Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “binary classification”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

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↗
DOE OSTI2020

Computer-aided classification of suspicious pigmented lesions using wide-field images

Early identification of melanoma is conducted through whole-body visual examinations to detect suspicious pigmented lesions, a situation that fluctuates in accuracy depending on the experience and time of the examiner. Computer-aided diagnosis tools for skin lesions are typically trained using pre-selected single-lesion images, taken under controlled conditions, which limits their use in wide-field scenes. Here, we propose a computer-aided classifier system with such input conditions to aid in the rapid identification of suspicious pigmented lesions at the primary care level. 133 patients with a multitude of skin lesions were recruited for this study. All lesions were examined by a board-certified dermatologist and classified into “suspicious” and “non-suspicious”. A new clinical database was acquired and created by taking Wide-Field images of all major body parts with a consumer-grade camera under natural illumination condition and with a consistent source of image variability. 3–8 images were acquired per patient on different sites of the body, and a total of 1759 pigmented lesions were extracted. A machine learning classifier was optimized and build into a computer aided classification system to binary classify each lesion using a suspiciousness score. In a testing set, our computer-aided classification system achieved a sensitivity of 100% for suspicious pigmented lesions that were later confirmed by dermoscopy examination (“SPL_A”) and 83.2% for suspicious pigmented lesions that were not confirmed after examination (“SPL_B”). Sensitivity for non-suspicious lesions was 72.1%, and accuracy was 75.9%. With these results we defined a suspiciousness score that is aligned with common macro-screening (naked eye) practices. This work demonstrates that wide-field photography combined with computer-aided classification systems can distinguish suspicious from non-suspicious pigmented lesions, and might be effective to assess the severity of a suspicious pigmented lesions. We believe this approach could be useful to support skin screenings at a population-level.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2011

Parametrization and Classification of 20 Billion LSST Objects: Lessons from SDSS

The Large Synoptic Survey Telescope (LSST) will be a large, wide-field ground-based system designed to obtain, starting in 2015, multiple images of the sky that is visible from Cerro Pachon in Northern Chile. About 90% of the observing time will be devoted to a deep-wide-fast survey mode which will observe a 20,000 deg{sup 2} region about 1000 times during the anticipated 10 years of operations (distributed over six bands, ugrizy). Each 30-second long visit will deliver 5{sigma} depth for point sources of r {approx} 24.5 on average. The co-added map will be about 3 magnitudes deeper, and will include 10 billion galaxies and a similar number of stars. We discuss various measurements that will be automatically performed for these 20 billion sources, and how they can be used for classification and determination of source physical and other properties. We provide a few classification examples based on SDSS data, such as color classification of stars, color-spatial proximity search for wide-angle binary stars, orbital-color classification of asteroid families, and the recognition of main Galaxy components based on the distribution of stars in the position-metallicity-kinematics space. Guided by these examples, we anticipate that two grand classification challenges for LSST will be (1) rapid and robust classification of sources detected in difference images, and (2) simultaneous treatment of diverse astrometric and photometric time series measurements for an unprecedentedly large number of objects.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Field validation of isotropic analytical models for simulating fabric shades

Fabric roller shades are common shading materials used in commercial and residential buildings. Accurately characterizing and modeling shades helps practitioners select the appropriate product and its control strategy based on climate and occupants' priorities, such as visual comfort and view to outdoors. Previous studies established a generalized method for modeling complex fenestration systems using data-driven tabulated bidirectional scattering distribution functions. However, deploying such a method at scale to all fabric shading products on the market is too costly and time-consuming. Analytical models that are based on a limited set of measurements (e.g., normal-normal and normal-hemispherical visible transmittance and reflectance, and directional cut-off angles) can be used to model the wide variety of shading products on the market. This study evaluates the performance of two isotropic analytical models, Roos-Wienold and Modified-Kotey, for modeling fabric roller shades, with a focus on the model's ability to predict occupant visual comfort. The performance evaluation was conducted through laboratory and field measurements and simulations. The results showed that both models are sufficient for predicting vertical illuminance at seated eye-level. Roos-Wienold model was able to predict binary visual comfort classification (glare/no-glare) under a wide range of luminance conditions, while Modified-Kotey model did not perform as well under high-contrast low-adaptation conditions. Both models are insufficient in predicting visual comfort at a four-point scale (e.g., imperceptible, perceptible, disturbing, intolerable). The two isotropic models become less accurate when the fabric exhibits high anisotropy.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2026

