Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed training”

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.

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

At least 1,153 records · Page 64

Assessment of the NASA Astrobiology Institute

Astrobiology is a scientific discipline devoted to the study of life in the universe--its origins, evolution, distribution, and future. It brings together the physical and biological sciences to address some of the most fundamental questions of the natural world: How do living systems emerge? How do habitable worlds form and how do they evolve? Does life exist on worlds other than Earth? As an endeavor of tremendous breadth and depth, astrobiology requires interdisciplinary investigation in order to be fully appreciated and examined. As part of a concerted effort to undertake such a challenge, the NASA Astrobiology Institute (NAI) was established in 1998 as an innovative way to develop the field of astrobiology and provide a scientific framework for flight missions. Now that the NAI has been in existence for almost a decade, the time is ripe to assess its achievements. At the request of NASA's Associate Administrator for the Science Mission Directorate (SMD), the Committee on the Review of the NASA Astrobiology Institute undertook the assignment to determine the progress made by the NAI in developing the field of astrobiology. It must be emphasized that the purpose of this study was not to undertake a review of the scientific accomplishments of NASA's Astrobiology program, in general, or of the NAI, in particular. Rather, the objective of the study is to evaluate the success of the NAI in achieving its stated goals of: 1. Conducting, supporting, and catalyzing collaborative interdisciplinary research; 2. Training the next generation of astrobiology researchers; 3. Providing scientific and technical leadership on astrobiology investigations for current and future space missions; 4. Exploring new approaches, using modern information technology, to conduct interdisciplinary and collaborative research among widely distributed investigators; and 5. Supporting outreach by providing scientific content for use in K-12 education programs, teaching undergraduate classes, and communicating directly with the public. The committee s assessment of the NAI's progress in these five areas is presented in Chapters 2 to 6, respectively.

Source record↗

High Performance EVA Glove Collaboration: Glove Injury Data Mining Effort

Human hands play a significant role during extravehicular activity (EVA) missions and Neutral Buoyancy Lab (NBL) training events, as they are needed for translating and performing tasks in the weightless environment. It is because of this high frequency usage that hand- and arm-related injuries and discomfort are known to occur during training in the NBL and while conducting EVAs. Hand-related injuries and discomforts have been occurring to crewmembers since the days of Apollo. While there have been numerous engineering changes to the glove design, hand-related issues still persist. The primary objectives of this study are therefore to: 1) document all known EVA glove-related injuries and the circumstances of these incidents, 2) determine likely risk factors, and 3) recommend ergonomic mitigations or design strategies that can be implemented in the current and future glove designs. METHODS: The investigator team conducted an initial set of literature reviews, data mining of Lifetime Surveillance of Astronaut Health (LSAH) databases, and data distribution analyses to understand the ergonomic issues related to glove-related injuries and discomforts. The investigation focused on the injuries and discomforts of U.S. crewmembers who had worn pressurized suits and experienced glove-related incidents during the 1980 to 2010 time frame, either during training or on-orbit EVA. In addition to data mining of the LSAH database, the other objective of the study was to find complimentary sources of information such as training experience, EVA experience, suit-related sizing data, and hand-arm anthropometric data to be tied to the injury data from LSAH. RESULTS: Past studies indicated that the hand was the most frequently injured part of the body during both EVA and NBL training. This study effort thus focused primarily on crew training data in the NBL between 2002 and 2010. Of the 87 recorded training incidents, 19 occurred to women and 68 to men. While crew ages ranged from thirties to fifties, the age category most affected was in the forties range. Incident rate calculations (incidents per 100 training runs) revealed that the 2002, 2003, and 2004 time periods registered the highest reported incident rate levels (3.4, 6.1, and 4.1 respectively) when compared to the following years (all ≤ 1.0). In addition to general hand-arm discomfort being the highest reported result from training, specific types of hand injuries or symptoms included erythema, fingernail delamination, abrasions, muscle soreness/fatigue, paresthesia, bruising, blanching, and edema. Specific body locations most affected by hand injuries included the metacarpophalangeal joints, fingernails, finger crotches, fingers in general, interphalangeal joints, and fingertips. Causes of injuries reported in the LSAH data were primarily attributed to the forces that the gloved hands were exposed to due to hand intensive tasks and/or poor glove sizing. DISCUSSION: Although the age data indicate that most injuries are reported by male crewmembers in their forties, that is also the dominant gender and age range of most EVA crew therefore it is not an unexpected finding. Age and gender analysis will continue as more details on the uninjured population is accrued. While there is a reasonable mechanism to link training quantity to injury, the results were inconsistent and point to the need for a consistent method of suit-related injury screening and documentation. For instance, the high-incident rate levels for the years 2002 to 2004 could be attributed to a comprehensive medical review of crewmembers post-NBL EVA training that occurred from July 19, 2002 to January 16, 2004. Furthermore, there could have been increased awareness from an investigation at the NBL. These investigations may have temporarily increased the fidelity of reported injuries and discomforts during these dates as compared to surrounding years, when injury signs and symptom were no longer actively being investigated but rather voluntarily reported. Data mining for possible mechanistic factors continues and includes more detailed training timelines, hand anthropometry, and suit sizing information. The limited published data looking at hand-arm anthropometry correlated hand-anthropometry metrics with injuries stemming from glove design and operation. Future work will include further evaluation of body sizing and fit in relation to hand injury incidents.

