Search

As urban populations grow, effectively accessing urban performance measures such as livability and comfort becomes increasingly important due to their significant socioeconomic impacts. While Point of Interest (POI) data has been utilized for various applications in location-based services, its potential for urban performance analytics remains unexplored. In this article, we present SenseMap, a novel approach for analyzing urban performance by leveraging POI data as a semantic representation of urban functions. We quantify the contribution of POIs to different urban performance measures by calculating semantic textual similarities on our constructed corpus. We propose Semantic-adaptive Kernel Density Estimation which takes into account POIs’ influential areas across different Traffic Analysis Zones and semantic contributions to generate semantic density maps for measures. We design and implement a feature-rich, real-time visual analytics system for users to explore the urban performance of their surroundings. Evaluations with human judgment and reference data demonstrate the feasibility and validity of our method. Usage scenarios and user studies demonstrate the capability, usability and explainability of our system.

DNGs are diverse network graphs with texts and different styles of nodes and edges, including mind maps, modeling graphs, and flowcharts. They are high-level visualizations that are easy for humans to understand but difficult for machines. Inspired by the process of human perception of graphs, we propose a method called GraphDecoder to extract data from raster images. Given a raster image, we extract the content based on a neural network. We built a semantic segmentation network based on U-Net. We increase the attention mechanism module, simplify the network model, and design a specific loss function to improve the model's ability to extract graph data. After this semantic segmentation network, we can extract the data of all nodes and edges. We then combine these data to obtain the topological relationship of the entire DNG. We also provide an interactive interface for users to redesign the DNGs. We verify the effectiveness of our method by evaluations and user studies on datasets collected on the internet and generated datasets.

Color has been widely used to encode data in all types of visualizations. Effective color palettes contain discriminable and harmonious colors, which allow information from visualizations to be accurately and aesthetically conveyed. However, predefined color palettes not only lack the flexibility of custom color palette generation but also ignore the context in which the visualizations are used. Designing an effective color palette is a time-consuming and challenging process for users, even experts. In this work, we propose the generation of an image-based visualization color palette to exploit the human perception of visually appealing images while considering visualization cognition. By analyzing color palette constraints, including harmony, discrimination, and context, we propose an image-driven color generation method. We design a color clustering method in the saliency-hue plane based on visual importance detection and then select the palette based on the visualization color constraints. In addition, we design two color optimization and assignment strategies for visualizations of different data types. Evaluations through numeric indicators and user experiments demonstrate that the palettes predicted by our method are visually related to the original images and are aesthetically pleasing, supporting diverse visualization contexts and data types in practical applications.

We present InvVis, a new approach for invertible visualization, which is reconstructing or further modifying a visualization from an image. InvVis allows the embedding of a significant amount of data, such as chart data, chart information, source code, etc., into visualization images. The encoded image is perceptually indistinguishable from the original one. We propose a new method to efficiently express chart data in the form of images, enabling large-capacity data embedding. We also outline a model based on the invertible neural network to achieve high-quality data concealing and revealing. We explore and implement a variety of application scenarios of InvVis. Additionally, we conduct a series of evaluation experiments to assess our method from multiple perspectives, including data embedding quality, data restoration accuracy, data encoding capacity, etc. The result of our experiments demonstrates the great potential of InvVis in invertible visualization.

We present an incremental sampling-based task and motion planner for retrieving near-cylindrical objects, like bottle, in cluttered scenes, which computes a plan for removing obstacles to generate a collision-free motion of a robot to retrieve the target object. Our proposed planner uses a two-level hierarchy, including the first-level roadmap for the target object motion and the second-level retrieval graph for the entire robot motion, to aid in deciding the order and trajectory of object removal. We use an incremental expansion strategy to update the roadmap and retrieval graph from the collisions between the target object, the robot, and the obstacles, in order to optimize the object removal sequence. The performance of our method is highlighted in several benchmark scenes, including a fixed robotic arm in a cluttered scene with known obstacle locations and a scene, where locations of some objects or even the target object are unknown due to occlusions. Our method can also efficiently solve the high-dimensional planning problem of object retrieval using a mobile manipulator and be combined with the symbolic planner to plan complex multistep tasks. We deploy our method to a physical robot and integrate it with nonprehensile actions to improve operational efficiency. Compared to the state-of-the-art approaches, our method reduces task and motion planning time up to 24.6$\%$ with a higher success rate, and still provides a near-optimal plan.

