Search NASA⌕ Search

SEARCH · Search NASA

Results for “Convolution”

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 829 records · Page 46

Automated Threat Recognition For Aviation Security Applications

We have developed a framework for automated threat recognition (ATR) of explosive threat materials for both single-energy and dual-energy X-ray CT systems. Under this framework, two different types of ATR have been developed. The first type of ATR employs supervised machine learning with statistical characterization of target materials for threat identification training. The reliance only on statistical characterization information for threat training uniquely enables this style of ATR to adapt quickly to evolving threats. The second type of ATR employs deep learning through convolutional neural networks. Convolutional neural networks are attractive due to their human-like capacity for learning and strong ability to identify trends and patterns. Although this method is more powerful than the first type, it requires large amounts of training data and therefore is less agile. Each ATR performs threat characterization at the voxel neighborhood level. This approach avoids the use of threat shape as a detection criterion, which is prohibited by DHS and TSA guidelines.

97 MATHEMATICS AND COMPUTING↗

Developing inductively driven diagnostic X-ray sources to enable transformative radiography and diffraction capabilities on Z

Penetrating X-rays are one of the most effective tools for diagnosing high energy density experiments, whether through radiographic imaging or X-ray diffraction. To expand the X-ray diagnostic capabilities at the 26-MA Z Pulsed Power Facility, we have developed a new diagnostic X-ray source called the inductively driven X-pinch (IDXP). This X-ray source is powered by a miniature transmission line that is inductively coupled to fringe magnetic fields in the final power feed. The transmission line redirects a small amount of Zs magnetic energy into a secondary cavity where 150+ kA of current is delivered to a hybrid X-pinch. In this report, we describe the multi-stage development of the IDXP concept through experiments both on Z and in a surrogate setup on the 1 MA Mykonos facility. Initial short-circuit experiments to verify power ow on Z are followed by short-circuit and X-ray source development experiments on Mykonos. The creation of a radiography-quality X-pinch hot spot is verified through a combination of X-ray diode traces, laser shadowgraphy, and source radiography. The success of the IDXP experiments on Mykonos has resulted in the design and fabrication of an IDXP for an upcoming Z experiment that will be the first-ever X-pinch fielded on Z. We have also pursued the development of two additional technologies. First, the extended convolute post (XCP) has been developed as an alternate method for powering diagnostic X-pinches on Z. This concept, which directly couples the current owing in one of the twelve Z convolute posts to an X-pinch, greatly increases the amount of available current relative to an IDXP (900 kA versus 150 kA). Initial short-circuit XCP experiments have demonstrated the efficacy of power ow in this geometry. The second technology pursued here is the inductively driven transmission line (IDTL) current monitor. These low-current IDTLs seek to measure the current in the final power feed with high fidelity. After three generations of development, IDTL current monitors frequently return cleaner current measurements than the standard B-dot sensors that are fielded on Z. This is especially true on high-inductance experiments where the harshest conditions are created in the nal power feed.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Concentric Spherical GNN for 3D Representation Learning

Learning 3D representations that generalize well to arbitrarily oriented inputs is a challenge of practical importance in applications varying from computer vision to physics and chemistry. We propose a novel multi-resolution convolutional architecture for learning over concentric spherical feature maps, of which the single sphere representation is a special case. Our hierarchical architecture is based on alternatively learning to incorporate both intra-sphere and inter-sphere information. We show the applicability of our method for two different types of 3D inputs, mesh objects, which can be regularly sampled, and point clouds, which are irregularly distributed. We also propose an efficient mapping of point clouds to concentric spherical images, thereby bridging spherical convolutions on grids with general point clouds. We demonstrate the effectiveness of our approach in improving state-of-the-art performance on 3D classification tasks with rotated data.

