Search NASA⌕ Search

SEARCH · Search NASA

Results for “feature vectors”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Contrasting Time-Frequency Representations for Unknown Waveform Detection

Identifying unseen electromagnetic waveforms is critical for many applications, like interference management, electronic warfare and spectrum management. Traditionally this is done using statistical methods for anomaly detection, which has evolved to deep learning models for identifying the unseen data, formally termed as open set recognition. Some prior methods use a generative model to emulate open set data, which face challenges in generating synthetic samples for open set while simultaneously selecting an optimal discriminator for accurate classification. To alleviate this issue, we propose a discriminative model that effectively combines time and frequency domain features of communication signals for accurate predictions. We further introduce a cosine similarity loss that makes the domain specific features unique to enhance the prediction rate. Additionally, our model avoids generic feature vectors by extracting class-specific features during training, resulting in improved class representation. The experiment results show that this combined feature approach with cosine loss outperforms single-domain models and improves accuracy by 10% over models without cosine loss.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

A knowledge-informed large language model framework for U.S. nuclear power plant shutdown initiating event classification for probabilistic risk assessment

Identifying and classifying shutdown initiating events (SDIEs) is critical for developing shutdown probabilistic risk assessment for nuclear power plants. Existing computational approaches cannot achieve satisfactory performance due to the challenges of unavailable large, labeled datasets, imbalanced event types, and label noise. To address these challenges, we propose a hybrid pipeline that integrates a knowledge-informed machine learning model to prescreen non-SDIEs and a large language model (LLM) to classify SDIEs into four types. In the prescreening stage, we proposed a set of 44 SDIE text patterns that consist of the most salient keywords and phrases from six SDIE types. Text vectorization based on the SDIE patterns generates feature vectors that are highly separable by using a simple binary classifier. The second stage builds Bidirectional Encoder Representations from Transformers (BERT)-based LLM, which learns generic English language representations from self-supervised pretraining on a large dataset and adapts to SDIE classification by fine-tuning it on an SDIE dataset. The proposed approaches are evaluated on a dataset with 10,928 events using precision, recall ratio, F 1 score, and average accuracy. In conclusion, the results demonstrate that the prescreening stage can exclude more than 97% non-SDIEs, and the LLM achieves an average accuracy of 95.1% for SDIE classification.

99 - GENERAL AND MISCELLANEOUS↗
NASA NTRS1988

Identification of terrain cover using the optimum polarimetric classifier

A systematic approach for the identification of terrain media such as vegetation canopy, forest, and snow-covered fields is developed using the optimum polarimetric classifier. The covariance matrices for various terrain cover are computed from theoretical models of random medium by evaluating the scattering matrix elements. The optimal classification scheme makes use of a quadratic distance measure and is applied to classify a vegetation canopy consisting of both trees and grass. Experimentally measured data are used to validate the classification scheme. Analytical and Monte Carlo simulated classification errors using the fully polarimetric feature vector are compared with classification based on single features which include the phase difference between the VV and HH polarization returns. It is shown that the full polarimetric results are optimal and provide better classification performance than single feature measurements.

Kong, J. A.↗
DOE OSTI2025

Q-Cluster: Quantum Error Mitigation Through Noise-Aware Unsupervised Learning

Quantum error mitigation (QEM) is critical in reducing the impact of noise in the pre-fault-tolerant era, and is expected to complement error correction in fault-tolerant quantum computing (FTQC). In this work, we propose a novel QEM approach, Q-Cluster, that uses unsupervised learning (clustering) to reshape the measured bit-string distribution. Our approach starts with a simplified bit-flip noise model. It first performs clustering on noisy measurement results, i.e., bit-strings, based on the Hamming distance. The centroid of each cluster is calculated using a qubit-wise majority vote. Next, the noisy distribution is adjusted with the clustering outcomes and the bitflip error rates using Bayesian inference. Our simulation results show that Q-Cluster can mitigate high noise rates (up to 40% per qubit) with the simple bit-flip noise model. However, real quantum computers do not fit such a simple noise model. To address the problem, we (a) apply Pauli twirling to tailor the complex noise channels to Pauli errors, and (b) employ a machine learning model, ExtraTrees regressor, to estimate an effective bit-flip error rate using a feature vector consisting of machine calibration data (gate & measurement error rates), circuit features (number of qubits, numbers of different types of gates, etc.) and the shape of the noisy distribution (entropy). Our experimental results show that our proposed Q-Cluster scheme improves the fidelity by a factor of 1.46x, on average, compared to the unmitigated output distribution, for a set of low-entropy benchmarks on five different IBM quantum machines. Our approach outperforms the state-of-art QEM approaches RZNE [28], M3 [24], Hammer [35], and QBEEP [33] by 1.26x,1.29x,1.47x, and 2.65 x, respectively.

