorithm for data quality assessment, single- and multi-connection feature selection methods for bio-marker detection. On the visualization side, novel designs are introduced which optimize network comparisons among contrasting subject groups and related connectivity features. Our design provides level-of-detail comparisons, from juxtaposed and explicit-coding views for subject group comparisons, to high-order composite view for correlation of network comparisons, and to fiber tract detail view for voxel-level comparisons. The proposed techniques are inspired and evaluated in expert studies, as well as through case analyses on diffusion and geometric bio-markers of certain neurology diseases. Results in these experiments demonstrate the effectiveness and superiority of MV^2Net over state-of-the-art approaches.

Deep reinforcement learning (DRL) targets to train an autonomous agent to interact with a pre-defined environment and strives to achieve specific goals through deep neural networks (DNN). Recurrent neural network (RNN) based DRL has demonstrated superior performance, as RNNs can effectively capture the temporal evolution of the environment and respond with proper agent actions. However, apart from the outstanding performance, little is known about how RNNs understand the environment internally and what has been memorized over time. Revealing these details is extremely important for deep learning experts to understand and improve DRLs, which in contrast, is also challenging due to the complicated data transformations inside these models. In this article, we propose Deep Reinforcement Learning Interactive Visual Explorer (DRLIVE), a visual analytics system to effectively explore, interpret, and diagnose RNN-based DRLs. Having focused on DRL agents trained for different Atari games, DRLIVE accomplishes three tasks: game episode exploration, RNN hidden/cell state examination, and interactive model perturbation. Using the system, one can flexibly explore a DRL agent through interactive visualizations, discover interpretable RNN cells by prioritizing RNN hidden/cell states with a set of metrics, and further diagnose the DRL model by interactively perturbing its inputs. Through concrete studies with multiple deep learning experts, we validated the efficacy of DRLIVE.

A major drawback of nonlinear dimensionality reduction (DR) techniques is their inability to preserve some authentic information from the source domain, leading to projections that are often hard to interpret when it comes to observing anything other than the topological structure of the data. In this paper, we propose a nonlinear DR approach enforcing projection constraints resulting from an a priori knowledge about the structure of the data in multivariate periodical time series. We then propose several ways of exploiting this constrained projection to extract user-relevant information, such as the nominal behavior of a periodical dynamical system or the deviant behaviors which may occur at different time scales. The techniques are demonstrated on both a synthetic dataset composed of simulated multivariate data exhibiting a periodical behavior, and a real dataset corresponding to six months of sensor data acquisitions and recordings inside experimental buildings. 1 We would like to thank the Institut National de l'Energie Solaire (INES) and the CEA, LITEN, Laboratoire Energetique du Bâtiment for providing the data.

Abstract The field of explainable artificial intelligence aims to help experts understand complex machine learning models. One key approach is to show the impact of a feature on the model prediction. This helps experts to verify and validate the predictions the model provides. However, many challenges remain open. For example, due to the subjective nature of interpretability, a strict definition of concepts such as the contribution of a feature remains elusive. Different techniques have varying underlying assumptions, which can cause inconsistent and conflicting views. In this work, we introduce local and global contribution-value plots as a novel approach to visualize feature impact on predictions and the relationship with feature value. We discuss design decisions and show an exemplary visual analytics implementation that provides new insights into the model. We conducted a user study and found the visualizations aid model interpretation by increasing correctness and confidence and reducing the time taken to obtain an insight. Graphic Abstract

Visual query of spatiotemporal data is becoming an increasingly important function in visual analytics applications. Various works have been presented for querying large spatiotemporal data in real time. However, the real-time query of spatiotemporal data distribution is still an open challenge. As spatiotemporal data become larger, methods of aggregation, storage and querying become critical. We propose a new visual query system that creates a low-memory storage component and provides real-time visual interactions of spatiotemporal data. We first present a peak-based kernel density estimation method to produce the data distribution for the spatiotemporal data. Then a novel density dictionary learning approach is proposed to compress temporal density maps and accelerate the query calculation. Moreover, various intuitive query interactions are presented to interactively gain patterns. The experimental results obtained on three datasets demonstrate that the presented system offers an effective query for visual analytics of spatiotemporal data.

The efficiency of warehouses is vital to e-commerce. Fast order processing at the warehouses ensures timely deliveries and improves customer satisfaction. However, monitoring, analyzing, and manipulating order processing in the warehouses in real time are challenging for traditional methods due to the sheer volume of incoming orders, the fuzzy definition of delayed order patterns, and the complex decision-making of order handling priorities. In this paper, we adopt a data-driven approach and propose OrderMonitor, a visual analytics system that assists warehouse managers in analyzing and improving order processing efficiency in real time based on streaming warehouse event data. Specifically, the order processing pipeline is visualized with a novel pipeline design based on the sedimentation metaphor to facilitate real-time order monitoring and suggest potentially abnormal orders. We also design a novel visualization that depicts order timelines based on the Gantt charts and Marey's graphs. Such a visualization helps the managers gain insights into the performance of order processing and find major blockers for delayed orders. Furthermore, an evaluating view is provided to assist users in inspecting order details and assigning priorities to improve the processing performance. The effectiveness of OrderMonitor is evaluated with two case studies on a real-world warehouse dataset.