97 MATHEMATICS AND COMPUTING↗

Unifying Combinatorial and Graphical Methods in Artificial Intelligence

Recently, a new graph Laplacian, called the inner product Laplacian, was introduced which generalizes many existing Laplacians, including the normalized and combinatorial Laplacian and their weighted variants. The key observation behind the inner product Laplacian is that by defining appropriate inner product spaces on the vertices and edges, the standard Laplacians can be recovered as Hodge Laplacians over the simplicial complex formed by the edges and vertices. These inner product spaces form a natural way to incorporate non-combinatorial information into the definition of a domain-specific Laplacian. In particular, in contrast to current domain-specific weighting schemes which rely solely on edge weights, information regarding the similarity of non-adjacent vertices and arbitrary pairs of edges can be effectively incorporated into the Laplacian. In order to illustrate this approach we consider the problem of calculating the potential energy of an atomistic configuration using Graph Neural Networks. In comparison with start-of-the-art approaches, such as SchNet, our approach replaces a learned (via auto-encoder) representation of the atom types with an inner product space on atoms based on scientific knowledge (e.g., electronegativity). We will illustrate how this approach captures key chemical properties of the molecules and compare the energy calculations with state-of-the-art neural network approaches. However, to compute the resulting Laplacian involves a mixture of sparse and dense matrix computation and yields a dense matrix as the basis for the graph convolution. This dense convolutional kernel necessitates moving away from the standard message passing framework for graph neural networks and increases the computational cost of applying the kernel. In order to mitigate these costs we investigate means of leveraging the mixed sparse and dense computations to reduce the overall computational cost and how these approaches can be automatically transferred to energy efficient hardware (e.g., field programmable gate arrays (FPGAs)).

97 MATHEMATICS AND COMPUTING↗

Rethinking skip connections in Spiking Neural Networks with Time-To-First-Spike coding

Time-To-First-Spike (TTFS) coding in Spiking Neural Networks (SNNs) offers significant advantages in terms of energy efficiency, closely mimicking the behavior of biological neurons. In this work, we delve into the role of skip connections, a widely used concept in Artificial Neural Networks (ANNs), within the domain of SNNs with TTFS coding. Our focus is on two distinct types of skip connection architectures: (1) addition-based skip connections, and (2) concatenation-based skip connections. We find that addition-based skip connections introduce an additional delay in terms of spike timing. On the other hand, concatenation-based skip connections circumvent this delay but produce time gaps between after-convolution and skip connection paths, thereby restricting the effective mixing of information from these two paths. To mitigate these issues, we propose a novel approach involving a learnable delay for skip connections in the concatenation-based skip connection architecture. This approach successfully bridges the time gap between the convolutional and skip branches, facilitating improved information mixing. We conduct experiments on public datasets including MNIST and Fashion-MNIST, illustrating the advantage of the skip connection in TTFS coding architectures. Additionally, we demonstrate the applicability of TTFS coding on beyond image recognition tasks and extend it to scientific machine-learning tasks, broadening the potential uses of SNNs.

97 MATHEMATICS AND COMPUTING↗

cTULIP: application of a human-based RNA-seq primary tumor classification tool for cross-species primary tumor classification in canine

The domestic dog, Canis familiaris, is quickly gaining traction as an advantageous model for use in the study of cancer, one of the leading causes of death worldwide. Naturally occurring canine cancers share clinical, histological, and molecular characteristics with the corresponding human diseases. In this study, we take a deep-learning approach to test how similar the gene expression profile of canine glioma and bladder cancer (BLCA) tumors are to the corresponding human tumors. We likewise develop a tool for identifying misclassified or outlier samples in large canine oncological datasets, analogous to that which was developed for human datasets. We test a number of machine learning algorithms and found that a convolutional neural network outperformed logistic regression and random forest approaches. We use a recently developed RNA-seq-based convolutional neural network, TULIP, to test the robustness of a human-data-trained primary tumor classification tool on cross-species primary tumor prediction. Our study ultimately highlights the molecular similarities between canine and human BLCA and glioma tumors, showing that protein-coding one-to-one homologs shared between humans and canines, are sufficient to distinguish between BLCA and gliomas. The results of this study indicate that using protein-coding one-to-one homologs as the features in the input layer of TULIP performs good primary tumor prediction in both humans and canines. Furthermore, our analysis shows that our selected features also contain the majority of features with known clinical relevance in BLCA and gliomas. Our success in using a human-data-trained model for cross-species primary tumor prediction also sheds light on the conservation of oncological pathways in humans and canines, further underscoring the importance of the canine model system in the study of human disease.

60 APPLIED LIFE SCIENCES↗

Wind Speed Prediction with Spatio–Temporal Correlation: A Deep Learning Approach

Wind speed prediction with spatio–temporal correlation is among the most challenging tasks in wind speed prediction. In this paper, the problem of predicting wind speed for multiple sites simultaneously is investigated by using spatio–temporal correlation. This paper proposes a model for wind speed prediction with spatio–temporal correlation, i.e., the predictive deep convolutional neural network (PDCNN). The model is a unified framework, integrating convolutional neural networks (CNNs) and a multi-layer perceptron (MLP). Firstly, the spatial features are extracted by CNNs located at the bottom of the model. Then, the temporal dependencies among these extracted spatial features are captured by the MLP. In this way, the spatial and temporal correlations are captured by PDCNN intrinsically. Finally, PDCNN generates the predicted wind speed by using the learnt spatio–temporal correlations. In addition, three error indices are defined to evaluate the prediction accuracy of the model on the wind turbine array. Experiment results on real-world data show that PDCNN can capture the spatio–temporal correlation effectively, and it outperforms the conventional machine learning models, including multi-layer perceptron, support vector regressor, decision tree, etc.

