Visual Informatics最新文献

Composite index is always derived with the weighted aggregation of hierarchical components, which is widely utilized to distill intricate and multidimensional matters in economic and business statistics. However, the composite indices always present inevitable anomalies at different levels oriented from the calculation and expression processes of hierarchical components, thereby impairing the precise depiction of specific economic issues. In this paper, we propose VisCI, a visualization framework for anomaly detection and interactive optimization of composite index. First, LSTM-AE model is performed to detect anomalies from the lower level to the higher level of the composite index. Then, a comprehensive array of visual cues is designed to visualize anomalies, such as hierarchy and anomaly visualization. In addition, an interactive operation is provided to ensure accurate and efficient index optimization, mitigating the adverse impact of anomalies on index calculation and representation. Finally, we implement a visualization framework with interactive interfaces, facilitating both anomaly detection and intuitive composite index optimization. Case studies based on real-world datasets and expert interviews are conducted to demonstrate the effectiveness of our VisCI in commodity index anomaly exploration and anomaly optimization.

Creating realistic materials is essential in the construction of immersive virtual environments. While existing techniques for material capture and conditional generation rely on flash-lit photos, they often produce artifacts when the illumination mismatches the training data. In this study, we introduce DiffMat, a novel diffusion model that integrates the CLIP image encoder and a multi-layer, cross-attention denoising backbone to generate latent materials from images under various illuminations. Using a pre-trained StyleGAN-based material generator, our method converts these latent materials into high-resolution SVBRDF textures, a process that enables a seamless fit into the standard physically based rendering pipeline, reducing the requirements for vast computational resources and expansive datasets. DiffMat surpasses existing generative methods in terms of material quality and variety, and shows adaptability to a broader spectrum of lighting conditions in reference images.

To help determine in what ways virtual reality (VR) technologies may benefit reservoir engineering workflows, we conducted a usability study on a prototype VR tool for performing reservoir model analysis tasks. By leveraging the strengths of VR technologies, this tool’s aim is to help advance reservoir analysis workflows beyond conventional methods by improving how one understands, analyzes, and interacts with reservoir model visualizations. To evaluate our tool’s VR approach to this, the study presented herein was conducted with reservoir engineering experts who used the VR tool to perform three common reservoir model analysis tasks: the spatial filtering of model cells using movable planes, the cross-comparison of multiple models, and well path planning. Our study found that accomplishing these tasks with the VR tool was generally regarded as easier, quicker, more effective, and more intuitive than traditional model analysis software while maintaining a feeling of low task workload on average. Overall, participants provided positive feedback regarding their experience with using VR to perform reservoir engineering work tasks, and in general, it was found to improve multi-model cross-analysis and rough object manipulation in 3D. This indicates the potential for VR to be better than conventional means for some work tasks and participants also expressed they could see it best utilized as an addition to current software in their reservoir model analysis workflows. There were, however, some concerns voiced when considering the full adoption of VR into their work that would be best first addressed before this took place.

Malicious webshells currently present tremendous threats to cloud security. Most relevant studies and open webshell datasets consider malicious webshell defense as a binary classification problem, that is, identifying whether a webshell is malicious or benign. However, a fine-grained multi-classification is urgently needed to enable precise responses and active defenses on malicious webshell threats. This paper introduces a malicious webshell family dataset named MWF to facilitate webshell multi-classification researches. This dataset contains 1359 malicious webshell samples originally obtained from the cloud servers of Alibaba Cloud. Each of them is provided with a family label. The samples of the same family generally present similar characteristics or behaviors. The dataset has a total of 78 families and 22 outliers. Moreover, this paper introduces the human–machine collaboration process that is adopted to remove benign or duplicate samples, address privacy issues, and determine the family of each sample. This paper also compares the distinguished features of the MWF dataset with previous datasets and summarizes the potential applied areas in cloud security and generalized sequence, graph, and tree data analytics and visualization.

Traffic congestion is becoming increasingly severe as a result of urbanization, which not only impedes people’s ability to travel but also hinders the economic development of cities. Modeling the correlation between congestion and its influencing factors using machine learning methods makes it possible to quickly identify congested road segments. Due to the intrinsic black-box character of machine learning models, it is difficult for experts to trust the decision results of road congestion prediction models and understand the significance of congestion-causing factors. In this paper, we present a model interpretability method to investigate the potential causes of traffic congestion and quantify the importance of various influencing factors using the SHAP method. Due to the multidimensionality of these factors, it can be challenging to visually represent the impact of all factors. In response, we propose TCEVis, an interactive visual analytics system that enables multi-level exploration of road conditions. Through three case studies utilizing actual data, we demonstrate that the TCEVis system offers advantages for assisting traffic managers in analyzing the causes of traffic congestion and elucidating the significance of various influencing factors.

