SCIENTIFIC COMPUTING AND IMAGING INSTITUTE
at the University of Utah

An internationally recognized leader in visualization, scientific computing, and image analysis

SCI Publications

2022


T. Nguyen, R.G. Baraniuk, R.M. Kirby, S.J. Osher, B. Wang. “Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization,” Subtitled “arXiv preprint arXiv:2208.00579,” 2022.

ABSTRACT

Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear attention and hashing tricks; efficient transformers have been proposed to reduce the quadratic complexity of transformers but significantly degrade the accuracy. In response, we first interpret the linear attention and residual connections in computing the attention map as gradient descent steps. We then introduce momentum into these components and propose the \emphmomentum transformer, which utilizes momentum to improve the accuracy of linear transformers while maintaining linear memory and computational complexities. Furthermore, we develop an adaptive strategy to compute the momentum value for our model based on the optimal momentum for quadratic optimization. This adaptive momentum eliminates the need to search for the optimal momentum value and further enhances the performance of the momentum transformer. A range of experiments on both autoregressive and non-autoregressive tasks, including image generation and machine translation, demonstrate that the momentum transformer outperforms popular linear transformers in training efficiency and accuracy.



C. A. Nizinski, C. Ly, C. Vachet, A. Hagen, T. Tasdizen, L. W. McDonald. “Characterization of uncertainties and model generalizability for convolutional neural network predictions of uranium ore concentrate morphology,” In Chemometrics and Intelligent Laboratory Systems, Vol. 225, Elsevier, pp. 104556. 2022.
ISSN: 0169-7439
DOI: https://doi.org/10.1016/j.chemolab.2022.104556

ABSTRACT

As the capabilities of convolutional neural networks (CNNs) for image classification tasks have advanced, interest in applying deep learning techniques for determining the natural and anthropogenic origins of uranium ore concentrates (UOCs) and other unknown nuclear materials by their surface morphology characteristics has grown. But before CNNs can join the nuclear forensics toolbox along more traditional analytical techniques – such as scanning electron microscopy (SEM), X-ray diffractometry, mass spectrometry, radiation counting, and any number of spectroscopic methods – a deeper understanding of “black box” image classification will be required. This paper explores uncertainty quantification for convolutional neural networks and their ability to generalize to out-of-distribution (OOD) image data sets. For prediction uncertainty, Monte Carlo (MC) dropout and random image crops as variational inference techniques are implemented and characterized. Convolutional neural networks and classifiers using image features from unsupervised vector-quantized variational autoencoders (VQ-VAE) are trained using SEM images of pure, unaged, unmixed uranium ore concentrates considered “unperturbed.” OOD data sets are developed containing perturbations from the training data with respect to the chemical and physical properties of the UOCs or data collection parameters; predictions made on the perturbation sets identify where significant shortcomings exist in the current training data and techniques used to develop models for classifying uranium process history, and provides valuable insights into how datasets and classification models can be improved for better generalizability to out-of-distribution examples.



D. K. Njeru, T. M. Athawale, J. J. France, C. R. Johnson. “Quantifying and Visualizing Uncertainty for Source Localisation in Electrocardiographic Imaging,” In Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, Taylor & Francis, pp. 1--11. 2022.
DOI: 10.1080/21681163.2022.2113824

ABSTRACT

Electrocardiographic imaging (ECGI) presents a clinical opportunity to noninvasively understand the sources of arrhythmias for individual patients. To help increase the effectiveness of ECGI, we provide new ways to visualise associated measurement and modelling errors. In this paper, we study source localisation uncertainty in two steps: First, we perform Monte Carlo simulations of a simple inverse ECGI source localisation model with error sampling to understand the variations in ECGI solutions. Second, we present multiple visualisation techniques, including confidence maps, level-sets, and topology-based visualisations, to better understand uncertainty in source localization. Our approach offers a new way to study uncertainty in the ECGI pipeline.



P. Olaya, J. Luettgau, N. Zhou, J. Lofstead, G. Scorzelli, V. Pascucci, M. Taufer. “NSDF-FUSE: A Testbed for Studying Object Storage via FUSE File Systems,” In Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing, Association for Computing Machinery, pp. 277–278. 2022.
ISBN: 9781450391993
DOI: 10.1145/3502181.3533709

ABSTRACT

This work presents NSDF-FUSE, a testbed for evaluating settings and performance of FUSE-based file systems on top of S3-compatible object storage; the testbed is part of a suite of services from the National Science Data Fabric (NSDF) project (an NSF-funded project that is delivering cyberinfrastructures for data scientists). We demonstrate how NSDF-FUSE can be deployed to evaluate eight different mapping packages that mount S3-compatible object storage to a file system, as well as six data patterns representing different I/O operations on two cloud platforms. NSDF-FUSE is open-source and can be easily extended to run with other software mapping packages and different cloud platforms.



