SEARCH · Engineering Papers

Results for “Learning Algorithm”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 415 records · Page 23

All sources NASA NTRS DOE OSTI

DOE OSTI2019

FPGA-Accelerated Machine Learning Inference as a Service for Particle Physics Computing

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that potentially requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave by Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) ms with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600–700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2020

Distributed fiber sensor and machine learning data analytics for pipeline protection against extrinsic intrusions and intrinsic corrosions

This paper presents an integrated technical framework to protect pipelines against both malicious intrusions and piping degradation using a distributed fiber sensing technology and artificial intelligence. A distributed acoustic sensing (DAS) system based on phase-sensitive optical time-domain reflectometry (φ-OTDR) was used to detect acoustic wave propagation and scattering along pipeline structures consisting of straight piping and sharp bend elbow. Signal to noise ratio of the DAS system was enhanced by femtosecond induced artificial Rayleigh scattering centers. Data harnessed by the DAS system were analyzed by neural network-based machine learning algorithms. The system identified with over 85% accuracy in various external impact events, and over 94% accuracy for defect identification through supervised learning and 71% accuracy through unsupervised learning.

Peng, Zhaoqiang↗

DOE OSTI2019

FPGAs as a Service to Accelerate Machine Learning Inference [PowerPoint]

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC, and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave b y Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) milliseconds with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600--700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2021

Optimizing Mu2e Spill Regulation System Algorithms

A slow extraction system is being developed for the Fermilab’s Delivery Ring to deliver protons to the Mu2e experiment. During the extraction, the beam on target experiences small intensity variations owing to many factors. Various adaptive learning algorithms will be employed for beam regulation to achieve the required spill quality. We discuss here preliminary results of the slow and fast regulation algorithms validation through the computer simulations before their implementation in the FPGA. Particle tracking with sextupole resonance was used to determine the fine shape of the spill profile. Fast semi-analytical simulation schemes and Machine Learning models were used to optimize the fast regulation loop.

43 PARTICLE ACCELERATORS↗

DOE OSTI2020

A novel active optimization approach for rapid and efficient design space exploration using ensemble machine learning

In this work, a novel design optimization technique based on active learning, which involves dynamic exploration and exploitation of the design space of interest using an ensemble of machine learning algorithms, is presented. In this approach, a hybrid methodology incorporating an explorative weak learner (regularized basis function model) which fits high-level information about the response surface, and an exploitative strong learner (based on committee machine) that fits finer details around promising regions identified by the weak learner, is employed. For each design iteration, an aristocratic approach is used to select a set of nominees, where points that meet a threshold merit value as predicted by the weak learner are selected to be evaluated using expensive function evaluation. In addition to these points, the global optimum as predicted by the strong learner is also evaluated to enable rapid convergence to the actual global optimum once the most promising region has been identified by the optimizer. This methodology is first tested by applying it to the optimization of a two-dimensional multi-modal surface. The performance of the new active learning approach is compared with traditional global optimization methods, namely micro-genetic algorithm (pGA) and particle swarm optimization (PSO). It is demonstrated that the new optimizer is able to reach the global optimum much faster with a significantly fewer number of function evaluations. Subsequently, the new optimizer is also applied to a complex internal combustion (IC) engine combustion optimization case with nine control parameters related to fuel injection, initial thermodynamic conditions, and in-cylinder flow. It is again found that the new approach significantly lowers the number of function evaluations that are needed to reach the optimum design configuration (by up to 80%) when compared to particle swarm and genetic algorithm-based optimization techniques.

