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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Ultrafast jet classification at the HL-LHC

Abstract Three machine learning models are used to perform jet origin classification. These models are optimized for deployment on a field-programmable gate array device. In this context, we demonstrate how latency and resource consumption scale with the input size and choice of algorithm. Moreover, the models proposed here are designed to work on the type of data and under the foreseen conditions at the CERN large hadron collider during its high-luminosity phase. Through quantization-aware training and efficient synthetization for a specific field programmable gate array, we show that O ( 100 ) ns inference of complex architectures such as Deep Sets and Interaction Networks is feasible at a relatively low computational resource cost.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Machine Learning-Enabled Image Classification for Automated Electron Microscopy

Abstract Traditionally, materials discovery has been driven more by evidence and intuition than by systematic design. However, the advent of “big data” and an exponential increase in computational power have reshaped the landscape. Today, we use simulations, artificial intelligence (AI), and machine learning (ML) to predict materials characteristics, which dramatically accelerates the discovery of novel materials. For instance, combinatorial megalibraries, where millions of distinct nanoparticles are created on a single chip, have spurred the need for automated characterization tools. This paper presents an ML model specifically developed to perform real-time binary classification of grayscale high-angle annular dark-field images of nanoparticles sourced from these megalibraries. Given the high costs associated with downstream processing errors, a primary requirement for our model was to minimize false positives while maintaining efficacy on unseen images. We elaborate on the computational challenges and our solutions, including managing memory constraints, optimizing training time, and utilizing Neural Architecture Search tools. The final model outperformed our expectations, achieving over 95% precision and a weighted F-score of more than 90% on our test data set. This paper discusses the development, challenges, and successful outcomes of this significant advancement in the application of AI and ML to materials discovery.

Materials Science↗
DOE OSTI2022

The Dark Energy Survey supernova program: cosmological biases from supernova photometric classification

ABSTRACT Cosmological analyses of samples of photometrically identified type Ia supernovae (SNe Ia) depend on understanding the effects of ‘contamination’ from core-collapse and peculiar SN Ia events. We employ a rigorous analysis using the photometric classifier SuperNNova on state-of-the-art simulations of SN samples to determine cosmological biases due to such ‘non-Ia’ contamination in the Dark Energy Survey (DES) 5-yr SN sample. Depending on the non-Ia SN models used in the SuperNNova training and testing samples, contamination ranges from 0.8 to 3.5 per cent, with a classification efficiency of 97.7–99.5 per cent. Using the Bayesian Estimation Applied to Multiple Species (BEAMS) framework and its extension BBC (‘BEAMS with Bias Correction’), we produce a redshift-binned Hubble diagram marginalized over contamination and corrected for selection effects, and use it to constrain the dark energy equation-of-state, w. Assuming a flat universe with Gaussian ΩM prior of 0.311 ± 0.010, we show that biases on w are <0.008 when using SuperNNova, with systematic uncertainties associated with contamination around 10 per cent of the statistical uncertainty on w for the DES-SN sample. An alternative approach of discarding contaminants using outlier rejection techniques (e.g. Chauvenet’s criterion) in place of SuperNNova leads to biases on w that are larger but still modest (0.015–0.03). Finally, we measure biases due to contamination on w0 and wa (assuming a flat universe), and find these to be <0.009 in w0 and <0.108 in wa, 5 to 10 times smaller than the statistical uncertainties for the DES-SN sample.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Carbon- and Oxygen-rich stars in MaStar: identification and classification