B.A. Orkild, J.A. Bergquist, L.C. Rupp, A. Busatto, B. Zenger, W.W. Good, J. Coll-Font, R.S. MacLeod. “A Sliding Window Approach to Regularization in Electrocardiographic Imaging,” In Computing in Cardiology, Vol. 49, 2022.

ABSTRACT

Introduction: The inverse problem of ECGI is ill-posed, so regularization must be applied to constrain the solution. Regularization is typically applied to each individual time point (instantaneous) or to the beat as a whole (global). These techniques often lead to over- or underregularization. We aimed to develop an inverse formulation that strikes a balance between these two approaches that would realize the benefits of both by implementing a sliding-window regularization. Methods: We formulated sliding-window regularization using the boundary element method with Tikhonov 0 and 2nd order regularization. We applied regularization to a varying time window of the body-surface potentials centered around each time sample. We compared reconstructed potentials from the sliding-window, instantaneous, and global regularization techniques to ground truth potentials for 10 heart beats paced from the ventricle in a large-animal model. Results: The sliding-window technique provided smoother transitions of regularization weights than instantaneous regularization while improving spatial correlation over global regularization. Discussion: Although the differences in regularization weights were nuanced, smoother transitions provided by the sliding-window regularization have the ability to eliminate discontinuities in potential seen with instantaneous regularization.



T.A.J. Ouermi, R.M. Kirby, M. Berzins. “ENO-Based High-Order Data-Bounded and Constrained Positivity-Preserving Interpolation,” Subtitled “https://arxiv.org/abs/2204.06168,” In Numerical Algorithms, 2022.

ABSTRACT

A number of key scientific computing applications that are based upon tensor-product grid constructions, such as numerical weather prediction (NWP) and combustion simulations, require property-preserving interpolation. Essentially Non-Oscillatory (ENO) interpolation is a classic example of such interpolation schemes. In the aforementioned application areas, property preservation often manifests itself as a requirement for either data boundedness or positivity preservation. For example, in NWP, one may have to interpolate between the grid on which the dynamics is calculated to a grid on which the physics is calculated (and back). Interpolating density or other key physical quantities without accounting for property preservation may lead to negative values that are nonphysical and result in inaccurate representations and/or interpretations of the physical data. Property-preserving interpolation is straightforward when used in the context of low-order numerical simulation methods. High-order property-preserving interpolation is, however, nontrivial, especially in the case where the interpolation points are not equispaced. In this paper, we demonstrate that it is possible to construct high-order interpolation methods that ensure either data boundedness or constrained positivity preservation. A novel feature of the algorithm is that the positivity-preserving interpolant is constrained; that is, the amount by which it exceeds the data values may be strictly controlled. The algorithm we have developed comes with theoretical estimates that provide sufficient conditions for data boundedness and constrained positivity preservation. We demonstrate the application of our algorithm on a collection of 1D and 2D numerical examples, and show that in all cases property preservation is respected.



Timbwaoga Aime Judicael (TAJO) Ouermi. “Accelerating Physics Schemes in Numerical Weather Prediction Codes and Preserving Positivity in the Physics-Dynamics coupling,” University of Utah, 2022.



E. Paccione, B. Hunt, E. Kwan, D. Dosdall, R. MacLeod, R. Ranjan. “Unipolar R:S Development in Chronic Atrial Fibrillation,” In Computing in Cardiology, Vol. 49, 2022.

ABSTRACT

Past studies have examined the differences between R and S waves of unipolar atrial signals in patients with atrial fibrillation (AF) and have shown a difference in the R to S ratio (R:S) in certain regions of the atria compared to a healthy population. This work indicates a potential use of R:S as a marker for AF. In this study, we further examine these claims and investigate temporal changes in R:S over AF development in animals.

Four canines underwent AF development protocols and endocardial sinus rhythm maps were recorded as AF progressed. Unipolar signals gathered from mapping were used to calculate R:S within the left atrium of each animal. Calculations were performed at time points: before AF initiation, 3-4 months of chronic AF, and 6 months of chronic AF. From our analysis, we observed an increase in R-dominant signals within the left atrium once AF is induced. Temporal results show that R dominance may be an indicator for chronic AF patients and may be associated with the presence of arrhythmogenic substrate. With the addition of regional information, this unipolar signal analysis could guide therapeutic strategies.