Reid, C. R.↗

Frequency Event Categorization in Power Distribution Systems Using Micro PMU Measurements

Frequency is an important metric for power stability. To enhance the situational awareness in power distribution systems, this article proposes a data-driven approach that utilizes the data from micro phasor measurement units (μPMU) to categorize frequency events observed in distribution feeders. The proposed approach has three layers, each of which analyzes if a frequency event is propagated from the transmission system, formed inside a distribution feeder or falsely produced by instantaneous frequency (IF) estimation algorithms, respectively. In the first layer, the Granger causality is utilized to compare the causal relations from measurements across different locations to decide if an event is propagated from the transmission side. In the second layer, a trained sparse coding dictionary is utilized to unmix the physical causes of a frequency event. In the third layer, a moving z-score based event-pair detector is applied to identify if a frequency event is algorithm-induced. The proposed approach is tested using the μPMU measurements collected from Lawrence Berkeley National Laboratory (LBNL) and Riverside Public Utility (RPU).

24 POWER TRANSMISSION AND DISTRIBUTION↗

New avenue to the parton distribution functions: Self-organizing maps

Neural network algorithms have been recently applied to construct parton distribution function (PDF) parametrizations which provide an alternative to standard global fitting procedures. In this exploratory study we propose a technique using self-organizing maps (SOMs). SOMs are a class of clustering algorithms based on competitive learning among spatially ordered neurons. Our SOMs are trained on selections of stochastically generated PDF samples. The selection criterion for every optimization iteration is based on the features of the clustered PDFs. Our goal is a fitting procedure that, at variance with the standard neural network approaches, will allow for an increased control of the systematic bias by enabling user interaction in the various stages of the process.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Deformable segmentation of 3D MR prostate images via distributed discriminative dictionary and ensemble learning

