InvVis: Large-Scale Data Embedding for Invertible Visualization.

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.

Aquaculture activities influencing the generation of geosmin and 2-methylisoborneol: a case study in the aquaculture regions of Hongze Lake, China.

Contamination by odor substances such as geosmin (GSM) and 2-methylisoborneol (2-MIB) was examined in the cultured water from aquaculture farming in the region of the Hongze Lake in 2022, and some factors influencing residual levels of them in the water were analyzed. Geographically, high concentrations of GSM were located mainly in the north and northeast culture areas of the lake, while those of 2-MIB were found in the northeast and southwest. Analysis of the water in the enclosure culture revealed significant differences in the concentrations of GSM and 2-MIB among the cultured species. The mean concentrations of GSM in culture water were ranked in the order: crab > the four major Chinese carps > silver and bighead carp, and silver and bighead carp > crab > the four major Chinese carps for 2-MIB. The concentration of GSM was significantly higher at 38.99 ± 18.93 ng/L in crab culture water compared to other fish culture water. Significant differences were observed in GSM concentrations between crab enclosure culture and pond culture, while 2-MIB levels were comparable. These findings suggest that cultural management practices significantly affect the generation of odor substances. The taste and odor (T&O) assessment revealed that the residual levels of GSM and 2-MIB in most samples were below the odor threshold concentrations (OTCs), although high levels of GSM and 2-MIB in all water bodies were at 30.9% and 27.5%, respectively. Compared with the corresponding data from other places and the regulation guidelines of Japan, USA, and China, the region in the Hongze Lake is generally classified as a slightly T&O area, capable of supporting the aquaculture production scale.

SenseMap: Urban Performance Visualization and Analytics via Semantic Textual Similarity.

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 paper, 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.

VividGraph: Learning to Extract and Redesign Network Graphs From Visualization Images.

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.

Image-Driven Harmonious Color Palette Generation for Diverse Information Visualization.

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.

GraphDecoder: Recovering Diverse Network Graphs from Visualization Images via Attention-Aware Learning.

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.

Visual Recommendation for Peer-To-Peer Accommodation with Online Reviews based on Sentiment Analysis and Topic Models.

Abstract: Peer-to-peer accommodation is developing rapidly in the era of sharing economy, and the visual recommendation of accommodation is also an urgent problem to be solved. Meanwhile, user-generated content is critical in P2P accommodations, because they contain a wealth of information about the opinions and experiences of users, which helps understand consumer decisions and improve products and services better. However, the huge volume of reviews makes it difficult for potential customers to gain useful insights and for managers to track customer opinions. In this paper, we propose a complete pipeline for recommending personalized accommodations for consumers, while also providing insights for managers. First, we use topic modeling techniques to mining opinions from review. Second, we build a deep learning network for review sentiment analysis. Third, we perform sentiment analysis of the reviews at the aspect level to obtain the sentiment vector representation of the accommodation. Finally, we propose a personalized accommodation recommendation method based on the above work. Moreover, we design a visual analytic system with a user-friendly interface to facilitate interactive analysis. Evaluation including user and case studies demonstrates the usefulness and effectiveness of our method and system.

DDLVis: Real-time Visual Query of Spatiotemporal Data Distribution via Density Dictionary Learning.

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.

VisCode: Embedding Information in Visualization Images using Encoder-Decoder Network.

We present an approach called VisCode for embedding information into visualization images. This technology can implicitly embed data information specified by the user into a visualization while ensuring that the encoded visualization image is not distorted. The VisCode framework is based on a deep neural network. We propose to use visualization images and QR codes data as training data and design a robust deep encoder-decoder network. The designed model considers the salient features of visualization images to reduce the explicit visual loss caused by encoding. To further support large-scale encoding and decoding, we consider the characteristics of information visualization and propose a saliency-based QR code layout algorithm. We present a variety of practical applications of VisCode in the context of information visualization and conduct a comprehensive evaluation of the perceptual quality of encoding, decoding success rate, anti-attack capability, time performance, etc. The evaluation results demonstrate the effectiveness of VisCode.

Learning Physical Parameters and Detail Enhancement for Gaseous Scene Design Based on Data Guidance.

