RESUMEN
With the increasing use of black-box Machine Learning (ML) techniques in critical applications, there is a growing demand for methods that can provide transparency and accountability for model predictions. As a result, a large number of local explainability methods for black-box models have been developed and popularized. However, machine learning explanations are still hard to evaluate and compare due to the high dimensionality, heterogeneous representations, varying scales, and stochastic nature of some of these methods. Topological Data Analysis (TDA) can be an effective method in this domain since it can be used to transform attributions into uniform graph representations, providing a common ground for comparison across different explanation methods. We present a novel topology-driven visual analytics tool, Mountaineer, that allows ML practitioners to interactively analyze and compare these representations by linking the topological graphs back to the original data distribution, model predictions, and feature attributions. Mountaineer facilitates rapid and iterative exploration of ML explanations, enabling experts to gain deeper insights into the explanation techniques, understand the underlying data distributions, and thus reach well-founded conclusions about model behavior. Furthermore, we demonstrate the utility of Mountaineer through two case studies using real-world data. In the first, we show how Mountaineer enabled us to compare black-box ML explanations and discern regions of and causes of disagreements between different explanations. In the second, we demonstrate how the tool can be used to compare and understand ML models themselves. Finally, we conducted interviews with three industry experts to help us evaluate our work.
RESUMEN
To reduce the number of pending cases and conflicting rulings in the Brazilian Judiciary, the National Congress amended the Constitution, allowing the Brazilian Supreme Court (STF) to create binding precedents (BPs), i.e., a set of understandings that both Executive and lower Judiciary branches must follow. The STF's justices frequently cite the 58 existing BPs in their decisions, and it is of primary relevance that judicial experts could identify and analyze such citations. To assist in this problem, we propose LegalVis, a web-based visual analytics system designed to support the analysis of legal documents that cite or could potentially cite a BP. We model the problem of identifying potential citations (i.e., non-explicit) as a classification problem. However, a simple score is not enough to explain the results; that is why we use an interpretability machine learning method to explain the reason behind each identified citation. For a compelling visual exploration of documents and BPs, LegalVis comprises three interactive visual components: the first presents an overview of the data showing temporal patterns, the second allows filtering and grouping relevant documents by topic, and the last one shows a document's text aiming to interpret the model's output by pointing out which paragraphs are likely to mention the BP, even if not explicitly specified. We evaluated our identification model and obtained an accuracy of 96%; we also made a quantitative and qualitative analysis of the results. The usefulness and effectiveness of LegalVis were evaluated through two usage scenarios and feedback from six domain experts.
RESUMEN
Analyzing classification model performance is a crucial task for machine learning practitioners. While practitioners often use count-based metrics derived from confusion matrices, like accuracy, many applications, such as weather prediction, sports betting, or patient risk prediction, rely on a classifier's predicted probabilities rather than predicted labels. In these instances, practitioners are concerned with producing a calibrated model, that is, one which outputs probabilities that reflect those of the true distribution. Model calibration is often analyzed visually, through static reliability diagrams, however, the traditional calibration visualization may suffer from a variety of drawbacks due to the strong aggregations it necessitates. Furthermore, count-based approaches are unable to sufficiently analyze model calibration. We present Calibrate, an interactive reliability diagram that addresses the aforementioned issues. Calibrate constructs a reliability diagram that is resistant to drawbacks in traditional approaches, and allows for interactive subgroup analysis and instance-level inspection. We demonstrate the utility of Calibrate through use cases on both real-world and synthetic data. We further validate Calibrate by presenting the results of a think-aloud experiment with data scientists who routinely analyze model calibration.
RESUMEN
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.
Asunto(s)
Gráficos por Computador , Crimen , Brasil , Ciudades , Factores de TiempoRESUMEN
Understanding the interpretation of machine learning (ML) models has been of paramount importance when making decisions with societal impacts, such as transport control, financial activities, and medical diagnosis. While local explanation techniques are popular methods to interpret ML models on a single instance, they do not scale to the understanding of a model's behavior on the whole dataset. In this article, we outline the challenges and needs of visually analyzing local explanations and propose SUBPLEX, a visual analytics approach to help users understand local explanations with subpopulation visual analysis. SUBPLEX provides steerable clustering and projection visualization techniques that allow users to derive interpretable subpopulations of local explanations with users' expertise. We evaluate our approach through two use cases and experts' feedback.