42 ENGINEERING↗
NASA NTRS1989

A static investigation of several STOVL exhaust system concepts

A static cold flow scale model test was performed in order to determine the internal performance characteristics of various STOVL exhaust systems. All of the concepts considered included a vectorable cruise nozzle and a separate vectorable vertical thrust ventral nozzle mounted on the tailpipe. The two ventral nozzle configurations tested featured vectorable constant thickness cascade vanes for area control and improved performance during transition and vertical lift flight. The best transition performance was achieved using a butterfly door type ventral nozzle and a pitch vectoring 2DCD or axisymmetric cruise nozzle. The clamshell blocker type of ventral nozzle had reduced transition performance due to the choking of the tailpipe flow upstream of the cruise nozzle.

Romine, B. M., Jr.↗
NASA NTRS1993

Feature extraction and classification algorithms for high dimensional data

Feature extraction and classification algorithms for high dimensional data are investigated. Developments with regard to sensors for Earth observation are moving in the direction of providing much higher dimensional multispectral imagery than is now possible. In analyzing such high dimensional data, processing time becomes an important factor. With large increases in dimensionality and the number of classes, processing time will increase significantly. To address this problem, a multistage classification scheme is proposed which reduces the processing time substantially by eliminating unlikely classes from further consideration at each stage. Several truncation criteria are developed and the relationship between thresholds and the error caused by the truncation is investigated. Next an approach to feature extraction for classification is proposed based directly on the decision boundaries. It is shown that all the features needed for classification can be extracted from decision boundaries. A characteristic of the proposed method arises by noting that only a portion of the decision boundary is effective in discriminating between classes, and the concept of the effective decision boundary is introduced. The proposed feature extraction algorithm has several desirable properties: it predicts the minimum number of features necessary to achieve the same classification accuracy as in the original space for a given pattern recognition problem; and it finds the necessary feature vectors. The proposed algorithm does not deteriorate under the circumstances of equal means or equal covariances as some previous algorithms do. In addition, the decision boundary feature extraction algorithm can be used both for parametric and non-parametric classifiers. Finally, some problems encountered in analyzing high dimensional data are studied and possible solutions are proposed. First, the increased importance of the second order statistics in analyzing high dimensional data is recognized. By investigating the characteristics of high dimensional data, the reason why the second order statistics must be taken into account in high dimensional data is suggested. Recognizing the importance of the second order statistics, there is a need to represent the second order statistics. A method to visualize statistics using a color code is proposed. By representing statistics using color coding, one can easily extract and compare the first and the second statistics.

Lee, Chulhee↗
NASA NTRS1993

Hidden Markov models for fault detection in dynamic systems

The invention is a system failure monitoring method and apparatus which learns the symptom-fault mapping directly from training data. The invention first estimates the state of the system at discrete intervals in time. A feature vector x of dimension k is estimated from sets of successive windows of sensor data. A pattern recognition component then models the instantaneous estimate of the posterior class probability given the features, p(w(sub i) perpendicular to x), 1 less than or equal to i is less than or equal to m. Finally, a hidden Markov model is used to take advantage of temporal context and estimate class probabilities conditioned on recent past history. In this hierarchical pattern of information flow, the time series data is transformed and mapped into a categorical representation (the fault classes) and integrated over time to enable robust decision-making.

Smyth, Padhraic J.↗
NASA NTRS1995

Hidden Markov models for fault detection in dynamic systems

The invention is a system failure monitoring method and apparatus which learns the symptom-fault mapping directly from training data. The invention first estimates the state of the system at discrete intervals in time. A feature vector x of dimension k is estimated from sets of successive windows of sensor data. A pattern recognition component then models the instantaneous estimate of the posterior class probability given the features, p(w(sub i) (vertical bar)/x), 1 less than or equal to i isless than or equal to m. Finally, a hidden Markov model is used to take advantage of temporal context and estimate class probabilities conditioned on recent past history. In this hierarchical pattern of information flow, the time series data is transformed and mapped into a categorical representation (the fault classes) and integrated over time to enable robust decision-making.