17 WIND ENERGY↗

Study of Anharmonicity in Zirconium Hydrides Using Inelastic Neutron Scattering and Ab-Initio Computer Modeling

The anharmonic phonon behavior in zirconium hydrides and deuterides, including ϵ-ZrH 2 , γ-ZrH, and γ-ZrD, has been investigated from aspects of inelastic neutron scattering (INS) and lattice dynamics calculations within the framework of density functional theory (DFT). The harmonic model failed to reproduce the spectral features observed in the experimental data, indicating the existence of anharmonicity in those materials and the necessity of further explanations. Here, we present a detailed study on the anharmonicity in zirconium hydrides/deuterides by exploring the 2D potential energy surface of hydrogen/deuterium atoms and solving the corresponding 2D single-particle Schrödinger equation to obtain the eigenfrequencies, which are then convoluted with the instrument resolution. The convoluted INS spectra qualitatively describe the anharmonic peaks in the experimental INS spectra and demonstrate that the anharmonicity originates from the deviations of hydrogen potentials from quadratic behavior in certain directions; the effects are apparent for the higher-order excited vibrational states, but small for the ground and first excited states.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

An Accuracy-Maximization Approach for Claims Classifiers in Document Content Analytics for Cybersecurity

This paper presents our research approach and findings towards maximizing the accuracy of our classifier of feature claims for cybersecurity literature analytics, and introduces the resulting model ClaimsBERT. Its architecture, after extensive evaluations of different approaches, introduces a feature map concatenated with a Bidirectional Encoder Representation from Transformers (BERT) model. We discuss deployment of this new concept and the research insights that resulted in the selection of Convolution Neural Networks for its feature mapping aspects. We also present our results showing ClaimsBERT to outperform all other evaluated approaches. This new claims classifier represents an essential processing stage within our vetting framework aiming to improve the cybersecurity of industrial control systems (ICS). Furthermore, in order to maximize the accuracy of our new ClaimsBERT classifier, we propose an approach for optimal architecture selection and determination of optimized hyperparameters, in particular the best learning rate, number of convolutions, filter sizes, activation function, the number of dense layers, as well as the number of neurons and the drop-out rate for each layer. Fine-tuning these hyperparameters within our model led to an increase in classification accuracy from 76% obtained with BertForSequenceClassification’s original model to a 97% accuracy obtained with ClaimsBERT.

Ameri, Kimia (ORCID:0000000328791871)↗

Seismic Waveform Inversion Capability on Resource-Constrained Edge Devices

Seismic full wave inversion (FWI) is a widely used non-linear seismic imaging method used to reconstruct subsurface velocity images, however it is time consuming, has high computational cost and depend heavily on human interaction. Recently, deep learning has accelerated it’s use in several data-driven techniques, however most deep learning techniques suffer from overfitting and stability issues. In this work, we propose an edge computing-based data-driven inversion technique based on supervised deep convolutional neural network to accurately reconstruct the subsurface velocities. Deep learning based data-driven technique depends mostly on bulk data training. In this work, we train our deep convolutional neural network (DCN) (UNet and InversionNet) on the raw seismic data and their corresponding velocity models during the training phase to learn the non-linear mapping between the seismic data and velocity models. The trained network is then used to estimate the velocity models from new input seismic data during the prediction phase. The prediction phase is performed on a resource-constrained edge device such as Raspberry Pi. Raspberry Pi provides real-time and on-device computational power to execute the inference process. In addition, we demonstrate robustness of our models to perform inversion in the presence on noise by performing both noise-aware and no-noise training and feeding the resulting trained models with noise at different signal-to-noise (SNR) ratio values. We make great efforts to achieve very feasible inference times on the Raspberry Pi for both models. Specifically, the inference times per prediction for UNet and InversionNet models on Raspberry Pi were 22 and 4 s respectively whilst inference times for both models on the GPU were 2 and 18 s which are very comparable. Finally, we have designed a user-friendly interactive graphical user interface (GUI) to automate the model execution and inversion process on the Raspberry Pi.