Asunto(s)
Aprendizaje Automático , Análisis por ConglomeradosRESUMEN
Automatic flood detection may be an important component for triggering damage control systems and minimizing the risk of social or economic impacts caused by flooding. Riverside images from regular cameras are a widely available resource that can be used for tackling this problem. Nevertheless, state-of-the-art neural networks, the most suitable approach for this type of computer vision task, are usually resource-consuming, which poses a challenge for deploying these models within low-capability Internet of Things (IoT) devices with unstable internet connections. In this work, we propose a deep neural network (DNN) architecture pruning algorithm capable of finding a pruned version of a given DNN within a user-specified memory footprint. Our results demonstrate that our proposed algorithm can find a pruned DNN model with the specified memory footprint with little to no degradation of its segmentation performance. Finally, we show that our algorithm can be used in a memory-constraint wireless sensor network (WSN) employed to detect flooding events of urban rivers, and the resulting pruned models have competitive results compared with the original models.
Asunto(s)
Internet de las Cosas , Algoritmos , Computadores , Inundaciones , Redes Neurales de la ComputaciónRESUMEN
Slower than anticipated, COVID-19 vaccine production and distribution have impaired efforts to curtail the current pandemic. The standard administration schedule for most COVID-19 vaccines currently approved is two doses administered 3 to 4 wk apart. To increase the number of individuals with partial protection, some governments are considering delaying the second vaccine dose. However, the delay duration must take into account crucial factors, such as the degree of protection conferred by a single dose, the anticipated vaccine supply pipeline, and the potential emergence of more virulent COVID-19 variants. To help guide decision-making, we propose here an optimization model based on extended susceptible, exposed, infectious, and removed (SEIR) dynamics that determines the optimal delay duration between the first and second COVID-19 vaccine doses. The model assumes lenient social distancing and uses intensive care unit (ICU) admission as a key metric while selecting the optimal duration between doses vs. the standard 4-wk delay. While epistemic uncertainties apply to the interpretation of simulation outputs, we found that the delay is dependent on the vaccine mechanism of action and first-dose efficacy. For infection-blocking vaccines with first-dose efficacy ≥50%, the model predicts that the second dose can be delayed by ≥8 wk (half of the maximal delay), whereas for symptom-alleviating vaccines, the same delay is recommended only if the first-dose efficacy is ≥70%. Our model predicts that a 12-wk second-dose delay of an infection-blocking vaccine with a first-dose efficacy ≥70% could reduce ICU admissions by 400 people per million over 200 d.
Asunto(s)
Vacunas contra la COVID-19/administración & dosificación , COVID-19/prevención & control , Hospitalización/estadística & datos numéricos , Unidades de Cuidados Intensivos/estadística & datos numéricos , SARS-CoV-2/inmunología , Tiempo de Tratamiento/normas , Vacunación/métodos , Algoritmos , Brasil/epidemiología , COVID-19/epidemiología , COVID-19/inmunología , Vacunas contra la COVID-19/provisión & distribución , Humanos , Resultado del Tratamiento , Vacunación/estadística & datos numéricosRESUMEN
A large number of stroke survivors suffer from a significant decrease in upper extremity (UE) function, requiring rehabilitation therapy to boost recovery of UE motion. Assessing the efficacy of treatment strategies is a challenging problem in this context, and is typically accomplished by observing the performance of patients during their execution of daily activities. A more detailed assessment of UE impairment can be undertaken with a clinical bedside test, the UE Fugl-Meyer Assessment, but it fails to examine compensatory movements of functioning body segments that are used to bypass impairment. In this work, we use a graph learning method to build a visualization tool tailored to support the analysis of stroke patients. Called NE-Motion, or Network Environment for Motion Capture Data Analysis, the proposed analytic tool handles a set of time series captured by motion sensors worn by patients so as to enable visual analytic resources to identify abnormalities in movement patterns. Developed in close collaboration with domain experts, NE-Motion is capable of uncovering important phenomena, such as compensation while revealing differences between stroke patients and healthy individuals. The effectiveness of NE-Motion is shown in two case studies designed to analyze particular patients and to compare groups of subjects.
