Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Networking”

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 1,621 records · Page 90
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Atlas of putative minima and low-lying energy networks of water clusters n = 3 - 25

We report a database consisting of the putative minima and ~3.2 million local minima lying within 5 kcal/mol from the putative minima for water clusters of sizes n = 3 – 25 using an improved version of the Monte Carlo Temperature Basin Paving (MCTBP) global optimization procedure in conjunction with the ab-initio based, flexible, polarizable Thole-Type Model (TTM2.1-F, version 2.1) interaction potential for water. Several of the low-lying structures, as well as lowlying penta-coordinated water networks obtained with the TTM2.1-F potential, were further refined at the Møller-Plesset second order perturbation MP2/aug-cc-pVTZ level of theory. In total, we have identified 3,138,303 networks corresponding to local minima of the clusters n = 3 – 25, whose Cartesian coordinates and relative energies can be obtained from the webpage https://sites.uw.edu/wdbase/. Networks containing penta-coordinated water molecules start to appear at n = 11 and, quite surprisingly, are energetically close (within 1 – 3 kcal/mol) to the putative minima, a fact that has been confirmed from the MP2 calculations. This large database of water cluster minima spanning quite dissimilar hydrogen bonding networks is expected to influence the development and assessment of the accuracy of interaction potentials for water as well as lower scaling electronic structure methods (such as different density functionals). Furthermore, it can also be used in conjunction with data science approaches (including but no limited to neural networks, machine and deep learning) to understand the properties of water, nature’s most important substance.

Rakshit, Avijit↗
DOE OSTI2023

Self-consistent hopping theory of activated relaxation and diffusion of dilute penetrants in dense crosslinked polymer networks

We generalize a microscopic statistical mechanical theory of the activated dynamics of dilute spherical penetrants in glass-forming liquids to study the influence of crosslinking in polymer networks on the penetrant relaxation time and diffusivity over a wide range of temperature and crosslink fraction (f n ). Our calculations are relevant to recent experimental studies of a nm-sized molecule diffusing in poly-(n-butyl methacrylate) networks. The theory predicts the penetrant relaxation time increases exponentially with the glass transition temperature, T g (f n ), which grows roughly linearly with the square root of fn due to the coupling of local hopping to longer-range collective elasticity. Moreover, T g is also found to be proportional to a geometric confinement parameter defined as the ratio of the penetrant diameter to the mean network mesh size. The decoupling ratio of the penetrant and Kuhn segment alpha times displays a complex non-monotonic dependence on f n and temperature that is well collapsed based on the variable T g (f n )/T. A model for the penetrant diffusion constant that combines activated relaxation and entropic mesh confinement is proposed, which results in a significantly stronger suppression of mass transport with degree of effective supercooling than predicted for the penetrant alpha time. Furthermore, this behavior corresponds to a new network-based type of “decoupling” of diffusion and relaxation. In contrast to the diffusion of larger nanoparticles in high temperature rubbery networks, our analysis in the supercooled regime suggests that for the penetrants studied the mesh confinement effects are of secondary importance relative to the consequences of crosslink-induced slowing down of activated hopping of glassy physics origin.

Chemistry↗
DOE OSTI2024

Using the Metropolis algorithm to explore the loss surface of a recurrent neural network

In the limit of small trial moves the Metropolis Monte Carlo algorithm is equivalent to gradient descent on the energy function in the presence of Gaussian white noise. This observation was originally used to demonstrate a correspondence between Metropolis Monte Carlo moves of model molecules and overdamped Langevin dynamics, but it also applies in the context of training a neural network: making small random changes to the weights of a neural network, accepted with the Metropolis probability, with the loss function playing the role of energy, has the same effect as training by explicit gradient descent in the presence of Gaussian white noise. We explore this correspondence in the context of a simple recurrent neural network. We also explore regimes in which this correspondence breaks down, where the gradient of the loss function becomes very large or small. In these regimes the Metropolis algorithm can still effect training, and so can be used as a probe of the loss function of a neural network in regimes in which gradient descent struggles. We also show that training can be accelerated by making purposely-designed Monte Carlo trial moves of neural-network weights.

