Search NASA⌕ Search

SEARCH · Search NASA

Results for “Network Performance”

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 703 records · Page 39

SOC Microstructural Property Estimator

This pre-trained ML model is a tool that uses basic compositional parameters for porous solid oxide cell (SOC) electrodes - the phase fractions and mean particle/pore diameters – as inputs and uses them to estimate additional electrochemical performance parameters: active (i.e., connected) TPB density, all tortuosity factors, and phase pair specific interfacial areas. The electrode is assumed to be composed of two solid phases and a pore phase. The property calculations are performed using neural network regression models trained on a large bank of synthetic electrode microstructural data that NETL has generated using the program DREAM3D (that bank is also hosted on EDX: https://edx.netl.doe.gov/dataset/soc-synthetic-microstructure-bank). This means the generated parameters are based on training from actual measured properties from 3D microstructures, not estimated from geometric simplifications. This tool was developed and is intended to replace percolation theory calculations in models that use hypothetical electrode properties. An example use case would be running SOC performance simulations across a parametric sweep of electrode designs (e.g., varying phase fractions and particle sizes) and assessing how it impacts the electrochemical performance of the SOC. Within the parameter space of the training data (statistics of that parameter space is provided in the readme file), this model achieves sub-5% mean absolute percent errors, an order of magnitude less error than percolation theory across the same parameter space. However, be aware that this tool was developed with parametric simulations in mind, and users are encouraged to assess accuracy for their own specific use case rather than taking accuracy metrics at face value. More info, including a usage guide, is in the included readme file. This tool should be cited with the DOI number provided.

Electrode Microstructure↗

GPU-based Real-Time Execution of Vehicular Mobility Models in Large-Scale Road Network Scenarios

A methodology and its associated algorithms are presented for mapping a novel, field-based vehicular mobility model onto graphical processing unit computational platform for simulating mobility in large-scale road networks. Of particular focus is the achievement of real-time execution, on desktop platforms, of vehicular mobility on road networks comprised of millions of nodes and links, and multi-million counts of simultaneously active vehicles. The methodology is realized in a system called GARFIELD, whose implementation details and performance study are described. The runtime characteristics of a prototype implementation are presented that show real-time performance in simulations of networks at the scale of a few states of the US road networks.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Regularizing Invertible Neural Networks for Airfoil Design Through Dimension Reduction

This work examines how dimension reduction can improve the performance of invertible neural networks (INN) for airfoil design. Design workflows are typically expensive, relying on many evaluations of high fidelity computational fluid dynamics (CFD) models. Furthermore, the inverse design problem is typically ill-posed. That is, multiple valid solutions exist that satisfy the design criteria. Regularization can reduce this inverse design space and simplify the problem. We study the use of subspace-based input dimension reduction to act as a regularizer for the INN model and improve the recovery of new airfoil shapes with desired performance characteristics. We find that the dimension reduction identifies two dominant modes, relating to airfoil thickness and camber, that optimally determine the airfoil's aerodynamics. We demonstrate the capability of the proposed INN model to generate 100 airfoils that satisfy the specific aerodynamic and structural characteristics.

airfoil design↗

GraMeR: Gra ph Me ta R einforcement learning for multi-objective influence maximization

Influence maximization (IM) is a combinatorial problem of identifying a subset of seed nodes in a network (graph), which when activated, provide a maximal spread of influence in the network for a given diffusion model and a budget for seed set size. IM has numerous applications such as viral marketing, epidemic control, sensor placement and other network-related tasks. However, its practical uses are limited due to the computational complexity of current algorithms. Recently, deep reinforcement learning has been leveraged to solve IM in order to ease the computational burden. However, there are serious limitations in current approaches, including narrow IM formulation that only consider influence via spread and ignore self-activation, low scalability to large graphs, and lack of generalizability across graph families leading to a large running time for every test network. In this work, we address these limitations through a unique approach that involves: (1) Formulating a generic IM problem as a Markov decision process that handles both intrinsic and influence activations; (2)incorporating generalizability via meta-learning across graph families. There are previous works that combine deep reinforcement learning with graph neural network, but this work solves a more realistic IM problem and incorporates generalizability across graphs via meta reinforcement learning. Extensive experiments are carried out in various standard networks to validate performance of the proposed Graph Meta Reinforcement learning (GraMeR) framework. Finally, the results indicate that GraMeR is multiple orders faster and generic than conventional approaches when applied on small to medium scale graphs.