Asunto(s)
Rehabilitación de Accidente Cerebrovascular , Accidente Cerebrovascular , Humanos , Movimiento , Recuperación de la Función , Extremidad SuperiorRESUMEN
Seeded segmentation methods have gained a lot of attention due to their good performance in fragmenting complex images, easy usability and synergism with graph-based representations. These methods usually rely on sophisticated computational tools whose performance strongly depends on how good the training data reflect a sought image pattern. Moreover, poor adherence to the image contours, lack of unique solution, and high computational cost are other common issues present in most seeded segmentation methods. In this work we introduce Laplacian Coordinates, a quadratic energy minimization framework that tackles the issues above in an effective and mathematically sound manner. The proposed formulation builds upon graph Laplacian operators, quadratic energy functions, and fast minimization schemes to produce highly accurate segmentations. Moreover, the presented energy functions are not prone to local minima, i.e., the solution is guaranteed to be globally optimal, a trait not present in most image segmentation methods. Another key property is that the minimization procedure leads to a constrained sparse linear system of equations, enabling the segmentation of high-resolution images at interactive rates. The effectiveness of Laplacian Coordinates is attested by a comprehensive set of comparisons involving nine state-of-the-art methods and several benchmarks extensively used in the image segmentation literature.
RESUMEN
São Paulo is the largest city in South America, with crime rates that reflect its size. The number and type of crimes vary considerably around the city, assuming different patterns depending on urban and social characteristics of each particular location. Previous works have mostly focused on the analysis of crimes with the intent of uncovering patterns associated to social factors, seasonality, and urban routine activities. Therefore, those studies and tools are more global in the sense that they are not designed to investigate specific regions of the city such as particular neighborhoods, avenues, or public areas. Tools able to explore specific locations of the city are essential for domain experts to accomplish their analysis in a bottom-up fashion, revealing how urban features related to mobility, passersby behavior, and presence of public infrastructures (e.g., terminals of public transportation and schools) can influence the quantity and type of crimes. In this paper, we present CrimAnalyzer, a visual analytic tool that allows users to study the behavior of crimes in specific regions of a city. The system allows users to identify local hotspots and the pattern of crimes associated to them, while still showing how hotspots and corresponding crime patterns change over time. CrimAnalyzer has been developed from the needs of a team of experts in criminology and deals with three major challenges: i) flexibility to explore local regions and understand their crime patterns, ii) identification of spatial crime hotspots that might not be the most prevalent ones in terms of the number of crimes but that are important enough to be investigated, and iii) understand the dynamic of crime patterns over time. The effectiveness and usefulness of the proposed system are demonstrated by qualitative and quantitative comparisons as well as by case studies run by domain experts involving real data. The experiments show the capability of CrimAnalyzer in identifying crime-related phenomena.
RESUMEN
Boundary detection has long been a fundamental tool for image processing and computer vision, supporting the analysis of static and time-varying data. In this work, we built upon the theory of Graph Signal Processing to propose a novel boundary detection filter in the context of graphs, having as main application scenario the visual analysis of spatio-temporal data. More specifically, we propose the equivalent for graphs of the so-called Laplacian of Gaussian edge detection filter, which is widely used in image processing. The proposed filter is able to reveal interesting spatial patterns while still enabling the definition of entropy of time slices. The entropy reveals the degree of randomness of a time slice, helping users to identify expected and unexpected phenomena over time. The effectiveness of our approach appears in applications involving synthetic and real data sets, which show that the proposed methodology is able to uncover interesting spatial and temporal phenomena. The provided examples and case studies make clear the usefulness of our approach as a mechanism to support visual analytic tasks involving spatio-temporal data.
RESUMEN
Multidimensional Projection is a fundamental tool for high-dimensional data analytics and visualization. With very few exceptions, projection techniques are designed to map data from a high-dimensional space to a visual space so as to preserve some dissimilarity (similarity) measure, such as the Euclidean distance for example. In fact, although adopting distinct mathematical formulations designed to favor different aspects of the data, most multidimensional projection methods strive to preserve dissimilarity measures that encapsulate geometric properties such as distances or the proximity relation between data objects. However, geometric relations are not the only interesting property to be preserved in a projection. For instance, the analysis of particular structures such as clusters and outliers could be more reliably performed if the mapping process gives some guarantee as to topological invariants such as connected components and loops. This paper introduces TopoMap, a novel projection technique which provides topological guarantees during the mapping process. In particular, the proposed method performs the mapping from a high-dimensional space to a visual space, while preserving the 0-dimensional persistence diagram of the Rips filtration of the high-dimensional data, ensuring that the filtrations generate the same connected components when applied to the original as well as projected data. The presented case studies show that the topological guarantee provided by TopoMap not only brings confidence to the visual analytic process but also can be used to assist in the assessment of other projection methods.
