Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “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 721 records · Page 40
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Classification Analysis of Southwest Pacific Tropical Cyclone Intensity Changes Prior to Landfall

This study evaluates the ability of a random forest classifier to identify tropical cyclone (TC) intensification or weakening prior to landfall over the western region of the Southwest Pacific Ocean (SWPO) basin. For both Australia mainland and SWPO island cases, when a TC first crosses land after spending ≥24 h over the ocean, the closest hour prior to the intersection is considered as the landfall hour. If the maximum wind speed (V max ) at the landfall hour increased or remained the same from the 24-h mark prior to landfall, the TC is labeled as intensifying and if the V max at the landfall hour decreases, the TC is labeled as weakening. Geophysical and aerosol variables closest to the 24 h before landfall hour were collected for each sample. The random forest model with leave-one-out cross validation and the random oversampling example technique was identified as the best-performing classifier for both mainland and island cases. The model identified longitude, initial intensity, and sea skin temperature as the most important variables for the mainland and island landfall classification decisions. Incorrectly classified cases from the test data were analyzed by sorting the cases by their initial intensity hour, landfall hour, monthly distribution, and 24-h intensity changes. TC intensity changes near land strongly impact coastal preparations such as wind damage and flood damage mitigations; hence, this study will contribute to improve identifying and prioritizing prediction of important variables contributing to TC intensity change before landfall.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Integration of Air Classification and Hydrothermal Carbonization to Enhance Energy Recovery of Corn Stover

Air classification (AC) is a cost-effective technology that separates the energy-dense light ash fraction (LAF) from the inorganic-rich high ash fraction (HAF) of corn stover. HAF could be upgraded into energy-dense solid fuel by hydrothermal carbonization (HTC). However, HTC is a high-temperature, high-pressure process, which requires additional energy to operate. In this study, three different scenarios (i.e., AC only, HTC only, and integrated AC–HTC) were investigated for the energy recovery of corn stover. AC was performed on corn stover at an 8 Hz fan speed, which yielded 84.4 wt. % LAF, 12.8 wt. % HAF, and 2.8 wt. % below screen particles. About 27 wt. % ash was reduced from LAF by the AC process. Furthermore, HTC was performed on raw corn stover and the HAF of corn stover at 200, 230, and 260 °C for 30 min. To evaluate energy recovery, solid products were characterized in terms of mass yield, ash yield, ultimate analysis, proximate analyses, and higher heating value (HHV). The results showed that the energy density was increased with the increase in HTC temperature, meanwhile the mass yield and ash yield were decreased with the increase in HTC temperature. Proximate analysis showed that fixed carbon increased 18 wt. % for original char and 27 wt. % for HAF char at 260 °C, compared to their respective feedstocks. Finally, the hydrochar resulting from HAF was mixed with LAF and pelletized at 180 bar and 90 °C to densify the energy content. An energy balance of the integrated AC–HTC process was performed, and the results shows that integrated AC with HTC performed at 230 °C resulted in an additional 800 MJ/ton of energy recovery compared to the AC-only scenario.

09 BIOMASS FUELS↗
DOE OSTI2021

CyBERT: Cybersecurity Claim Classification by Fine-Tuning the BERT Language Model

We introduce CyBERT, a cybersecurity feature claims classifier based on bidirectional encoder representations from transformers and a key component in our semi-automated cybersecurity vetting for industrial control systems (ICS). To train CyBERT, we created a corpus of labeled sequences from ICS device documentation collected across a wide range of vendors and devices. This corpus provides the foundation for fine-tuning BERT’s language model, including a prediction-guided relabeling process. We propose an approach to obtain optimal hyperparameters, including the learning rate, the number of dense layers, and their configuration, to increase the accuracy of our classifier. Fine-tuning all hyperparameters of the resulting model led to an increase in classification accuracy from 76% obtained with BertForSequenceClassification’s original architecture to 94.4% obtained with CyBERT. Furthermore, we evaluated CyBERT for the impact of randomness in the initialization, training, and data-sampling phases. CyBERT demonstrated a standard deviation of ±0.6% during validation across 100 random seed values. Finally, we also compared the performance of CyBERT to other well-established language models including GPT2, ULMFiT, and ELMo, as well as neural network models such as CNN, LSTM, and BiLSTM. The results showed that CyBERT outperforms these models on the validation accuracy and the F1 score, validating CyBERT’s robustness and accuracy as a cybersecurity feature claims classifier.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Two-Stage Wildlife Event Classification for Edge Deployment