Casert, Corneel↗
DOE OSTI2024

Machine learning without a processor: Emergent learning in a nonlinear analog network

Standard deep learning algorithms require differentiating large nonlinear networks, a process that is slow and power-hungry. Electronic contrastive local learning networks (CLLNs) offer potentially fast, efficient, and fault-tolerant hardware for analog machine learning, but existing implementations are linear, severely limiting their capabilities. These systems differ significantly from artificial neural networks as well as the brain, so the feasibility and utility of incorporating nonlinear elements have not been explored. Here, we introduce a nonlinear CLLN—an analog electronic network made of self-adjusting nonlinear resistive elements based on transistors. We demonstrate that the system learns tasks unachievable in linear systems, including XOR (exclusive or) and nonlinear regression, without a computer. We find our decentralized system reduces modes of training error in order (mean, slope, curvature), similar to spectral bias in artificial neural networks. The circuitry is robust to damage, retrainable in seconds, and performs learned tasks in microseconds while dissipating only picojoules of energy across each transistor. This suggests enormous potential for fast, low-power computing in edge systems like sensors, robotic controllers, and medical devices, as well as manufacturability at scale for performing and studying emergent learning.

Science & Technology - Other Topics↗
DOE OSTI2017

A novel approach to estimate emissions from large transportation networks: Hierarchical clustering-based link-driving-schedules for EPA-MOVES using dynamic time warping measures

We present that EPA-MOVES (Motor Vehicle Emission Simulator) is often integrated with traffic simulators to assess emission levels of large-scale urban networks with signalized intersections. High variations in speed profiles exist in the context of congested urban networks with signalized intersections. The traditional average-speed-based emission estimation technique with EPA-MOVES provides faster execution while underestimates the emissions in most cases because of ignoring the speed variation at congested networks with signalized intersections. In contrast, the atomic second-by-second speed profile (i.e., the trajectory of each vehicle)-based technique provides accurate emissions at the cost of excessive computational power and time. We addressed this issue by developing a novel method to determine the link-driving-schedules (LDSs) for the EPA-MOVES tool. Our research developed a hierarchical clustering technique with dynamic time warping similarity measures (HC-DTW) to find the LDS for EPA-MOVES that is capable of producing emission estimates better than the average-speed-based technique with execution time faster than the atomic speed profile approach. We applied the HC-DTW on a sample data from a signalized corridor and found that HC-DTW can significantly reduce computational time without compromising the accuracy. The developed technique in this research can substantially contribute to the EPA-MOVES-based emission estimation process for large-scale urban transportation network by reducing the computational time with reasonably accurate estimates. This method is highly appropriate for transportation networks with higher variation in speed such as signalized intersections. Lastly, experimental results show error difference ranging from 2% to 8% for most pollutants except PM 10 .

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Particle image velocimetry analysis with simultaneous uncertainty quantification using Bayesian neural networks

Particle image velocimetry (PIV) is an effective tool in experimental fluid mechanics for extracting flow fields from images. Recently, convolutional neural networks (CNNs) have been used to perform PIV analysis with accuracy on par with classical methods. Here we extend the use of CNNs to analyze PIV data while providing simultaneous uncertainty quantification on the inferred flow field. The method we apply in this paper is a Bayesian convolutional neural network (BCNN) which learns distributions of the CNN weights through variational Bayes. In order to demonstrate the utility of BCNNs for the PIV task, we compare the performance of three distinct BCNN models with simple architectures. The first network estimates flow velocity from image interrogation regions only. Our second model learns to infer velocity from both the image interrogation regions and interrogation region cross-correlation maps. Finally, our best performing network infers velocities from interrogation region cross-correlation maps only. We find that BCNNs using interrogation region cross-correlation maps as inputs perform better than those using interrogation windows only as inputs and discuss reasons why this may be the case. Additionally, we test the best performing BCNN on a full synthetic test image pair and a real image pair from the 1st International PIV Challenge. We show that ~98% of true particle displacements from the full synthetic image pair can be captured within the BCNN's 95% confidence intervals, and that the BCNN's performance on the real image pair is quantitatively similar to that of algorithms tested in the 1st International PIV Challenge. Finally, we show that BCNNs can be generalized to be used with multi-pass PIV algorithms with a moderate loss in accuracy, which may be overcome by future work on finetuning and training schemes. So to our knowledge, this is the first use of Bayesian neural networks to perform PIV.

47 OTHER INSTRUMENTATION↗
DOE OSTI2014

Big Data over a 100G network at Fermilab

As the need for Big Data in science becomes ever more relevant, networks around the world are upgrading their infrastructure to support high-speed interconnections. To support its mission, the high-energy physics community as a pioneer in Big Data has always been relying on the Fermi National Accelerator Laboratory to be at the forefront of storage and data movement. This need was reiterated in recent years with the data-taking rate of the major LHC experiments reaching tens of petabytes per year. At Fermilab, this resulted regularly in peaks of data movement on the Wide area network (WAN) in and out of the laboratory of about 30 Gbit/s and on the Local are network (LAN) between storage and computational farms of 160 Gbit/s. To address these ever increasing needs, as of this year Fermilab is connected to the Energy Sciences Network (ESnet) through a 100 Gb/s link. To understand the optimal system-and application-level configuration to interface computational systems with the new highspeed interconnect, Fermilab has deployed a Network Research & Development facility connected to the ESnet 100G Testbed. For the past two years, the High Throughput Data Program (HTDP) has been using the Testbed to identify gaps in data movement middleware [5] when transferring data at these high-speeds. The program has published evaluations of technologies typically used in High Energy Physics, such as GridFTP [4], XrootD [9], and Squid [8]. Furthermore, this work presents the new R&D facility and the continuation of the evaluation program.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