RESUMEN
The brachial plexus is a complex network of peripheral nerves that enables sensing from and control of the movements of the arms and hand. Nowadays, the coordination between the muscles to generate simple movements is still not well understood, hindering the knowledge of how to best treat patients with this type of peripheral nerve injury. To acquire enough information for medical data analysis, physicians conduct motion analysis assessments with patients to produce a rich dataset of electromyographic signals from multiple muscles recorded with joint movements during real-world tasks. However, tools for the analysis and visualization of the data in a succinct and interpretable manner are currently not available. Without the ability to integrate, compare, and compute multiple data sources in one platform, physicians can only compute simple statistical values to describe patient's behavior vaguely, which limits the possibility to answer clinical questions and generate hypotheses for research. To address this challenge, we have developed MOTION BROWSER, an interactive visual analytics system which provides an efficient framework to extract and compare muscle activity patterns from the patient's limbs and coordinated views to help users analyze muscle signals, motion data, and video information to address different tasks. The system was developed as a result of a collaborative endeavor between computer scientists and orthopedic surgery and rehabilitation physicians. We present case studies showing physicians can utilize the information displayed to understand how individuals coordinate their muscles to initiate appropriate treatment and generate new hypotheses for future research.
RESUMEN
Visual analysis of multidimensional data requires expressive and effective ways to reduce data dimensionality to encode them visually. Multidimensional projections (MDP) figure among the most important visualization techniques in this context, transforming multidimensional data into scatter plots whose visual patterns reflect some notion of similarity in the original data. However, MDP come with distortions that make these visual patterns not trustworthy, hindering users to infer actual data characteristics. Moreover, the patterns present in the scatter plots might not be enough to allow a clear understanding of multidimensional data, motivating the development of layout enrichment methodologies to operate together with MDP. This survey attempts to cover the main aspects of MDP as a visualization and visual analytic tool. It provides detailed analysis and taxonomies as to the organization of MDP techniques according to their main properties and traits, discussing the impact of such properties for visual perception and other human factors. The survey also approaches the different types of distortions that can result from MDP mappings and it overviews existing mechanisms to quantitatively evaluate such distortions. A qualitative analysis of the impact of distortions on the different analytic tasks performed by users when exploring multidimensional data through MDP is also presented. Guidelines for choosing the best MDP for an intended task are also provided as a result of this analysis. Finally, layout enrichment schemes to debunk MDP distortions and/or reveal relevant information not directly inferable from the scatter plot are reviewed and discussed in the light of new taxonomies. We conclude the survey providing future research axes to fill discovered gaps in this domain.
RESUMEN
Traditional vector field visualization has a close focus on velocity, and is typically constrained to the dynamics of massless particles. In this paper, we present a novel approach to the analysis of the force-induced dynamics of inertial particles. These forces can arise from acceleration fields such as gravitation, but also be dependent on the particle dynamics itself, as in the case of magnetism. Compared to massless particles, the velocity of an inertial particle is not determined solely by its position and time in a vector field. In contrast, its initial velocity can be arbitrary and impacts the dynamics over its entire lifetime. This leads to a four-dimensional problem for 2D setups, and a six-dimensional problem for the 3D case. Our approach avoids this increase in dimensionality and tackles the visualization by an integrated topological analysis approach. We demonstrate the utility of our approach using a synthetic time-dependent acceleration field, a system of magnetic dipoles, and N-body systems both in 2D and 3D.
RESUMEN
Existing algorithms for building layouts from geometric primitives are typically designed to cope with requirements such as orthogonal alignment, overlap removal, optimal area usage, hierarchical organization, among others. However, most techniques are able to tackle just a few of those requirements simultaneously, impairing their use and flexibility. In this work we propose a novel methodology for building layouts from geometric primitives that concurrently addresses a wider range of requirements. Relying on multidimensional projection and mixed integer optimization, our approach arranges geometric objects in the visual space so as to generate well structured layouts that preserve the semantic relation among objects while still making an efficient use of display area. Moreover, scalability is handled through a hierarchical representation scheme combined with navigation tools. A comprehensive set of quantitative comparisons against existing geometry-based layouts and applications on text, image, and video data set visualization prove the effectiveness of our approach.