Purpose: Automatic prostate segmentation from MR images is an important task in various clinical applications such as prostate cancer staging and MR-guided radiotherapy planning. However, the large appearance and shape variations of the prostate in MR images make the segmentation problem difficult to solve. Traditional Active Shape/Appearance Model (ASM/AAM) has limited accuracy on this problem, since its basic assumption, i.e., both shape and appearance of the targeted organ follow Gaussian distributions, is invalid in prostate MR images. To this end, the authors propose a sparse dictionary learning method to model the image appearance in a nonparametric fashion and further integrate the appearance model into a deformable segmentation framework for prostate MR segmentation. Methods: To drive the deformable model for prostate segmentation, the authors propose nonparametric appearance and shape models. The nonparametric appearance model is based on a novel dictionary learning method, namely distributed discriminative dictionary (DDD) learning, which is able to capture fine distinctions in image appearance. To increase the differential power of traditional dictionary-based classification methods, the authors' DDD learning approach takes three strategies. First, two dictionaries for prostate and nonprostate tissues are built, respectively, using the discriminative features obtained from minimum redundancy maximum relevance feature selection. Second, linear discriminant analysis is employed as a linear classifier to boost the optimal separation between prostate and nonprostate tissues, based on the representation residuals from sparse representation. Third, to enhance the robustness of the authors' classification method, multiple local dictionaries are learned for local regions along the prostate boundary (each with small appearance variations), instead of learning one global classifier for the entire prostate. These discriminative dictionaries are located on different patches of the prostate surface and trained to adaptively capture the appearance in different prostate zones, thus achieving better local tissue differentiation. For each local region, multiple classifiers are trained based on the randomly selected samples and finally assembled by a specific fusion method. In addition to this nonparametric appearance model, a prostate shape model is learned from the shape statistics using a novel approach, sparse shape composition, which can model nonGaussian distributions of shape variation and regularize the 3D mesh deformation by constraining it within the observed shape subspace. Results: The proposed method has been evaluated on two datasets consisting of T2-weighted MR prostate images. For the first (internal) dataset, the classification effectiveness of the authors' improved dictionary learning has been validated by comparing it with three other variants of traditional dictionary learning methods. The experimental results show that the authors' method yields a Dice Ratio of 89.1% compared to the manual segmentation, which is more accurate than the three state-of-the-art MR prostate segmentation methods under comparison. For the second dataset, the MICCAI 2012 challenge dataset, the authors' proposed method yields a Dice Ratio of 87.4%, which also achieves better segmentation accuracy than other methods under comparison. Conclusions: A new magnetic resonance image prostate segmentation method is proposed based on the combination of deformable model and dictionary learning methods, which achieves more accurate segmentation performance on prostate T2 MR images.

60 APPLIED LIFE SCIENCES↗

EdgeAI: Machine learning via direct attached accelerator for streaming data processing at high shot rate x-ray free-electron lasers

We present a case for low batch-size inference with the potential for adaptive training of a lean encoder model. We do so in the context of a paradigmatic example of machine learning as applied in data acquisition at high data velocity scientific user facilities such as the Linac Coherent Light Source-II x-ray Free-Electron Laser. We discuss how a low-latency inference model operating at the data acquisition edge can capitalize on the naturally stochastic nature of such sources. We simulate the method of attosecond angular streaking to produce representative results whereby simulated input data reproduce high-resolution ground truth probability distributions. By minimizing the mean-squared error between the decoded output of the latent representation and the ground truth distributions, we ensure that the encoding layers and resulting latent representation maintains full fidelity for any downstream task, be it classification or regression. We present throughput results for data-parallel inference of various batch sizes, some with throughput exceeding 100 k images per second. We also show in situ training below 10 s per epoch for the full encoder–decoder model as would be relevant for streaming and adaptive real-time data production at our nation’s scientific light sources.

97 MATHEMATICS AND COMPUTING↗

New Design and Improvement of Planetary Gear Trains

The development of new types of planetary and planetary face-gear drives is proposed. The new designs are based on regulating backlash between the gears and modifying the tooth surfaces to improve the design. The goal of this work is to obtain a nearly uniform distribution of load between the planet gears. In addition, a new type of planetary face-gear drive was developed in this project.

Handschuh, Robert↗

ResNet and CycleGAN for pulse shape discrimination of He-4 detector pulses: Recovering pulses conventional algorithms fail to label unanimously