97 MATHEMATICS AND COMPUTING↗

Harnessing Neural Networks for Elucidating X-ray Absorption Structure–Spectrum Relationships in Amorphous Carbon

Improved understanding of structural and chemical properties through local experimental probes, such as X-ray absorption near-edge structure (XANES) spectroscopy, is crucial for the understanding and design of functional materials. In recent years, significant advancements have been made in the development of data science approaches for the automated interpretation of XANES structure–spectrum relationships. However, existing studies have primarily focused on crystalline solids and small molecules, while fewer efforts have been devoted to disordered systems. Thus, in this work, we demonstrate the development of neural network models for predicting and interpreting XANES spectra of amorphous carbon (a-C) from local structural descriptors. Comparison between different structural descriptors expectedly shows that the inclusion of both bond length and bond angle information is necessary for an accurate prediction of the spectra. Among the descriptors considered in this work, we find that the local many-body tensor representation yields the highest accuracy and greatest interpretability so that it can be leveraged to understand the importance of structural motifs in determining XANES spectra. Furthermore, we also discuss performance of neural network models for predicting both local structure features, such as bond lengths and bond angles, and global chemical composition, such as the sp:sp 2 :sp 3 ratio.

36 MATERIALS SCIENCE↗

Quantitative Analysis of Ca, Mg, and K in the Roots of Angelica pubescens f. biserrata by Laser-Induced Breakdown Spectroscopy Combined with Artificial Neural Networks

Laser-induced breakdown spectroscopy has been applied for the quantitative analysis of Ca, Mg, and K in the roots of Angelica pubescens Maxim. f. biserrata Shan et Yuan used in traditional Chinese medicine. Ca II 317.993 nm, Mg I 517.268 nm, and K I 769.896 nm spectral lines have been chosen to set up calibration models for the analysis using the external standard and artificial neural network methods. The linear correlation coefficients of the predicted concentrations versus the standard concentrations of six samples determined by the artificial neural network method are 0.9896, 0.9945, and 0.9911 for Ca, Mg, and K, respectively, which are better than for the external standard method. The artificial neural network method also gives better performance comparing with the external standard method for the average and maximum relative errors, average relative standard deviations, and most maximum relative standard deviations of the predicted concentrations of Ca, Mg, and K in the six samples. Finally, it is proved that the artificial neural network method gives better performance compared to the external standard method for the quantitative analysis of Ca, Mg, and K in the roots of Angelica pubescens.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Accelerating Hamiltonian Monte Carlo for Bayesian inference in neural networks and neural operators

Hamiltonian Monte Carlo (HMC) is a powerful and accurate method to sample from the posterior distribution in Bayesian inference. However, HMC techniques are computationally demanding for Bayesian neural networks due to the high dimensionality of the network’s parameter space and the non-convexity of their posterior distributions. Therefore, various approximation techniques, such as variational inference (VI) or stochastic gradient MCMC, are often employed to infer the posterior distribution of the network parameters. Such approximations introduce inaccuracies in the inferred distributions, resulting in unreliable uncertainty estimates. In this work, we propose a hybrid approach that combines inexpensive VI and accurate HMC methods to efficiently and accurately quantify uncertainties in neural networks and neural operators. The proposed approach leverages an initial VI training on the full network. We examine the influence of individual parameters on the prediction uncertainty, which shows that a large proportion of the parameters do not contribute substantially to uncertainty in the network predictions. This information is then used to significantly reduce the dimension of the parameter space, and HMC is performed only for the subset of network parameters that strongly influence prediction uncertainties. This yields a framework for accelerating the full batch HMC for posterior inference in neural networks. We demonstrate the efficiency and accuracy of the proposed framework on deep neural networks and operator networks, showing that inference can be performed for large networks with tens to hundreds of thousands of parameters. Finally, we show that this method can effectively learn surrogates for complex physical systems by modeling the operator that maps from upstream conditions to wall-pressure data on a cone in hypersonic flow.