A unified large language model–based framework for heterogeneous PV image diagnosis

With advances in imaging technologies, modern photovoltaic (PV) systems generate large volumes of heterogeneous image data, including visible, electroluminescence (EL), and infrared (IR) images. Existing PV image analysis models, particularly deep learning approaches, are typically task-specific and lack cross-modality generalization. To address this limitation, this paper proposes an open-source large language model (LLM)–based unified framework for heterogeneous PV image diagnostics. Through task-aware diagnostic prompting, the framework enables analysis of visible, EL, and IR images within a single pipeline, supporting both zero-shot and few-shot inference and binary and multiclass classification. It is compatible with state-of-the-art multimodal LLMs, including ChatGPT, Gemini, Claude, Qwen, and CLIP. The framework is evaluated on PV module condition classification (clean, soiling, snow, hail, and bird droppings) using visible images, cell crack detection using EL images, and hotspot detection using IR images. GPT-5.1 in few-shot mode achieves the best performance, with classification accuracy exceeding 97.3%. Open-source models such as Qwen and CLIP also deliver competitive results on visible images (around 90% accuracy), though their performance is more limited on EL and IR modalities. On the full ELPV dataset, the framework achieves 83.5% zero-shot accuracy, within 2.8% of the supervised CNN baseline, confirming scalability to larger benchmarks. Practical aspects such as reproducibility, response latency, and confidence estimation are systematically analyzed. The framework operates across PV image modalities without modality- or task-specific training, making it well suited as a rapid pre-screening tool to support downstream detailed diagnostics. A benchmark dataset of diverse labeled PV images is also released.

Li, Baojie↗
DOE OSTI2021

An end-to-end trainable hybrid classical-quantum classifier

Abstract We introduce a hybrid model combining a quantum-inspired tensor network and a variational quantum circuit to perform supervised learning tasks. This architecture allows for the classical and quantum parts of the model to be trained simultaneously, providing an end-to-end training framework. We show that compared to the principal component analysis, a tensor network based on the matrix product state with low bond dimensions performs better as a feature extractor for the input data of the variational quantum circuit in the binary and ternary classification of MNIST and Fashion-MNIST datasets. The architecture is highly adaptable and the classical-quantum boundary can be adjusted according to the availability of the quantum resource by exploiting the correspondence between tensor networks and quantum circuits.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Radiological Anomaly Detection And Identification (RADAI) v1.0

The Radiological Anomaly Detection and Identification (RADAI) software package is a python library for implementing, training, and storing algorithms that detect and identify anomalies in gamma-ray spectra. The library defines a general framework for implementing detection (binary) and identification (classification) algorithms, objects to encapsulate the results of analyses, a variety of temporal filtering tools that can be used in constructing algorithms, and conceptual design that allows easy reading and writing of algorithms (and their time dependent state). In addition to this framework, the library includes implementations of a variety of algorithms from the scientific literature including: gross-counts k-sigma, SPRT, N-SCRAD, Region of Interest, and Censored Energy Window. The implementation of these algorithms within the RADAI package was done to facilitate user-initiated training and configuration to by applied to different gamma-ray detector types. Finally, benchmarked and synthetic datasets will be made available for standardized algorithm characterization with corresponding utilities in the RADAI package for data access and processing.

Joshi, Tenzing↗
DOE OSTI2019

Conditional Generative Adversarial Networks (cGANs) for Near Real-Time Precipitation Estimation from Multispectral GOES-16 Satellite Imageries—PERSIANN-cGAN

In this paper, we present a state-of-the-art precipitation estimation framework which leverages advances in satellite remote sensing as well as Deep Learning (DL). The framework takes advantage of the improvements in spatial, spectral and temporal resolutions of the Advanced Baseline Imager (ABI) onboard the GOES-16 platform along with elevation information to improve the precipitation estimates. The procedure begins by first deriving a Rain/No Rain (R/NR) binary mask through classification of the pixels and then applying regression to estimate the amount of rainfall for rainy pixels. A Fully Convolutional Network is used as a regressor to predict precipitation estimates. The network is trained using the non-saturating conditional Generative Adversarial Network (cGAN) and Mean Squared Error (MSE) loss terms to generate results that better learn the complex distribution of precipitation in the observed data. Common verification metrics such as Probability Of Detection (POD), False Alarm Ratio (FAR), Critical Success Index (CSI), Bias, Correlation and MSE are used to evaluate the accuracy of both R/NR classification and real-valued precipitation estimates. Statistics and visualizations of the evaluation measures show improvements in the precipitation retrieval accuracy in the proposed framework compared to the baseline models trained using conventional MSE loss terms. This framework is proposed as an augmentation for PERSIANN-CCS (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Network- Cloud Classification System) algorithm for estimating global precipitation.