Pulse shape discrimination (PSD) capable detectors, such as He-4, that respond to neutron and gamma-ray 7 interactions have a threshold deposited energy value below which n/γ discrimination vanishes when using 8 conventional PSD algorithms. Recent attempts in applying supervised learning based artificial neural 9 networks for PSD use the pulses in the separated regions to train the networks so they can be used to classify 10 another set of separated pulses. In doing so, pulses previously indistinguishable are not recovered for 11 classification, which would have increased the number of neutron and gamma-ray pulses that could be used 12 for further analysis. Assuming the reason why conventional PSD algorithms have unseparated regions is 13 because the parameter space of the algorithms fail to capture the intrinsic (but subtle) distinguishing 14 behavior of some of the neutron and gamma-ray pulses, a cycle-consistent generative adversarial network 15 (CycleGAN) was trained to amplify those differences and extract well separated neutron and gamma-ray 16 clusters. Results show that, once the network is trained with pulses from separated and unseparated regions, 17 it was able to transform the pulses in the unseparated region to improve the PSD. Subsequent n/γ 18 classification was performed using deep residual network (ResNet) that takes pulses with 512 data points 19 as an input. Two different ResNets were explored – simple ResNet and modified ResNet which takes 20 segmented pulse inputs in the first layer and the corresponding time axis values in the last hidden layer. 21 The later approach enables the network to extract time correlated pulse features to enhance its ability to 22 capture the pulse behaviors relevant for PSD. Although it achieves slightly lower accuracy, 99.41% versus 23 99.89%, based on simply counting the number of correct n/γ labels assigned, compared to the simple 24 ResNet, the modified ResNets architecture was able to decreases the cross-entropy loss function by half, 25 which implies that the correct n/γ labels assigned are less likely to be accidental. PSD parameter 26 distributions based on n/γ classification by ResNet before and after transforming unseparated pulses using 27 CycleGAN show that by enhancing the separation between neutrons and gamma-rays, the transformation 28 helps improve the performance of classifier networks that are trained using labeled dataset. The 29 enhancement of neutron and gamma-ray separation by the CycleGAN increased the PSD figure of merit 30 (FOM) by up to 70% in some regions. Here, the results show that, if a given detector achieves clear separation 31 between neutron and gamma-ray pulses in any energy region, such neural network approaches can help 32 lower the energy threshold for the separation and increasing the number of neutron and gamma-ray pulses 33 that can be used for further analysis.

4He↗

A segmented approach to modeling building height: Delineating high-rise and low-rise buildings for enhanced height estimation

Understanding building height is imperative to the overall study of energy efficiency, population distribution, urban morphologies, emergency response, among others. Currently, existing approaches for modeling building height at scale are hindered by two pervasive issues. First, there is no consistent approach to quantify what a high-rise building is at a macro scale, leaving researchers unable to accurately compare results across geographies and domains. Second, high-rise buildings represent a small fraction of the built environment, implying data imbalance challenges that negatively affect current approaches. This is a problem of practical relevance since information on high-rise buildings is important for studies on urban heat islands, population dynamics, and pollution dispersion. Here, we introduce a novel approach to map building height which first identifies two distinct distributions within the built environment, with one being composed of low-rise buildings and one composed of high-rise buildings. We then develop an ensemble scheme where discrete specialist models are trained for each subset of low-rise buildings and high-rise buildings to infer building height from morphology features. For experiments mapping heights of 4.85 million buildings in Japan, we show an increase of 34 % in accuracy within 3m error when compared to the current state-of-the-art when modeling high-rise buildings, which based on KNN experimentation we define as any building > 12m . Our findings show that such an ensemble framework outperforms the current state-of-the-art approaches, which is especially relevant in relation to inferring height for high-rise buildings, a prominent issue of existing approaches for mapping the built environment.

97 MATHEMATICS AND COMPUTING↗

Spatiotemporally dynamic implicit large eddy simulation using machine learning classifiers