A growing number of longitudinal cohort studies are generating data with extensive patient observations across multiple timepoints. Such data offers promising opportunities to better understand the progression of diseases. However, these observations are usually treated as general events in existing visual analysis tools. As a result, their capabilities in modeling disease progression are not fully utilized. To fill this gap, we designed and implemented ThreadStates, an interactive visual analytics tool for the exploration of longitudinal patient cohort data. The focus of ThreadStates is to identify the states of disease progression by learning from observation data in a human-in-the-loop manner. We propose a novel Glyph Matrix design and combine it with a scatter plot to enable seamless identification, observation, and refinement of states. The disease progression patterns are then revealed in terms of state transitions using Sankey-based visualizations. We employ sequence clustering techniques to find patient groups with distinctive progression patterns, and to reveal the association between disease progression and patient-level features. The design and development were driven by a requirement analysis and iteratively refined based on feedback from domain experts over the course of a 10-month design study. Case studies and expert interviews demonstrate that ThreadStates can successively summarize disease states, reveal disease progression, and compare patient groups.

Semantic segmentation is a critical component in autonomous driving and has to be thoroughly evaluated due to safety concerns. Deep neural network (DNN) based semantic segmentation models are widely used in autonomous driving. However, it is challenging to evaluate DNN-based models due to their black-box-like nature, and it is even more difficult to assess model performance for crucial objects, such as lost cargos and pedestrians, in autonomous driving applications. In this work, we propose VASS, a Visual Analytics approach to diagnosing and improving the accuracy and robustness of Semantic Segmentation models, especially for critical objects moving in various driving scenes. The key component of our approach is a context-aware spatial representation learning that extracts important spatial information of objects, such as position, size, and aspect ratio, with respect to given scene contexts. Based on this spatial representation, we first use it to create visual summarization to analyze models' performance. We then use it to guide the generation of adversarial examples to evaluate models' spatial robustness and obtain actionable insights. We demonstrate the effectiveness of VASS via two case studies of lost cargo detection and pedestrian detection in autonomous driving. For both cases, we show quantitative evaluation on the improvement of models' performance with actionable insights obtained from VASS.

The spatial time series generated by city sensors allow us to observe urban phenomena like environmental pollution and traffic congestion at an unprecedented scale. However, recovering causal relations from these observations to explain the sources of urban phenomena remains a challenging task because these causal relations tend to be time-varying and demand proper time series partitioning for effective analyses. The prior approaches extract one causal graph given long-time observations, which cannot be directly applied to capturing, interpreting, and validating dynamic urban causality. This paper presents Compass, a novel visual analytics approach for in-depth analyses of the dynamic causality in urban time series. To develop Compass, we identify and address three challenges: detecting urban causality, interpreting dynamic causal relations, and unveiling suspicious causal relations. First, multiple causal graphs over time among urban time series are obtained with a causal detection framework extended from the Granger causality test. Then, a dynamic causal graph visualization is designed to reveal the time-varying causal relations across these causal graphs and facilitate the exploration of the graphs along the time. Finally, a tailored multi-dimensional visualization is developed to support the identification of spurious causal relations, thereby improving the reliability of causal analyses. The effectiveness of Compass is evaluated with two case studies conducted on the real-world urban datasets, including the air pollution and traffic speed datasets, and positive feedback was received from domain experts.

Building a visual overview of temporal event sequences with an optimal level-of-detail (i.e. simplified but informative) is an ongoing challenge - expecting the user to zoom into every important aspect of the overview can lead to missing insights. We propose a technique to build a multilevel overview of event sequences, whose granularity can be transformed across sequence clusters (vertical level-of-detail) or longitudinally (horizontal level-of-detail), using hierarchical aggregation and a novel cluster data representation Align-Score-Simplify. By default, the overview shows an optimal number of sequence clusters obtained through the average silhouette width metric - then users are able to explore alternative optimal sequence clusterings. The vertical level-of-detail of the overview changes along with the number of clusters, whilst the horizontal level-of-detail refers to the level of summarization applied to each cluster representation. The proposed technique has been implemented into a visualization system called Sequence Cluster Explorer (Sequen-C) that allows multilevel and detail-on-demand exploration through three coordinated views, and the inspection of data attributes at cluster, unique sequence, and individual sequence level. We present two case studies using real-world datasets in the healthcare domain: CUREd and MIMIC-III; which demonstrate how the technique can aid users to obtain a summary of common and deviating pathways, and explore data attributes for selected patterns., Comment: This is the author's version of the article to be published in IEEE Transactions on Visualization and Computer Graphics

Modern virtual reality (VR) technology has garnered significant attention in the geographic visualization community for its ability to immerse users within geospatial data sets. While immersion within one-to-one models of reality offers unique and powerful perspectives from which to view spatial data, VR also allows users to transcend the physical limitations of the real world, thereby allowing them to visualize, experience, and interact with spatial data at any scale, in any virtual environment, at any time. This paper presents a collection of 3D data-driven geovisualization case studies, implemented in an immersive virtual GIScience data visualization space (IVEVA). IVEVA was purposefully designed and developed to highlight the differences in spatial data type, the challenges associated with spatial data visualization in an immersive virtual environment, and the importance of adhering to the established design heuristics of cartography, human–computer interaction, and extended reality (XR) development. Through this process, we offer our observations on how well each data type fits this medium of visualization and interpretation, and how the design heuristics play out for an immersive virtual environment that extends the practicable space in which GIScience and visual analytics are performed. Finally, we offer our perspectives, from designing and developing this prototype, on the future for immersive interface-based GIScience.

The availability of massive temporal multivariate data provides unprecedented opportunities to analyze anomaly pattern evolution. However, due to the complicated relationships and dynamic temporality, it is a challenging problem to efficiently reveal and perceive the evolution of abnormal patterns. Existing methods mostly focus on the use of automated algorithms to capture anomalies, which limits the understanding of the evolutionary law. In this paper, we propose a novel visual analytics system, PEVis, to help domain experts extract four types of abnormal evolution patterns and quantitatively analyze the contribution of different features to its occurrence. By aggregating different anomaly detection algorithms, the anomalous data that deviate seriously from other densely distributed points or with small isolated clusters can be identified. A strategy for perceiving temporal multivariate data is proposed to solve the conflict between exploring the global time-varying law and local data distribution in visualization, through aligning dimension reduction space of adjacent timestamp and designing a doughnut glyph to visually display data distribution and feature contributions. Experiments on two real-world datasets, namely air quality index data and consumer price index data, demonstrate that the proposed methods can effectively reveal the seasonal variation of abnormal phenomena.

