Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 667 records · Page 37
All sourcesNASA NTRSDOE OSTI
NASA NTRS2015

A High Performance Computing Approach to Tree Cover Delineation in 1-m NAIP Imagery Using a Probabilistic Learning Framework

Tree cover delineation is a useful instrument in deriving Above Ground Biomass (AGB) density estimates from Very High Resolution (VHR) airborne imagery data. Numerous algorithms have been designed to address this problem, but most of them do not scale to these datasets, which are of the order of terabytes. In this paper, we present a semi-automated probabilistic framework for the segmentation and classification of 1-m National Agriculture Imagery Program (NAIP) for tree-cover delineation for the whole of Continental United States, using a High Performance Computing Architecture. Classification is performed using a multi-layer Feedforward Backpropagation Neural Network and segmentation is performed using a Statistical Region Merging algorithm. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on Conditional Random Field, which helps in capturing the higher order contextual dependencies between neighboring pixels. Once the final probability maps are generated, the framework is updated and re-trained by relabeling misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates. The tree cover maps were generated for the whole state of California, spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles. The framework produced true positive rates of around 88% for fragmented forests and 74% for urban tree cover areas, with false positive rates lower than 2% for both landscapes. Comparative studies with the National Land Cover Data (NLCD) algorithm and the LiDAR canopy height model (CHM) showed the effectiveness of our framework for generating accurate high-resolution tree-cover maps.

Segments↗
NASA NTRS1997

Enhancing End-to-End Performance of Information Services Over Ka-Band Global Satellite Networks

The Internet has been growing at a rapid rate as the key medium to provide information services such as e-mail, WWW and multimedia etc., however its global reach is limited. Ka-band communication satellite networks are being developed to increase the accessibility of information services via the Internet at global scale. There is need to assess satellite networks in their ability to provide these services and interconnect seamlessly with existing and proposed terrestrial telecommunication networks. In this paper the significant issues and requirements in providing end-to-end high performance for the delivery of information services over satellite networks based on various layers in the OSI reference model are identified. Key experiments have been performed to evaluate the performance of digital video and Internet over satellite-like testbeds. The results of the early developments in ATM and TCP protocols over satellite networks are summarized.

Bhasin, Kul B.↗
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 OSTI2026

Neural Scaling Laws of Deep ReLU and Deep Operator Network: A Theoretical Study

Neural scaling laws play a pivotal role in the performance of deep neural networks and have been observed in a wide range of tasks. However, a complete theoretical framework for understanding these scaling laws remains underdeveloped. In this paper, we explore the neural scaling laws for deep operator networks, which involve learning mappings between function spaces, with a focus on the Chen and Chen style architecture. These approaches, which include the popular Deep Operator Network (DeepONet), approximate the output functions using a linear combination of learnable basis functions and coefficients that depend on the input functions. We establish a theoretical framework to quantify the neural scaling laws by analyzing its approximation and generalization errors. We articulate the relationship between the approximation and generalization errors of deep operator networks and key factors such as network model size and training data size. Moreover, we address cases where input functions exhibit low-dimensional structures, allowing us to derive tighter error bounds. These results also hold for deep ReLU networks and other similar structures. Our results offer a partial explanation of the neural scaling laws in operator learning and provide a theoretical foundation for their applications.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2010

Understanding the Scalability of Bayesian Network Inference Using Clique Tree Growth Curves

One of the main approaches to performing computation in Bayesian networks (BNs) is clique tree clustering and propagation. The clique tree approach consists of propagation in a clique tree compiled from a Bayesian network, and while it was introduced in the 1980s, there is still a lack of understanding of how clique tree computation time depends on variations in BN size and structure. In this article, we improve this understanding by developing an approach to characterizing clique tree growth as a function of parameters that can be computed in polynomial time from BNs, specifically: (i) the ratio of the number of a BN s non-root nodes to the number of root nodes, and (ii) the expected number of moral edges in their moral graphs. Analytically, we partition the set of cliques in a clique tree into different sets, and introduce a growth curve for the total size of each set. For the special case of bipartite BNs, there are two sets and two growth curves, a mixed clique growth curve and a root clique growth curve. In experiments, where random bipartite BNs generated using the BPART algorithm are studied, we systematically increase the out-degree of the root nodes in bipartite Bayesian networks, by increasing the number of leaf nodes. Surprisingly, root clique growth is well-approximated by Gompertz growth curves, an S-shaped family of curves that has previously been used to describe growth processes in biology, medicine, and neuroscience. We believe that this research improves the understanding of the scaling behavior of clique tree clustering for a certain class of Bayesian networks; presents an aid for trade-off studies of clique tree clustering using growth curves; and ultimately provides a foundation for benchmarking and developing improved BN inference and machine learning algorithms.