This article articulates a novel learning framework for both parameter estimation and detail enhancement for Eulerian gas based on data guidance. The key motivation of this article is to devise a new hybrid, grid-based simulation that could inherit modeling and simulation advantages from both physically-correct simulation methods and powerful data-driven methods, while combating existing difficulties exhibited in both approaches. We first employ a convolutional neural network (CNN) to estimate the physical parameters of gaseous phenomena in Eulerian settings, then we can use the just-learnt parameters to re-simulate (with or without artists' guidance) for specific scenes with flexible coupling effects. Next, a second CNN is adopted to reconstruct the high-resolution velocity field to guide a fast re-simulation on the finer grid, achieving richer and more realistic details with little extra computational expense. From the perspective of physics-based simulation, our trained networks respect temporal coherence and physical constraints. From the perspective of the data-driven machine-learning approaches, our network design aims at extracting a meaningful parameters and reconstructing visually realistic details. Additionally, our implementation based on parallel acceleration could significantly enhance the computational performance of every involved module. Our comprehensive experiments confirm the controllability, effectiveness, and accuracy of our novel approach when producing various gaseous scenes with rich details for widespread graphics applications.

Reexamining the relationship between urbanization and pollutant emissions in China based on the STIRPAT model.

Understanding the relationship between urbanization and pollutant emissions in China is of great significance to realizing sustainable development. Previous studies focused on the relationship between urbanization and air pollutants in China. However, the relationship between urbanization and industrial or domestic pollutants remains unclear. In this paper, we used the stochastic impacts by regression on population, affluence, and technology (STIRPAT) model to examine whether an environmental Kuznets curve (EKC) relationship exists between urbanization and pollutant emissions, including industrial wastewater, industrial SO2, industrial soot (dust), and domestic garbage based on panel data for 277 prefecture-level cities in China from 2003 to 2015. We found that industrial soot (dust) emissions and domestic garbage increased by 83.0% and 43.5%, respectively, whereas industrial wastewater discharge and SO2 emissions decreased by 7.4% and 10.5%, respectively. The identified inverted U-shaped relationship between the urbanization ratio (i.e., percentage of the population living in urban areas) and industrial pollutants supports the EKC hypothesis. However, the domestic garbage volume increased with increasing urbanization ratio. In the future, more attention should be paid to the prevention and control of domestic pollution. In addition, small and medium-sized cities should reduce pollutant emissions and determine effective ways to achieve sustainable development.

GenerativeMap: Visualization and Exploration of Dynamic Density Maps via Generative Learning Model.

The density map is widely used for data sampling, time-varying detection, ensemble representation, etc. The visualization of dynamic evolution is a challenging task when exploring spatiotemporal data. Many approaches have been provided to explore the variation of data patterns over time, which commonly need multiple parameters and preprocessing works. Image generation is a well-known topic in deep learning, and a variety of generating models have been promoted in recent years. In this paper, we introduce a general pipeline called GenerativeMap to extract dynamics of density maps by generating interpolation information. First, a trained generative model comprises an important part of our approach, which can generate nonlinear and natural results by implementing a few parameters. Second, a visual presentation is proposed to show the density change, which is combined with the level of detail and blue noise sampling for a better visual effect. Third, for dynamic visualization of large-scale density maps, we extend this approach to show the evolution in regions of interest, which costs less to overcome the drawback of the learning-based generative model. We demonstrate our method on different types of cases, and we evaluate and compare the approach from multiple aspects. The results help identify the effectiveness of our approach and confirm its applicability in different scenarios.

Assessment of five satellite-derived LAI datasets for GPP estimations through ecosystem models.

Ecosystem models have been widely used for obtaining gross primary productivity (GPP) estimations at multiple scales. Leaf area index (LAI) is a critical variable in these models for describing the vegetation canopy structure and predicting vegetation-atmosphere interactions. However, the uncertainties in LAI datasets and the effects of their representation on simulated GPP remain unclear, especially over complex terrain. Here, five most popular datasets, namely the Long-term Global Mapping (GLOBMAP) LAI, Global LAnd Surface Satellite (GLASS) LAI, Geoland2 version 1 (GEOV1) LAI, Global Inventory Monitoring and Modeling System (GIMMS) LAI, and Moderate Resolution Imaging Spectroradiometer (MODIS) LAI, were selected to examine the influences of LAI representation on GPP estimations at 95 eddy covariance (EC) sites. The GPP estimations from the Boreal Ecosystem Productivity Simulator (BEPS) model and the Eddy Covariance Light Use Efficiency (EC-LUE) model were evaluated against EC GPP to assess the performances of LAI datasets. Results showed that MODIS LAI had stronger linear correlations with GLASS and GEOV1 than GIMMS and GLOMAP at the study sites. The GPP estimations from GLASS LAI had a better agreement with EC GPP than those from other four LAI datasets at forest sites, while the GPP estimations from GEOVI LAI matched best with EC GPP at grass sites. Additionally, the GPP estimations from GLASS and GEOVI LAI presented better performances than the other three LAI datasets at crop sites. Besides, the results also showed that complex terrain had larger discrepancies of LAI and GPP estimations, and flat terrain presented better performances of LAI datasets in GPP estimations. Moreover, the simulated GPP from BEPS was more sensitive to LAI than those from EC - LUE, suggesting that LAI datasets can also lead to different uncertainties in GPP estimations from different model structures. Our study highlights that the satellite-derived LAI datasets can cause uncertainties in GPP estimations through ecosystem models.