Consumption of digital content through medium like mobile phones, television set and laptop has seen dramatic increase over recent years. Possible increase behind this rise of consumption is the availability of internet across different regions and drastic rise in availability of internet bandwidth at a nominal cost. Eventually preparation of digital content to cater various user entertainment taste profile has increased. Since there is an increase in consumption of the digital content, it opens new challenges on securing this content. Visual analytics of the digital content on periodic basis is in rise to keep a check on the security of the content. Broadcast logo availability as part of digital content is unique and tracking this logo is one of the methods to distinguish between original content and pirated content. In recent years there's significant increase in research work carried out on the problems associated with object detection and classification. This implies there is a significant increase in terms of recognition performance of objects of interest. In this paper, the discussion is on different TV broadcast channel logo dataset creation, enhancing this dataset using different data augmentation techniques to extend the logo corpus. Proposed system includes TV broadcast/broadband content logo detection and classification pipeline that demonstrate the application of state-of-the-art object detection algorithm Single shot detector (SSD) for logo detection and classification on TV broadcast channel logo dataset which has undergone significant makeover for representing different logo conditions. Experimental result shows the pipeline potential to robustly recognize the logos under makeover in the context of content piracy

Machine learning (ML) models are nowadays used in complex applications in various domains, such as medicine, bioinformatics, and other sciences. Due to their black box nature, however, it may sometimes be hard to understand and trust the results they provide. This has increased the demand for reliable visualization tools related to enhancing trust in ML models, which has become a prominent topic of research in the visualization community over the past decades. To provide an overview and present the frontiers of current research on the topic, we present a State-of-the-Art Report (STAR) on enhancing trust in ML models with the use of interactive visualization. We define and describe the background of the topic, introduce a categorization for visualization techniques that aim to accomplish this goal, and discuss insights and opportunities for future research directions. Among our contributions is a categorization of trust against different facets of interactive ML, expanded and improved from previous research. Our results are investigated from different analytical perspectives: (a) providing a statistical overview, (b) summarizing key findings, (c) performing topic analyses, and (d) exploring the data sets used in the individual papers, all with the support of an interactive web-based survey browser. We intend this survey to be beneficial for visualization researchers whose interests involve making ML models more trustworthy, as well as researchers and practitioners from other disciplines in their search for effective visualization techniques suitable for solving their tasks with confidence and conveying meaning to their data.

Visual Analytics is very effective in many applications especially in education field and improved the decision making on enhancing the student assessment. Student assessment has become very important and is identified as a systematic process that measures and collects data such as marks and scores in a manner that enables the educator to analyze the achievement of the intended learning outcomes. The objective of this study is to investigate the suitable visual analytics design to represent the student assessment data with the suitable interaction techniques of the visual analytics approach. sheet. There are six types of analytical models, such as the Generalized Linear Model, Deep Learning, Decision Tree Model, Random Forest Model, Gradient Boosted Model, and Support Vector Machine were used to conduct this research. Our experimental results show that the Decision Tree Models were the fastest way to optimize the result. The Gradient Boosted Model was the best performance to optimize the result.

Recent advances in computational and algorithmic power are evolving the field of medical imaging rapidly. In cancer research, many new directions are sought to characterize patients with additional imaging features derived from radiology and pathology images. The emerging field of Computational Pathology targets the high-throughput extraction and analysis of the spatial distribution of cells from digital histopathology images. The associated morphological and architectural features allow researchers to quantify and characterize new imaging biomarkers for cancer diagnosis, prognosis, and treatment decisions. However, while the image feature space grows, exploration and analysis become more difficult and ineffective. There is a need for dedicated interfaces for interactive data manipulation and visual analysis of computational pathology and clinical data. For this purpose, we present IIComPath , a visual analytics approach that enables clinical researchers to formulate hypotheses and create computational pathology pipelines involving cohort construction, spatial analysis of image-derived features, and cohort analysis. We demonstrate our approach through use cases that investigate the prognostic value of current diagnostic features and new computational pathology biomarkers.

The number of songs are increasing at a very high rate around the globe. Out of the songs released every year, only the top few songs make it to the billboard hit charts .The lyrics of the songs place an important role in making them big hits combined with various other factors like loudness, liveness, speech ness, pop, etc. The artists are faced with the problem of finding the most desired topics to create song lyrics on. This problem is further amplified in selecting the most unique, catchy words which if added, could create more powerful lyrics for the songs. We propose a solution of finding the bag of unique evergreen words using the term frequency-inverse document frequency (TF-IDF) technique of natural language processing. The words from this bag of unique evergreen words could be added in the lyrics of the songs to create more powerful lyrics in the future.

The number, size and complexity of ‘big science’ projects are growing — as are the size, complexity and value of the data sets and software services they produce. In this context, big data gives a new way to analyse, understand, manage and communicate the inner workings of collaborations that often involve thousands of experts, thousands of scholarly publications, hundreds of new instruments and petabytes of data. We compare the evolving geospatial and topical impact of big science projects in physics, astronomy and biomedical sciences. A total of 13,893 publications and 1,139 grants by 21,945 authors cited more than 333,722 times are analysed and visualized to help characterize the distinct phases of big science projects, document increasing internationalization and densification of collaboration networks, and reveal the increase in interdisciplinary impact over time. All data sets and visual analytics workflows are freely available on GitHub in support of future big science studies. This Perspective describes how visualizations help to understand several key aspects of big science projects: productivity and impact over different phases, evolution of teams and their management, big data and cyberinfrastructure, and measuring and communicating success.

