Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Feature Extraction”

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 1,261 records · Page 70
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

GeoAI: spatially explicit artificial intelligence techniques for geographic knowledge discovery and beyond

Recent progress in Artificial Intelligence (AI) techniques, the large-scale availability of high-quality data, as well as advances in both hardware and software to efficiently process these data, are transforming a range of fields from computer vision and natural language processing to autonomous driving and healthcare. For example, the availability of high-resolution geographic data and high-performance computing techniques together with deep learning fuel progress in fast and accurate object detection. Recent examples of GeoAI work include the detections of terrain features and densely-distributed building footprints, information extraction from scanned historical maps, semantic classification (e.g. LiDAR point clouds), novel methods for spatial interpolation, and advances in traffic forecasting. Similarly, machine learning and natural language processing are facilitating the extraction of geographic information from unstructured (textual) data, such as news articles and Wikipedia as well as the matching of natural features in multiple gazetteers.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2018

Online Diagnosis of Performance Variation in HPC Systems Using Machine Learning

As the size and complexity of HPC systems grow in line with advancements in hardware and software technology, HPC systems increasingly suffer from performance variation due to shared resource contention as well as software- and hardware-related problems. Such performance variations can lead to failures and inefficiencies, and are among the main challenges in system resiliency. To minimize the impact of performance variation, one must quickly and accurately detect and diagnose the anomalies that cause the variation and take mitigating actions. However, it is difficult to identify anomalies based on the voluminous, high-dimensional, and noisy data collected by system monitoring infrastructures. This paper presents a novel machine learning based framework to automatically diagnose performance anomalies at runtime. Our framework leverages historical resource usage data to extract signatures of previously-observed anomalies. We first convert the collected time series data into easy-to-compute statistical features. We then identify the features that are required to detect anomalies, and extract the signatures of these anomalies. At runtime, we use these signatures to diagnose anomalies with negligible overhead. Here, we evaluate our framework using experiments on a real-world HPC supercomputer and demonstrate that our approach successfully identifies 98% of injected anomalies and consistently outperforms existing anomaly diagnosis techniques.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1993

A Novel Optical/digital Processing System for Pattern Recognition

This paper describes two processing algorithms that can be implemented optically: the Radon transform and angular correlation. These two algorithms can be combined in one optical processor to extract all the basic geometric and amplitude features from objects embedded in video imagery. We show that the internal amplitude structure of objects is recovered by the Radon transform, which is a well-known result, but, in addition, we show simulation results that calculate angular correlation, a simple but unique algorithm that extracts object boundaries from suitably threshold images from which length, width, area, aspect ratio, and orientation can be derived. In addition to circumventing scale and rotation distortions, these simulations indicate that the features derived from the angular correlation algorithm are relatively insensitive to tracking shifts and image noise. Some optical architecture concepts, including one based on micro-optical lenslet arrays, have been developed to implement these algorithms. Simulation test and evaluation using simple synthetic object data will be described, including results of a study that uses object boundaries (derivable from angular correlation) to classify simple objects using a neural network.

Boone, Bradley G.↗
DOE OSTI2022

A meta-analysis of semantic classification of citations

The aim of this literature review is to examine the current state of the art in the area of citation classification. In particular, we investigate the approaches for characterizing citations based on their semantic type. We conduct this literature review as a meta-analysis covering 60 scholarly articles in this domain. Although we included some of the manual pioneering works in this review, more emphasis is placed on the later automated methods, which use Machine Learning and Natural Language Processing (NLP) for analyzing the fine-grained linguistic features in the surrounding text of citations. The sections are organized based on the steps involved in the pipeline for citation classification. Specifically, we explore the existing classification schemes, data sets, pre-processing methods, extraction of contextual and non-contextual features, and the different types of classifiers and evaluation approaches. The review highlights the importance of identifying the citation types for research evaluation, the challenges faced by the researchers in the process, and the existing research gaps in this field.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2022