Camera-based wildlife monitoring is often overwhelmed by non-target triggers and slowed by manual review or cloud-dependent inference, which can prevent timely intervention for high stakes human–wildlife conflicts. Our key contribution is a deployable, fully offline edge vision sensor that achieves near-real-time, highly accurate wildlife event classification by combining detector-based empty-image suppression with a lightweight classifier trained with a staged transfer-learning curriculum. Specifically, Stage 1 uses a pretrained You Only Look Once (YOLO)-family detector for permissive animal localization and empty-trigger suppression, and Stage 2 uses a lightweight EfficientNet-based binary classifier to confirm puma on detector crops and gate downstream actions. Our design is robust to low-quality nighttime monochrome imagery (motion blur, low contrast, illumination artifacts, and partial-body captures) and operates using commercially available components in connectivity-limited settings. In field deployments running since May 2025, end-to-end latency from camera trigger to action command is approximately 4 s. Ablation studies using a dataset of labeled wildlife images (pumas, not pumas) show that the two-stage approach substantially reduces false alarms in identifying pumas relative to a full-image classifier while maintaining high recall. On the held-out test set (N = 1434 events), the proposed two-stage cascade achieves precision 0.983, recall 0.975, F1 0.979, accuracy 0.986, and balanced accuracy 0.983, with only 8 false positives and 12 false negatives. The system can be easily adapted for other species, as demonstrated by rapid retraining of the second stage to classify ringtails. Downstream responses (e.g., notifications and optional audio/light outputs) provide flexible actuation capabilities that can be configured to support intervention.

58 GEOSCIENCES↗
DOE OSTI2021

An Optical Overview of Blazars with LAMOST. II. Gamma-Ray Blazar Candidates and Updated Classifications

Blazars represent the dominant class of associated γ-ray sources detected by the Fermi Large Area Telescope (LAT). However, in the more recent release of the Fourth Fermi-LAT Point Source Catalog (4FGL), ∼25% of the sources associated with lower-energy counterparts show a multifrequency behavior similar to that of blazars, but lacks an optical spectroscopic confirmation of their nature and are therefore classified as Blazar Candidates of Uncertain Type (BCUs). A particularly challenging task in blazar studies is to classify these BCUs and, when possible to estimate their redshifts, in particular for BL Lac objects, characterized by almost featureless optical spectra with only weak emission lines. Continuing our study of blazars with Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) optical spectral data, we perform an extensive search for optical spectra available in the LAMOST Data Release 6 archive. Our aim is confirming the blazar nature of BCUs and to test if new data can allow us to get a redshift estimate for BL Lac objects that lack measurement, as well as to search for and discover changing-look blazars. We selected sources out of the 4FGL catalog, the list of targets from our follow-up spectroscopic campaign of unidentified and/or unassociated γ-ray sources, and the Roma-BZCAT multifrequency catalog of blazars, finding a total of 42 sources with available LAMOST DR6 spectra. We confirmed the blazar-like nature of four blazar candidates . For the remaining 37 sources we confirm their previous classification.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Data supporting manuscript from L. Sheneman, G. Stephanopoulos, A.E. Vasdekis titled "Deep learning classification of lipid droplets in quantitative phase images" as currently under review at PLOS ONE. This includes: 1) raw and binary labeled Quantitative Phase Images (QPI) of Y. lipolytica cells used in the analyses described within the manuscript. 2) various derived data including classifier scores, etc.

Data supporting manuscript from L. Sheneman, G. Stephanopoulos, A.E. Vasdekis titled "Deep learning classification of lipid droplets in quantitative phase images" as currently under review at PLOS ONE. This includes: 1) raw and binary labeled Quantitative Phase Images (QPI) of Y. lipolytica cells used in the analyses described within the manuscript. 2) various derived data including classifier scores, etc.