Machine learning, active learning, design optimiza↗

DOE OSTI2018

Flexible Learning-Free Segmentation and Reconstruction of Neural Volumes

Imaging is a dominant strategy for data collection in neuroscience, yielding stacks of images that often scale to gigabytes of data for a single experiment. Machine learning algorithms from computer vision can serve as a pair of virtual eyes that tirelessly processes these images, automatically detecting and identifying microstructures. Unlike learning methods, our Flexible Learning-free Reconstruction of Imaged Neural volumes (FLoRIN) pipeline exploits structure-specifc contextual clues and requires no training. This approach generalizes across diferent modalities, including serially-sectioned scanning electron microscopy (sSEM) of genetically labeled and contrast enhanced processes, spectral confocal refectance (SCoRe) microscopy, and high-energy synchrotron X-ray microtomography (μCT) of large tissue volumes. We deploy the FLoRIN pipeline on newly published and novel mouse datasets, demonstrating the high biological fdelity of the pipeline’s reconstructions. FLoRIN reconstructions are of sufcient quality for preliminary biological study, for example examining the distribution and morphology of cells or extracting single axons from functional data. Compared to existing supervised learning methods, FLoRIN is one to two orders of magnitude faster and produces high-quality reconstructions that are tolerant to noise and artifacts, as is shown qualitatively and quantitatively.

47 OTHER INSTRUMENTATION↗

DOE OSTI2018

Publisher Correction: Flexible Learning-Free Segmentation and Reconstruction of Neural Volumes

Imaging is a dominant strategy for data collection in neuroscience, yielding stacks of images that often scale to gigabytes of data for a single experiment. Machine learning algorithms from computer vision can serve as a pair of virtual eyes that tirelessly processes these images, automatically detecting and identifying microstructures. Unlike learning methods, our Flexible Learning-free Reconstruction of Imaged Neural volumes (FLoRIN) pipeline exploits structure-specific contextual clues and requires no training. This approach generalizes across different modalities, including serially-sectioned scanning electron microscopy (sSEM) of genetically labeled and contrast enhanced processes, spectral confocal reflectance (SCoRe) microscopy, and high-energy synchrotron X-ray microtomography (μCT) of large tissue volumes. We deploy the FLoRIN pipeline on newly published and novel mouse datasets, demonstrating the high biological fidelity of the pipeline’s reconstructions. FLoRIN reconstructions are of sufficient quality for preliminary biological study, for example examining the distribution and morphology of cells or extracting single axons from functional data. Compared to existing supervised learning methods, FLoRIN is one to two orders of magnitude faster and produces high-quality reconstructions that are tolerant to noise and artifacts, as is shown qualitatively and quantitatively.

Shahbazi, Ali↗

DOE OSTI2020

Ambient Synchrophasor Measurement Based System Inertia Estimation

This paper develops an algorithm to estimate the system inertia value based on ambient synchrophasor measurement. Informative features are extracted from ambient synchrophasor measurements for machine-learning-based inertia estimation. Besides ambient synchrophasor measurements of FNET/GridEye, other available data relevant to inertia (such as weather and system load data) are also used to improve the inertia estimation accuracy. Then a machine learning algorithm to estimate system inertia is developed. A test dataset including ambient synchrophasor data from FNET/GridEye measurements and the WECC system inertia data from NERC is used to evaluate the performance of the developed inertia estimation method. The average and maximum estimation errors of the developed inertia estimation method is lower than 5% and 10%, respectively. This accuracy is higher than reported accuracy values in existing literature.

CUI, YI↗

DOE OSTI2023

The Feasibility of Incorporating a 3D Velocity Model Into Earthquake Location Around Salt Lake City, UT Using a Physics Informed Neural Network

Earthquake location algorithms typically require travel time calculation. Doing this calculation in 3D, despite advances in algorithm efficiency and computational power, can still be prohibitively expensive in terms of resources and storage. Implementation of high-resolution 3D models in routine earthquake location would be a significant step forward in most of the world. Machine learning algorithms have potential to act as substitutes for travel time calculation algorithms or stored travel time tables. We investigate EikoNet - a physics informed neural network machine learning model that estimates travel times very quickly and comes with negligible memory-overhead. Specifically, we apply EikoNet to the Wasatch Fault Community Velocity Model (WFCVM), a highly detailed and complex 3D velocity model of the Salt Lake City, UT region. While routine locations in the area and studies of the 2020 Magna, UT earthquake sequence used a 1D velocity model, a 3D model may help better our understanding the structure of the major fault in the region. Our primary goal was to test the speed, memory requirements, and accuracy of EikoNet compared to a reference eikonal solver. We find that while the EikoNet is exceedingly fast and requires little memory overhead, achieving acceptable accuracy in estimated travel times is difficult and requires extensive computational resources.