Machine Learning Guided Synthesis of Flash Graphene

Advances in nanoscience have enabled the synthesis of nanomaterials, such as graphene, from low-value or waste materials through flash Joule heating. Though this capability is promising, the complex and entangled variables that govern nanocrystal formation in the Joule heating process remain poorly understood. In this work, machine learning (ML) models are constructed to explore the factors that drive the transformation of amorphous carbon into graphene nanocrystals during flash Joule heating. An XGBoost regression model of crystallinity achieves an r 2 score of 0.8051 ± 0.054. Feature importance assays and decision trees extracted from these models reveal key considerations in the selection of starting materials and the role of stochastic current fluctuations in flash Joule heating synthesis. Furthermore, partial dependence analyses demonstrate the importance of charge and current density as predictors of crystallinity, implying a progression from reaction-limited to diffusion-limited kinetics as flash Joule heating parameters change. Finally, a practical application of the ML models is shown by using Bayesian meta-learning algorithms to automatically improve bulk crystallinity over many Joule heating reactions. Furthermore, these results illustrate the power of ML as a tool to analyze complex nanomanufacturing processes and enable the synthesis of 2D crystals with desirable properties by flash Joule heating.

01 COAL, LIGNITE, AND PEAT↗
DOE OSTI2026

Velocity Extraction Using Complete Time-Domain Waveform Data and Audio Machine Learning

We developed a new machine learning-based tool for extracting information from interferometry measurements: MIDWAZE (Modular Interferometry Direct Waveform AnalyZEr). This paper showcases MIDWAZE’s ability to extract an object’s velocity information from Photonic Doppler Velocimetry (PDV) data at near-human accuracy with little to no human intervention. MIDWAZE can extract velocities roughly 350 times as fast as a human analyst "rushing" to complete their extractions, with similar extraction accuracy. MIDWAZE’s most outstanding feature is that it operates directly in waveform/temporal space, freeing analysis from certain limitations imposed by traditional spectrogram-based approaches and opening the way to "phase aware" PDV analysis. MIDWAZE also has limited ability to discriminate between different solid objects, which we develop as a first step towards automated discrimination of different kinds of objects such as ejecta clouds.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Recovery of p -Hydroxybenzoic Acid from Cu-Catalyzed Alkaline Hydrogen Peroxide Pretreatment of Hybrid Poplar

p-Hydroxybenzoic acid (pHBA) is present in some hardwood biomass feedstocks as an ester attached to the polymeric lignin subunits. Here, we report the isolation and recovery of pHBA from alkaline liquor waste streams obtained from fractionation of hybrid poplar using the “Cu-AHP process”. This process features two stages: alkaline pre-extraction (AP) of the biomass and copper-catalyzed alkaline hydrogen peroxide pretreatment. On a biomass scale of 100 g, 0.5 g of pHBA with a purity of 96% was obtained after decolorization and crystallization. The scalability of the purification process was demonstrated by using liquor obtained from the first-stage AP with 900 g of poplar biomass to afford 3.5 g of crystalline pHBA with 97% purity. Altogether, these results show that pHBA may be isolated and purified from waste streams generated in the two-stage Cu-AHP process without any alteration of the process conditions or impact on carbohydrate and lignin fractionation.

09 BIOMASS FUELS↗
DOE OSTI2012

Dielectric Function Spectra and Critical-Point Energies of Cu2ZnSnSe4 from 0.5 to 9.0 eV

We present dielectric function {var_epsilon} = {var_epsilon}{sub 1} + i{var_epsilon}{sub 2} spectra and critical-point energies of Cu{sub 2}ZnSnSe{sub 4} determined by spectroscopic ellipsometry from 0.5 to 9.0 eV. We reduce artifacts from surface overlayers to the maximum extent possible by performing chemical-mechanical polishing and wet-chemical etching of the surface of a Cu{sub 2}ZnSnSe{sub 4} thin film. Ellipsometric data are analyzed by the multilayer model and the {var_epsilon} spectra are extracted. The data exhibit numerous spectral features associated with critical points, whose energies are obtained by fitting standard lineshapes to second energy derivatives of the data. The experimental results are in good agreement with the {var_epsilon} spectra calculated within the GW quasi-particle approximation, and possible origins of the pronounced critical-point structures are identified.

14 SOLAR ENERGY↗
DOE OSTI2015

Synthesis and characterization of nanorods for magnetic rotational spectroscopy

Magnetic rotational spectroscopy (MRS) with magnetic nanoprobes is a powerful method for in-situ characterization of minute amounts of complex fluids. In MRS, a uniformly rotating magnetic field rotates magnetic micro- or nano-probes in the liquid and one analyzes the features of the probe rotation to extract rheological parameters of liquids. Magnetic properties of nanoprobes must be well characterized and understood to make results reliable and reproducible. Ni and Co nanorods synthesized by electrochemical template synthesis in alumina membranes are discussed in applications to MRS. We employ alternating gradient field magnetometry, X-ray diffraction, and magnetic force microscopy to evaluate and compare properties of these nanorods and study their performance as the MRS probes. It is shown that nickel nanorods do not seem to violate any assumptions of the MRS rigid dipole theory, while cobalt nanorods do.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2015