Network graphs are common visualization charts. They often appear in the form of bitmaps in articles, web pages, magazine prints, and designer sketches. People often want to modify graphs because of their poor design, but it is difficult to obtain their underlying data. In this article, we present VividGraph, a pipeline for automatically extracting and redesigning graphs from static images. We propose using convolutional neural networks to solve the problem of graph data extraction. Our method is robust to hand-drawn graphs, blurred graph images, and large graph images. We also present a graph classification module to make it effective for directed graphs. We propose two evaluation methods to demonstrate the effectiveness of our approach. It can be used to quickly transform designer sketches, extract underlying data from existing graphs, and interactively redesign poorly designed graphs.

Due to sectoral interactions in the economy, the overall green efficiency (GE) of China’s industrial system relies heavily on fundamental sectors that contribute substantial energy to the supply chain production of other sectors but shows low sectoral GE. For the three fundamental sectors in China’s industrial systems, namely the smelting and pressing of nonferrous metals (SPNFM), the processing of petroleum, coking, and nuclear fuel (PPCNF); and the manufacturing of nonmetallic mineral products (MNMMP), we employed a three-stage data envelopment analysis (DEA) model to measure GE in the fundamental sectors in 30 provinces from 2010 to 2015. We then adopted a stochastic frontier analysis (SFA) model to evaluate the influence of technological innovation (TI), industrial agglomeration (IA), environmental regulation (ER), and intraindustry competition (IC). The results showed that GE in the three fundamental sectors varied spatially. Specifically, TI promoted GE in MNMMP, but the effect was not obvious in the SPNFM and PPCNF sectors. Moreover, ER had positive impacts on GE in the fundamental sectors. The effects of IA and IC on GE in the fundamental sectors varied in direction and strength. After eliminating the impacts of environmental effects and statistical noise, the real GE in the three fundamental sectors varied significantly compared to the comprehensive GE. Policy opportunities for enhancing GE in the fundamental sectors mainly lie in region-specific policy and regulations that avoid a “one-size-fits-all” governance approach.

This paper describes a novel hybrid method for fluid simulation of saturating anisotropic porous material via fluid-structure coupling. Our framework employs particle finite element method (PFEM) that not only adopts Lagrangian scheme to model the motion of freely-moving particles, but also produces the extended Delaunay Tessellation to furnish the governing equations with FEM discretization. We first employ adaptive smoothed particle hydrodynamics (SPH) to simulate porous flow respecting the anisotropic permeability with little cost. Second, the extended Delaunay Tessellation is obtained to solve differential equations for skeletal deformation. Third, a hybrid particle system is adopted to track the surface and topological changes. At the physical level, we introduce dynamic permeability considering skeletal deformation via fluid-structure coupling. At the geometric level, PFEM reduces the computational cost and effectively tracks topological changes. Moreover, our implementation on CUDA improves the performance in high-quality physics-based graphics applications. Consequently, the proposed method realistically reproduces interactions between pore-scale flow and anisotropic porous material. [ABSTRACT FROM AUTHOR]

The study of genealogy is an increasingly popular activity pursued by millions of people, ranging from hobbyists to professional researchers. Such genealogical datasets provide a great opportunity for social science analysts, historians, and the public to study a wide variety of topics in demography, family and household, kinship, stratification, and health. Nevertheless, the large scale and characteristics of the data such as hierarchical, spatiotemporal, and multidimensional also pose special challenges for effective data analysis. In this paper, we introduce GenealogyVis, a visual analytic system to analyze family history and evolution by using the China Multigenerational Panel Dataset-Liaoning, which has more than 1.5 million observations and provides socioeconomic, demographic, and other information for more than 260 000 residents, and further enable users to explore the correlation between the development of families and the social context of environments, economics, policies, and so on. This system includes five main linked views: the Scatter-plot View to provide an overview of the data and further explore the correlation analysis, the Tree View to show the family structure and details for individuals, the Migration View to present the genealogical migratory behaviors, the Matrix View to analyze the reproduction pattern between two generations, and the Stream View to show various statistical information such as demographic information and temporal information. A design study was conducted with a research group led by a domain expert of humanities and social sciences in an iterative manner over half a year. Several in-depth case studies, involving the research group, are described to demonstrate the usefulness of GenealogyVis and discuss new findings.