Mengshoel, Ole J.↗
NASA NTRS2006

DCS-Neural-Network Program for Aircraft Control and Testing

A computer program implements a dynamic-cell-structure (DCS) artificial neural network that can perform such tasks as learning selected aerodynamic characteristics of an airplane from wind-tunnel test data and computing real-time stability and control derivatives of the airplane for use in feedback linearized control. A DCS neural network is one of several types of neural networks that can incorporate additional nodes in order to rapidly learn increasingly complex relationships between inputs and outputs. In the DCS neural network implemented by the present program, the insertion of nodes is based on accumulated error. A competitive Hebbian learning rule (a supervised-learning rule in which connection weights are adjusted to minimize differences between actual and desired outputs for training examples) is used. A Kohonen-style learning rule (derived from a relatively simple training algorithm, implements a Delaunay triangulation layout of neurons) is used to adjust node positions during training. Neighborhood topology determines which nodes are used to estimate new values. The network learns, starting with two nodes, and adds new nodes sequentially in locations chosen to maximize reductions in global error. At any given time during learning, the error becomes homogeneously distributed over all nodes.

Jorgensen, Charles C.↗
DOE OSTI2020

NAPAbench 2: A network synthesis algorithm for generating realistic protein-protein interaction (PPI) network families

Comparative network analysis provides effective computational means for gaining novel insights into the structural and functional compositions of biological networks. In recent years, various methods have been developed for biological network alignment, whose main goal is to identify important similarities and critical differences between networks in terms of their topology and composition. A major impediment to advancing network alignment techniques has been the lack of gold-standard benchmarks that can be used for accurate and comprehensive performance assessment of such algorithms. The original NAPAbench (network alignment performance assessment benchmark) was developed to address this problem, and it has been widely utilized by many researchers for the development, evaluation, and comparison of novel network alignment techniques. In this work, we introduce NAPAbench 2—a major update of the original NAPAbench that was introduced in 2012. NAPAbench 2 includes a completely redesigned network synthesis algorithm that can generate protein-protein interaction (PPI) network families whose characteristics closely match those of the latest real PPI networks. Furthermore, the network synthesis algorithm comes with an intuitive GUI that allows users to easily generate PPI network families with an arbitrary number of networks of any size, according to a flexible user-defined phylogeny. In addition, NAPAbench 2 provides updated benchmark datasets—created using the redesigned network synthesis algorithm—which can be used for comprehensive performance assessment of network alignment algorithms and their scalability.

42 ENGINEERING↗
DOE OSTI2024

Improving ADAM through an implicit-explicit (IMEX) time-stepping approach

The ADAM optimizer, often used in machine learning for neural network training, corresponds to an underlying ordinary differential equation (ODE) in the limit of very small learning rates. Here, this work shows that the classical ADAM algorithm is a first-order implicit-explicit (IMEX) Euler discretization of the underlying ODE. Employing the time discretization point of view, we propose new extensions of the ADAM scheme obtained by using higher-order IMEX methods to solve the ODE. Based on this approach, we derive a new optimization algorithm for neural network training that performs better than classical ADAM on several regression and classification problems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Semantic segmentation with a sparse convolutional neural network for event reconstruction in MicroBooNE

We present the performance of a semantic segmentation network, SparseSSNet, that provides pixel-level classification of MicroBooNE data. The MicroBooNE experiment employs a liquid argon time projection chamber for the study of neutrino properties and interactions. SparseSSNet is a submanifold sparse convolutional neural network, which provides the initial machine learning based algorithm utilized in one of MicroBooNE's ν e -appearance oscillation analyses. The network is trained to categorize pixels into five classes, which are re-classified into two classes more relevant to the current analysis. The output of SparseSSNet is a key input in further analysis steps. This technique, used for the first time in liquid argon time projection chambers data and is an improvement compared to a previously used convolutional neural network, both in accuracy and computing resource utilization. Here, the accuracy achieved on the test sample is ≥ 99%. For full neutrino interaction simulations, the time for processing one image is ≈ 0.5 sec, the memory usage is at 1 GB level, which allows utilization of most typical CPU worker machine.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS1984

Performance of the Colorado wind-profiling network, part 1.5A

The Wave Propagation Laboratory (WPL) has operated a network of radar wind Profilers in Colorado for about 1 year. The network consists of four VHF (50-MHz) radars and a UHF (915-MHz) radar. The Platteville VHF radar was developed by the Aeronomy Laboratory (AL) and has been operated jointly by WPL and AL for several years. The other radars were installed between February and May 1983. Experiences with these radars and some general aspects of tropospheric wind measurements with Doppler radar are discussed.

Strauch, R. G.↗
NASA NTRS1990

Solid-state reprogrammable analog resistive devices for electronic neural networks

The fabrication and performance of WO3-based, solid-state, three-terminal device configurations as programmable analog memory elements are reported. These transistorlike device structures exhibit good resistance progammability with a remarkable resolution of a few percent of the resistive strength over a four orders of magnitude dynamic range. The most critical component of these devices is an insulating layer between the active WO3 and the cation donor layer. The progamming characteristics and operation mechanisms of the device are described, and probable reaction mechanisms critical to the device stability are discussed.