Particle-in-cell based parameter study of 12-cavity, 12-cathode rising-sun relativistic magnetrons for improved performance

Particle-in-cell simulations are performed to analyze the efficiency, output power and leakage currents in a 12-Cavity, 12-Cathode rising-sun magnetron with diffraction output (MDO). The central goal is to conduct a parameter study of a rising-sun magnetron that comprehensively incorporates performance enhancing features such as transparent cathodes, axial extraction, the use of endcaps, and cathode extensions. Our optimum results demonstrate peak output power of about 2.1 GW, with efficiencies of ∼70% and low leakage currents at a magnetic field of 0.45 Tesla, a 400 kV bias with a single endcap, for a range of cathode extensions between 3 and 6 centimeters.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Let it rip: The mechanics of self-bisection in asexual planarians determines their population reproductive strategies

Asexual freshwater planarians reproduce by transverse bisection (binary fission) into two pieces. This process produces a head and a tail, which fully regenerate within 1-2 weeks. How planarians split into two offspring - using only their musculature and substrate traction – is a challenging biomechanics problem. We found that three different species, Dugesia japonica, Girardia tigrina and Schmidtea mediterranea, have evolved three different mechanical solutions to self-bisect. Using time lapse imaging of the fission process, we quantitatively characterize the main steps of division in the three species and extract the distinct and shared key features. Across the three species, planarians actively alter their body shape, regulate substrate traction, and use their muscles to generate tensile stresses large enough to overcome the ultimate tensile strength of the tissue. Moreover, we show that how each planarian species divides dictates how resources are split among its offspring. This ultimately determines offspring survival and reproductive success. Furthermore, heterospecific differences in the mechanics of self-bisection of individual worms explain the observed differences in the population reproductive strategies of different planarian species.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Photovoltaic Cable Connectors: A Comparative Assessment of the Present State of the Industry

The consequences of failure for balance-of-systems components (such as photovoltaic (PV) cable connectors) include offline module string(s); low system voltage; arc, ground, insulation, and overtemperature faults; triggered fuse(s); system shutdown; and fire. The degradation modes for connectors are studied here through an industry survey and its subsequent examination, which are compared with field-degraded specimens. A total of 117 specimens were obtained from a variety of locations and climates or accelerated tests. A failure analysis for connectors from PV installations was developed (and applied to 54 specimens), including nondestructive examinations (photography, a custom resistance-current scan, and X-ray computed tomography) and destructive examinations (featuring milling of the external plastic, extraction of the internal convolute spring, and potting and polishing in cross section). Surface and through-thickness composition of the metal pins and springs was quantified using scanning electron microscopy with energy-dispersive X-ray spectroscopy. Fourier transform infrared spectroscopy was used to verify the base polymer materials and compare the chemical structure of the connector body, bushing, end nut, and o-ring. Thermogravimetric analysis and differential scanning calorimetry were used to further verify the degradation of the same polymeric components.

cable connectors↗
DOE OSTI2023

Characterizing Quantum Classifier Utility in Natural Language Processing Workflows

Quantum Natural Language Processing (QNLP) develops natural language processing (NLP) models for deployment on quantum computers. We explore feature and data prototype selection techniques to address challenges posed by encoding high dimensional features. Our study builds quantum circuit classifiers that includes classical feature pre-processing, quantum embedding and quantum model training. The quantum models are built on 4 or 6 qubits and the quantum neural network (QNN) uses the established bricklayer design. We compare the dependence of model performance (in terms of accuracy and F1 scores) on feature length, embedding gates and parameterized unitary design. We compare the performance of quantum machine learning models to classical convolution neural network model (CNN) on binary and multi-class classification tasks using two datasets of synthetic features and labels. The first is the ECP-CANDLE P3B3 dataset a corpus of synthetically generated cancer pathology reports. The second dataset is extracted from well-known benchmark dataset (MADELON) - features are generated with a combination of informative, repeated and uninformative features. Both datasets are used for binary classification and multi-class classification with 3 classes. We observe robust, accurate performance from all models on the binary classification tasks, but multiclass classification is a challenge for the quantum models-there is a notable decrease in accuracy when using 3 classes. Overall the performance is comparable in terms of recall and accuracy between QNNs and CNNs, even with large datasets. These results provide a point of comparison between quantum and classical models on real-world datasets.