42 ENGINEERING↗
DOE OSTI2020

Genetic Algorithm for Hyperparameter Optimization in Gaussian Process Modeling

A genetic algorithm is developed and applied to optimize hyperparameters of convolutional recursively determined dual neural network-Gaussian process (NNGP) kernels. As a specific application of the combined GPNN-GA algorithm, it is applied to image classification in publicly available data of Hyper Suprime-Cam Subaru Strategic Program. Matthews correlation coefficient is calculated based on results of binary star-galaxy classification and used as a fitting function of the GA module of the algorithm. The simulation results confirm significant improvement of the classification accuracy with optimized hyperparameters.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2012

THE CLASSIFICATION OF KEPLER B-STAR VARIABLES

The light curves of 252 B-star candidates in the Kepler database are analyzed in a similar fashion to that done by Balona et al. to further characterize B-star variability, increase the sample of variable B stars for future study, and to identify stars whose power spectra include particularly interesting features such as frequency groupings. Stars are classified as either constant light emitters, {beta} Cep stars, slowly pulsating B stars (SPBs), hybrid pulsators, binaries or stars whose light curves are dominated by rotation (Bin/Rot), hot subdwarfs, or white dwarfs. One-hundred stars in our sample were found to be either light constants or to be variable at a level of less than 0.02 mmag. We increase the number of candidate B-star variables found in the Kepler database by Balona et al. in the following fashion: {beta} Cep stars from 0 to 10, SPBs from eight to 54, hybrid pulsators from seven to 21, and Bin/Rot stars from 23 to 82. For comparison purposes, approximately 51 SPBs and six hybrids had been known prior to 2007. The number of {beta} Cep stars known prior to 2004 was 93. A secondary result of this study is the identification of an additional 11 pulsating white dwarf candidates, four of which possess frequency groupings.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2011

PHOTOMETRIC TYPE Ia SUPERNOVA CANDIDATES FROM THE THREE-YEAR SDSS-II SN SURVEY DATA

We analyze the three-year Sloan Digital Sky Survey II (SDSS-II) Supernova (SN) Survey data and identify a sample of 1070 photometric Type Ia supernova (SN Ia) candidates based on their multiband light curve data. This sample consists of SN candidates with no spectroscopic confirmation, with a subset of 210 candidates having spectroscopic redshifts of their host galaxies measured while the remaining 860 candidates are purely photometric in their identification. We describe a method for estimating the efficiency and purity of photometric SN Ia classification when spectroscopic confirmation of only a limited sample is available, and demonstrate that SN Ia candidates from SDSS-II can be identified photometrically with {approx}91% efficiency and with a contamination of {approx}6%. Although this is the largest uniform sample of SN candidates to date for studying photometric identification, we find that a larger spectroscopic sample of contaminating sources is required to obtain a better characterization of the background events. A Hubble diagram using SN candidates with no spectroscopic confirmation, but with host galaxy spectroscopic redshifts, yields a distance modulus dispersion that is only {approx}20%-40% larger than that of the spectroscopically confirmed SN Ia sample alone with no significant bias. A Hubble diagram with purely photometric classification and redshift-distance measurements, however, exhibits biases that require further investigation for precision cosmology.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2010

REVISED SUPERNOVA RATES FROM THE IfA DEEP SURVEY

The IfA Deep Survey uncovered {approx} 130 thermonuclear supernova (TN SN, i.e., Type Ia) candidates at redshifts from z = 0.1 out to beyond z = 1. The TN SN explosion rates derived from these data have been controversial, conflicting with evidence emerging from other surveys. This work revisits the IfA Deep Survey to re-evaluate the photometric evidence. Applying the SOFT program to the light curves of all SN candidates, we derive new classification grades and redshift estimates. We find a volumetric rate for z {approx} 0.5 that is substantially smaller than the originally published values, bringing the revised IfA Deep rate into good agreement with other surveys. With our improved photometric analysis techniques, we are able to confidently extend the rate measurements to higher redshifts and we find a steadily increasing TN SN rate, with no indication of a peak out to z = 1.05.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2010