58 GEOSCIENCES↗

DOE OSTI2013

Predicting diagnostic error in radiology via eye-tracking and image analytics: Preliminary investigation in mammography

Purpose: The primary aim of the present study was to test the feasibility of predicting diagnostic errors in mammography by merging radiologists’ gaze behavior and image characteristics. A secondary aim was to investigate group-based and personalized predictive models for radiologists of variable experience levels.Methods: The study was performed for the clinical task of assessing the likelihood of malignancy of mammographic masses. Eye-tracking data and diagnostic decisions for 40 cases were acquired from four Radiology residents and two breast imaging experts as part of an IRB-approved pilot study. Gaze behavior features were extracted from the eye-tracking data. Computer-generated and BIRADS images features were extracted from the images. Finally, machine learning algorithms were used to merge gaze and image features for predicting human error. Feature selection was thoroughly explored to determine the relative contribution of the various features. Group-based and personalized user modeling was also investigated.Results: Machine learning can be used to predict diagnostic error by merging gaze behavior characteristics from the radiologist and textural characteristics from the image under review. Leveraging data collected from multiple readers produced a reasonable group model [area under the ROC curve (AUC) = 0.792 ± 0.030]. Personalized user modeling was far more accurate for the more experienced readers (AUC = 0.837 ± 0.029) than for the less experienced ones (AUC = 0.667 ± 0.099). The best performing group-based and personalized predictive models involved combinations of both gaze and image features.Conclusions: Diagnostic errors in mammography can be predicted to a good extent by leveraging the radiologists’ gaze behavior and image content.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

DOE OSTI2015

MapReduce SVM Game

Despite technological advances making computing devices faster, smaller, and more prevalent in today's age, data generation and collection has outpaced data processing capabilities. Simply having more compute platforms does not provide a means of addressing challenging problems in the big data era. Rather, alternative processing approaches are needed and the application of machine learning to big data is hugely important. The MapReduce programming paradigm is an alternative to conventional supercomputing approaches, and requires less stringent data passing constrained problem decompositions. Rather, MapReduce relies upon defining a means of partitioning the desired problem so that subsets may be computed independently and recom- bined to yield the net desired result. However, not all machine learning algorithms are amenable to such an approach. Game-theoretic algorithms are often innately distributed, consisting of local interactions between players without requiring a central authority and are iterative by nature rather than requiring extensive retraining. Effectively, a game-theoretic approach to machine learning is well suited for the MapReduce paradigm and provides a novel, alternative new perspective to addressing the big data problem. In this paper we present a variant of our Support Vector Machine (SVM) Game classifier which may be used in a distributed manner, and show an illustrative example of applying this algorithm.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Multi-fidelity modeling to predict the rheological properties of a suspension of fibers using neural networks and Gaussian processes

Unveiling the rheological properties of fiber suspensions is of paramount interest to many industrial applications. There are multiple factors, such as fiber aspect ratio and volume fraction, that play a significant role in altering the rheological behavior of suspensions. Three-dimensional (3D) numerical simulations of coupled differential equations of the suspension of fibers are computationally expensive and time-consuming. Machine learning algorithms can be trained on the available data and make predictions for the cases where no numerical data are available. However, some widely used machine learning surrogates, such as neural networks, require a relatively large training dataset to produce accurate predictions. Multi-fidelity models, which combine high-fidelity data from numerical simulations and less expensive lower fidelity data from resources such as simplified constitutive equations, can pave the way for more accurate predictions. Here, we focus on neural networks and the Gaussian processes with two levels of fidelity, i.e., high and low fidelity networks, to predict the steady-state rheological properties, and compare them to the single-fidelity network. High-fidelity data are obtained from direct numerical simulations based on an immersed boundary method to couple the fluid and solid motion. The low-fidelity data are produced by using constitutive equations. Multiple neural networks and the Gaussian process structures are used for the hyperparameter tuning purpose. Results indicate that with the best choice of hyperparameters, both the multi-fidelity Gaussian processes and neural networks are capable of making predictions with a high level of accuracy with neural networks demonstrating marginally better performance.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2024