In this article, we utilize machine learning to dynamically determine if a point on the computational grid requires implicit numerical dissipation for large eddy simulation (LES). The decision making process is learnt through a priori training on quantities derived from direct numerical simulation (DNS) data. In particular, we compute eddy-viscosities obtained through the coarse-graining of DNS quantities and utilize their projection onto a Gaussian distribution to categorize areas that may require dissipation. If our learning determines that closure is necessary, an upwinded scheme is utilized for computing the non-linear Jacobian. In contrast, if it is determined that closure is unnecessary, a symmetric and second-order accurate energy and enstrophy preserving Arakawa scheme is utilized instead. This results in a closure framework that precludes the specification of any model-form for the small scale contributions of turbulence but deploys an appropriate numerical dissipation from explicit closure driven hypotheses. Here, this methodology is deployed for the Kraichnan turbulence test-case and assessed through various statistical quantities such as angle-averaged kinetic energy spectra and vorticity structure functions. Our framework thus establishes a link between the use of explicit LES ideologies for closure and numerical dissipation-based modeling of turbulence leading to improved statistical fidelity of a posteriori simulations.

42 ENGINEERING↗

Node-degree aware edge sampling mitigates inflated classification performance in biomedical random walk-based graph representation learning

Motivation: Graph representation learning is a family of related approaches that learn low-dimensional vector representations of nodes and other graph elements called embeddings. Embeddings approximate characteristics of the graph and can be used for a variety of machine-learning tasks such as novel edge prediction. For many biomedical applications, partial knowledge exists about positive edges that represent relationships between pairs of entities, but little to no knowledge is available about negative edges that represent the explicit lack of a relationship between two nodes. For this reason, classification procedures are forced to assume that the vast majority of unlabeled edges are negative. Existing approaches to sampling negative edges for training and evaluating classifiers do so by uniformly sampling pairs of nodes. Results: We show here that this sampling strategy typically leads to sets of positive and negative examples with imbalanced node degree distributions. Using representative heterogeneous biomedical knowledge graph and random walk-based graph machine learning, we show that this strategy substantially impacts classification performance. If users of graph machine-learning models apply the models to prioritize examples that are drawn from approximately the same distribution as the positive examples are, then performance of models as estimated in the validation phase may be artificially inflated. We present a degree-aware node sampling approach that mitigates this effect and is simple to implement. Availability and implementation: Our code and data are publicly available at https://github.com/monarch-initiative/negativeExampleSelection.

59 BASIC BIOLOGICAL SCIENCES↗

Convolutional Variational Autoencoder-based Unsupervised Learning for Power Systems Faults

Classification of power system event data is a growing need, particularly where non-protective relaying-based sensors are used to monitor grid performance. Given the high burden of obtaining event data with appropriate labeling, an unsupervised approach is highly valuable. This approach enables using event data without labeling, which is far easier to obtain. This paper presents an unsupervised learning method to classify and label transients observed in the distribution grid. A Convolutional Variational Autoencoder (CVAE) was developed for this purpose. We demonstrate the efficacy of our approach using the transient data generated from the simulations. The simulation data is used to train the CVAE that identifies different faults as different clusters in the latent space. The clusters are then used as the foundation model to categorize the real-world data.

Alam, Maksudul↗

Simplified Model and Approach to Transform Infrared Surface Temperature to Film Effectiveness in a Conjugate Heat Transfer Experiment

In the pursuit of more efficient gas turbines, film cooling is a critical technology. This article describes a simplified engineering model based on a one-dimensional thermal resistance network. The model is used to relate film-cooling effectiveness and heat transfer augmentation to local overall cooling effectiveness in a conjugate flat plate experiment. Here, this article presents experimental proof-of-concept data to demonstrate the potential for this model. In contrast to previous approaches, neither the wall heat flux nor the adiabatic wall temperature is required to estimate the local film-cooling performance parameters. The model predicts surface temperatures that are within the experimental uncertainties over the range for which the model is trained and to within five percent when the model is extrapolated to higher coolant channel Reynolds numbers. This article is relevant to conjugate test rigs that can measure the hot-surface temperature distribution with and without film cooling. This information may also be relevant to designers as a method to approximate surface temperatures or used as an approximate heat transfer model for optimization studies.