Bayesian inference↗

Performance Evaluation of Vertical Federated Machine Learning Against Adversarial Threats on Wide-Area Control System: Preprint

Federated machine learning (FL) is gaining significant popularity to develop cybersecurity solutions in power grids because of its advanced capability to support decentralized data handing at local devices, its privacy preservation, and its low-bandwidth requirement. However, the evolving adversarial machine learning (AML) threats raise significant concerns for the cybersecurity of FL architectures. The FL-based split neural network (SplitNN) achieves high performance through the decentralized training of local neural network models while preserving data privacy across multiple entities. In this paper, we propose a methodology for evaluating the performance of a vertical FLbased anomaly detector against different types of AML attacks, including denial-of-service attacks, adversarial data injection attacks, and replay attacks on the trained local models deployed in the grid network. For a case study, we consider the modified IEEE 13-bus system, and we develop SplitNN-based binary and multiclass classification models to detect, locate, and identify different types of data integrity attacks on the volt-watt control with two pooling layers: maximum pooling and AvgPool. Our experimental results, computed through performance metrics, reveal that the severity of these AML attacks varies with the integrated pooling mechanism, the type of classification model, and the nature of the cyberattack. Further, the AML attacks negatively impacted the prediction time per sample for the pretrained SplitNN during the online testing.

adversarial threats↗

Radial feature descriptors for cell classification and recommendation

This paper introduces computational tools for cell classification into normal and abnormal, as well as content-based-image-retrieval (CBIR) for cell recommendation. It also proposes the radial feature descriptors (RFD), which define evenly interspaced segments around the nucleus, and proportional to the convexity of the nuclear boundary. Experiments consider Herlev and CRIC image databases as input to classification via Random Forest and bootstrap; we compare 14 different feature sets by means of False Negative Rate (FNR) and Kappa (κ), obtaining FNR =0.02 and κ=0.89 for Herlev, and FNR =0.14 and κ=0.78 for CRIC. Next, we sort and rank cell images using convolutional neural networks and evaluate performance with the Mean Average Precision (MAP), achieving MAP =0.84 and MAP =0.82 for Herlev and CRIC, respectively. Finally, cell classification show encouraging results regarding RFD, including its sensitivity to intensity variation around the nuclear membrane as it bypasses cytoplasm segmentation.

47 OTHER INSTRUMENTATION↗

Dendritic Computing with Multigate Ferroelectric Field-Effect Transistors

Although inspired by neuronal systems in the brain, artificial neural networks generally employ point-neurons, which offer computational complexity far less than that of their biological counterparts. Neurons have dendritic arbors that connect to different sets of synapses and offer local nonlinear accumulation – playing a pivotal role in processing and learning. Inspired by this, we propose a novel neuron design based on a multigate ferroelectric field-effect transistor that mimics dendrites. It leverages ferroelectric nonlinearity for local computations within dendritic branches while utilizing the transistor action to generate the neuronal output. The branched architecture enables smaller crossbar arrays in hardware integration, improving efficiency. Using an experimentally calibrated device-circuit-algorithm cosimulation framework, we demonstrate that networks incorporating our dendritic neurons achieve superior performance compared to much larger networks without dendrites (∼ 17× fewer trainable weight parameters). These findings suggest that dendritic hardware can significantly improve computational efficiency and learning capacity of neuromorphic systems optimized for edge applications.

36 MATERIALS SCIENCE↗

Multiverse: Bayesian model selection for neural networks

Multiverse is a code repository for a set of tools for Bayesian model selection for neural networks. The goal of the tools is to provide capabilities for selecting among prior and model specifications for Bayesian neural networks. Multiverse will include tools for creating Bayesian neural networks, evaluating the Bayesian model evidence, and performing inference in Bayesian neural networks. These components are written in Python, a high-level programming language that takes advantage of the Python ecosystem of high-quality open-source packages for machine learning and signal processing.