ABSTRACT Carbon- and Oxygen-rich stars populating the Thermally Pulsing Asymptotic Giant Branch (TP-AGB) phase of stellar evolution are relevant contributors to the spectra of ∼1 Gyr old populations. Atmosphere models for these types are uncertain, due to complex molecules and mass-loss effects. Empirical spectra are then crucial, but samples are small due to the short (∼3 Myr) TP-AGB lifetime. Here we exploit the vastness of the MaNGA Stellar library MaStar (∼60 000 spectra) to identify C and O-rich type stars. We define an optical colour selection with cuts of (g − r) > 2 and (g − i) < 1.55(g − r) − 0.07, calibrated with known C- and O-rich spectra. This identifies C- and O-rich stars along clean, separated sequences. An analogue selection is found in V, R, I bands. Our equation identifies C-rich and O-rich spectra with predictive performance metric F1-scores of 0.72 and 0.74 (over 1), respectively. We finally identify 41 C- and 87 O-rich type AGB stars in MaStar, 5 and 49 of which do not have a SIMBAD counterpart. We also detect a sample of non-AGB, dwarf C-stars. We further design a fitting procedure to classify the spectra into broad spectral types, by using as fitting templates empirical C- and O-rich spectra. We find remarkably good fits for the majority of candidates and categorize them into C- and O-rich bins following existing classifications, which correlate to effective temperature. Our selection models can be applied to large photometric surveys (e.g. Euclid, Rubin). The classified spectra will facilitate future evolutionary population synthesis models.

Hill, Lewis (ORCID:0000000180528080)↗
DOE OSTI2021

SCOPe: improvements to the structural classification of proteins – extended database to facilitate variant interpretation and machine learning

Abstract The Structural Classification of Proteins—extended (SCOPe, https://scop.berkeley.edu) knowledgebase aims to provide an accurate, detailed, and comprehensive description of the structural and evolutionary relationships amongst the majority of proteins of known structure, along with resources for analyzing the protein structures and their sequences. Structures from the PDB are divided into domains and classified using a combination of manual curation and highly precise automated methods. In the current release of SCOPe, 2.08, we have developed search and display tools for analysis of genetic variants we mapped to structures classified in SCOPe. In order to improve the utility of SCOPe to automated methods such as deep learning classifiers that rely on multiple alignment of sequences of homologous proteins, we have introduced new machine-parseable annotations that indicate aberrant structures as well as domains that are distinguished by a smaller repeat unit. We also classified structures from 74 of the largest Pfam families not previously classified in SCOPe, and we improved our algorithm to remove N- and C-terminal cloning, expression and purification sequences from SCOPe domains. SCOPe 2.08-stable classifies 106 976 PDB entries (about 60% of PDB entries).

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

GALAXY CRUISE: Spiral and ring classifications for bright galaxies at z = 0.01–0.3

Abstract This paper presents a morphology classification catalog of spiral and ring features of 59854 magnitude-limited galaxies (r < 17.8 mag, and additional 628005 subsamples down to r = 20 mag) at z = 0.01–0.3 based on the Third Public Data Release of the Hyper Suprime-Cam Subaru Strategic Program. We employ two deep-learning classifiers to determine the spiral and ring structures separately based on GALAXY CRUISE Data Release 1, which is dedicated to Hyper Suprime-Cam data. The number of spiral and ring galaxies contain 31864 and 8808 sources, respectively, which constitute 53% and 15% of the sample. A notable result of this study is the construction of a large sample of ring galaxies utilizing high-quality imaging data delivered by the Subaru Hyper Suprime-Cam. However, the accurate identification of ring galaxies remains difficult at a limited seeing resolution. Additionally, we confirm that most spiral galaxies are located on the star-forming main sequence, whereas ring galaxies preferentially reside in the green valley at stellar masses of 1010.5–1011 solar mass. Furthermore, decreasing fractions of spiral and ring galaxies are observed toward the centers of the galaxy clusters. The obtained morphology catalog is publicly available on the GALAXY CRUISE website.