Manu, Daniel (ORCID:0000000154982677)↗

THE GINI COEFFICIENT AS A MORPHOLOGICAL MEASUREMENT OF STRONGLY LENSED GALAXIES IN THE IMAGE PLANE

Characterization of the morphology of strongly lensed galaxies is challenging because images of such galaxies are typically highly distorted. Lens modeling and source plane reconstruction is one approach that can provide reasonably undistorted images from which morphological measurements can be made, though at the expense of a highly spatially variable telescope point-spread function (PSF) when mapped back to the source plane. Unfortunately, modeling the lensing mass is a time- and resource-intensive process, and in many cases there are too few constraints to precisely model the lensing mass. If, however, useful morphological measurements could be made in the image plane rather than the source plane, it would bypass this issue and obviate the need for a source reconstruction process for some applications. We examine the use of the Gini coefficient as one such measurement. Because it depends on the cumulative distribution of the light of a galaxy, but not the relative spatial positions, the fact that surface brightness is conserved by lensing means that the Gini coefficient may be well preserved by strong gravitational lensing. Through simulations, we test the extent to which the Gini coefficient is conserved, including by effects due to PSF convolution and pixelization, to determine whether it is invariant enough under lensing to be used as a measurement of galaxy morphology that can be made in the image plane.

79 ASTRONOMY AND ASTROPHYSICS↗

Photometric Classification of Early-time Supernova Light Curves with SCONE

Abstract In this work, we present classification results on early supernova light curves from SCONE, a photometric classifier that uses convolutional neural networks to categorize supernovae (SNe) by type using light-curve data. SCONE is able to identify SN types from light curves at any stage, from the night of initial alert to the end of their lifetimes. Simulated LSST SNe light curves were truncated at 0, 5, 15, 25, and 50 days after the trigger date and used to train Gaussian processes in wavelength and time space to produce wavelength–time heatmaps. SCONE uses these heatmaps to perform six-way classification between SN types Ia, II, Ibc, Ia-91bg, Iax, and SLSN-I. SCONE is able to perform classification with or without redshift, but we show that incorporating redshift information improves performance at each epoch. SCONE achieved 75% overall accuracy at the date of trigger (60% without redshift), and 89% accuracy 50 days after trigger (82% without redshift). SCONE was also tested on bright subsets of SNe ( r < 20 mag) and produced 91% accuracy at the date of trigger (83% without redshift) and 95% five days after trigger (94.7% without redshift). SCONE is the first application of convolutional neural networks to the early-time photometric transient classification problem. All of the data processing and model code developed for this paper can be found in the SCONE software package 1 1 github.com/helenqu/scone located at github.com/helenqu/scone (Qu 2021).

79 ASTRONOMY AND ASTROPHYSICS↗

X-Ray Spectro-polarimetry with Photoelectric Polarimeters

We derive a generalization of forward fitting for X-ray spectroscopy to include linear polarization of X-ray sources, appropriate for the anticipated next generation of space-based photoelectric polarimeters. We show that the inclusion of polarization sensitivity requires joint fitting to three observed spectra, one for each of the Stokes parameters, I(E), U(E), and Q(E). The equations for Stokes’ I(E) (the total intensity spectrum) are identical to the familiar case with no polarization sensitivity, and for which the model-predicted spectrum is obtained by a convolution of the source spectrum, F(E′), with the familiar energy response function, ϵ(E′) R(E′, E), where ϵ(E′) and R(E′, E) are the effective area and energy redistribution matrix, respectively. In addition to the energy spectrum, the two new relations for U(E) and Q(E) include the source polarization fraction and position angle versus energy, a(E′), and ψ{sub 0}{sup ′}(E{sup ′}), respectively, and the model-predicted spectra for these relations are obtained by a convolution with the “modulated” energy response function, μ(E′) ϵ (E′)R(E, E′), where μ(E′) is the energy-dependent modulation fraction that quantifies a polarimeter’s angular response to 100% polarized radiation. We present results of simulations with response parameters appropriate for the proposed PRAXyS Small Explorer observatory to illustrate the procedures and methods, and we discuss some aspects of photoelectric polarimeters with relevance to understanding their calibration and operation.