Klein, Natalie↗

Proteomic-based mechanistic investigation of low-dose radiation-induced cellular responses/effects

The goal of our project is to apply our unique systems investigation strategy to reveal the molecular mechanisms underlying the radiation induction and transmission of oxidative damage, adaptive response, and bystander effect at low-doses. Beginning with simple in vitro systems such as fibroblast or epithelial pure culture, our amino acid-coded mass tagging (AACT) comparative proteomic platform will be used to measure quantitatively proteomic changes at high- or low-dose level with respect to their endogenous damage levels respectively, in which a broad range of unique regulated proteins sensitive to low-dose IR will be distinguished. To zoom in how these regulated proteins interact with other in the form of networks in induction/transmission pathways, these regulated proteins will be selected as baits for making a series of fibroblast cell lines that stably express each of them. Using our newly developed method of 'dual-tagging' quantitative proteomics that integrate the capabilities of natural complex expression/formation, simple epitope affinity isolation (not through tandem affinity purification or TAP), and 'in-spectra' AACT quantitative measurements using mass spectrometry (MS), we will be able to distinguish systematically interacting proteins with each bait in real time. Further, in addition to both proteome-wide (global differentially expressed proteins) and pathway-scale (bait-specific) profiling information, we will perform a computational network analysis to elucidate a global pathway/mechanisms underlying cellular responses to real-time low-dose IR. Similarly, we will extend our scheme to investigate systematically those induction/transmission pathways occurring in a fibroblast-epithelial interacting model in which the bystander cell (fibroblast) monitor the IR damage to the target cell (epithelial cell). The results will provide the proteome base (molecular mechanisms/pathways for signaling) for the low dose radiation-induced essential tissue environment interactions, including cell-cell, extracellular matrix and extracellular paracrine interactions.

59 BASIC BIOLOGICAL SCIENCES↗

Fail-Slow at Scale: Evidence of Hardware Performance Faults in Large Production Systems

Fail-slow hardware is an under-studied failure mode. We present a study of 114 reports of fail-slow hardware incidents, collected from large-scale cluster deployments in 14 institutions. We show that all hardware types such as disk, SSD, CPU, memory, and network components can exhibit performance faults. We made several important observations such as faults convert from one form to another, the cascading root causes and impacts can be long, and fail-slow faults can have varying symptoms. From this study, we make suggestions to vendors, operators, and systems designers.

fail-slow↗

Identification of important invasion and proliferation related genes in adrenocortical carcinoma

Adrenocortical carcinoma (ACC) is an end‐stage hormonal syndrome. Although profound attempts have been made to illuminate the pathogenesis, the molecular mechanisms of ACC remain to be clarified. To identify the important genes in the progression of ACC, microarray datasets GSE19775 was downloaded from the gene expression omnibus database. The differentially-expressed genes (DEGs) were identified, and pathway and GO enrichment analyses were performed. The protein–protein interaction (PPI) network was constructed and the module analysis was performed using the protein interaction network analysis and Cytoscape. Also constructed target genes–miRNA regulatory network and target genes–TF regulatory network. Correlation of the hub genes were analyzed in The Cancer Genome Atlas. The prognostic values of hub genes were further validated by online tool UALCAN. Mutation analysis was done by online tool CBio Cancer Genomics Portal. A total of 884 DEGs were identified, with 441 in up regulation and 443 in down regulation. Pathways in catecholamine biosynthesis, aldosterone synthesis and secretion, pyrimidine deoxyribonucleosides salvage and systemic lupus erythematosus were the most significantly enriched for DEGs (up and down regulated). Blood vessel morphogenesis and cell cycle phase transition were the most significantly enriched term in biological processes, while extracellular matrix and chromosome, centromeric region were in cellular component and heparin binding and protein dimerization activity were in molecular function. Among the PPI networks and its module, target genes–miRNA regulatory network and target genes–TF regulatory network, hub genes were YWHAZ, FN1, GRK5, VCAM1, GATA6, TXNIP, HSPA1A, and F11R. Hub genes such as YWHAZ, STAT1, ICAM1, SH3BP5, CD83, FN1, TK1, HIST1H1C, CABLES1, and MCM3 were associated with poor overall survival, while hub genes such as STAT1, ICAM1, CD83, FN1, TK1, HIST1H1C, and MCM3 were highly expressed in stage 4. In conclusion, DEGs and hub genes diagnosed in this study may deepen our understanding of molecular mechanisms underlying the progression of ACC, and provide important targets for diagnosis and treatment of ACC.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