Machine learning opportunities for nucleosynthesis studies

Nuclear astrophysics is an interdisciplinary field focused on exploring the impact of nuclear physics on the evolution and explosions of stars and the cosmic creation of the elements. While researchers in astrophysics and in nuclear physics are separately using machine learning approaches to advance studies in their fields, there is currently little use of machine learning in nuclear astrophysics. We briefly describe the most common types of machine learning algorithms, and then detail their numerous possible uses to advance nuclear astrophysics, with a focus on simulation-based nucleosynthesis studies. We show that machine learning offers novel, complementary, creative approaches to address many important nucleosynthesis puzzles, with the potential to initiate a new frontier in nuclear astrophysics research.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2020

SubTSBR to tackle high noise and outliers for data-driven discovery of differential equations

Data-driven discovery of differential equations has been an emerging research topic. We propose a novel algorithm subsampling-based threshold sparse Bayesian regression (SubTSBR) to tackle high noise and outliers. The subsampling technique is used for improving the accuracy of the Bayesian learning algorithm. It has two parameters: subsampling size and the number of subsamples. When the subsampling size increases with fixed total sample size, the accuracy of our algorithm goes up and then down. When the number of subsamples increases, the accuracy of our algorithm keeps going up. We demonstrate how to use our algorithm step by step and compare our algorithm with threshold sparse Bayesian regression (TSBR) for the discovery of differential equations. We show that our algorithm produces better results. We also discuss the merits of discovering differential equations from data and demonstrate how to discover models with random initial and boundary condition as well as models with bifurcations. The numerical examples are: (1) predator-prey model with noise, (2) shallow water equations with outliers, (3) heat diffusion with random initial and boundary condition, and (4) fish-harvesting problem with bifurcations.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

AdenPredictor: accurate prediction of the adenylation domain specificity of nonribosomal peptide biosynthetic gene clusters in microbial genomes

Microbial natural products represent a major source of bioactive compounds for drug discovery. Among these molecules, nonribosomal peptides (NRPs) represent a diverse class that include antibiotics, immunosuppressants, anticancer agents, toxins, siderophores, pigments, and cytostatics. The discovery of novel NRPs remains a laborious process because many NRPs consist of nonstandard amino acids that are assembled by nonribosomal peptide synthetases (NRPSs). Adenylation domains (A-domains) in NRPSs are responsible for selection and activation of monomers appearing in NRPs. During the past decade, several support vector machine-based algorithms have been developed for predicting the specificity of the monomers present in NRPs. These algorithms utilize physiochemical features of the amino acids present in the A-domains of NRPSs. In this article, we benchmarked the performance of various machine learning algorithms and features for predicting specificities of NRPSs and we showed that the extra trees model paired with one-hot encoding features outperforms the existing approaches. Moreover, we show that unsupervised clustering of 453560 A-domains reveals many clusters that correspond to potentially novel amino acids. While it is challenging to predict the chemical structure of these amino acids, we developed novel techniques to predict their various properties, including polarity, hydrophobicity, charge, and presence of aromatic rings, carboxyl, and hydroxyl groups.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

Recursive Use of the Short-Time Fast Fourier Transform for Signature Analysis in Continuous Processes