The adoption of artificial intelligence (AI) systems in environments that involve high risk and high consequence decision-making is severely hampered by critical design issues. These issues include system transparency and brittleness, where transparency relates to (i) the explainability of results and (ii) the ability of a user to inspect and verify system goals and constraints; and brittleness, (iii) the ability of a system to adapt to new user demands. Transparency is a particular concern for criminal intelligence analysis, where there are significant ethical and trust issues that arise when algorithmic and system processes are not adequately understood by a user. This prevents adoption of potentially useful technologies in policing environments. In this article, we present a novel approach to designing a conversational agent (CA) AI system for intelligence analysis that tackles these issues. We discuss the results and implications of three different studies; a Cognitive Task Analysis to understand analyst thinking when retrieving information in an investigation, Emergent Themes Analysis to understand the explanation needs of different system components, and an interactive experiment with a prototype conversational agent. Our prototype conversational agent, named Pan, demonstrates transparency provision and mitigates brittleness by evolving new CA intentions. We encode interactions with the CA with human factors principles for situation recognition and use interactive visual analytics to support analyst reasoning. Our approach enables complex AI systems, such as Pan, to be used in sensitive environments, and our research has broader application than the use case discussed.

The increased usage of the environmental monitoring system and sensors, installed on a day-to-day basis to explore information and monitor the cities’ environment and pollution conditions, are in demand. Sensor networking advancement with quality and quantity of environmental data has given rise to increasing techniques and methodologies supporting spatiotemporal data interactive visualisation analyses. Moreover, Visualisation (Vis) and Visual Analytics (VA) of spatiotemporal data have become essential for research, policymakers, and industries to improve energy efficiency, environmental management, and cities’ air pollution planning. A platform covering Vis and VA of spatiotemporal data collected from a city helps to portray such techniques’ potential in exploring crucial environmental inside, which is still required. Therefore, this work presents Vis and VA interface for the spatiotemporal data represented in terms of location, including time, and several measured attributes like Particular Matter (PM) PM2.5 and PM10, along with humidity, and wind (speed and direction) to assess the detailed temporal patterns of these parameters in Stuttgart, Germany. The time series are analysed using the unsupervised HDBSCAN clustering on a series of (above mentioned) parameters. Furthermore, with the in-depth sensors nature understanding and trends, Machine Learning (ML) approach called Transformers Network predictor model is integrated, that takes successive time values of parameters as input with sensors’ locations and predict the future dominant (highly measured) values with location in time as the output. The selected parameters variations are compared and analysed in the spatiotemporal frame to provide detailed estimations on how average conditions would change in a region over the time. This work would help to get a better insight into the urban system and enable the sustainable development of cities by improving human interaction with the spatiotemporal data. Hence, the increasing environmental problems for big industrial cities could be alarmed and reduced for the future with proposed work.

Geographical areal data usually presents hierarchical structures, and its characteristics vary at different scales. At the higher scales, the visualization of geographical areal data is abstract and the detailed features are easily missed. As a difference, more detailed information is presented at the lower scales while the visual perception of global features is easily disturbed due to the overdrawing of visual elements. As the geographical areal data is visualized at a single scale at the same time, it seems impossible to balance the visual perception of both the global features and detailed characteristics. In this paper, we propose a multi-scale geographical areal data visualization method based on spatial attribute association to enhance the visual perception of both the global features and detailed characteristics. Firstly, the geographical areal data is aggregated into hierarchical clusters based on the spatial similarity. Then, the coefficient of variation is applied to estimate the attribute distribution of each cluster in the hierarchy, and a novel geographical areal data visualization scheme is proposed to adaptively present the multi-scale clusters with lower variation coefficients at the same time. In addition, a rich set of visual interfaces and user-friendly interactions are provided enabling users to specify those clusters of interest at different scales and compare multi-scale visualizations with different hierarchies. Finally, we implement a geographical areal data visualization framework, allowing users to visually explore the global features and detailed characteristics at the same time and get deeper insights into the potential features in the geographical areal data. Case studies and quantitative comparisons based on real-world datasets have been conducted to demonstrate the effectiveness of the proposed multi-scale visualization method for in-depth visual exploration of geographical areal data.

Human Bio-Behavioral Rhythms (HBRs) such as sleep-wake cycles (Circadian Rhythms), and the degree of regularity of sleep and physical activity have important health ramifications. Ubiquitous devices such as smartphones can sense HBRs by continuously analyzing data gathered passively by built-in sensors to discover important clues about the degree of regularity and disruptions in behavioral patterns. As human behavior is complex and smartphone data is voluminous with many channels (sensor types), it can be challenging to make meaningful observations, detect unhealthy HBR deviations and most importantly pin-point the causes of disruptions. Prior work has largely utilized computational methods such as machine and deep learning approaches, which while accurate, are often not explainable and present few actionable insights on HBR patterns or causes. To assist analysts in the discovery and understanding of HBR patterns, disruptions and causes, we propose ARGUS, an interactive visual analytics framework. As a foundation of ARGUS, we design an intuitive Rhythm Deviation Score (RDS) that analyzes users’ smartphone sensor data, extracts underlying twenty-four-hour rhythms and quantifies their degree of irregularity.​ This score is then visualized using a glyph that makes it easy to recognize disruptions in the regularity of HBRs. ARGUS also facilitates deeper HBR insights and understanding of causes by linking multiple visualization panes that are overlaid with objective sensor information such as geo-locations and phone state (screen locked, charging), and user-provided or smartphone-inferred ground truth information. This array of visualization overlays in ARGUS enables​ analysts to gain a more comprehensive picture of HBRs, behavioral patterns and deviations from regularity. The design of ARGUS was guided by a goal and task analysis study involving an expert versed in HBR and smartphone sensing. To demonstrate its utility and generalizability, two different datasets were explored using ARGUS and our use cases and designs were strongly validated in evaluation sessions with expert and non-expert users.