Assessing the environmental externalities for biomass- and coal-fired electricity generation in China: A supply chain perspective.

Biomass power in China is usually regarded as less economically competitive than coal power, partially because the external costs of power generation technologies' effects on human health and the environment are always neglected. To understand the real economic performance of biomass- and coal-fired power in China, a hybrid life cycle inventory modeling approach was developed to estimate the fuel-to-electricity environmental emissions and complete (direct and external) economic costs of the two fuel options. The results show that the direct economic cost of biomass power is 0.44 Chinese yuan (CNY) per kilowatt-hour, about 25%-37% higher than that of coal power. However, because of the significant emissions of greenhouse gas and PM2.5 pollutants during power generation, the external cost of coal-fired power is estimated at 0.17 CNY/kWh on average, substantially higher than that of biomass power (0.06 CNY/kWh). Thus, the economic situations of biomass power reverse when environmental externalities are considered. Specially, wood residue-fired electricity has the lowest complete economic cost (0.48 CNY/kWh), approximately 2%-14% less than that of coal power. Therefore, a reasonable and comprehensive cost accounting mechanism is crucial for the development of the biomass power sector in China. Additionally, win-win policies could be developed to improve the environmental and economic performance of the country's power generation industry.

Realtime Hand-Object Interaction Using Learned Grasp Space for Virtual Environments.

We present a realtime virtual grasping algorithm to model interactions with virtual objects. Our approach is designed for multi-fingered hands and makes no assumptions about the motion of the user's hand or the virtual objects. Given a model of the virtual hand, we use machine learning and particle swarm optimization to automatically pre-compute stable grasp configurations for that object. The learning pre-computation step is accelerated using GPU parallelization. At runtime, we rely on the pre-computed stable grasp configurations, and dynamics/non-penetration constraints along with motion planning techniques to compute plausible looking grasps. In practice, our realtime algorithm can perform virtual grasping operations in less than 20ms for complex virtual objects, including high genus objects with holes. We have integrated our grasping algorithm with Oculus Rift HMD and Leap Motion controller and evaluated its performance for different tasks corresponding to grabbing virtual objects and placing them at arbitrary locations. Our user evaluation suggests that our virtual grasping algorithm can increase the user's realism and participation in these tasks and offers considerable benefits over prior interaction algorithms, such as pinch grasping and raycast picking.

Survival, growth performance and immune capacity of the juvenile lined seahorse Hippocampus erectus fed with rifampicin-treated copepods.

Gastrointestinal disease is one of the most serious diseases in cultured seahorse juveniles. Treatment with antimicrobials of live food (i.e. copepods and Artemia) that is used to feed the juveniles may be a promising measure to alleviate the occurrence of gastrointestinal disease. However, relevant investigations are rare. In the present study, we first investigated the antimicrobial efficacies on bacteria within copepods that were treated with 4 antimicrobials, including 3 antibiotics (i.e. enrofloxacin hydrochloride, oxytetracycline and rifampicin [RFP]) that are approved for use in aquaculture and 1 disinfectant (i.e. povidone iodine). We then assessed the effects of copepods treated with the antimicrobial that had the best antimicrobial efficacy on survival, growth performance and immune capacity of juvenile lined seahorses Hippocampus erectus. The results showed that RFP had the best antimicrobial efficacy on both Pseudoalteromonas spp. and Vibrio spp., 2 dominant bacteria with potential pathogenicity within the copepods; the proper concentration of RFP was 6 mg l-1. Moreover, H. erectus juveniles fed with RFP-treated copepods demonstrated an improved survivorship and immune capacity and had a lower abundance of pathogenic bacteria within their gastrointestinal tracts compared to juveniles fed with untreated copepods. These results suggest that treating live food with RFP is a potential measure for reducing the incidence of gastrointestinal disease in seahorse juveniles.