ANN↗
NASA NTRS1993

Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning

Since most real-world applications of classification learning involve continuous-valued attributes, properly addressing the discretization process is an important problem. This paper addresses the use of the entropy minimization heuristic for discretizing the range of a continuous-valued attribute into multiple intervals.

discretization continuous-valued attributes classi↗
NASA NTRS2005

Data Format Classification for Autonomous Software Defined Radios

We present maximum-likelihood (ML) coherent and noncoherent classifiers for discriminating between NRZ and Manchester coded (biphase-L) data formats for binary phase-shift-keying (BPSK) modulation. Such classification of the data format is an essential element of so-called autonomous software defined radio (SDR) receivers (similar to so-called cognitive SDR receivers in the military application) where it is desired that the receiver perform each of its functions by extracting the appropriate knowledge from the received signal and, if possible, with as little information of the other signal parameters as possible. Small and large SNR approximations to the ML classifiers are also proposed that lead to simpler implementation with comparable performance in their respective SNR regions. Numerical performance results obtained by a combination of computer simulation and, wherever possible, theoretical analyses, are presented and comparisons are made among the various configurations based on the probability of misclassification as a performance criterion. Extensions to other modulations such as QPSK are readily accomplished using the same methods described in the paper.

classification↗
NASA NTRS2019

Automated Classification of Transient Contamination in Stationary Acoustic Data

An automated procedure for the classification of transient contamination of stationary acoustic data is proposed and analyzed. The procedure requires the assumption that the stationary acoustic data of interest can be modeled as a band-limited, Gaussian random process. It also requires that the transient contamination be of higher variance than the acoustic data of interest. When these assumptions are satisfied, it is a blind separation procedure, aside from the initial input specifying how to subdivide the time series of interest. No a priori threshold criterion is required. Simulation results show that for a sufficient number of blocks, the method performs well, as long as the occasional false positive or false negative is acceptable. The effectiveness of the procedure is demonstrated with an application to experimental wind tunnel acoustic test data which are contaminated by hydrodynamic gusts.

binary classification↗
DOE OSTI2025

Robustness of Deep Learning Classification to Adversarial Input on GPUs: Asynchronous Parallel Accumulation Is a Source of Vulnerability

The ability of machine learning (ML) classification models to resist small, targeted input perturbations—known as adversarial attacks—is a key measure of their safety and reliability. We show that floating-point non associativity (FPNA) coupled with asynchronous parallel programming on GPUs is sufficient to result in misclassification, without any perturbation to the input. Additionally, we show that this misclassification is particularly significant for inputs close to the decision boundary and that standard adversarial robustness results may be overestimated up to 4.6 when not considering machine-level details. We first study a linear classifier, before focusing on standard Graph Neural Network (GNN) architectures and datasets used in robustness assessments. We develop a novel black-box attack using Bayesian optimization to discover external workloads that can change the instruction scheduling which bias the output of reductions on GPUs and reliably lead to misclassification. Motivated by these results, we present a new learnable permutation (LP) gradient-based approach to learning floating-point operation orderings that lead to misclassifications. The LP approach provides a worst-case estimate in a computationally efficient manner, avoiding the need to run identical experiments tens of thousands of times over a potentially large set of possible GPU states or architectures. Finally, using instrumentation-based testing, we investigate parallel reduction ordering across different GPU architectures under external background workloads, when utilizing multi-GPU virtualization, and when applying power capping. Our results demonstrate that parallel reduction ordering varies significantly across architectures under the first two conditions, substantially increasing the search space required to fully test the effects of this parallel scheduler-based vulnerability. These results and the methods developed here can help to include machine-level considerations into adversarial robustness assessments, which can make a difference in safety and mission critical applications.