Understanding the relationship between urban areas is essential to the extraction of human mobility patterns. Most popular algorithms use word embedding technology to vectorize urban areas to calculate the similarity between them. However, noise generated by the traffic hub area is often ignored, such as crossroads and road toll stations, which affect the training time of the model and the accuracy of vectorization. In this paper, we propose a vectorized representation method of urban geographic areas based on the distribution of trajectories, combining with the filtering of traffic hub areas based on the law of similarity to eliminate their noise. A novel visual analytics system is designed, which enables experts to analyse the relationship between urban areas and explore human mobility patterns based on this vectorized representation method. Finally, we analyse the relevance to long-distance areas and campus crowd mobility patterns on real datasets, which proves the effectiveness of our method.

Due to the limitations of existing experimental methods for capturing stereochemical molecular data, there usually is an inherent level of uncertainty present in models describing the conformation of macromolecules. This uncertainty can originate from various sources and can have a significant effect on algorithms and decisions based upon such models. Incorporating uncertainty in state-of-the-art visualization approaches for molecular data is an important issue to ensure that scientists analyzing the data are aware of the inherent uncertainty present in the representation of the molecular data. In this work, we introduce a framework that allows biochemists to explore molecular data in a familiar environment while including uncertainty information within the visualizations. Our framework is based on an anisotropic description of proteins that can be propagated along with required computations, providing multiple views that extend prominent visualization approaches to visually encode uncertainty of atom positions, allowing interactive exploration. We show the effectiveness of our approach by applying it to multiple real-world datasets and gathering user feedback.

Visual representation of a many-objective Pareto-optimal front in a high-dimensional (four or more) objective space requires a large number of data points. Choosing a single point from a large number of data points even with preference information is problematic, as it causes a large cognitive burden on the part of the decision-makers. Therefore, many-objective optimization and analytics practitioners have been interested in practical visualization methods that enable them to filter down a large set of data points to a few critical points for further analysis. Most existing visualization methods are borrowed from other data analytics domain and they are too generic to be effective for many-criteria decision making. In this paper, we propose a visualization method, following an earlier concept, using star-coordinate plots for effectively visualizing many-objective trade-off solutions (data points). We demonstrate the use of the proposed method to a couple of high-dimensional test problems and a 4-objective portfolio optimization problem. We also show a case of interactive exploratory data analytics where we use the ‘Pareto Race’ technique from the multi-criteria decision analysis (MCDA) literature to demonstrate the ease and advantage of the proposed visualization method.

It is a time-consuming and laborious task to conduct accurate geological interpretation based on large-scale logging data. A subset of drilling wells are always selected undergoing detailed stratigraphic correlation, aiming to enhance the efficiency of geological interpretation and retain the matching accuracy of stratigraphic structures. However, standard wells are selected by hand in the course of traditional standard well selection, which will easily bring many uncertainties for subsequent interpretation of geological structures. In this paper, we propose a visual analytics system to support supervised standard well selection via a discrete choice model. Firstly, an adaptive blue noise sampling model is applied to determine spatial distribution of standard wells, and a stratigraphic correlation model is designed to measure the similarity between drilling wells from different attribute perspectives. Then, we utilize a discrete choice model to select standard wells with the spatial distribution and multiple attributes taken into consideration. Furthermore, several meaningful visualizations are designed allowing users to get deeper insights into the selection of standard wells, and a rich set of interactions are also provided enabling users to further optimize the discrete choice model. At last, a visualization framework is implemented to integrate the models and visual designs, by means of which the geological interpreters are able to visually select, evaluate and optimize the standard wells. The effectiveness of our work and its application values for geological interpretation are further demonstrated through case studies based on real-world datasets and interviews with domain experts.

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. published

Motivation Astrocytes, the most abundant glial cells in the mammalian brain, have an instrumental role in developing neuronal circuits. They contribute to the physical structuring of the brain, modulating synaptic activity and maintaining the blood–brain barrier in addition to other significant aspects that impact brain function. Biophysically, detailed astrocytic models are key to unraveling their functional mechanisms via molecular simulations at microscopic scales. Detailed, and complete, biological reconstructions of astrocytic cells are sparse. Nonetheless, data-driven digital reconstruction of astroglial morphologies that are statistically identical to biological counterparts are becoming available. We use those synthetic morphologies to generate astrocytic meshes with realistic geometries, making it possible to perform these simulations. Results We present an unconditionally robust method capable of reconstructing high fidelity polygonal meshes of astroglial cells from algorithmically-synthesized morphologies. Our method uses implicit surfaces, or metaballs, to skin the different structural components of astrocytes and then blend them in a seamless fashion. We also provide an end-to-end pipeline to produce optimized two- and three-dimensional meshes for visual analytics and simulations, respectively. The performance of our pipeline has been assessed with a group of 5000 astroglial morphologies and the geometric metrics of the resulting meshes are evaluated. The usability of the meshes is then demonstrated with different use cases. Availability and implementation Our metaball skinning algorithm is implemented in Blender 2.82 relying on its Python API (Application Programming Interface). To make it accessible to computational biologists and neuroscientists, the implementation has been integrated into NeuroMorphoVis, an open source and domain specific package that is primarily designed for neuronal morphology visualization and meshing. Supplementary information Supplementary data are available at Bioinformatics online.