M. Parashar. “Advancing Reproducibility in Parallel and Distributed Systems Research,” In Computer, Vol. 55, No. 5, pp. 4--5. 2022.
DOI: 10.1109/MC.2022.3158156

ABSTRACT

This installment of Computer’s series highlighting the work published in IEEE Computer Society journals comes from IEEE Transactions on Parallel and Distributed Systems.



M. Parashar, A. Friedlander, E. Gianchandani,, M. Martonosi. “Transforming science through cyberinfrastructure,” In Communications of the ACM, Vol. 65, No. 8, pp. 30–32. 2022.

ABSTRACT

NSF's vision for the U.S. cyberinfrastructure ecosystem for science and engineering in the 21st century.



M. Parashar, M.A. Heroux, V. Stodde. “Research Reproducibility,” In Computer, Vol. 55, No. 8, IEEE, pp. 16--18. August, 2022.

ABSTRACT

Reproducibility has a foundational role in ensuring robust and trustworthy research, but achieving reproducibility can be challenging. This theme issue explores these challenges along with research and implementations across communities addressing them, with the goal of understanding the impact of existing solutions and synthesizing lessons learned and emerging best practices.



M. Parashar. “Democratizing Science Through Advanced Cyberinfrastructure,” In Computer, IEEE, 2022.

ABSTRACT

Democratizing access to cyberinfrastructure is essential to democratizing science. This article explores knowledge, technical, and social barriers to accessing and using cyberinfrastructure and explores approaches to addresses them. It also highlights recent activities and investments at the National Science Foundation that implement some of these approaches.



A.C. Peterson, R.J. Lisonbee, N. Krähenbühl, C.L. Saltzman, A. Barg, N. Khan, S. Elhabian, A.L. Lenz. “Multi-level multi-domain statistical shape model of the subtalar, talonavicular, and calcaneocuboid joints,” In Frontiers in Bioengineering and Biotechnology, 2022.
DOI: 10.3389/fbioe.2022.1056536

ABSTRACT

Traditionally, two-dimensional conventional radiographs have been the primary tool to measure the complex morphology of the foot and ankle. However, the subtalar, talonavicular, and calcaneocuboid joints are challenging to assess due to their bone morphology and locations within the ankle. Weightbearing computed tomography is a novel high-resolution volumetric imaging mechanism that allows detailed generation of 3D bone reconstructions. This study aimed to develop a multi-domain statistical shape model to assess morphologic and alignment variation of the subtalar, talonavicular, and calcaneocuboid joints across an asymptomatic population and calculate 3D joint measurements in a consistent weightbearing position. Specific joint measurements included joint space distance, congruence, and coverage. Noteworthy anatomical variation predominantly included the talus and calcaneus, specifically an inverse relationship regarding talar dome heightening and calcaneal shortening. While there was minimal navicular and cuboid shape variation, there were alignment variations within these joints; the most notable is the rotational aspect about the anterior-posterior axis. This study also found that multi-domain modeling may be able to predict joint space distance measurements within a population. Additionally, variation across a population of these four bones may be driven far more by morphology than by alignment variation based on all three joint measurements. These data are beneficial in furthering our understanding of joint-level morphology and alignment variants to guide advancements in ankle joint pathological care and operative treatments.



A. Quistberg, C.I. Gonzalez, P. Arbeláez, O.L. Sarmiento, L. Baldovino-Chiquillo, Q. Nguyen, T. Tasdizen, L.A.G. Garcia, D. Hidalgo, S.J. Mooney, A.V.D. Roux, G. Lovasi. “430 Training neural networks to identify built environment features for pedestrian safety,” In Injury Prevention, Vol. 28, No. 2, BMJ, pp. A65. 2022.
DOI: 10.1136/injuryprev-2022-safety2022.194

ABSTRACT

Background
We used panoramic images and neural networks to measure street-level built environment features with relevance to pedestrian safety.

Methods
Street-level features were identified from systematic literature search and local experience in Bogota, Colombia (study location). Google Street View© panoramic images were sampled from 10,810 intersection and street segment locations, including 2,642 where pedestrian collisions occurred 2015–2019; the most recent, nearest (<25 meters) available image was selected for each sampled intersection or segment. Human raters annotated image features which were used to train neural networks. Neural networks and human raters were compared across all features using mean Average Recall (mAR) and mean Average Precision (mAP) estimated performance. Feature prevalence was compared by pedestrian vs non-pedestrian collision locations.