THE DUSTY NOVA V1065 CENTAURI (NOVA CEN 2007): A SPECTROSCOPIC ANALYSIS OF ABUNDANCES AND DUST PROPERTIES

We examine the ejecta evolution of the classical nova V1065 Centauri, constructing a detailed picture of the system based on spectrophotometric observations obtained from 9 to approximately 900 days post-outburst with extensive coverage from optical to mid-infrared wavelengths. We estimate a reddening toward the system of E(B-V) = 0.5 {+-} 0.1, based upon the B - V color and analysis of the Balmer decrement, and derive a distance estimate of 8.7{sup +2.8}{sub -2.1} kpc. The optical spectral evolution is classified as P {sup o}{sub fe} N{sub ne} A{sub o} according to the CTIO Nova Classification system of Williams et al. Photoionization modeling yields absolute abundance values by number, relative to solar of He/H = 1.6 {+-} 0.3, N/H = 144 {+-} 34, O/H = 58 {+-} 18, and Ne/H = 316 {+-} 58 for the ejecta. We derive an ejected gas mass of M{sub g} = (1.6 {+-} 0.2) x 10{sup -4} M{sub sun}. The infrared excess at late epochs in the evolution of the nova arises from dust condensed in the ejecta composed primarily of silicate grains. We estimate a total dust mass, M{sub d} , of order (0.2-3.7) x 10{sup -7} M{sub sun}, inferred from modeling the spectral energy distribution observed with the Spitzer IRS and Gemini-South GNIRS spectrometers. Based on the speed class, neon abundance, and the predominance of silicate dust, we classify V1065 Cen as an ONe-type classical nova.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Accelerating Random Forest Classification on GPU and FPGA

Random Forests (RFs) are a commonly used machine learning method for classification and regression tasks spanning a variety of application domains, including bioinformatics, business analytics, and software optimization. While prior work has focused primarily on improving performance of the training of RFs, many applications, such as malware identification, cancer prediction, and banking fraud detection, require fast RF classification. In this work, we accelerate RF classification on GPU and FPGA. In order to provide efficient support for large datasets, we propose a hierarchical memory layout suitable to the GPU/FPGA memory hierarchy. We design three RF classification code variants based on that layout, and we investigate GPU- and FPGA-specific considerations for these kernels. Our experimental evaluation, performed on an Nvidia Xp GPU and on a Xilinx Alveo U250 FPGA accelerator card using publicly available datasets on the scale of millions of samples and tens of features, covers various aspects. First, we evaluate the performance benefits of our hierarchical data structure over the standard compressed sparse row (CSR) format. Second, we compare our GPU implementation with cuML, a machine learning library targeting Nvidia GPUs. Third, we explore the performance/accuracy tradeoff resulting from the use of different tree depths in the RF. Finally, we perform a comparative performance analysis of our GPU and FPGA implementations. Our evaluation shows that for high accuracy targets, our GPU implementation yields 5-9x speedup over CSR, and up to a 2x speedup over cuML.

FPGA, Xilinx FPGA, GPU, Random Forest classificati↗
DOE OSTI2015

Discrimination of Mild Cognitive Impairment and Alzheimer′s Disease Using Transfer Entropy Measures of Scalp EEG

Mild cognitive impairment (MCI) is a neurological condition related to early stages of dementia including Alzheimer′s disease (AD). This study investigates the potential of measures of transfer entropy in scalp EEG for effectively discriminating between normal aging, MCI, and AD participants. Resting EEG records from 48 age‐matched participants (mean age 75.7 years)—15 normal controls, 16 MCI, and 17 early AD—are examined. The mean temporal delays corresponding to peaks in inter‐regional transfer entropy are computed and used as features to discriminate between the three groups of participants. Three‐way classification schemes based on binary support vector machine models demonstrate overall discrimination accuracies of 91.7— 93.8%, depending on the protocol condition. These results demonstrate the potential for EEG transfer entropy measures as biomarkers in identifying early MCI and AD. Moreover, the analyses based on short data segments (two minutes) render the method practical for a primary care setting.