With the rapid development of mobile Internet, the popularity of video capture devices has brought a surge in multimedia video resources. Utilizing machine learning methods combined with well-designed features, we could automatically obtain video summarization to relax video resource consumption and retrieval issues. However, there always exists a gap between the summarization obtained by the model and the ones annotated by users. How to help users understand the difference, provide insights in improving the model, and enhance the trust in the model remains challenging in the current study. To address these challenges, we propose VSumVis under a user-centered design methodology, a visual analysis system with multi-feature examination and multi-level exploration, which could help users explore and analyze video content, as well as the intrinsic relationship that existed in our video summarization model. The system contains multiple coordinated views, i.e., video view, projection view, detail view, and sequential frames view. A multi-level analysis process to integrate video events and frames are presented with clusters and nodes visualization in our system. Temporal patterns concerning the difference between the manual annotation score and the saliency score produced by our model are further investigated and distinguished with sequential frames view. Moreover, we propose a set of rich user interactions that enable an in-depth, multi-faceted analysis of the features in our video summarization model. We conduct case studies and interviews with domain experts to provide anecdotal evidence about the effectiveness of our approach. Quantitative feedback from a user study confirms the usefulness of our visual system for exploring the video summarization model.

Clustering is an important task in knowledge discovery with the goal to identify structures of similar data points in a dataset. Here, the focus lies on methods that use a human-in-the-loop, i.e., incorporate user decisions into the clustering process through 2D and 3D displays of the structures in the data. Some of these interactive approaches fall into the category of visual analytics and emphasize the power of such displays to identify the structures interactively in various types of datasets or to verify the results of clustering algorithms. This work presents a new method called interactive projection-based clustering (IPBC). IPBC is an open-source and parameter-free method using a human-in-the-loop for an interactive 2.5D display and identification of structures in data based on the user’s choice of a dimensionality reduction method. The IPBC approach is systematically compared with accessible visual analytics methods for the display and identification of cluster structures using twelve clustering benchmark datasets and one additional natural dataset. Qualitative comparison of 2D, 2.5D and 3D displays of structures and empirical evaluation of the identified cluster structures show that IPBC outperforms comparable methods. Additionally, IPBC assists in identifying structures previously unknown to domain experts in an application.

Multi-dimensional data exploration is a classic research topic in visualization. Most existing approaches are designed for identifying record patterns in dimensional space or subspace. In this paper, we propose a visual analytics approach to exploring subset patterns. The core of the approach is a subset embedding network (SEN) that represents a group of subsets as uniformly-formatted embeddings. We implement the SEN as multiple subnets with separate loss functions. The design enables to handle arbitrary subsets and capture the similarity of subsets on single features, thus achieving accurate pattern exploration, which in most cases is searching for subsets having similar values on few features. Moreover, each subnet is a fully-connected neural network with one hidden layer. The simple structure brings high training efficiency. We integrate the SEN into a visualization system that achieves a 3-step workflow. Specifically, analysts (1) partition the given dataset into subsets, (2) select portions in a projected latent space created using the SEN, and (3) determine the existence of patterns within selected subsets. Generally, the system combines visualizations, interactions, automatic methods, and quantitative measures to balance the exploration flexibility and operation efficiency, and improve the interpretability and faithfulness of the identified patterns. Case studies and quantitative experiments on multiple open datasets demonstrate the general applicability and effectiveness of our approach.

With the rapid development of sensing technologies, massive spatiotemporal data have been acquired from the urban space with respect to different domains, such as transportation and environment. Numerous co-occurrence patterns (e.g., traffic speed foggy , and air quality = unhealthy ) between the transportation data and other types of data can be obtained with given spatiotemporal constraints (e.g., within 3 kilometers and lasting for 2 hours) from these heterogeneous data sources. Such patterns present valuable implications for many urban applications, such as traffic management, pollution diagnosis, and transportation planning. However, extracting and understanding these patterns is beyond manual capability because of the scale, diversity, and heterogeneity of the data. To address this issue, a novel visual analytics system called CorVizor is proposed to identify and interpret these co-occurrence patterns. CorVizor comprises two major components. The first component is a co-occurrence mining framework involving three steps, namely, spatiotemporal indexing, co-occurring instance generation, and pattern mining. The second component is a visualization technique called CorView that implements a level-of-detail mechanism by integrating tailored visualizations to depict the extracted spatiotemporal co-occurrence patterns. The case studies and expert interviews are conducted to demonstrate the effectiveness of CorVizor.

Among the challenges of the big data era, the analysis of high-dimensional data is still an open research area. As a result, several multidimensional projection techniques have been developed to reduce data dimensionality, becoming important visualization and visual analytics tools. In order to ensure the quality of projections, it is necessary to assess the low-dimensional embeddings by using different dataset configurations as input and analyzing evaluation metrics. However, it is not clear to the user how factors such as the number of dimensions, instances, or clusters, can affect the projection mapping and its quality regarding different projection techniques and assessment metrics. The research reported in this paper aims to clarify how much these factors affect each response variable via performance evaluation planning. We present an evaluation approach, supported by factorial design, that carries out a complete analysis, in the sense of measuring all possible combinations of all the input factors. The results of the analyses of local and global structure preservation in the projections yield a better understanding of how distinct dataset properties can influence the choice of projections based on quality metrics results.

Decision makers often find themselves in situations where they need to consider time-varying values for multi-criteria decision-making. Skyline queries are one of the most widely used methods of approaching multi-criteria decision-making problems because they reduce the size of search space by excluding inferior data. However, skylines in time-series data fluctuate with changes in attributes. Moreover, the number of skyline points increases as the number of dimensions increases, and the skyline query itself does not provide any ranking method. Thus, users are required to direct a considerable amount of effort into analyzing and finding the best selection. To address these issues, we propose SkyFlow, a visual analytical system for comparing time-varying data to facilitate the decision-making process. We apply two datasets in our system and describe scenarios to demonstrate the effectiveness of SkyFlow. In addition, we conduct a qualitative study to highlight the efficiency of our system in assisting users to compare candidates and make decisions involving time-series data.