Shimakawa, Rhythm (ORCID:0000000344422750)↗
DOE OSTI2025

Symmetry-Based Classification of Exact Flat Bands in Single and Bilayer Moiré Systems

Landau levels have been central to the discovery of exotic quantum phases and their unprecedentedly deep roots in geometry and topology. A powerful concept called “vortexability” extends this framework to moiré systems. In this Letter, we show that vortexable systems support not only Landau-level-like flat bands but also entirely new types with distinct topological properties. Notably, while 𝑛𝑏 Landau levels have total Chern number 𝐶 = 𝑛 𝑏 , vortexable moiré systems can host 𝑛 𝑏 flat bands with 𝐶 = 1 ≠ 𝑛 𝑏 . Here, we provide a complete classification of such exact flat bands in single and bilayer systems with Dirac or quadratic band crossings, identifying the symmetry conditions that govern their number and topology. Up to six flat bands can be symmetry protected. We construct explicit wave functions, showing that sublattice-polarized states always sum to Chern number ±1 and satisfy ideal non-Abelian quantum geometry. When the Berry curvature is sharply peaked, we show that a topological heavy-fermion description remains valid—even for bands with high degeneracy.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Towards a classification of bifurcations in Vlasov equations

Here, we propose a classification of bifurcations of Vlasov equations, based on the strength of the resonance between the unstable mode and the continuous spectrum on the imaginary axis. We then identify and characterize a new type of generic bifurcation where this resonance is weak, but the unstable mode couples with a stable mode and a Casimir invariant of the system to form a size-3 Jordan block. We derive a three-dimensional reduced noncanonical Hamiltonian system describing this bifurcation. Comparison of the reduced dynamics with direct numerical simulations on a test case gives excellent agreement. We finally discuss the relevance of this bifurcation to specific physical situations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2026

Improving neutrino oscillation measurements through event classification

Precise neutrino energy reconstruction is essential for next-generation long-baseline oscillation experiments, yet current methods remain limited by large uncertainties in neutrino-nucleus interaction modeling. Even so, it is well established that different interaction channels produce systematically varying amounts of missing energy and therefore yield different reconstruction performance–information that standard calorimetric approaches do not exploit. We introduce a strategy that incorporates this structure by classifying events according to their underlying interaction type prior to energy reconstruction. Using supervised machine-learning techniques trained on labeled generator events, we leverage intrinsic kinematic differences among quasielastic scattering, meson-exchange current, resonance production, and deep-inelastic scattering processes. A cross-generator testing framework demonstrates that this classification approach is robust to microphysics mismodeling and, when applied to a simulated DUNE 𝜈 𝜇 disappearance analysis, yields improved accuracy and sensitivity at the 10%–20% level. These results highlight a practical path toward reducing reconstruction-driven systematics in future oscillation measurements.

Ellis, Sebastian A. R. [King's College, London (Un↗
DOE OSTI2023

Machine Learning Models for Network Traffic Classification in Programmable Logic

Network traffic classification via machine learning on network packet payloads has emerged as an active area of research for network security due to the high accuracy machine learning models have achieved in classifying payloads. For effective deployment as part of network security, these machine learning models must not only classify malicious packet payloads accurately, they must also identify anomalous payloads and perform inference at speeds generally faster than 10,000 packets per second to be effective. This work explores the in- ference speeds and accuracy of several neural network models implemented in programmable logic on various field programmable gate arrays (FPGA) including the Xilinx VC1902 and Xilinx Zynq Ultrascale+. This work also presents the design and performance of both an autoencoder and variational autoencoder programmed on the FPGA for identifying anomalous packet payloads. The performance benefits of the FPGA implementation for this type of packet payload inspection driven by machine learning are compared against graphics processing unit (GPU) inference implementations run on two state-of-the-art datacenter GPU devices, the NVIDIA V100 and A100. The model accuracy difference between the FPGA and GPU implementations was found to be 4% or less while the Xilinx VC1902 outperformed both the NVIDIA V100 and A100 for inference speeds on all the models explored except the variational autoencoder.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Sampling Subjective Polygons for Patch-Based Deep Learning Land-Use Classification in Satellite Images

Model generalization remains a key challenge in the analysis of large amounts of heterogeneous satellite image data. One major limiting factor in developing generalizable models, in the context of supervised learning, is the lack of high quality training datasets. A model's capacity to perform well on new data is often inhibited by imbalance and bias in the data that was used for training. This is especially a problem when using convolutional neural networks to classify urban land-use in satellite images. Notable dataset imbalance issues in this application include land-use type imbalance and image scene imbalance. To begin understanding these dataset imbalance problems in more detail, we develop and test a number of sampling methods for generating training image datasets from subjective training polygons for urban land-use classification. We investigate sampling at different point densities as a means to reduce content repetition and therefore content imbalance and bias in the training image dataset.