DistGANS- Distributed Generative Adversarial Neural Networks

DistGANs is a Python package to perform distributed training of conditional generative adversarial neural networks for multi-class labeled image data. DistGANs partitionins the training data according to data labels, and enhances scalability by performing a parallel training where multiple generators are concurrently trained, each one of them focusing on a single data label.

Lupo Pasini, Massimiliano [Oak Ridge National Lab.↗

An analysis of image storage systems for scalable training of deep neural networks

This study presents a principled empirical evaluation of image storage systems for training deep neural networks. We employ the Caffe deep learning framework to train neural network models for three different data sets, MNIST, CIFAR-10, and ImageNet. While training the models, we evaluate five different options to retrieve training image data: (1) PNG-formatted image files on local file system; (2) pushing pixel arrays from image files into a single HDF5 file on local file system; (3) in-memory arrays to hold the pixel arrays in Python and C++; (4) loading the training data into LevelDB, a log-structured merge tree based key-value storage; and (5) loading the training data into LMDB, a B+tree based key-value storage. The experimental results quantitatively highlight the disadvantage of using normal image files on local file systems to train deep neural networks and demonstrate reliable performance with key-value storage based storage systems. When training a model on the ImageNet dataset, the image file option was more than 17 times slower than the key-value storage option. Along with measurements on training time, this study provides in-depth analysis on the cause of performance advantages/disadvantages of each back-end to train deep neural networks. We envision the provided measurements and analysis will shed light on the optimal way to architect systems for training neural networks in a scalable manner.

Lim, Seung-Hwan↗

Multi-rate OCDMA system BER performance evaluations for different ML-code sequences

This paper analyzes Bit Error Rate (BER) of Optical Code Division Multiple Access (OCDMA) networks for different class of services which are data, voice, and video; whereas Multi-Length Weighted Modified Prime Code (ML-WMPC) sequences are utilized as a spreading code in with respect to previously used ML-Optical Orthogonal codes. Due to variations in bit rates between the mentioned services, each of them assigns a different WMPC sequence length. In addition, the shot noise, thermal noise, and the Multiple Access Interference (MAI) are included and considered as sources of noise in the BER performance analysis. Furthermore, Pulse Position Modulation, Manchester encoding and MAI cancellation (MAIC) technique are utilized to improve the network performance at a higher number of active users. For analysis, the BER performance calculations are investigated for three types of OCDMA receivers such as simple receiver, receiver with MAIC technique, and receiver with MAIC and Manchester encoding. Moreover, the BER mathematical models have been introduced for different bit rates according to the type of service in the presence of the ML-WMPC and the last of three mentioned OCDMA receivers. Finally, these models and their results are compared with the other existing models, where the results show an improvement in BER performance in the proposed approach.

42 ENGINEERING↗

Recall Performance for Content-Addressable Memory Using Adiabatic Quantum Optimization

A content-addressable memory (CAM) stores key-value associations such that the key is recalled by providing its associated value. While CAM recall is traditionally performed using recurrent neural network models, we show how to solve this problem using adiabatic quantum optimization. Our approach maps the recurrent neural network to a commercially available quantum processing unit by taking advantage of the common underlying Ising spin model. We then assess the accuracy of the quantum processor to store key-value associations by quantifying recall performance against an ensemble of problem sets. We observe that different learning rules from the neural network community influence recall accuracy but performance appears to be limited by potential noise in the processor. The strong connection established between quantum processors and neural network problems supports the growing intersection of these two ideas.

97 MATHEMATICS AND COMPUTING↗