Browsing by Author "Telea, Alexandru C."

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    Deep Learning Inverse Multidimensional Projections
    (The Eurographics Association, 2019) Espadoto, Mateus; Rodrigues, Francisco Caio Maia; Hirata, Nina S. T.; Hirata Jr., Roberto; Telea, Alexandru C.; Landesberger, Tatiana von and Turkay, Cagatay
    We present a new method for computing inverse projections from 2D spaces to arbitrary high-dimensional spaces. Given any projection technique, we train a deep neural network to learn a low-to-high dimensional mapping based on a projected training set, and next use this mapping to infer the mapping on arbitrary points. We compare our method with two recent inverse projection techniques on three datasets, and show that our method has similar or higher accuracy, is one to two orders of magnitude faster, and delivers result that match well known ground-truth information about the respective high-dimensional data. Visual analytics Unsupervised learning Dimensionality reduction and manifold learning.
  • Thumbnail Image
    Item
    Guided Stable Dynamic Projections
    (The Eurographics Association and John Wiley & Sons Ltd., 2021) Vernier, Eduardo Faccin; Comba, João L. D.; Telea, Alexandru C.; Borgo, Rita and Marai, G. Elisabeta and Landesberger, Tatiana von
    Projections aim to convey the relationships and similarity of high-dimensional data in a low-dimensional representation. Most such techniques are designed for static data. When used for time-dependent data, they usually fail to create a stable and suitable low dimensional representation. We propose two dynamic projection methods (PCD-tSNE and LD-tSNE) that use global guides to steer projection points. This avoids unstable movement that does not encode data dynamics while keeping t-SNE's neighborhood preservation ability. PCD-tSNE scores a good balance between stability, neighborhood preservation, and distance preservation, while LD-tSNE allows creating stable and customizable projections. We compare our methods to 11 other techniques using quality metrics and datasets provided by a recent benchmark for dynamic projections.
  • Thumbnail Image
    Item
    HyperNP: Interactive Visual Exploration of Multidimensional Projection Hyperparameters
    (The Eurographics Association and John Wiley & Sons Ltd., 2022) Appleby, Gabriel; Espadoto, Mateus; Chen, Rui; Goree, Samuel; Telea, Alexandru C.; Anderson, Erik W.; Chang, Remco; Borgo, Rita; Marai, G. Elisabeta; Schreck, Tobias
    Projection algorithms such as t-SNE or UMAP are useful for the visualization of high dimensional data, but depend on hyperparameters which must be tuned carefully. Unfortunately, iteratively recomputing projections to find the optimal hyperparameter values is computationally intensive and unintuitive due to the stochastic nature of such methods. In this paper we propose HyperNP, a scalable method that allows for real-time interactive hyperparameter exploration of projection methods by training neural network approximations. A HyperNP model can be trained on a fraction of the total data instances and hyperparameter configurations that one would like to investigate and can compute projections for new data and hyperparameters at interactive speeds. HyperNP models are compact in size and fast to compute, thus allowing them to be embedded in lightweight visualization systems. We evaluate the performance of HyperNP across three datasets in terms of performance and speed. The results suggest that HyperNP models are accurate, scalable, interactive, and appropriate for use in real-world settings.
  • Thumbnail Image
    Item
    Quantitative Evaluation of Time-Dependent Multidimensional Projection Techniques
    (The Eurographics Association and John Wiley & Sons Ltd., 2020) Vernier, Eduardo Faccin; Garcia, Rafael; Silva, Iron Prando da; Comba, João L. D.; Telea, Alexandru C.; Viola, Ivan and Gleicher, Michael and Landesberger von Antburg, Tatiana
    Dimensionality reduction methods are an essential tool for multidimensional data analysis, and many interesting processes can be studied as time-dependent multivariate datasets. There are, however, few studies and proposals that leverage on the concise power of expression of projections in the context of dynamic/temporal data. In this paper, we aim at providing an approach to assess projection techniques for dynamic data and understand the relationship between visual quality and stability. Our approach relies on an experimental setup that consists of existing techniques designed for time-dependent data and new variations of static methods. To support the evaluation of these techniques, we provide a collection of datasets that has a wide variety of traits that encode dynamic patterns, as well as a set of spatial and temporal stability metrics that assess the quality of the layouts. We present an evaluation of 9 methods, 10 datasets, and 12 quality metrics, and elect the best-suited methods for projecting time-dependent multivariate data, exploring the design choices and characteristics of each method. Additional results can be found in the online benchmark repository. We designed our evaluation pipeline and benchmark specifically to be a live resource, open to all researchers who can further add their favorite datasets and techniques at any point in the future.
  • Thumbnail Image
    Item
    Selecting and Sharing Multidimensional Projection Algorithms: A Practical View
    (The Eurographics Association, 2020) Espadoto, Mateus; Vernier, Eduardo Faccin; Telea, Alexandru C.; Gillmann, Christina and Krone, Michael and Reina, Guido and Wischgoll, Thomas
    Multidimensional Projection techniques are often used by data analysts for exploring multivariate datasets, but the task of selecting the best technique for the job is not trivial, as there are many candidates and the reasons for picking one over another are usually unclear. On the other hand, researchers developing new techniques can have a hard time comparing their new technique to existing ones and sharing their code in a way that makes it readily available for the public. In this paper, we try to address those issues systematically by analyzing recent surveys in the area, identifying the methods and tools used, and discussing challenges, limitations, and ideas for further work.
  • Thumbnail Image
    Item
    Turbulent Details Simulation for SPH Fluids via Vorticity Refinement
    (© 2021 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd, 2021) Liu, Sinuo; Wang, Xiaokun; Ban, Xiaojuan; Xu, Yanrui; Zhou, Jing; Kosinka, Jiří; Telea, Alexandru C.; Benes, Bedrich and Hauser, Helwig
    A major issue in smoothed particle hydrodynamics (SPH) approaches is the numerical dissipation during the projection process, especially under coarse discretizations. High‐frequency details, such as turbulence and vortices, are smoothed out, leading to unrealistic results. To address this issue, we introduce a vorticity refinement (VR) solver for SPH fluids with negligible computational overhead. In this method, the numerical dissipation of the vorticity field is recovered by the difference between the theoretical and the actual vorticity, so as to enhance turbulence details. Instead of solving the Biot‐Savart integrals, a stream function, which is easier and more efficient to solve, is used to relate the vorticity field to the velocity field. We obtain turbulence effects of different intensity levels by changing an adjustable parameter. Since the vorticity field is enhanced according to the curl field, our method can not only amplify existing vortices, but also capture additional turbulence. Our VR solver is straightforward to implement and can be easily integrated into existing SPH methods.