Medical image generation has recently garnered significant interest among researchers. However, the primary generative models, such as Generative Adversarial Networks (GANs), often encounter challenges during training, including mode collapse. To address these issues, we proposed the AE-COT-GAN model (Autoencoder-based Conditional Optimal Transport Generative Adversarial Network) for the generation of medical images belonging to specific categories. The training process of our model comprises three fundamental components. The training process of our model encompasses three fundamental components. First, we employ an autoencoder model to obtain a low-dimensional manifold representation of real images. Second, we apply extended semi-discrete optimal transport to map Gaussian noise distribution to the latent space distribution and obtain corresponding labels effectively. This procedure leads to the generation of new latent codes with known labels. Finally, we integrate a GAN to train the decoder further to generate medical images. To evaluate the performance of the AE-COT-GAN model, we conducted experiments on two medical image datasets, namely DermaMNIST and BloodMNIST. The model’s performance was compared with state-of-the-art generative models. Results show that the AE-COT-GAN model had excellent performance in generating medical images. Moreover, it effectively addressed the common issues associated with traditional GANs.

This paper presents a survey on automatic or semi-automatic recommendation systems that help users create dashboards. It starts by showing the important role that dashboards play in data science, and give an informal definition of dashboards, i.e., a set of visualizations possibly with linkage, a screen layout and user feedback. We are mainly interested in systems that use a fully or partially automatic mechanism to recommend dashboards to users. This automation includes the suggestion of data and visualizations, the optimization of the layout and the use of user feedback. We position our work with respect to existing surveys. Starting from a set of over 1000 papers, we have selected and analyzed 19 papers/systems along several dimensions. The main dimensions were the set of considered visualizations, the suggestion method, the utility/objective functions, the layout, and the user interface. We conclude by highlighting the main achievements in this domain and by proposing perspectives.

Data have become valuable assets for enterprises. Data governance aims to manage and reuse data assets, facilitating enterprise management and enabling product innovations. A data lineage graph (DLG) is an abstracted collection of data assets and their data lineages in data governance. Analyzing DLGs can provide rich data insights for data governance. However, the progress of data governance technologies is hindered by the shortage of available open datasets for DLGs. This paper introduces an open dataset of DLGs, including the DLG model, the dataset construction process, and applied areas. This real-world dataset is sourced from Huawei Cloud Computing Technology Company Limited, which contains 18 DLGs with three types of data assets and two types of relations. To the best of our knowledge, this dataset is the first open dataset of DLGs for data governance. This dataset can also support the development of other application areas, such as graph analytics and visualization.

As computer graphics technology supports pursuing a photorealistic style, replicated artworks with a photorealistic style overwhelmingly predominate in the computer-generated art circle. Along with the progression of generative technology, this trend may make generative art a virtual world of photorealistic fake, in which the single criterion of expressive style imperils art into the context of a single boring stereotype. This article focuses on the issue of style diversity and its technical feasibility by artistic experiments of generating flower images in StyleGAN. The author insisted that photo both technology and artistic style should not be confined merely for realistic purposes. This proposition was validated in the GAN generation experiment by changing the training materials.

Mixed reality offers a larger visualization space and more intuitive means of interaction for data exploration, and many works have been dedicated to combining 2D visualizations on screen with mixe reality. However, for each combination, we need to customize the implementation of the corresponding mixed reality 3D visualization. It is a challenge to simplify this development process and enable agile building of mixed reality 3D visualizations for 2D visualizations. In addition, many existing 2D visualizations do not provide interfaces oriented to immersive analytics, so how to extend the mixed reality 3D space from existing 2D visualizations is another challenge. This work presents an agile and flexible approach to interactively transfer visualizations from 2D screens to mixed reality 3D spaces. We designed an interactive process for spatial generation of mixed-reality 3D visualizations, defined a unified data transfer framework, integrated data deconstruction techniques for 2D visualizations, implemented interfaces to immersive visualization building tool-kits, and encapsulated these techniques into a tool named X-Space. We validated that the approach is feasible and effective through 2D visualization cases including scatter plots, stacked bar charts, and adjacency matrix. Finally, we conducted expert interviews to discuss the usability and value of the method.