Although a nuclear reactor is a hostile environment for sensing and electrical communications, the reactor core is amenable to acoustic communication. An acoustic measurement infrastructure (AMI) has been installed in the Advanced Test Reactor (ATR) to record acoustic signals that can capture its different operating regimes. AMI uses coolant pumps as continuous signal sources, coolant and structural components as transmission lines, and accelerometers to capture system motion. A recursive signal processing technique based on the short-time fast Fourier transform (STFFT) for continuous processes provides unique signatures for diagnostic and prognostic analyses from the system motion data. Here this article presents a recursive STFFT methodology that processes acoustic signals from continuous industrial processes. The article first discusses the initial STFFT use with simulated data to elucidate the basic principles necessary to understand and interpret the STFFT results from actual pump vibration data. Each repetitive use of the STFFT on pump vibration data using the results from the prior STFFT processing will generate additional complimentary time-frequency-based signatures. These signatures are generated by the coolant pumps operating under different process conditions. After each use of the STFFT, the resulting signatures provide exemplary examples of the diversity and intuitive nature of recursively using the STFFT. This article focuses on recursively using the STFFT to provide numerous complimentary and diverse signatures that will ultimately be inputs for machine learning algorithms that provide predictive data analytics. The intuitive nature of the information and signatures from recursive STFFT processing will also bring intuitive interpretation capabilities to machine learning and predictive data analytic techniques.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2023

DLIO: A DATA-CENTRIC BENCHMARK FOR DEEP LEARNING APPLICATIONS

SF-22-136 Deep learning has been shown as a successful method for various tasks, and its popularity results in numerous open-source deep learning software tools. Deep learning has been applied to a broad spectrum of scientific domains such as cosmology, particle physics, computer vision, fusion, and astrophysics. Scientists have performed a great deal of work to optimize the computational performance of deep learning frameworks. However, the same cannot be said for I/O performance. As deep learning algorithms rely on big-data volume and variety to effectively train neural networks accurately, I/O is a significant bottleneck on large-scale distributed deep learning training. DLIO, is a novel representative benchmark suite built based on the I/O profiling of the selected workloads. DLIO can be utilized to accurately emulate the I/O behavior of modern deep learning applications. Using DLIO, application developers and system software solution architects can identify potential I/O bottlenecks in their applications and guide optimizations to boost the I/O performance leading to lower training times. The storage vendor can also use DLIO as a guide for designing and optimize the storage and filesystem targeting at deep learning application.

ZHENG, HUIHUO↗

DOE OSTI2020

Galaxy and Mass Assembly: A Comparison between Galaxy–Galaxy Lens Searches in KiDS/GAMA

Strong gravitational lenses are a rare and instructive type of astronomical object. Identification has long relied on serendipity, but different strategies—such as mixed spectroscopy of multiple galaxies along the line of sight, machine-learning algorithms, and citizen science—have been employed to identify these objects as new imaging surveys become available. We report on the comparison between spectroscopic, machine-learning, and citizen-science identification of galaxy–galaxy lens candidates from independently constructed lens catalogs in the common survey area of the equatorial fields of the Galaxy and Mass Assembly survey. In these, we have the opportunity to compare high completeness spectroscopic identifications against high-fidelity imaging from the Kilo Degree Survey used for both machine-learning and citizen-science lens searches. We find that the three methods—spectroscopy, machine learning, and citizen science—identify 47, 47, and 13 candidates, respectively, in the 180 square degrees surveyed. These identifications barely overlap, with only two identified by both citizen science and machine learning. We have traced this discrepancy to inherent differences in the selection functions of each of the three methods, either within their parent samples (i.e., citizen science focuses on low redshift) or inherent to the method (i.e., machine learning is limited by its training sample and prefers well-separated features, while spectroscopy requires sufficient flux from lensed features to lie within the fiber). These differences manifest as separate samples in estimated Einstein radius, lens stellar mass, and lens redshift. The combined sample implies a lens candidate sky density of ∼0.59 deg{sup −2} and can inform the construction of a training set spanning a wider mass–redshift space. A combined approach and refinement of automated searches would result in a more complete sample of galaxy–galaxy lens candidates for future surveys.

79 ASTRONOMY AND ASTROPHYSICS↗