Smyth, Padhraic J.↗
DOE OSTI2026

Unsupervised domain adaptation for radioisotope identification in gamma spectroscopy

Training machine learning models for radioisotope identification using gamma spectroscopy remains an elusive challenge for many practical applications, largely stemming from the difficulty of acquiring and labeling large, diverse experimental datasets. Simulations can mitigate this challenge, but the accuracy of models trained on simulated data can deteriorate substantially when deployed to an out-of-distribution operational environment. In this study, we demonstrate that unsupervised domain adaptation (UDA) can improve the ability of a model trained on synthetic data to generalize to a new testing domain, provided unlabeled data from the target domain are available. Conventional supervised techniques are unable to utilize this data because the absence of isotope labels precludes defining a supervised classification loss. Instead, we first pretrain a spectral classifier using labeled synthetic data and subsequently leverage unlabeled target data to align the learned feature representations between the source and target domains. We compare a range of different UDA techniques, finding that minimizing the maximum mean discrepancy (MMD) between source and target feature vectors yields the most consistent improvement to testing scores. For instance, using a custom transformer-based neural network, we achieved a testing accuracy of $0.904 \pm 0.022$ on an experimental LaBr test set after performing unsupervised feature alignment via MMD minimization, compared to $0.754 \pm 0.014$ before alignment. Overall, our results highlight the potential of using UDA to adapt a radioisotope classifier trained on synthetic data for real-world deployment.

Lalor, Peter W.↗
NASA NTRS1983

Advanced technology exhaust nozzle development

The requirement for greater tactical aircraft operational capabilities has led to increasing research emphasis on the refinement of engine/airframe integration methods and exhaust nozzle flexibility. A major prospective advancement in the development of these capabilities takes the form of multifunctional exhaust nozzle systems with thrust reversal and thrust vectoring features, whose operation will be shared by both airframe and powerplant control systems. Attention is presently given to the two-dimensional convergent-divergent and single expansion ramp nozzle designs, with emphasis on the variable geometry mechanical systems by which they assume cruising flight, vectoring, and thrust reversal operations. The nozzles have been wind tunnel model-tested for the cases of the F-18 fighter and a supersonic cruise configuration concept.

Dusa, D. J.↗
NASA NTRS2016

Exploration Clinical Decision Support System: Medical Data Architecture

The Exploration Clinical Decision Support (ECDS) System project is intended to enhance the Exploration Medical Capability (ExMC) Element for extended duration, deep-space mission planning in HRP. A major development guideline is the Risk of "Adverse Health Outcomes & Decrements in Performance due to Limitations of In-flight Medical Conditions". ECDS attempts to mitigate that Risk by providing crew-specific health information, actionable insight, crew guidance and advice based on computational algorithmic analysis. The availability of inflight health diagnostic computational methods has been identified as an essential capability for human exploration missions. Inflight electronic health data sources are often heterogeneous, and thus may be isolated or not examined as an aggregate whole. The ECDS System objective provides both a data architecture that collects and manages disparate health data, and an active knowledge system that analyzes health evidence to deliver case-specific advice. A single, cohesive space-ready decision support capability that considers all exploration clinical measurements is not commercially available at present. Hence, this Task is a newly coordinated development effort by which ECDS and its supporting data infrastructure will demonstrate the feasibility of intelligent data mining and predictive modeling as a biomedical diagnostic support mechanism on manned exploration missions. The initial step towards ground and flight demonstrations has been the research and development of both image and clinical text-based computer-aided patient diagnosis. Human anatomical images displaying abnormal/pathological features have been annotated using controlled terminology templates, marked-up, and then stored in compliance with the AIM standard. These images have been filtered and disease characterized based on machine learning of semantic and quantitative feature vectors. The next phase will evaluate disease treatment response via quantitative linear dimension biomarkers that enable image content-based retrieval and criteria assessment. In addition, a data mining engine (DME) is applied to cross-sectional adult surveys for predicting occurrence of renal calculi, ranked by statistical significance of demographics and specific food ingestion. In addition to this precursor space flight algorithm training, the DME will utilize a feature-engineering capability for unstructured clinical text classification health discovery. The ECDS backbone is a proposed multi-tier modular architecture providing data messaging protocols, storage, management and real-time patient data access. Technology demonstrations and success metrics will be finalized in FY16.