79 ASTRONOMY AND ASTROPHYSICS↗

Development of a Machine-Learned Cruise Guide Indicator for Rotorcraft

This paper presents a machine-learned virtual cruise guide indicator (vCGI) for Chinook helicopters. Two temporal neural networks were trained and evaluated on measured data from 55 flight tests, one for the fore rotor and another for the aft rotor, to predict a vCGI value, which protects 23 components from fatigue damage during steady-state conditions. Three different classes of machine learning architectures were evaluated for prediction of the vCGI from time sequences: a temporal convolutional neural network with 1D dilated causal convolutions, a long short-term memory recurrent neural network, and an attention-based transformer architecture. The final average model accuracy on unseen flight data is currently greater than 93% for CGI values which could result in fatigue damage and 90% for normal operation CGI values. Model accuracy was improved through a series of advancements in:(1) selection of optimal training data using temporal collective variables and unsupervised learning, (2) dataset augmentation with maximum-entropy temporal collective variables, and (3) implementation of a mixture-of-experts classification- regression approach using an adversarial classification approach to assign maneuver labels. The results are presented for each advancement in model development along with lessons learned in training machine learning models on real- world, time-dependent rotorcraft data.

Boyer, Mathew↗

DMTN-021: Implementation of Image Difference Decorrelation

Herein, we describe a method for decorrelating image differences produced by the Alard and Lupton (1998) method of PSF matching. Inspired by the recent work of Zackay et al. (2016) and the prior work of Kaiser [2004], this proposed method uses a single post-subtraction convolution of an image difference to remove the neighboring pixel covariances in the image difference that result from the convolution of the template image by the PSF matching kernel. We describe the method in detail, analyze its effects on image differences (both real and simulated) as well as on detections and photometry of detected sources in decorrelated image differences. We also compare the decorrelated image differences with those resulting from a basic implementation of Zackay et al. (2016). We describe the implementation of the new correction in the LSST image differencing pipeline, and discuss potential issues and areas of future research.

79 ASTRONOMY AND ASTROPHYSICS↗

Efficient algorithm for generating spectra using line-by-lne methods

A method is presented for efficient generation of spectra using line-by-line approaches. The only approximation is replacing the line shape function with an interpolation procedure, which makes the method independent of the line profile functional form. The resulting computational savings for large number of lines is proportional to the number of frequency points in the spectral range. Therefore, for large-scale problems the method can provide speedups of two orders of magnitude or more. A method was presented to generate line-by-line spectra efficiently. The first step was to replace the explicit calculation of the profile by the Newton divided-differences interpolating polynomial. The second step is to accumulate the lines effectively reducing their number to the number of frequency points. The final step is recognizing the resulting expression as a convolution and amenable to FFT methods. The reduction in computational effort for a configuration-to-configuration transition array with large number of lines is proportional to the number of frequency points. The method involves no approximations except for replacing the explicit profile evaluation by interpolation. Specifically, the line accumulation and convolution are exact given the interpolation procedure. Furthermore, the interpolation makes the method independent of the line profile functional form contrary to other schemes using FFT methods to generate line-by-line spectra but relying on the analytic form of the profile Fourier transform. Finally, the method relies on a uniform frequency mesh. For non-uniform frequency meshes, however, the method can be applied by using a suitable temporary uniform mesh and the results interpolated onto the final mesh with little additional cost.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Spectral Fluctuations of Incoherent Radiation And Measurement of Longitudinal Bunch Profile

A method for measurement of ultrashort beam current profile I{sub b}(t) is proposed that is based on detecting fluctuations of the spectral intensity P ({omega}) of single bunch incoherent radiation. We show that the variance of the Fourier transform of the spectrum is proportional to the convolution function of the beam current. After the convolution function is found, using phase retrieval technique one can restore the shape of the pulse in many practical cases.

43 PARTICLE ACCELERATORS↗

Variable-pulse-shape pulsed-power accelerator

A variable-pulse-shape pulsed-power accelerator is driven by a large number of independent LC drive circuits. Each LC circuit drives one or more coaxial transmission lines that deliver the circuit's output power to several water-insulated radial transmission lines that are connected in parallel at small radius by a water-insulated post-hole convolute. The accelerator can be impedance matched throughout. The coaxial transmission lines are sufficiently long to transit-time isolate the LC drive circuits from the water-insulated transmission lines, which allows each LC drive circuit to be operated without being affected by the other circuits. This enables the creation of any power pulse that can be mathematically described as a time-shifted linear combination of the pulses of the individual LC drive circuits. Therefore, the output power of the convolute can provide a variable pulse shape to a load that can be used for magnetically driven, quasi-isentropic compression experiments and other applications.

24 POWER TRANSMISSION AND DISTRIBUTION↗