Local Prediction Models for Spatiotemporal Volume Visualization

Tkachev, Gleb; Frey, Steffen; Ertl, Thomas

doi:10.1109/tvcg.2019.2961893

Cited by 23 publications

(24 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we also apply neural networks to support flow visualization but use them to generate visual features that guide the analysis. Tkachev et al (2019) trained neural networks on spatiotemporal volumes to detect irregular behavior. We use a similar idea for our anomaly detection in this work, but we apply our model to time series of extracted droplet quantities.…”

Section: Related Workmentioning

confidence: 99%

“…Also, we train a regression model to capture typical temporal patterns in droplets' quantities and then compute the deviations from this model to guide the researcher to anomalous cases in the sense of being uncommon. Akin to previous work (Tkachev et al 2019), we chose artificial neural networks (ANNs) due to their generality, performance efficiency on large data (compared to, e.g., non-parametric models), and their successful applications across many diverse tasks (Sect. 3.4).…”

Section: Preprocessing: Extraction Clustering and Anomaly Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Visual analysis of droplet dynamics in large-scale multiphase spray simulations

Heinemann

Frey

Tkachev

et al. 2021

J Vis

Self Cite

View full text Add to dashboard Cite

We present a data-driven visual analysis approach for the in-depth exploration of large numbers of droplets. Understanding droplet dynamics in sprays is of interest across many scientific fields for both simulation scientists and engineers. In this paper, we analyze large-scale direct numerical simulation datasets of the two-phase flow of non-Newtonian jets. Our interactive visual analysis approach comprises various dedicated exploration modalities that are supplemented by directly linking to ParaView. This hybrid setup supports a detailed investigation of droplets, both in the spatial domain and in terms of physical quantities . Considering a large variety of extracted physical quantities for each droplet enables investigating different aspects of interest in our data. To get an overview of different types of characteristic behaviors, we cluster massive numbers of droplets to analyze different types of occurring behaviors via domain-specific pre-aggregation, as well as different methods and parameters. Extraordinary temporal patterns are of high interest, especially to investigate edge cases and detect potential simulation issues. For this, we use a neural network-based approach to predict the development of these physical quantities and identify irregularly advected droplets. Graphic Abstract

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Preprocessing: Extraction Clustering and Anomaly Detectionmentioning

confidence: 99%

Visual analysis of droplet dynamics in large-scale multiphase spray simulations

Heinemann

Frey

Tkachev

et al. 2021

J Vis

Self Cite

View full text Add to dashboard Cite

show abstract

“…Han et al (2021) designed a GAN to enable exploration of multivariate time-varying data in variable selection and translation analysis. Tkachev et al (2021) introduced a prediction model for spatiotemporal volume data, which can facilitate irregular process detection and time step selection. These works incorporate deep learning effectively into the visual analytics workflow of volume data.…”

Section: Deep Learning For Volume Visualizationmentioning

confidence: 99%

IsoExplorer: an isosurface-driven framework for 3D shape analysis of biomedical volume data

Dai

Tao

et al. 2021

J Vis

View full text Add to dashboard Cite

“…To detect and to visualize the complex behavior in spatiotemporal volumes, a machine learning algorithm has been proposed in [ 41 ]. The algorithm detects the spatiotemporal regions of various complexities by training several models.…”

Section: Related Workmentioning

confidence: 99%

Communication-Efficient Tracking of Unknown, Spatially Correlated Signals in Ad-Hoc Wireless Sensor Networks: Two Machine Learning Approaches

Alasti

2021

Sensors

View full text Add to dashboard Cite

A low-cost machine learning (ML) algorithm is proposed and discussed for spatial tracking of unknown, correlated signals in localized, ad-hoc wireless sensor networks. Each sensor is modeled as one neuron and a selected subset of these neurons are called to identify the spatial signal. The algorithm is implemented in two phases of spatial modeling and spatial tracking. The spatial signal is modeled using its M iso-contour lines at levels {ℓj}j=1M and those sensors that their sensor observations are in Δ margin of any of these levels report their sensor observations to the fusion center (FC) for spatial signal reconstruction. In spatial modeling phase, the number of these contour lines, their levels and a proper Δ are identified. In this phase, the algorithm may either use adaptive-weight stochastic gradient or scaled stochastic gradient method to select a proper Δ. Additive white Gaussian noise (AWGN) with zero mean is assumed along with the sensor observations. To reduce the observation noise’s effect, each sensor applies moving average filter on its observation to drastically reduce the effect of noise. The modeling performance, the cost and the convergence of the algorithm are discussed based on extensive computer simulations and reasoning. The algorithm is proposed for climate and environmental monitoring. In this paper, the percentage of wireless sensors that initiate a communication attempt is assumed as cost. The performance evaluation results show that the proposed spatial tracking approach is low-cost and can model the spatial signal over time with the same performance as that of spatial modeling.

show abstract

Local Prediction Models for Spatiotemporal Volume Visualization

Cited by 23 publications

References 35 publications

Visual analysis of droplet dynamics in large-scale multiphase spray simulations

Visual analysis of droplet dynamics in large-scale multiphase spray simulations

IsoExplorer: an isosurface-driven framework for 3D shape analysis of biomedical volume data

Communication-Efficient Tracking of Unknown, Spatially Correlated Signals in Ad-Hoc Wireless Sensor Networks: Two Machine Learning Approaches

Contact Info

Product

Resources

About