Arndt, Jacob↗
DOE OSTI2024

Deep Learning Scene Classification Experiments in Automatic Detection of Slums on Planetscope Imagery

Population growth is increasingly happening in slum settlements of the large urban centers in the Global South. The term "slum" encompasses a wide range of communities, located mostly in underserved areas, and often exhibiting distinct structural and functional informalities with a relatively high concentration of marginalized populations. To address the issues confronting slums for effective planning and development, including the realistic estimation of the resident population, identifying them accurately is fundamental. Given the disagreements over a universal definition, diverse characteristic features, and socio-political limitations, global detection of slums is a veritable challenge. In this paper, we present experiments in slum detection using a scene classification algorithm and 3-meter spatial resolution satellite imagery. We train and evaluate the model for slum detection in Mumbai, India for the year 2023 and test the temporal generalization of the trained model on Mumbai in 2020 and 2018. In addition, we explore the pathways toward geographic generalization to Kolkata and Delhi (India). We discuss several limitations in the workflow and model, situate our findings in the existing literature, and suggest improvements and alternatives. With this, we establish baseline methods and experiments as a first step towards developing an image-based global slum detection framework and algorithm. This work adds to the community discussion on methods, data challenges, and open questions related to the detection of slums globally. With this research, we hope to improve our understanding of human settlements, especially in critical areas, improve population estimates, and help measure progress towards the sustainable development goals.

Arndt, Jacob↗
DOE OSTI2020

Analyzing Deep Learning Model Inferences for Image Classification using OpenVINO

It may be desirable to execute deep learning model inferences on an integrated GPU at the edge. While such GPUs are much less powerful than discrete GPUs, it is able to deliver higher floating-point operations per second than a CPU located on the same die. For edge devices, the benefit of moving to lower precision with minimal loss of accuracy to obtain higher performance is also attractive. Hence, we chose 14 deep learning models for image classification to evaluate their inference performance with the OpenVINO toolkit. Then, we analyzed the implementation of the fastest inference model of all the models. The experimental results are promising. Compared to the performance of full-precision (FP32) models, the speedup of the 8-bit (INT8) quantization ranges from 1.02 to 1.56 on an Intel (R) Xeon (R) 4-core CPU, and the speedup of the FP16 models ranges from 1.1 to 2 on an Intel (R) Iris (TM) Pro GPU. For the FP32 models, the GPU is on average 1.5X faster than the CPU.

CPU↗
DOE OSTI2022

Adversarial Attacks on Deep Neural Network-based Power System Event Classification Models

Online event classification is essential to strengthening the reliability of the power transmission system. Recently, deep learning based methods have achieved great success in numerous domains such as computer vision and natural language processing. Researchers began to adopt deep learning based methods to solve the power system event identification problem and achieved effective results. However, these previous works do not consider that deep learning models are vulnerable to adversarial attacks, potentially influencing real-world applications' reliability. In this paper, we adopt several adversarial attack mechanisms by adding tailored noise signal to the input Phasor Measurement Units (PMU) time series and make the deep learning model misclassify the power system event. This numerical study discloses that current state-of-the-art deep learning based power system event classifiers are extremely vulnerable to adversarial attacks, which may jeopardize the reliability of the power transmission system.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Comparative Analysis of ML Techniques for Data-Driven Anomaly Detection, Classification and Localization in Distribution System