Hamilton, Kathleen↗
DOE OSTI2019

Bridging the Gap: Thermal Properties in Composites from Microscale Constituents to Macroscale Performance

In this work, a finite element analysis model was developed to predict the frequency domain thermal response to heat input from a gaussian heat source for arbitrary 2-dimensional geometries. The model was used for geometric parameter fitting of samples experimentally measured using Frequency Domain Thermoreflectance (FDTR). Inverse fitting was performed to on experimental data to extract characteristic geometries of samples with feature sizes smaller than the Il e 2 radius of the laser used to probe the system. Further simulations were done to demonstrate the ability of the system to detect a variety of feature types. Silicon wafers with 50 nm to 1 pm of wet thermal oxide were measured and fit. Finally, microparticles suspended in epoxy were imaged using FDTR.

42 ENGINEERING↗
DOE OSTI2024

Photovoltaic Cable Connectors: A Comparative Assessment of the Present State of the Industry [Slides]

The consequences of failure for balance of systems (BoS) components (such as PV cable connectors) include offline module string(s); low system voltage; arc, ground, insulation, and over-temperature faults; triggered fuse(s); system shutdown; and fire. The degradation modes for connectors are studied here through an industry survey and its subsequent examination, which are compared to field-degraded specimens. 117 specimens were obtained from a variety of locations and climates or accelerated tests. A failure analysis for connectors from PV installations was developed (and applied to 54 specimens) including nondestructive examinations (photography, a custom resistance-current scan, and X-ray computed tomography) and destructive examinations (featuring milling of the external plastic, extraction of the internal convolute spring, and potting and polishing in cross-section). Surface and through-thickness composition of the metal pins and springs was quantified using scanning electron microscopy with energy-dispersive X-ray spectroscopy. Fourier-transform infrared spectroscopy was used to verify the base polymer materials and compare the chemical structure of the connector body, bushing, end nut, and o-ring. Thermogravimetric analysis and differential scanning calorimetry were used to further verify the degradation of the same polymeric components. Updated from 2023 NIST/UL Workshop on Photovoltaic Materials Durability (website: https://events.ul.com/WPMogn?rt=aAuoWsl4E0KaORLCMeOgfA) and 2024 PVRW workshop (https://pvrw.nrel.gov/past-proceedings).

14 SOLAR ENERGY↗
DOE OSTI2025

Low-Cost Identification and Monitoring of Diverse MELs in Residential and Commercial Buildings with PowerBlade (Final Technical Report)

This report describes our progress in developing a scalable wireless metering system that integrates plug-load energy meters that measure real, reactive, and apparent power along with load monitoring based on extracting high-fidelity electrical waveform features collected at every load to capture power profiles and automatically identify and categorize MELs, and make this technology available to the research, commercial, and government sectors.

47 OTHER INSTRUMENTATION↗
NASA NTRS1975

A boundary finding algorithm and its applications

An algorithm for locating gray level and/or texture edges in digitized pictures is presented. The algorithm is based on the concept of hypothesis testing. The digitized picture is first subdivided into subsets of picture elements, e.g., 2 x 2 arrays. The algorithm then compares the first- and second-order statistics of adjacent subsets; adjacent subsets having similar first- and/or second-order statistics are merged into blobs. By continuing this process, the entire picture is segmented into blobs such that the picture elements within each blob have similar characteristics. The boundaries between the blobs comprise the boundaries. The algorithm always generates closed boundaries. The algorithm was developed for multispectral imagery of the earth's surface. Application of this algorithm to various image processing techniques such as efficient coding, information extraction (terrain classification), and pattern recognition (feature selection) are included.

Gupta, J. N.↗
NASA NTRS1975

Geological significance of features observed in Colorado from orbital altitudes

Three major investigations using LANDSAT and Skylab imagery concerned with analyses of color anomalies and linear features of central Colorado are discussed. The studies conducted are concerned with the geological significance of spectral and spatial features on the images. Color anomalies in Skylab photographs were analyzed and evaluated for locating indicators of mineralization. The relationships were determined of all linear features in a LANDSAT image to the rock joint systems and the detectable larger geologic structures; techniques for extracting that geologic information are indicated. Some anomalous megalinear features in LANDSAT and Skylab images are analyzed which transect major structures and, their associated geologic features are described.

Sawatzky, D. L.↗