Spatiotemporal data mining (STDM) discovers useful patterns from the dynamic interplay between space and time. Several available surveys capture STDM advances and report a wealth of important progress in this field. However, STDM challenges and problems are not thoroughly discussed and presented in articles of their own. We attempt to fill this gap by providing a comprehensive literature survey on state-of-the-art advances in STDM. We describe the challenging issues and their causes and open gaps of multiple STDM directions and aspects. Specifically, we investigate the challenging issues in regards to spatiotemporal relationships, interdisciplinarity, discretisation, and data characteristics. Moreover, we discuss the limitations in the literature and open research problems related to spatiotemporal data representations, modelling and visualisation, and comprehensiveness of approaches. We explain issues related to STDM tasks of classification, clustering, hotspot detection, association and pattern mining, outlier detection, visualisation, visual analytics, and computer vision tasks. We also highlight STDM issues related to multiple applications including crime and public safety, traffic and transportation, earth and environment monitoring, epidemiology, social media, and Internet of Things., Comment: Accepted for publication at Artificial Intelligence Review

A new vision of harnessing the ocean of video data captured by cameras in an efficient, secure, and manageable way. Following the hardware trends in reality, we advocate to treat cameras as the first-class computing and storage platform, and expose their services to third parties. To this end, the cameras should move from hard-coded to software-defined, from dumb data source to autonomous data processor, from isolated to orchestrated, and from one-shot to human-in-the-loop.

The quest for greater insights into algorithm strengths and weaknesses, as revealed when studying algorithm performance on large collections of test problems, is supported by interactive visual analytics tools. A recent advance is Instance Space Analysis, which presents a visualization of the space occupied by the test datasets, and the performance of algorithms across the instance space. The strengths and weaknesses of algorithms can be visually assessed, and the adequacy of the test datasets can be scrutinized through visual analytics. This article presents the first Instance Space Analysis of regression problems in Machine Learning, considering the performance of 14 popular algorithms on 4,855 test datasets from a variety of sources. The two-dimensional instance space is defined by measurable characteristics of regression problems, selected from over 26 candidate features. It enables the similarities and differences between test instances to be visualized, along with the predictive performance of regression algorithms across the entire instance space. The purpose of creating this framework for visual analysis of an instance space is twofold: one may assess the capability and suitability of various regression techniques; meanwhile the bias, diversity, and level of difficulty of the regression problems popularly used by the community can be visually revealed. This article shows the applicability of the created regression instance space to provide insights into the strengths and weaknesses of regression algorithms, and the opportunities to diversify the benchmark test instances to support greater insights.

Modern soccer increasingly places trust in visual analysis and statistics rather than only relying on the human experience. However, soccer is an extraordinarily complex game that no widely accepted quantitative analysis methods exist. The statistics collection and visualization are time consuming which result in numerous adjustments. To tackle this issue, we developed GreenSea, a visual-based assessment system designed for soccer game analysis, tactics, and training. The system uses a broad learning system (BLS) to train the model in order to avoid the time-consuming issue that traditional deep learning may suffer. Users are able to apply multiple views of a soccer game, and visual summarization of essential statistics using advanced visualization and animation that are available. A marking system trained by BLS is designed to perform quantitative analysis. A novel recurrent discriminative BLS (RDBLS) is proposed to carry out long-term tracking. In our RDBLS, the structure is adjusted to have better performance on the binary classification problem of the discriminative model. Several experiments are carried out to verify that our proposed RDBLS model can outperform the standard BLS and other methods. Two studies were conducted to verify the effectiveness of our GreenSea. The first study was on how GreenSea assists a youth training coach to assess each trainee's performance for selecting most potential players. The second study was on how GreenSea was used to help the U20 Shanghai soccer team coaching staff analyze games and make tactics during the 13th National Games. Our studies have shown the usability of GreenSea and the values of our system to both amateur and expert users.

Machine learning is a powerful and effective tool for medical image analysis to perform computer-aided diagnosis (CAD). Having great potential in improving the accuracy of a diagnosis, CAD systems are often analyzed in terms of the final accuracy, leading to a limited understanding of the internal decision process, impossibility to gain insights, and ultimately to skepticism from clinicians. We present a visual analytics approach to uncover the decision-making process of a CAD system for classifying pancreatic cystic lesions. This CAD algorithm consists of two distinct components: random forest (RF), which classifies a set of predefined features, including demographic features, and a convolutional neural network (CNN), which analyzes radiological (imaging) features of the lesions. We study the class probabilities generated by the RF and the semantical meaning of the features learned by the CNN. We also use an eye tracker to better understand which radiological features are particularly useful for a radiologist to make a diagnosis and to quantitatively compare with the features that lead the CNN to its final classification decision. Additionally, we evaluate the effects and benefits of supplying the CAD system with a case-based visual aid in a second-reader setting.

Understanding the mental representations used for hazard recognition would help the development of inspection strategies for effective safety management. This study is part of ongoing research to identify hazard recognition patterns based on users’ mental representations. Hence, this study explored normative visual patterns for improving hazard recognition performance using a crisp-set qualitative comparative analysis (cs-QCA). Eye-tracking data and visual trajectories were collected using an eye-tracking device in a structural laboratory. A cs-QCA approach was adopted to analyze and summarize normative visual patterns that were used to successfully detect hazards by all participants, namely, potential electrical contact, a large machine with no guardrails, and steel bars dump. The results show that object identification should suffice as the basis for identifying electricity-related hazards, while struck-by hazards should focus on the objects and their pivot points or potential movement trajectories. The experimental design and analytical approach provide new insights into visual analytics in hazard recognition. The research extends and supplements recognition by component theory in the context of construction hazard recognition. The results also provide new and practical references for hazard inspection training, as well as for future development of automated hazard recognition systems.