High penetration of Distributed Energy Resources (DERs), fundamental load behavior changes, controllable loads, and significant increase in Electrical Vehicles (EVs) lead to complex dynamic behavior of the electric distribution system. Increasing number of components also means more measurements, more data and more data anomalies. Detecting, classifying and localizing these anomalies are important for situational awareness, and at the same time, very challenging given increasing complexity of the system. Highly accurate and high-resolution analytical techniques are needed to support anomaly detection, classification and localization (AD-C-L) for monitoring, root cause analysis and decision making. This paper provides comprehensive review and analysis of the existing spatio-temporal AD-C-L techniques within the distribution system. Challenges for specific problems in AD-C- L have been also discussed in this paper. Existing AD-C- L techniques have been categorized and synthesized for specific merits and limitations of multiple Machine Learning (ML) methodologies using common developed metrics of performance. The comparative analysis is summarized and presented with the open research challenges and path forward for future research needs.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Safe and Robust Binary Classification and Fault Detection Using Reinforcement Learning

In this paper, we propose a learning-based method utilizing the Soft Actor-Critic (SAC) algorithm to train a binary Support Vector Machine (SVM) classifier. This classifier is designed to identify valid input spaces in high-dimensional, highly constrained systems while minimizing the total runtime of offline simulations. The simulations adapt their runtime based on the likelihood that a given training input will be informative to the classifier. Furthermore, we introduce a method for using the trained SAC model to predict whether a desired system input is likely to violate constraints, along with a technique to adjust the input as necessary. Additionally, we explore the potential of this model to detect faults or adversarial attacks within the system. The effectiveness of our approach is demonstrated through various simulations of challenging classification problems and a constrained quadrotor model.

Netter, Josh [Georgia Institute of Technology, Atl↗
DOE OSTI2024

CNN-Based Phase Fault Classification in Real and Simulated Power Systems Data

This study proposes a convolutional neural network (CNN)–based two-step phase fault detection and identification method to classify anomalies in the power grid signal. Specifically, the first step checks the fault’s existence and determines the need for the second step. Subsequently, in the case of anomalies in the power grid signal, the second step identifies the type of fault, including line-to-line, single-line-to-ground, double-line-to-ground, and triple-line. Accordingly, the CNN architecture is both designed for the classification layers and trained with simulated data. To provide maximum prediction accuracy with minimum processing time, this study investigates the combinations of various feature extraction (FE) techniques, such as fast Fourier transform (FFT), amplitude and phase (AP), auto-correlation function, power spectral density, and wavelet transform (WT). Consequently, simulated and real-world results demonstrate that the proposed two-step method outperforms conventional one-step techniques, with the best performance obtained by using the combination of AP-AP, AP-WT, FFT-AP, and FFT-WT–based FE methods.

Alaca, Ozgur↗
DOE OSTI2022

Light-Duty Vehicle Trip Classification Using One-Class Novelty Detection and Exhaustive Feature Extraction

Travel mode classification within travel survey data sets, especially light-duty vehicle (LDV) trips, is foundational, though nontrivial, to emerging mobility systems, travel behavior analysis, and fuel consumption estimation. Current travel mode detection approaches require well-sampled and balanced data sets with ground truth travel mode labels. The detection approaches are rarely applied and validated on large-scale, real-world data sets, which may not satisfy the dataset requirements. This work proposes an LDV trip detection model as a supplement to current travel mode detection methods, for the case when the training set is highly (and/or completely) unbalanced, to the extent that classical machine-learning approaches become difficult or impossible to deploy. The proposed model uses a novelty detection technique - one-class support vector machines (OCSVMs) - and a novel exhaustive feature extraction (EFE) technique on continuous time series data (i.e., Global Positioning System [GPS] speed profiles) for single-mode trip trajectories. Training and validation of the model are conducted on a large-scale, real-world data set. The proposed method accurately identifies LDV trips from a broad set of multimodal trips by leveraging a wealth of preexisting in-vehicle GPS travel data. Additional sensitivity analysis sheds light on the optimal training size and feature selection, which will benefit applications limited by highly imbalanced data. The paper also discusses performance comparison with regular machine-learning approaches, the model's robustness, and the potential to extend the proposed model to multi-modal trip prediction.

33 ADVANCED PROPULSION SYSTEMS↗