Biomedical support↗
NASA NTRS1985

Application of a computable model of human spatial vision to phase discrimination

A computable model of human spatial vision is used to make predictions for phase-discrimination experiments. This model is being developed to deal with a broad range of problems in vision and was not specifically formulated to deal with phase discrimination. In the model, cross-correlation of the stimuli with an array of sensors produces feature vectors that are operated on by a position-uncertain ideal observer to simulate detection and discrimination experiments. In this report, the stimuli are compound sinusoidal gratings composed of a fundamental and a higher-frequency component added in various phases. Model predictions are compared with three key results from the literature: (1) the effect of the contrast of the fundamental on phase discrimination, (2) threshold phase difference as a function of the fundamental frequency, and (3) the contrast required for phase discrimination as a function of the frequency ratio of the two grating components. In the first two cases, the predictions capture the main features of the data, although quantitative discrepancies remain. In the third case, the model fails, and this failure suggests additional restrictions on the combination of information across sensors.

Nielsen, K. R. K.↗
DOE OSTI2025

Reduced Order Modeling conditioned on monitored features for response and error bounds estimation in engineered systems

Reduced Order Models (ROMs) form essential tools across engineering domains by virtue of their function as surrogates for computationally intensive digital twinning simulators. Although purely data-driven methods are available for ROM construction, schemes that allow to retain a portion of the physics tend to enhance the interpretability and generalization of ROMs. However, physics-based techniques can adversely scale when dealing with nonlinear systems that feature parametric dependencies. This study introduces a generative physics-based ROM that is suited for nonlinear systems with parametric dependencies and is additionally able to provide numerical error bounds associated with the respective estimates. A main contribution of this work is the conditioning of these parametric ROMs to features that can be derived from monitoring measurements, feasibly in an online fashion. This is contrary to most existing ROM schemes, which remain restricted to the prescription of the physics-based, and usually a priori unknown, system parameters. Our work utilizes conditional Variational Autoencoders to continuously map the required reduction bases to a feature vector extracted from limited output measurements, while additionally allowing for a probabilistic assessment of the ROM-estimated Quantities of Interest. An auxiliary task using a neural network-based parametrization of suitable probability distributions is introduced to re-establish the link with physical model parameters. We verify the proposed scheme on a series of simulated case studies incorporating effects of geometric and material nonlinearity under parametric dependencies related to system properties and input load characteristics.

Conditional VAEs↗
DOE OSTI2024

Accelerating the Discovery of New, Single Phase High Entropy Ceramics via Active Learning

High-entropy ceramics have garnered interest due to their remarkable hardness, compressive strength, thermal stability, and fracture toughness; yet the discovery of new high-entropy ceramics (out of a tremendous number of possible elemental permutations) still largely requires costly, inefficient, trial-and-error experimental and computational approaches. The entropy forming ability (EFA) factor was recently proposed as a computational descriptor that positively correlates with the likelihood that a 5-metal high-entropy carbide (HECs) will form the desired single phase, homogeneous solid solution; however, discovery of new compositions is computationally expensive. If you consider 8 candidate metals, the HEC EFA approach uses 49 optimizations for each of the 56 unique 5-metal carbides, requiring a total of 2744 costly density functional theory calculations. Here, we describe an orders-of-magnitude more efficient active learning (AL) approach for identifying novel HECs. To begin, we compared numerous methods for generating composition-based feature vectors (e.g., magpie and mat2vec), deployed an ensemble of machine learning (ML) models to generate an average and distribution of predictions, and then utilized the distribution as an uncertainty. Here we then deployed an AL approach to extract new training data points where the ensemble of ML models predicted a high EFA value or was uncertain of the prediction. Our approach has the combined benefit of decreasing the amount of training data required to reach acceptable prediction qualities and biases the predictions toward identifying HECs with the desired high EFA values, which are tentatively correlated with the formation of single phase HECs. Using this approach, we increased the number of 5-metal carbides screened from 56 to 15,504, revealing 4 compositions with record-high EFA values that were previously unreported in the literature. Our AL framework is also generalizable and could be modified to rationally predict optimized candidate materials/combinations with a wide range of desired properties (e.g., mechanical stability, thermal conductivity).