Results
Thirty features were identified related to roadway (e.g., medians), crossing areas (e.g., crosswalk), traffic control (e.g., pedestrian signal), and roadside (e.g., trees) with streetlights the most frequently detected object (N=10,687 images). Neural networks achieved mAR=15.4 versus 25.4 for humans, and a mAP=16.0. Bus lanes, pedestrian signals, and pedestrian bridges were significantly more prevalent at pedestrian collision locations, whereas speed bumps, school zones, sidewalks, trees, potholes and streetlights were significantly more prevalent at non-pedestrian collision locations.

Conclusion
Neural networks have substantial potential to obtain timely, accurate built environment data crucial to improve road safety. Training images need to be well-annotated to ensure accurate object detection and completeness.

Learning Outcomes
1) Describe how neural networks can be used for road safety research; 2) Describe challenges of using neural networks.



D. Reed, D. Gannon, J. Dongarra. “Reinventing High Performance Computing: Challenges and Opportunities,” Subtitled “UUSCI-2022-001,” University of Utah, 2022.

ABSTRACT

The world of computing is in rapid transition, now dominated by a world of smartphones and cloud services, with profound implications for the future of advanced scientific computing. Simply put, high-performance computing (HPC) is at an important inflection point. For the last 60 years, the world's fastest supercomputers were almost exclusively produced in the United States on behalf of scientific research in the national laboratories. Change is now in the wind. While costs now stretch the limits of U.S. government funding for advanced computing, Japan and China are now leaders in the bespoke HPC systems funded by government mandates. Meanwhile, the global semiconductor shortage and political battles surrounding fabrication facilities affect everyone. However, another, perhaps even deeper, fundamental change has occurred. The major cloud vendors have invested in global networks of massive scale systems that dwarf today's HPC systems. Driven by the computing demands of AI, these cloud systems are increasingly built using custom semiconductors, reducing the financial leverage of traditional computing vendors. These cloud systems are now breaking barriers in game playing and computer vision, reshaping how we think about the nature of scientific computation. Building the next generation of leading edge HPC systems will require rethinking many fundamentals and historical approaches by embracing end-to-end co-design; custom hardware configurations and packaging; large-scale prototyping, as was common thirty years ago; and collaborative partnerships with the dominant computing ecosystem companies, smartphone, and cloud computing vendors.



J.R. Reimer, F.R. Adler, K.M. Golden, A. Narayan. “Uncertainty quantification for ecological models with random parameters,” In Ecology Letters, Wiley, pp. 1--13. 2022.

ABSTRACT

There is often considerable uncertainty in parameters in ecological models. This uncertainty can be incorporated into models by treating parameters as random variables with distributions, rather than fixed quantities. Recent advances in uncertainty quantification methods, such as polynomial chaos approaches, allow for the analysis of models with random parameters. We introduce these methods with a motivating case study of sea ice algal blooms in heterogeneous environments. We compare Monte Carlo methods with polynomial chaos techniques to help understand the dynamics of an algal bloom model with random parameters. Modelling key parameters in the algal bloom model as random variables changes the timing, intensity and overall productivity of the modelled bloom. The computational efficiency of polynomial chaos methods provides a promising avenue for the broader inclusion of parametric uncertainty in ecological models, leading to improved model predictions and synthesis between models and data.



L.C. Rupp, B. Zenger, J.A. Bergquist, A. Busatto, R.S. MacLeod. “The Role of Beta-1 Receptors in the Response to Myocardial Ischemia,” In Computing in Cardiology, Vol. 49, 2022.

ABSTRACT

Acute myocardial ischemia is commonly diagnosed by ST-segment deviations. These deviations, however, can show a paradoxical recovery even in the face of ongoing ischemic stress. A possible mechanism for this response may be the cardio-protective effects of the autonomic nervous system (ANS) via beta-1 receptors. We assessed the role of norepinephrine (NE), a beta-1 agonist, and esmolol (ES), a beta-1 antagonist, in the recovery of ST-segment deviations during myocardial ischemia. We used an experimental model of controlled myocardial ischemia in which we simultaneously recorded electrograms intramurally and on the epicardial surface. We measured ischemia as deviations in the potentials measured at 40% of the ST-segment duration. During control intervention, 27% of epicardial electrodes showed no ischemic ST-segment deviations, whereas during the interventions with NE and ES, 100% of epicardial electrodes showed no ischemic ST-segment deviations. Intramural electrodes revealed a different behavior with 71% of electrodes showing no ischemic ST-segment deviations during control ischemia, increasing to 79% and 82% for NE infusion and ES infusion interventions, respectively. These preliminary results suggest that recovery of intramural regions of the heart is delayed by the presence of both beta-1 agonists and antagonists even as epicardial potentials show almost complete recovery.