advanced turbines↗

Analysis of Fission Products on the AGR-1 Capsule Components

The components of the AGR-1 irradiation capsules were analyzed to determine the retained inventory of fission products in order to determine the extent of in-pile fission product release from the fuel compacts. This includes analysis of (1) the metal capsule components, (2) the graphite fuel holders, (3) the graphite spacers, and (4) the gas exit lines. The fission products most prevalent in the components were Ag-110m, Cs-134, Cs-137, Eu-154, and Sr-90, and the most common location was the metal capsule components and the graphite fuel holders. Gamma scanning of the graphite fuel holders was also performed to determine spatial distribution of Ag-110m and radiocesium. Silver was released from the fuel components in significant fractions. The total Ag-110m inventory found in the capsules ranged from 1.2×10 -2 (Capsule 3) to 3.8×10 -1 (Capsule 6). Ag-110m was not distributed evenly in the graphite fuel holders, but tended to concentrate at the axial ends of the graphite holders in Capsules 1 and 6 (located at the top and bottom of the test train) and near the axial center in Capsules 2, 3, and 5 (in the center of the test train). The Ag-110m further tended to be concentrated around fuel stacks 1 and 3, the two stacks facing the ATR reactor core and location of higher burnup, neutron fluence, and temperatures compared with Stack 2. Detailed correlation of silver release with fuel type and irradiation temperatures is problematic at the capsule level due to the large range of temperatures experienced by individual fuel compacts in each capsule. A comprehensive Ag-110m mass balance for the capsules was performed using measured inventories of individual compacts and the inventory on the capsule components. For most capsules, the mass balance was within 11% of the predicted inventory. The Ag-110m release from individual compacts often exhibited a very large range within a particular capsule.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Deploying Adversarial Attacks in Super-Resolution Models

Reliable super-resolution methods are crucial for applications like remote sensing, grid resilience and disaster impact analysis, and standoff biometrics. These methods infuse additional high-frequency information into reconstructions, allowing for better contextualization and image intelligence. However, super-resolution models can also introduce hallucinations or other unseen vulnerabilities that could be exploited by an adversary. This is further compounded by the prominence of deep learning in these models, as models are often blindly applied on out-of-distribution images. In this work, we implement adversarial attacks in common open-source super-resolution models and examine their impact on reconstructions and downstream classification tasks. We find that an adversarially trained super-resolution model can produce high-quality reconstructions that degrade downstream classifications. Moreover, these attacks do not require access to low-resolution imagery or class labels at inference time. These results demonstrate the vulnerability of super-resolution methods to malicious actors and motivates the development of a detector for super-resolution adversarial attacks. Further exploration of adversarial attacks in this domain is required to ensure trustworthiness and robustness of super-resolution models for national security applications.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Optical/IR from ground

Optical/infrared (O/IR) astronomy in the 1990's is reviewed. The following subject areas are included: research environment; science opportunities; technical development of the 1980's and opportunities for the 1990's; and ground-based O/IR astronomy outside the U.S. Recommendations are presented for: (1) large scale programs (Priority 1: a coordinated program for large O/IR telescopes); (2) medium scale programs (Priority 1: a coordinated program for high angular resolution; Priority 2: a new generation of 4-m class telescopes); (3) small scale programs (Priority 1: near-IR and optical all-sky surveys; Priority 2: a National Astrometric Facility); and (4) infrastructure issues (develop, purchase, and distribute optical CCDs and infrared arrays; a program to support large optics technology; a new generation of large filled aperture telescopes; a program to archive and disseminate astronomical databases; and a program for training new instrumentalists)

Strom, Stephen↗

Use of simulated neural networks of aerial image classification

The utility of one layer neural network in aerial image classification is examined. The network was trained with the delta rule. This method was shown to be useful as a classifier in aerial images with good resolution. It is fast, it is easy to implement, because it is distribution-free, nothing about statistical distribution of the data is needed, and it is very efficient as a boundary detector.

Medina, Frances I.↗

Automatic Rock Detection and Mapping from HiRISE Imagery

This system includes a C-code software program and a set of MATLAB software tools for statistical analysis and rock distribution mapping. The major functions include rock detection and rock detection validation. The rock detection code has been evolved into a production tool that can be used by engineers and geologists with minor training.

Huertas, Andres↗