Ramesham, R.↗
NASA NTRS1990

Improving processing and toughness of a high performance composite matrix through an interpenetrating polymer network. VI

A simultaneous semi-interpenetrating polymer network (semi-IPN) concept is presented which combines easy-to-process, but brittle, thermosetting polyimides with tough, but difficult to process, linear thermoplastic polyimides. The combination results in a semi-IPN with the easy processability of a thermoset and good toughness of a thermoplastic. Four simultaneous semi-IPN systems were developed from commercially available NR-150B2 combined with each of the four Thermid materials (LR-600, AL-600, MC-600, and FA-700). It is concluded that there is a significant improvement in resin fracture toughness of Thermid-polyimide-based semi-IPN systems and some improvement in composite microcracking resistance compared to Thermid LR-600. Excellent composite mechanical properties have been achieved. These new semi-IPN materials have the potential to be used as composite matrices, adhesives, and molding materials.

Pater, Ruth H.↗
NASA NTRS1997

Process for controlling morphology and improving thermal-mechanical performance of high performance interpenetrating and semi-interpenetrating polymer networks

In the process of the present invention, a non-polar, aprotic solvent is removed from an oligomer/polymer solution by freeze-drying in order to produce IPNs and semi-IPNs. By thermally quenching the solution to a solid in a short length of time, the size of the minor constituent-rich regions is greatly reduced as they are excluded along with the major constituent from the regions of crystallizing solvent. The use of this process sequence of controlling phase morphology provides IPNs and semi-IPNs with improved fracture toughness, microcracking resistance, and other physical-mechanical properties as compared to IPNs and semi-IPNs formed when the solvent is evaporated rather than sublimed.

Pater, Ruth H.↗
NASA NTRS2007

Solutions Network Formulation Report. Using NASA Sensors to Perform Crop Type Assessment for Monitoring Insect Resistance in Corn

The EPA (U.S. Environmental Protection Agency) is tasked to monitor for insect pest resistance to transgenic crops. Several models have been developed to understand the resistance properties of insects. The Population Genetics Simulator model is used in the EPA PIRDSS (Pest Infestation and Resistance Decision Support System). The EPA Office of Pesticide Programs uses the DSS to help understand the potential for insect pest resistance development and the likelihood that insect pest resistance will negatively affect transgenic corn. Once the DSS identifies areas of concern, crews are deployed to collect insect pest samples, which are tested to identify whether they have developed resistance to the toxins in transgenic corn pesticides. In this candidate solution, VIIRS (Visible/Infrared Imager/Radiometer Suite) vegetation index products will be used to build hypertemporal layerstacks for crop type and phenology assessment. The current phenology attribute is determined by using the current time of year to index the expected growth stage of the crop. VIIRS might provide more accurate crop type assessment and also might give a better estimate on the crop growth stage.

Lewis, David↗
NASA NTRS2012

Integrated RF/Optical Interplanetary Networking Preliminary Explorations and Empirical Results

Over the last decade interplanetary telecommunication capabilities have been significantly expanded--specifically in support of the Mars exploration rover and lander missions. NASA is continuing to drive advances in new, high payoff optical communications technologies to enhance the network to Gbps performance from Mars, and the transition from technology demonstration to operational system is examined through a hybrid RF/optical approach. Such a system combines the best features of RF and optical communications considering availability and performance to realize a dual band trunk line operating within characteristic constraints. Disconnection due to planetary obscuration and solar conjunction, link delays, timing, ground terminal mission congestion and scheduling policy along with space and atmospheric weather disruptions all imply the need for network protocol solutions to ultimately manage the physical layer in a transparent manner to the end user. Delay Tolerant Networking (DTN) is an approach under evaluation which addresses these challenges. A multi-hop multi-path hybrid RF and optical test bed has been constructed to emulate the integrated deep space network and to support protocol and hardware refinement. Initial experimental results characterize several of these challenges and evaluate the effectiveness of DTN as a solution to mitigate them.

Raible, Daniel E.↗
NASA NTRS2008

Web-Enabled Optoelectronic Particle-Fallout Monitor

A Web-enabled optoelectronic particle- fallout monitor has been developed as a prototype of future such instruments that (l) would be installed in multiple locations for which assurance of cleanliness is required and (2) could be interrogated and controlled in nearly real time by multiple remote users. Like prior particle-fallout monitors, this instrument provides a measure of particles that accumulate on a surface as an indication of the quantity of airborne particulate contaminants. The design of this instrument reflects requirements to: Reduce the cost and complexity of its optoelectronic sensory subsystem relative to those of prior optoelectronic particle fallout monitors while maintaining or improving capabilities; Use existing network and office computers for distributed display and control; Derive electric power for the instrument from a computer network, a wall outlet, or a battery; Provide for Web-based retrieval and analysis of measurement data and of a file containing such ancillary data as a log of command attempts at remote units; and Use the User Datagram Protocol (UDP) for maximum performance and minimal network overhead.

Lineberger, Lewis P.↗