On the use of neural networks for energy reconstruction in high-granularity calorimeters

We contrasted the performance of deep neural networks — Convolutional Neural Network (CNN) and Graph Neural Network (GNN) — to current state of the art energy regression methods in a finely 3D-segmented calorimeter simulated by GEANT4. This comparative benchmark gives us some insight to assess the particular latent signals neural network methods exploit to achieve superior resolution. A CNN trained solely on a pure sample of pions achieved substantial improvement in the energy resolution for both single pions and jets over the conventional approaches. It maintained good performance for electron and photon reconstruction. We also used the Graph Neural Network (GNN) with edge convolution to assess the importance of timing information in the shower development for improved energy reconstruction. We implement a simple simulation based correction to the energy sum derived from the fraction of energy deposited in the electromagnetic shower component. This serves as an approximate dual-readout analogue for our benchmark comparison. Although this study does not include the simulation of detector effects, such as electronic noise, the margin of improvement seems robust enough to suggest these benefits will endure in real-world application. We also find reason to infer that the CNN/GNN methods leverage latent features that concur with our current understanding of the physics of calorimeter measurement.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

Waveform processing using neural network algorithms on the front-end electronics

In a multi-channel radiation detector readout system, waveform sampling, digitization, and raw data transmission to the data acquisition system constitute a conventional processing chain. The deposited energy on the sensor is estimated by extracting peak amplitudes, area under pulse envelopes from the raw data, and starting times of signals or time of arrivals. However, such quantities can be estimated using machine learning algorithms on the front-end Application-Specific Integrated Circuits (ASICs), often termed as “edge computing”. Edge computation offers enormous benefits, especially when the analytical forms are not fully known or the registered waveform suffers from noise and imperfections of practical implementations. In this work, we aim to predict peak amplitude from a single waveform snippet whose rising and falling edges containing only 3 to 4 samples. We thoroughly studied two well-accepted neural network algorithms, Multi-Layer Perceptron (MLP) and Convolutional Neural Network (CNN) by varying their model sizes. Further, to better fit front-end electronics, neural network model reduction techniques, such as network pruning methods and variable-bit quantization approaches, were also studied. By combining pruning and quantization, our best performing model has the size of 1.5 KB, reduced from 16.6 KB of its full model counterpart. It can reach mean absolute error of 0.034 comparing to that of a naive baseline of 0.135. Such parameter-efficient and predictive neural network models established feasibility and practicality of their deployment on front-end ASICs.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

Generative adversarial networks for scintillation signal simulation in EXO-200

Generative Adversarial Networks trained on samples of simulated or actual events have been proposed as a way of generating large simulated datasets at a reduced computational cost. In this work, a novel approach to perform the simulation of photodetector signals from the time projection chamber of the EXO-200 experiment is demonstrated. The method is based on a Wasserstein Generative Adversarial Network — a deep learning technique allowing for implicit non-parametric estimation of the population distribution for a given set of objects. Our network is trained on real calibration data using raw scintillation waveforms as input. We find that it is able to produce high-quality simulated waveforms an order of magnitude faster than the traditional simulation approach and, importantly, generalize from the training sample and discern salient high-level features of the data. In particular, the network correctly deduces position dependency of scintillation light response in the detector and correctly recognizes dead photodetector channels. Furthermore, the network output is then integrated into the EXO-200 analysis framework to show that the standard EXO-200 reconstruction routine processes the simulated waveforms to produce energy distributions comparable to that of real waveforms. Finally, the remaining discrepancies and potential ways to improve the approach further are highlighted.