For various reasons, such as new requirements, architecture refactoring, and bug fixing, software projects often evolve to yield better quality and performance. All changes produced during the development process are reflected in the source code, which provides an opportunity to explore software evolution. In this paper, we propose a visual analytics system to support evolution analysis based on topic modeling. We focus on three aspects: (1) when significant changes to source code occur, (2) how software features evolve, and (3) why software evolution occurs. Each source file is regarded as a document and represented by its topic vector. The files of each two successive versions are classified into four types to quantify version differences, and the number of topic-associated files is denoted as the topic assignment to characterize feature evolution. Finally, we inspect the causes of software evolution through the visual comparison between versions. Two case studies on JavaScript libraries demonstrate the usefulness and effectiveness of our system.

Deep learning methods are being increasingly used for urban traffic prediction where spatiotemporal traffic data is aggregated into sequentially organized matrices that are then fed into convolution-based residual neural networks. However, the widely known modifiable areal unit problem within such aggregation processes can lead to perturbations in the network inputs. This issue can significantly destabilize the feature embeddings and the predictions - rendering deep networks much less useful for the experts. This paper approaches this challenge by leveraging unit visualization techniques that enable the investigation of many-to-many relationships between dynamically varied multi-scalar aggregations of urban traffic data and neural network predictions. Through regular exchanges with a domain expert, we design and develop a visual analytics solution that integrates 1) a Bivariate Map equipped with an advanced bivariate colormap to simultaneously depict input traffic and prediction errors across space, 2) a Moran's I Scatterplot that provides local indicators of spatial association analysis, and 3) a Multi-scale Attribution View that arranges non-linear dot plots in a tree layout to promote model analysis and comparison across scales. We evaluate our approach through a series of case studies involving a real-world dataset of Shenzhen taxi trips, and through interviews with domain experts. We observe that geographical scale variations have important impact on prediction performances, and interactive visual exploration of dynamically varying inputs and outputs benefit experts in the development of deep traffic prediction models.

We present a comprehensive framework for evaluating line chart smoothing methods under a variety of visual analytics tasks. Line charts are commonly used to visualize a series of data samples. When the number of samples is large, or the data are noisy, smoothing can be applied to make the signal more apparent. However, there are a wide variety of smoothing techniques available, and the effectiveness of each depends upon both nature of the data and the visual analytics task at hand. To date, the visualization community lacks a summary work for analyzing and classifying the various smoothing methods available. In this paper, we establish a framework, based on 8 measures of the line smoothing effectiveness tied to 8 low-level visual analytics tasks. We then analyze 12 methods coming from 4 commonly used classes of line chart smoothing-rank filters, convolutional filters, frequency domain filters, and subsampling. The results show that while no method is ideal for all situations, certain methods, such as G aussian filters and TOPOLOGY-based subsampling, perform well in general. Other methods, such as low-pass CUTOFF filters and D ouglas-peucker subsampling, perform well for specific visual analytics tasks. Almost as importantly, our framework demonstrates that several methods, including the commonly used UNIFORM subsampling, produce low-quality results, and should, therefore, be avoided, if possible.

An important approach for scientific inquiry across many disciplines involves using observational time series data to understand the relationships between key variables to gain mechanistic insights into the underlying rules that govern the given system. In real systems, such as those found in ecology, the relationships between time series variables are generally not static; instead, these relationships are dynamical and change in a nonlinear or state-dependent manner. To further understand such systems, we investigate integrating methods that appropriately characterize these dynamics (i.e., methods that measure interactions as they change with time-varying system states) with visualization techniques that can help analyze the behavior of the system. Here, we focus on empirical dynamic modeling (EDM) as a state-of-the-art method that specifically identifies causal variables and measures changing state-dependent relationships between time series variables. Instead of using approaches centered on parametric equations, EDM is an equation-free approach that studies systems based on their dynamic attractors. We propose a visual analytics system to support the identification and mechanistic interpretation of system states using an EDM-constructed dynamic graph. This work, as detailed in four analysis tasks and demonstrated with a GUI, provides a novel synthesis of EDM and visualization techniques such as brush-link visualization and visual summarization to interpret dynamic graphs representing ecosystem dynamics. We applied our proposed system to ecological simulation data and real data from a marine mesocosm study as two key use cases. Our case studies show that our visual analytics tools support the identification and interpretation of the system state by the user, and enable us to discover both confirmatory and new findings in ecosystem dynamics. Overall, we demonstrated that our system can facilitate an understanding of how systems function beyond the intuitive analysis of high-dimensional information based on specific domain knowledge.

Traffic light detection is crucial for environment perception and decision-making in autonomous driving. State-of-the-art detectors are built upon deep Convolutional Neural Networks (CNNs) and have exhibited promising performance. However, one looming concern with CNN based detectors is how to thoroughly evaluate the performance of accuracy and robustness before they can be deployed to autonomous vehicles. In this work, we propose a visual analytics system, VATLD , equipped with a disentangled representation learning and semantic adversarial learning, to assess, understand, and improve the accuracy and robustness of traffic light detectors in autonomous driving applications. The disentangled representation learning extracts data semantics to augment human cognition with human-friendly visual summarization, and the semantic adversarial learning efficiently exposes interpretable robustness risks and enables minimal human interaction for actionable insights. We also demonstrate the effectiveness of various performance improvement strategies derived from actionable insights with our visual analytics system, VATLD , and illustrate some practical implications for safety-critical applications in autonomous driving.