McBride, Joseph↗
DOE OSTI2017

The Galah Survey: Classification and Diagnostics with t-SNE Reduction of Spectral Information

Galah is an ongoing high-resolution spectroscopic survey with the goal of disentangling the formation history of the Milky Way using the fossil remnants of disrupted star formation sites that are now dispersed around the Galaxy. It is targeting a randomly selected magnitude-limited ( V ≤ 14) sample of stars, with the goal of observing one million objects. To date, 300,000 spectra have been obtained. Not all of them are correctly processed by parameter estimation pipelines, and we need to know about them. We present a semi-automated classification scheme that identifies different types of peculiar spectral morphologies in an effort to discover and flag potentially problematic spectra and thus help to preserve the integrity of the survey results. To this end, we employ the recently developed dimensionality reduction technique t-SNE ( t -distributed stochastic neighbor embedding), which enables us to represent the complex spectral morphology in a two-dimensional projection map while still preserving the properties of the local neighborhoods of spectra. We find that the majority (178,483) of the 209,533 Galah spectra considered in this study represents normal single stars, whereas 31,050 peculiar and problematic spectra with very diverse spectral features pertaining to 28,579 stars are distributed into 10 classification categories: hot stars, cool metal-poor giants, molecular absorption bands, binary stars, H α /H β emission, H α /H β emission superimposed on absorption, H α /H β P-Cygni, H α /H β inverted P-Cygni, lithium absorption, and problematic. Classified spectra with supplementary information are presented in the catalog, indicating candidates for follow-up observations and population studies of the short-lived phases of stellar evolution.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2011

THE CONTINUING OUTBURST OF V1647 ORIONIS: WINTER/SPRING 2011 OBSERVATIONS

We present optical and near-IR observations of the young eruptive variable star V1647 Orionis which illuminates McNeil's Nebula. In late 2003, V1647 Ori was observed to brighten by around 5 mag to r' = 17.7. In early 2006 the star faded back to its quiescent brightness of r' {approx} 23, however in mid-2008 it brightened yet again by {approx}5 mag. Our new observations, taken in early 2011, show V1647 Ori to be in an elevated photometric state with an optical brightness similar to the value found at the start of the 2003 and 2008 outbursts. Optical images taken between 2008 and 2011 suggest that the star has remained in outburst from mid-2008 to the present. H{alpha} and the far-red Ca II triplet lines remain in emission with H{alpha} possessing a significant P Cygni profile. A self-consistent study of the accretion luminosity and rate using data taken in 2004, 2007, 2008, and 2011 indicates that when bright, V1647 Ori has values of 16 {+-} 2 L{sub sun} and (4 {+-} 2) x 10{sup -6} M{sub sun} yr{sup -1}, respectively. We support the premise that the accretion luminosity and rate both declined by a factor of 2-3 during the 5 mag fading in 2007. However, a significant part of the fading was due to either variable extinction or dust reformation. We discuss these new observations in relation to previous published data and the classification schemes for young eruptive variables.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2017

A Double-line M-dwarf Eclipsing Binary from CSS × SDSS

Eclipsing binaries offer a unique opportunity to determine basic stellar properties. With the advent of wide-field camera and all-sky time-domain surveys, thousands of eclipsing binaries have been charted via light curve classification, yet their fundamental properties remain unexplored mainly due to the extensive efforts needed for spectroscopic follow-ups. In this paper, we present the discovery of a short-period ( P = 0.313 day), double-lined M-dwarf eclipsing binary, CSSJ114804.3+255132/SDSSJ114804.35+255132.6, by cross-matching binary light curves from the Catalina Sky Survey and spectroscopically classified M dwarfs from the Sloan Digital Sky Survey. We obtain follow-up spectra using the Gemini telescope, enabling us to determine the mass, radius, and temperature of the primary and secondary component to be M {sub 1} = 0.47 ± 0.03(statistic) ± 0.03(systematic) M {sub ⊙}, M {sub 2} = 0.46 ± 0.03(statistic) ± 0.03(systematic) M {sub ⊙}, R {sub 1} = 0.52 ± 0.08(statistic) ± 0.07(systematic) R {sub ⊙}, R {sub 2} =0.60 ± 0.08(statistic) ± 0.08(systematic) R {sub ⊙}, T {sub 1} = 3560 ± 100 K, and T {sub 2} = 3040 ± 100 K, respectively. The systematic error was estimated using the difference between eccentric and non-eccentric fits. Our analysis also indicates that there is definitively third-light contamination (66%) in the CSS photometry. The secondary star seems inflated, probably due to tidal locking of the close secondary companion, which is common for very short-period binary systems. Future spectroscopic observations with high resolution will narrow down the uncertainties of stellar parameters for both components, rendering this system as a benchmark for studying fundamental properties of M dwarfs.

79 ASTRONOMY AND ASTROPHYSICS↗