There would be value to several domains in discovering and visualizing sentiments in online posts. This paper presents SentiView, an interactive visualization system that aims to analyze public sentiments for popular topics on the Internet. SentiView combines uncertainty modeling and model-driven adjustment. By searching and correlating frequent words in text data, it mines and models the changes of the sentiment on public topics. In addition, using a time-varying helix together with an attribute astrolabe to represent sentiments, it can visualize the changes of multiple attributes and relationships among demographics of interest and the sentiments of participants on popular topics. The relationships of interest among different participants are presented in a relationship map. Using a new evolution model that is based on cellular automata, it is able to compare the time-varying features for sentiment-driven forums on both simulated and real data. Adaptable for different social networking platforms, such as Twitter, blog and forum, the methods demonstrate the effectiveness of SentiView in analyzing and visualizing public sentiments on the Web.

[Display omitted] The appearance styles of natural terrains vary significantly from region to region in real world, and there is a strong need to effectively produce realistic terrain with certain style in computer graphics. In this paper, we advocate a novel neural network approach to the rapid synthesis of multi-style terrains that could directly learn and infer from real terrain data. The key idea is to explicitly devise a conditional generative adversarial network (GAN) which encourages and favors the maximum-distance embedding of acquired styles in the latent space. Towards this functionality, we first collect a dataset that exhibits apparent terrain style diversity in their style attributes. Second, we design multiple discriminators that can distinguish different terrain styles. Third, we employ discriminators to extract terrain features in different spatial scales, so that the developed generator can produce new terrains by fusing the finer-scale and coarser-scale styles. In our experiments, we collect 10 typical terrain datasets from real terrain data that cover a wide range of regions. Our approach successfully generates realistic terrains with global-to-local style control. The experimental results have confirmed our neural network can produce natural terrains with high fidelity, which are user-friendly to style interpolation and style mixing for the terrain authoring task. [ABSTRACT FROM AUTHOR]

Physically based fluid simulation in recent years has been successful for small-scale fluids such as liquid in a cubic cavity. However, for boundless free-surface flow of large scale and irregular area, there is a critical trade-off between simulation efficiency and accuracy because of the restriction of the traditional regular computational grids. This paper introduces boundless computational grids based on hierarchical runlength encoding to simulate large-scale free-surface flow. We first modeled the free-surface flow with a lattice Boltzmann method, and calculated the surface curvature in the update process. We then introduced an effective method with which to calculate the surface curvature according to the surface tension so that the surface detail was enhanced, and obtained the curvature of each surface effectively as it was extracted. Furthermore, we dynamically compressed and indexed the computational cells with the improved hierarchical run-length encoding algorithm, so that the grid expands dynamically according to the fluid flow and the computational resources used were proportional to the volume of the fluid. Finally fluids in different situations were simulated realistically. The proposed method makes the best of the computational resources to perform the simulation with high resolution, and dynamically allocates resources so that the fluid can expand in random directions without boundaries, which is suited to the simulation of large-scale visual scenes.

A snowing scene has a unique fascination for people due to its incomparable beauty. However, little work has been presented on the real-time generation of a dynamic snowing scene, partially due to the difficulty that the simulation of a dynamic snowing process involves the complex modeling of the wind field and the interaction between wind and snow. In this paper, by fully considering the physical characteristics of wind and snow, we construct a three-dimensional wind field based on the discrete form of the Boltzmann equation. According to the interaction laws between wind and snow, we simulate the falling of snow, deposition and erosion in 3D space. Experimental results show that realistic wind-driven snow scenes under different speeds of wind with different amounts of snowfall can be rendered in real-time. A snowing scene has a unique fascination for people due to its incomparable beauty. However, little work has been presented on the real-time generation of a dynamic snowing scene, partially due to the difficulty that the simulation of a dynamic snowing process involves the complex modeling of the wind field and the interaction between wind and snow. In this paper, by fully considering the physical characteristics of wind and snow, we construct a three-dimensional wind field based on the discrete form of the Boltzmann equation. According to the interaction laws between wind and snow, we simulate the falling of snow, deposition and erosion in 3D space. Experimental results show that realistic wind-driven snow scenes under different speeds of wind with different amounts of snowfall can be rendered in real-time.

This paper proposes a new method to generate the dynamic infrared outer space scene in real time. In the paper, we first model the dynamic infrared background of star sky based on the infrared star catalogue and temporal and spacial coordinate transformations. We also present a new concept called infrared star magnitude for given infrared receiving wavebands to display the infrared star sky effectively. Then we put forward an infrared image synthesis model for outer space targets based on the method of divided elements and energy equilibrium. To generate the dynamic infrared outer space scene, several simplification and accelerating techniques such as Billboard, Levels of Details and Occlusion Culling are hired to accelerate the generating speed of the scene. Finally infrared images of targets, background of outer space scene at different infrared receiving wavebands are drawn and the dynamic infrared outer space scene is successfully carried out in real time.