CMP­N­acetylneuraminic acid synthetase interacts with fragile X related protein 1.

Fragile X mental retardation protein (FMRP), fragile X related 1 protein (FXR1P) and FXR2P are the members of the FMR protein family. These proteins contain two KH domains and a RGG box, which are characteristic of RNA binding proteins. The absence of FMRP, causes fragile X syndrome (FXS), the leading cause of hereditary mental retardation. FXR1P is expressed throughout the body and important for normal muscle development, and its absence causes cardiac abnormality. To investigate the functions of FXR1P, a screen was performed to identify FXR1P­interacting proteins and determine the biological effect of the interaction. The current study identified CMP­N­acetylneuraminic acid synthetase (CMAS) as an interacting protein using the yeast two­hybrid system, and the interaction between FXR1P and CMAS was validated in yeast using a ß­galactosidase assay and growth studies with selective media. Furthermore, co­immunoprecipitation was used to analyze the FXR1P/CMAS association and immunofluorescence microscopy was performed to detect expression and intracellular localization of the proteins. The results of the current study indicated that FXR1P and CMAS interact, and colocalize in the cytoplasm and the nucleus of HEK293T and HeLa cells. Accordingly, a fragile X related 1 (FXR1) gene overexpression vector was constructed to investigate the effect of FXR1 overexpression on the level of monosialotetrahexosylganglioside 1 (GM1). The results of the current study suggested that FXR1P is a tissue­specific regulator of GM1 levels in SH­SY5Y cells, but not in HEK293T cells. Taken together, the results initially indicate that FXR1P interacts with CMAS, and that FXR1P may enhance the activation of sialic acid via interaction with CMAS, and increase GM1 levels to affect the development of the nervous system, thus providing evidence for further research into the pathogenesis of FXS.

A Probabilistic Associative Model for Segmenting Weakly-Supervised Images.

Weakly-supervised image segmentation is an important yet challenging task in image processing and pattern recognition fields. It is defined as: in the training stage, semantic labels are only at the image-level, without regard to their specific object/scene location within the image. Given a test image, the goal is to predict the semantics of every pixel/superpixel. In this paper, we propose a new weakly-supervised image segmentation model, focusing on learning the semantic associations between superpixel sets (graphlets in this work). In particular, we first extract graphlets from each image, where a graphlet is a small-sized graph measures the potential of multiple spatially neighboring superpixels (i.e., the probability of these superpixels sharing a common semantic label, such as the "sky" or the "sea"). To compare dierent-sized graphlets and to incorporate image-level labels, a manifold embedding algorithm is designed to transform all graphlets into equal-length feature vectors. Finally, we present a hierarchical Bayesian network (BN) to capture the semantic associations between post-embedding graphlets, based on which the semantics of each superpixel is inferred accordingly. Experimental results demonstrate that: 1) our approach performs competitively compared with the state-of-the-art approaches on three public data sets, and 2) considerable performance enhancement is achieved when using our approach on segmentation-based photo cropping and image categorization.

Bcl-2-associated transcription factor 1 interacts with fragile X-related protein 1.

The absence of fragile X mental retardation protein (FMRP) causes fragile X syndrome (FXS), which is the leading cause of hereditary mental retardation. Fragile X-related protein 1 (FXR1P), which plays an important role in normal muscle development, is one of the two autosomal paralogs of FMRP. To understand the functions of FXR1P, we screened FXR1P-interacting proteins by using a yeast two-hybrid system. The fragile X-related gene 1 (FXR1) was fused to pGBKT7 and then used as the bait to screen the human fetal brain cDNA library. The screening results revealed 10 FXR1P-interacting proteins including Bcl-2-associated transcription factor 1 (BTF). The interaction between FXR1P and BTF was confirmed by using both ß-galactosidase assay and growth test in selective media. Co-immunoprecipitation assay in mammalian cells was also carried out to confirm the FXR1P/BTF interaction. Moreover, we confirmed that BTF co-localized with FXR1P in the cytoplasm around the nucleus in rat vascular smooth muscle cells by using confocal fluorescence microscopy. These results provide clues to elucidate the relationship between FXR1P and FXS.