RESUMEN
Internet users are very familiar with the results of a search query displayed as a ranked list of snippets. Each textual snippet shows a content summary of the referred document (or webpage) and a link to it. This display has many advantages, for example, it affords easy navigation and is straightforward to interpret. Nonetheless, any user of search engines could possibly report some experience of disappointment with this metaphor. Indeed, it has limitations in particular situations, as it fails to provide an overview of the document collection retrieved. Moreover, depending on the nature of the query--for example, it may be too general, or ambiguous, or ill expressed--the desired information may be poorly ranked, or results may contemplate varied topics. Several search tasks would be easier if users were shown an overview of the returned documents, organized so as to reflect how related they are, content wise. We propose a visualization technique to display the results of web queries aimed at overcoming such limitations. It combines the neighborhood preservation capability of multidimensional projections with the familiar snippet-based representation by employing a multidimensional projection to derive two-dimensional layouts of the query search results that preserve text similarity relations, or neighborhoods. Similarity is computed by applying the cosine similarity over a "bag-of-words" vector representation of collection built from the snippets. If the snippets are displayed directly according to the derived layout, they will overlap considerably, producing a poor visualization. We overcome this problem by defining an energy functional that considers both the overlapping among snippets and the preservation of the neighborhood structure as given in the projected layout. Minimizing this energy functional provides a neighborhood preserving two-dimensional arrangement of the textual snippets with minimum overlap. The resulting visualization conveys both a global view of the query results and visual groupings that reflect related results, as illustrated in several examples shown.
RESUMEN
We propose an approach for verification of volume rendering correctness based on an analysis of the volume rendering integral, the basis of most DVR algorithms. With respect to the most common discretization of this continuous model (Riemann summation), we make assumptions about the impact of parameter changes on the rendered results and derive convergence curves describing the expected behavior. Specifically, we progressively refine the number of samples along the ray, the grid size, and the pixel size, and evaluate how the errors observed during refinement compare against the expected approximation errors. We derive the theoretical foundations of our verification approach, explain how to realize it in practice, and discuss its limitations. We also report the errors identified by our approach when applied to two publicly available volume rendering packages.
RESUMEN
Robust analysis of vector fields has been established as an important tool for deriving insights from the complex systems these fields model. Traditional analysis and visualization techniques rely primarily on computing streamlines through numerical integration. The inherent numerical errors of such approaches are usually ignored, leading to inconsistencies that cause unreliable visualizations and can ultimately prevent in-depth analysis. We propose a new representation for vector fields on surfaces that replaces numerical integration through triangles with maps from the triangle boundaries to themselves. This representation, called edge maps, permits a concise description of flow behaviors and is equivalent to computing all possible streamlines at a user defined error threshold. Independent of this error streamlines computed using edge maps are guaranteed to be consistent up to floating point precision, enabling the stable extraction of features such as the topological skeleton. Furthermore, our representation explicitly stores spatial and temporal errors which we use to produce more informative visualizations. This work describes the construction of edge maps, the error quantification, and a refinement procedure to adhere to a user defined error bound. Finally, we introduce new visualizations using the additional information provided by edge maps to indicate the uncertainty involved in computing streamlines and topological structures.
RESUMEN
Creating high-quality quad meshes from triangulated surfaces is a highly nontrivial task that necessitates consideration of various application specific metrics of quality. In our work, we follow the premise that automatic reconstruction techniques may not generate outputs meeting all the subjective quality expectations of the user. Instead, we put the user at the center of the process by providing a flexible, interactive approach to quadrangulation design. By combining scalar field topology and combinatorial connectivity techniques, we present a new framework, following a coarse to fine design philosophy, which allows for explicit control of the subjective quality criteria on the output quad mesh, at interactive rates. Our quadrangulation framework uses the new notion of Reeb atlas editing, to define with a small amount of interactions a coarse quadrangulation of the model, capturing the main features of the shape, with user prescribed extraordinary vertices and alignment. Fine grain tuning is easily achieved with the notion of connectivity texturing, which allows for additional extraordinary vertices specification and explicit feature alignment, to capture the high-frequency geometries. Experiments demonstrate the interactivity and flexibility of our approach, as well as its ability to generate quad meshes of arbitrary resolution with high-quality statistics, while meeting the user's own subjective requirements.