•We propose a GAN-based method to analyze the latent space of density maps, and latent codes are available for compression to save transmission time. Our method can be applied to any density maps in the spatiotemporal visualization.•Based on latent codes, we calculate the dynamic changes of the density map by morphing, which can complete missing data in a spatiotemporal visualization.•We collect thousands of density maps in three ways and process them for training and testing. We demonstrate the effectiveness of our method in three forms of density maps such as spatial density maps and slices of the volume data.

This research further extends an existing state-of-the-art GPU framework of SPH simulation for better performance without any compromise of numerical accuracy and sacrifice of simulation detail. Towards this grand goal, we devise three new strategies. First, we design a novel hierarchical grid to decompose the simulation space, where we can locate particles in a more refined unit space. With this organization, particle distribution coherence in global memory is improved. As a result, global memory operations can be more efficient. Second, based on our well designed hierarchical grid, we propose a hierarchical neighbor search strategy for catering to the heterogeneous distribution of particles in cells, so we can search a neighbor particle in different-level grids. In a cell with dense particles, we can search particles in a higher-level grid whose unit space is more refined, which means we can narrow the search space for decreasing the access of false neighbor particles. In contrast, in a cell with sparse particles, we search particles in a lower-level grid whose unit space is relatively large, which means we can decrease the loop iterations when we search the entire neighbor cell. In this way, we can avoid the unnecessary overhead of loop iterations. After designing a reasonable neighbor search strategy, an efficient thread cooperation strategy can further improve the performance of our framework by realizing more potentials of GPGPU. The existing state-of-the-art method is concentrating on task assignment strategy for taking the full advantage of shared memory. The method decomposes particles in a cell into several tasks and then assigns a cooperation thread array (CTA) to each task. However, this method has not fully considered the uniformity of tasks belonging to the same cell, as these tasks always share a lot of particles with the same neighborhood. Finally, we propose a hierarchical task assignment strategy by merging such successive tasks into a larger task, which means we only load the same neighbor particles once and the corresponding CTAs are arranged to work together to handle the new task. Our method can greatly reduce the overload of neighbor particles and the overhead of neighbor search iterations. Through our comprehensive tests validated in practice, our work can exhibit 1.73 × speedup when compared with other state-of-the-art GPGPU frameworks for SPH simulation. [ABSTRACT FROM AUTHOR]

Visualization of customer behavior is urgently needed for an increasing number of customer orders on takeout service. Although many works have been done on visualizing customer opinion or customer click events of one store, visualizing customer switching behavior among stores is still challenging. The challenge is to show customer order records over time and structure the inter-connection among different stores when customer switching behavior happens. In this work, we focus on takeout service to present a novel visual analysis system for retailers focusing on customer switching behavior patterns. Firstly we define five customer segments based on switching behavior. Then this system enables temporal-spatial driver exploration for different segments through several interactive views. Moreover, in order to visualize inter-connection sequences, augmented streamgraph with the bundled parallel coordinates is proposed as one alternative technique to visualize temporal event sequences. Evaluation including user and case studies also demonstrates the usefulness and effectiveness of this system in helping customer relationship management.

Biologists often use gene chip to get massive experimental data in the field of bioscience and chemical sciences. Facing a large amount of experimental data, researchers often need to find out a few interesting data or simple regulations. This paper presents a set of methods to visualize and analyze the data for gene expression signatures of people who smoke. We use the latest research data from National Center for Biotechnology Information. Totally, there are more than 400 thousand expressions data. Using these data, we can use parallel coordinates method to visualize the different gene expressions between smokers and nonsmokers and we can distinguish non-smokers, former smokers and current smokers by using the different colors. It can be easy to find out which gene is more important during the lung cancer angiogenesis in the smoking people. In another way, we can use a hierarchical model to visualize the inner relation of different genes. The location of the nodes shows different expression moment and the distance to the root shows the sequence of the expression. We can use the ring layout to represent all the nodes, and connect the different nodes which are related with color lines. Combined with the parallel coordinates method, the visualization result show the important genes and some inner relation obviously, which is useful for examination and prevention of lung cancer.