Shanmugavelu, Sanjif [Maxeler Technologies, a Groq↗
DOE OSTI2023

The ABC of RPV: classification of R-parity violating signatures at the LHC for small couplings

We perform a classification of all potential supersymmetric R-parity violating signatures at the LHC to address the question: are existing bounds on supersymmetric models robust, or are there still signatures not covered by existing searches, allowing LHC scale supersymmetry to be hiding? We analyze all possible scenarios with one dominant RPV trilinear coupling at a time, allowing for arbitrary LSPs and mass spectra. We consider direct production of the LSP, as well as production via gauge-cascades, and find 6 different experimental signatures for the $LL\overline{E}$-case, 6 for the $LQ\overline{D}$-case, and 5 for the $\overline{U}$ $\overline{D}$ $\overline{D}$-case; together these provide complete coverage of the RPV-MSSM landscape. This set of signatures is confronted with the existing searches by ATLAS and CMS. We find all signatures have been covered at the LHC, although not at the sensitivity level needed to probe the direct production of all LSP types. For the case of a dominant $LL\overline{E}$-operator, we use CheckMATE to quantify the current lower bounds on the supersymmetric masses and find the limits to be comparable to or better than the R-parity conserving case. Our treatment can be easily extended to scenarios with more than one non-zero RPV coupling.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Is infrared-collinear safe information all you need for jet classification?

Machine learning-based jet classifiers are able to achieve impressive tagging performance in a variety of applications in high-energy and nuclear physics. However, it remains unclear in many cases which aspects of jets give rise to this discriminating power, and whether jet observables that are tractable in perturbative QCD such as those obeying infrared-collinear (IRC) safety serve as sufficient inputs. In this article, we introduce a new classifier, Jet Flow Networks (JFNs), in an effort to address the question of whether IRC unsafe information provides additional discriminating power in jet classification. JFNs are permutation-invariant neural networks (deep sets) that take as input the kinematic information of reconstructed subjets. The subjet radius and a cut on the subjet’s transverse momenta serve as tunable hyperparameters enabling a controllable sensitivity to soft emissions and nonperturbative effects. We demonstrate the performance of JFNs for quark vs. gluon and Z vs. QCD jet tagging. For small subjet radii and transverse momentum cuts, the performance of JFNs is equivalent to the IRC-unsafe Particle Flow Networks (PFNs), demonstrating that infrared-collinear unsafe information is not necessary to achieve strong discrimination for both cases. As the subjet radius is increased, the performance of the JFNs remains essentially unchanged until physical thresholds that we identify are crossed. For relatively large subjet radii, we show that the JFNs may offer an increased model independence with a modest tradeoff in performance compared to classifiers that use the full particle information of the jet. These results shed new light on how machines learn patterns in high-energy physics data.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Explainable AI classification for parton density theory

Quantitatively connecting properties of parton distribution functions (PDFs, or parton densities) to the theoretical assumptions made within the QCD analyses which produce them has been a longstanding problem in HEP phenomenology. To confront this challenge, we introduce an ML-based explainability framework, XAI4PDF, to classify PDFs by parton flavor or underlying theoretical model using ResNet-like neural networks (NNs). By leveraging the differentiable nature of ResNet models, this approach deploys guided backpropagation to dissect relevant features of fitted PDFs, identifying x-dependent signatures of PDFs important to the ML model classifications. By applying our framework, we are able to sort PDFs according to the analysis which produced them while constructing quantitative, human-readable maps locating the x regions most affected by the internal theory assumptions going into each analysis. This technique expands the toolkit available to PDF analysis and adjacent particle phenomenology while pointing to promising generalizations.

Artificial Intelligence↗
DOE OSTI2020

Towards a classification of rank r $\mathscr{N}$ = 2 SCFTs. Part II. Special Kahler stratification of the Coulomb branch

We study the stratification of the singular locus of four dimensional $\mathscr{N}$ = 2 Coulomb branches. We present a set of self-consistency conditions on this stratification which can be used to extend the classification of scale-invariant rank 1 Coulomb branch geometries to two complex dimensions, and beyond. The calculational simplicity of the arguments presented here stems from the fact that the main ingredients needed - the rank 1 deformation patterns and the pattern of inclusions of rank 2 strata - are discrete topological data which satisfy strong self-consistency conditions through their relationship to the central charges of the SCFT. This relationship of the stratification data to the central charges is used here, but is derived and explained in a companion paper by one of the authors. We illustrate the use of these conditions by re-analyzing many previously-known examples of rank 2 SCFTs, and also by finding examples of new theories. The power of these conditions stems from the fact that for Coulomb branch stratifications a conjecturally complete list of physically allowed “elementary slices” is known. By contrast, constraining the possible elementary slices of symplectic singularities relevant for Higgs branch stratifications remains an open problem.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