36 MATERIALS SCIENCE↗
DOE OSTI2024

Structure Sensitive Reaction Kinetics of Chiral Molecules on Intrinsically Chiral Surfaces

Enantiospecific heterogeneous catalysis utilizes chiral surfaces to resolve enantiomers via structure sensitive surface chemistry. The catalyst design challenge is the identification of chiral surface structures that maximize enantiospecificity. Herein, we develop data driven models for the enantiospecificity of tartaric acid reactions on chiral Cu(hkl) R&S surfaces. Measurements of enantiospecific rate constants were obtained by using curved Cu(hkl) R&S surfaces that enable kinetic measurements on hundreds of chiral surface orientations. One model uses feature vectors derived from generalized coordination numbers to capture the local structure around Cu atoms exposed by the Cu(hkl) R&S surfaces. The second model introduces the use of chiral cubic harmonic functions to capture the symmetry constraints of the face-centered cubic Cu structure. The model using 58 generalized coordination numbers has a fitting error similar to that of the model using only 5 cubic harmonic functions. The two models predict maxima in the enantiospecificity on surfaces with very similar surface orientations. The models developed in this work are applicable for any enantiospecific reaction happening on any chiral material with a cubic lattice structure, opening the way to understanding the surface structure sensitivity of the enantiospecific reaction kinetics.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Predictive Indicators of the Performance of Large Language Models

In several mission contexts, it is desirable to estimate the performance of large language models (LLMs) on tasks that we cannot run directly. In light of published “scaling laws” our hypothesis is that some tasks should be consistently more challenging than others based on characteristics of the task. The goal of this project was to begin quantifying how much information about LLM performance can be gained from the features of a model and a task. Two of our statistical models struggled to converge. Pass/fail test results may provide limited information for inference beyond model quality and task difficulty, but we see no evidence at this time for significant feature interaction effect sizes, arguing for simple models. Future work extending the models to capitalize on perplexity of ground truth answers is suggested. This project also introduces “Depth of Knowledge Variant Testing” as a strategy for more finely assessing language models on open domain question and answer tasks. We developed sets of questions that ask a language model to produce similar information while demonstrating increasing depth of knowledge, and also relabeled existing Q&A test questions with their depth of knowledge. Our results suggest further consideration of Bloom’s taxonomy and further refinement of prompts to properly elicit information at varying depths. In the course of this work, we set up a basic infrastructure for standardizing tasks and testing many language models on these tasks. In addition to testing the predictive quality of model features and performance across test suites, with this project we have introduced two new task features to contextualize each test question: the Dewey Classification main category of information covered, and the Bloom’s taxonomy level that corresponds to the depth of knowledge probed by the question. Splits across these and other features produced over five hundred task subtypes with distinct feature vectors, which we tested on half a dozen models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Data and Code for Understanding Generative AI Content with Embedding Models

This repository contains code for the experiments in the paper "Understanding Generative AI Content with Embedding Models". Constructing high-quality features is critical to any quantitative data analysis. While feature engineering was historically addressed by carefully hand-crafting data representations based on domain expertise, deep neural networks (DNNs) now offer a radically different approach. DNNs implicitly engineer features by transforming their input data into hidden feature vectors called embeddings. For embedding vectors produced by foundation models -- which are trained to be useful across many contexts -- we demonstrate that simple and well-studied dimensionality-reduction techniques such as Principal Component Analysis uncover inherent heterogeneity in input data concordant with human-understandable explanations. Of the many applications for this framework, we find empirical evidence that there is intrinsic separability between real samples and those generated by artificial intelligence (AI).

Vargas, Max [Pacific Northwest National Laboratory↗
NASA NTRS1982

Misregistration's effects on classification and proportion estimation accuracy

The estimates of crop type and acreage are undertaken in the AgRISTARS program by registering multiple date acquisitions of small subareas of LANDSAT scenes (termed segments), and applying multispectral analysis to them. An important contribution to errors in classification and acreage estimates is misregistration between multiple acquisitions. The formula used to express this relationship is given and the operations applied are so shown in diagrams. The taking of a LANDSAT feature vector and the derivation of the brightness and greeness are illustrated. It is shown that for any given sensor IFOV geometry, typical populations of fields can be derived and histograms can be plotted of the number of fields against field size according to ground truth. As a function of the resolution element, the IFOV of the sensor can draw the proportion of pure pixels in a given crop. Because the thematic mapper has a smaller resolution, the proportion of pixels that are pure in any given area will be larger.

Juday, R. D.↗