47 OTHER INSTRUMENTATION↗
DOE OSTI2020

Compressing deep neural networks on FPGAs to binary and ternary precision with hls4ml

We present the implementation of binary and ternary neural networks in the hls4ml library, designed to automatically convert deep neural network models to digital circuits with FPGA firmware. Starting from benchmark models trained with floating point precision, we investigate different strategies to reduce the network's resource consumption by reducing the numerical precision of the network parameters to binary or ternary. We discuss the trade-off between model accuracy and resource consumption. In addition, we show how to balance between latency and accuracy by retaining full precision on a selected subset of network components. As an example, we consider two multiclass classification tasks: handwritten digit recognition with the MNIST data set and jet identification with simulated proton-proton collisions at the CERN Large Hadron Collider. The binary and ternary implementation has similar performance to the higher precision implementation while using drastically fewer FPGA resources.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

PRODeepSyn: predicting anticancer synergistic drug combinations by embedding cell lines with protein–protein interaction network

Abstract Although drug combinations in cancer treatment appear to be a promising therapeutic strategy with respect to monotherapy, it is arduous to discover new synergistic drug combinations due to the combinatorial explosion. Deep learning technology holds immense promise for better prediction of in vitro synergistic drug combinations for certain cell lines. In methods applying such technology, omics data are widely adopted to construct cell line features. However, biological network data are rarely considered yet, which is worthy of in-depth study. In this study, we propose a novel deep learning method, termed PRODeepSyn, for predicting anticancer synergistic drug combinations. By leveraging the Graph Convolutional Network, PRODeepSyn integrates the protein–protein interaction (PPI) network with omics data to construct low-dimensional dense embeddings for cell lines. PRODeepSyn then builds a deep neural network with the Batch Normalization mechanism to predict synergy scores using the cell line embeddings and drug features. PRODeepSyn achieves the lowest root mean square error of 15.08 and the highest Pearson correlation coefficient of 0.75, outperforming two deep learning methods and four machine learning methods. On the classification task, PRODeepSyn achieves an area under the receiver operator characteristics curve of 0.90, an area under the precision–recall curve of 0.63 and a Cohen’s Kappa of 0.53. In the ablation study, we find that using the multi-omics data and the integrated PPI network’s information both can improve the prediction results. Additionally, the case study demonstrates the consistency between PRODeepSyn and previous studies.

Wang, Xiaowen↗
DOE OSTI2021

Deep graph representations embed network information for robust disease marker identification

We report that the accurate disease diagnosis and prognosis based on omics data rely on the effective identification of robust prognostic and diagnostic markers that reflect the states of the biological processes underlying the disease pathogenesis and progression. In this article, we present GCNCC, a Graph Convolutional Network-based approach for Clustering and Classification, that can identify highly effective and robust network-based disease markers. Based on a geometric deep learning framework, GCNCC learns deep network representations by integrating gene expression data with protein interaction data to identify highly reproducible markers with consistently accurate prediction performance across independent datasets possibly from different platforms. GCNCC identifies these markers by clustering the nodes in the protein interaction network based on latent similarity measures learned by the deep architecture of a graph convolutional network, followed by a supervised feature selection procedure that extracts clusters that are highly predictive of the disease state. By benchmarking GCNCC based on independent datasets from different diseases (psychiatric disorder and cancer) and different platforms (microarray and RNA-seq), we show that GCNCC outperforms other state-of-the-art methods in terms of accuracy and reproducibility.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

RF-Net 2: fast inference of virus reassortment and hybridization networks

Abstract Motivation A phylogenetic network is a powerful model to represent entangled evolutionary histories with both divergent (speciation) and convergent (e.g. hybridization, reassortment, recombination) evolution. The standard approach to inference of hybridization networks is to (i) reconstruct rooted gene trees and (ii) leverage gene tree discordance for network inference. Recently, we introduced a method called RF-Net for accurate inference of virus reassortment and hybridization networks from input gene trees in the presence of errors commonly found in phylogenetic trees. While RF-Net demonstrated the ability to accurately infer networks with up to four reticulations from erroneous input gene trees, its application was limited by the number of reticulations it could handle in a reasonable amount of time. This limitation is particularly restrictive in the inference of the evolutionary history of segmented RNA viruses such as influenza A virus (IAV), where reassortment is one of the major mechanisms shaping the evolution of these pathogens. Results Here, we expand the functionality of RF-Net that makes it significantly more applicable in practice. Crucially, we introduce a fast extension to RF-Net, called Fast-RF-Net, that can handle large numbers of reticulations without sacrificing accuracy. In addition, we develop automatic stopping criteria to select the appropriate number of reticulations heuristically and implement a feature for RF-Net to output error-corrected input gene trees. We then conduct a comprehensive study of the original method and its novel extensions and confirm their efficacy in practice using extensive simulation and empirical IAV evolutionary analyses. Availability and implementation RF-Net 2 is available at https://github.com/flu-crew/rf-net-2. Supplementary information Supplementary data are available at Bioinformatics online.