S. Saha, O, Choi, R. Whitaker. “Few-Shot Segmentation of Microscopy Images Using Gaussian Process,” In Medical Optical Imaging and Virtual Microscopy Image Analysis, Springer Nature Switzerland, pp. 94--104. 2022.
DOI: 10.1007/978-3-031-16961-8_10

ABSTRACT

Few-shot segmentation has received recent attention because of its promise to segment images containing novel classes based on a handful of annotated examples. Few-shot-based machine learning methods build generic and adaptable models that can quickly learn new tasks. This approach finds potential application in many scenarios that do not benefit from large repositories of labeled data, which strongly impacts the performance of the existing data-driven deep-learning algorithms. This paper presents a few-shot segmentation method for microscopy images that combines a neural-network architecture with a Gaussian-process (GP) regression. The GP regression is used in the latent space of an autoencoder-based segmentation model to learn the distribution of functions from the encoded image representations to the corresponding representation of the segmentation masks in the support set. This regression analysis serves as the prior for predicting the segmentation mask for the query image. The rich latent representation built by the GP using examples in the support set significantly impacts the performance of the segmentation model, demonstrated by extensive experimental evaluation.



S. Sane, C. R. Johnson, H. Childs. “Demonstrating the viability of Lagrangian in situ reduction on supercomputers,” In Journal of Computational Science, Vol. 61, Elsevier, 2022.

ABSTRACT

Performing exploratory analysis and visualization of large-scale time-varying computational science applications is challenging due to inaccuracies that arise from under-resolved data. In recent years, Lagrangian representations of the vector field computed using in situ processing are being increasingly researched and have emerged as a potential solution to enable exploration. However, prior works have offered limited estimates of the encumbrance on the simulation code as they consider “theoretical” in situ environments. Further, the effectiveness of this approach varies based on the nature of the vector field, benefitting from an in-depth investigation for each application area. With this study, an extended version of Sane et al. (2021), we contribute an evaluation of Lagrangian analysis viability and efficacy for simulation codes executing at scale on a supercomputer. We investigated previously unexplored cosmology and seismology applications as well as conducted a performance benchmarking study by using a hydrodynamics mini-application targeting exascale computing. To inform encumbrance, we integrated in situ infrastructure with simulation codes, and evaluated Lagrangian in situ reduction in representative homogeneous and heterogeneous HPC environments. To inform post hoc accuracy, we conducted a statistical analysis across a range of spatiotemporal configurations as well as a qualitative evaluation. Additionally, our study contributes cost estimates for distributed-memory post hoc reconstruction. In all, we demonstrate viability for each application — data reduction to less than 1% of the total data via Lagrangian representations, while maintaining accurate reconstruction and requiring under 10% of total execution time in over 90% of our experiments.



S. Subramanian, R.M. Kirby, M.W. Mahoney, A. Gholami. “Adaptive Self-supervision Algorithms for Physics-informed Neural Networks ,” Subtitled “arXiv:2207.04084,” 2022.

ABSTRACT

Physics-informed neural networks (PINNs) incorporate physical knowledge from the problem domain as a soft constraint on the loss function, but recent work has shown that this can lead to optimization difficulties. Here, we study the impact of the location of the collocation points on the trainability of these models. We find that the vanilla PINN performance can be significantly boosted by adapting the location of the collocation points as training proceeds. Specifically, we propose a novel adaptive collocation scheme which progressively allocates more collocation points (without increasing their number) to areas where the model is making higher errors (based on the gradient of the loss function in the domain). This, coupled with a judicious restarting of the training during any optimization stalls (by simply resampling the collocation points in order to adjust the loss landscape) leads to better estimates for the prediction error. We present results for several problems, including a 2D Poisson and diffusion-advection system with different forcing functions. We find that training vanilla PINNs for these problems can result in up to 70% prediction error in the solution, especially in the regime of low collocation points. In contrast, our adaptive schemes can achieve up to an order of magnitude smaller error, with similar computational complexity as the baseline. Furthermore, we find that the adaptive methods consistently perform on-par or slightly better than vanilla PINN method, even for large collocation point regimes. The code for all the experiments has been open sourced.