Markin, Alexey (ORCID:0000000332809050)↗
DOE OSTI2014

Causal network inference using biochemical kinetics

Motivation: Networks are widely used as structural summaries of biochemical systems. Statistical estimation of networks is usually based on linear or discrete models. However, the dynamics of biochemical systems are generally non-linear, suggesting that suitable non-linear formulations may offer gains with respect to causal network inference and aid in associated prediction problems. Results: We present a general framework for network inference and dynamical prediction using time course data that is rooted in nonlinear biochemical kinetics. This is achieved by considering a dynamical system based on a chemical reaction graph with associated kinetic parameters. Both the graph and kinetic parameters are treated as unknown; inference is carried out within a Bayesian framework. This allows prediction of dynamical behavior even when the underlying reaction graph itself is unknown or uncertain. Results, based on (i) data simulated from a mechanistic model of mitogen-activated protein kinase signaling and (ii) phosphoproteomic data from cancer cell lines, demonstrate that non-linear formulations can yield gains in causal network inference and permit dynamical prediction and uncertainty quantification in the challenging setting where the reaction graph is unknown. Availability and implementation: MATLAB R2014a software is available to download from warwick.ac.uk/chrisoates.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2019

Temporal network alignment via GoT-WAVE

Abstract Motivation Network alignment (NA) finds conserved regions between two networks. NA methods optimize node conservation (NC) and edge conservation. Dynamic graphlet degree vectors are a state-of-the-art dynamic NC measure, used within the fastest and most accurate NA method for temporal networks: DynaWAVE. Here, we use graphlet-orbit transitions (GoTs), a different graphlet-based measure of temporal node similarity, as a new dynamic NC measure within DynaWAVE, resulting in GoT-WAVE. Results On synthetic networks, GoT-WAVE improves DynaWAVE’s accuracy by 30% and speed by 64%. On real networks, when optimizing only dynamic NC, the methods are complementary. Furthermore, only GoT-WAVE supports directed edges. Hence, GoT-WAVE is a promising new temporal NA algorithm, which efficiently optimizes dynamic NC. We provide a user-friendly user interface and source code for GoT-WAVE. Availability and implementation http://www.dcc.fc.up.pt/got-wave/ Supplementary information Supplementary data are available at Bioinformatics online.

Aparício, David↗
DOE OSTI2018

False alarms and the IMS infrasound network: Understanding the factors influencing the creation of false events

The International Monitoring System (IMS) infrasound network has been designed to acquire the necessary data to detect and locate explosions in the atmosphere with a yield equivalent to 1 kiloton of TNT anywhere on Earth. A major associated challenge is the task of automatically processing data from all IMS infrasound stations to identify possible nuclear tests for subsequent review by analysts. This paper is the first attempt to quantify the false alarm rate (FAR) of the IMS network, and in particular to assess how the FAR is affected by the numbers and distributions of detections at each infrasound station. To ensure that the results are sufficiently general, and not dependent entirely on one detection algorithm, the assessment is based on two detection algorithms that can be thought of as end members in their approach to the trade-off between missed detections and false alarms. The results show that the FAR for events formed at only two arrays is extremely high (ranging from 10’s to 100’s of false events per day across the IMS network, depending on the detector tuning). It is further shown that the FAR for events formed at three or more IMS arrays is driven by ocean-generated waves (microbaroms), despite efforts within both detection algorithms for avoiding these signals, indicating that further research into this issue is merited. Overall, the results highlight the challenge of processing data from a globally sparse network of stations to detect and form events. On the basis of these results, it is shown that further work on understanding signal and noise characteristics is needed before attempting to automatically form events detected at only two arrays on the global network. In particular, more work is required to reduce false alarms caused by the detection of microbarom signals.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Generalization Across Experimental Parameters in Neural Network Analysis of High-Resolution Transmission Electron Microscopy Datasets

Neural networks are promising tools for high-throughput and accurate transmission electron microscopy (TEM) analysis of nanomaterials, but are known to generalize poorly on data that is “out-of-distribution” from their training data. Given the limited set of image features typically seen in high-resolution TEM imaging, it is unclear which images are considered out-of-distribution from others. Here, we investigate how the choice of metadata features in the training dataset influences neural network performance, focusing on the example task of nanoparticle segmentation. We train and validate neural networks across curated, experimentally collected high-resolution TEM image datasets of nanoparticles under various imaging and material parameters, including magnification, dosage, nanoparticle diameter, and nanoparticle material. Overall, we find that our neural networks are not robust across microscope parameters, but do generalize across certain sample parameters. Additionally, data preprocessing can have unintended consequences on neural network generalization. Our results highlight the need to understand how dataset features affect deployment of data-driven algorithms.

42 ENGINEERING↗