Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data 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 1,513 records · Page 84
All sourcesNASA NTRSDOE OSTI
NASA NTRS1987

A spectral-knowledge-based approach for urban land-cover discrimination

A prototype expert system was developed to demonstrate the feasibility of classifying multispectral remotely sensed data on the basis of spectral knowledge. The spectral expert was developed and tested with Thematic Mapper Simulator (TMS) data having eight spectral bands and a spatial resolution of 5 m. A knowledge base was developed that describes the target categories in terms of characteristic spectral relationships. The knowledge base was developed under the following assumptions: the data are calibrated to ground reflectance, the area is well illuminated, the pixels are dominated by a single category, and the target categories can be recognized without the use of spatial knowledge. Classification decisions are made on the basis of convergent evidence as derived from applying the spectral rules to a multiple spatial resolution representation of the image. The spectral expert achieved an accuracy of 80-percent correct or higher in recognizing 11 spectral categories in TMS data for the washington, DC, area. Classification performance can be expected to decrease for data that do not satisfy the above assumptions as illustrated by the 63-percent accuracy for 30-m resolution Thematic Mapper data.

Wharton, Stephen W.↗
NASA NTRS1975

Adaptive statistical pattern classifiers for remotely sensed data

A technique for the adaptive estimation of nonstationary statistics necessary for Bayesian classification is developed. The basic approach to the adaptive estimation procedure consists of two steps: (1) an optimal stochastic approximation of the parameters of interest and (2) a projection of the parameters in time or position. A divergence criterion is developed to monitor algorithm performance. Comparative results of adaptive and nonadaptive classifier tests are presented for simulated four dimensional spectral scan data.

Gonzalez, R. C.↗
DOE OSTI2022

Combinatorial Evaluation of Physical Feature Engineering, Classical Machine Learning, and Deep Learning Models for Synchrophasor Data at Scale

A major objective of the project was to train and evaluate the effectiveness of multiple event and anomaly detection, identification and classification deep temporal learning models for processing of real-time phasor measurement unit (PMU) data streams. A vast dataset, consisting of two years of phasor measurements from all three U.S. Interconnections, was curated and released by the Department of Energy (DOE) through Pacific Northwest National Laboratory (PNNL). The dataset also included an event log that provided event times and types (e.g. generator trips, line trips, planned service events, transformer operations, etc.). Our analysis of this dataset addressed six (6) of the eleven (11) research priorities identified in Funding Opportunity Announcement (FOA) DE-FOA-0001861 “Big Data Analysis of Synchrophasor Data” (FOA 1861). Rather than being limited to pre-determined specific algorithms, this project relied on the uniquely structured, highly performant underlying time series database capabilities of the PredictiveGrid platform to assess the vast dataset utilizing a wide variety of algorithms.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

What’s the Difference? The Potential for Convolutional Neural Networks for Transient Detection without Template Subtraction

Abstract We present a study of the potential for convolutional neural networks (CNNs) to enable separation of astrophysical transients from image artifacts, a task known as “real–bogus” classification, without requiring a template-subtracted (or difference) image, which requires a computationally expensive process to generate, involving image matching on small spatial scales in large volumes of data. Using data from the Dark Energy Survey, we explore the use of CNNs to (1) automate the real–bogus classification and (2) reduce the computational costs of transient discovery. We compare the efficiency of two CNNs with similar architectures, one that uses “image triplets” (templates, search, and difference image) and one that takes as input the template and search only. We measure the decrease in efficiency associated with the loss of information in input, finding that the testing accuracy is reduced from ∼96% to ∼91.1%. We further investigate how the latter model learns the required information from the template and search by exploring the saliency maps. Our work (1) confirms that CNNs are excellent models for real–bogus classification that rely exclusively on the imaging data and require no feature engineering task and (2) demonstrates that high-accuracy (>90%) models can be built without the need to construct difference images, but some accuracy is lost. Because, once trained, neural networks can generate predictions at minimal computational costs, we argue that future implementations of this methodology could dramatically reduce the computational costs in the detection of transients in synoptic surveys like Rubin Observatory's Legacy Survey of Space and Time by bypassing the difference image analysis entirely.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1987

Space Station Information System requirements for integrated communications

Space Station Information System (SSIS) requirements for integrated end-to-end communications are presented. The SSIS is defined as the integrated set of space and ground data and information systems and networks which will provide required data services to the Space Station flight crew, ground operations personnel, and customer communities. This model is based on the International Standards Organization (ISO) layered model for Open System Interconnection (OSI). These SSIS requirements include grades of service, priority classifications, systems management, flow control, bandwidth allocation, and standard SSIS data services.

Marker, W.↗
DOE OSTI2021

Deep Learning for Fish Identification from Sonar Data: CRADA 481 [Abstract only]

To help solve the challenges of hydropower energy production related to the potential for eel injury and mortality from passage through hydropower turbines, we will develop a deep learning method for identifying migrating eels from imaging sonar. This project continues with a prior project conducted by the Pacific Northwest National Laboratory (PNNL) and the Electric Power Research Institute (EPRI) in FY2018-2019. The proposed method employs Convolution Neural Network (CNN), a powerful deep learning method for image classification, to distinguish between images of eels and non-eel moving objects. We propose to collect more laboratory data and add more existing field data to train a powerful deep learning model. In addition to eels and sticks as classified in previous studies, we will add images containing several non-eel fish species and macrophyte mats to the training data. A multi-class classification model will be developed to distinguish these objects. Object detection algorithm will be explored and developed to locate and identify multiple objects in each sonar frame. Motion analysis will be performed to track the movement of objects in sonar video clips. We will also improve the data conversion algorithm so that it can read in both DIDSON and ARIS (both are imaging sonars developed by Sound Metrics Corp) data files and convert them to images with comparably high resolution, regardless of the varying detection ranges in different environments. The developed algorithms will be packaged as a software with a graphic user interface. The software will be evaluated by external collaborators in the field. The developed framework can be generalized for automatic monitoring of fish passage and migration using other imaging sonars like ARIS and will benefit the design and operation of ecologically friendly hydroelectric projects. The developed wavelet and CNN model configuration parameters can potentially be transferred to lamprey detection in similar riverine environments.

13 HYDRO ENERGY↗
DOE OSTI2024

Radioisotope Identification with List-Mode Gamma Ray Data: A rigorous assessment on the value of temporal information applied to radioisotope identification.

This work explores the potential of utilizing temporal data from gamma-ray detectors, known as list-mode data, to enhance radioisotope identification. Traditional identification methods, which rely on full gamma-ray spectrum analysis, often require long dwell times and struggle with “confuser” sources, or spectra with similarly spaced spectral peaks. We hypothesize that by leveraging the probabilistic nature of nuclear decay and the time-encoded information from decay sequences and interactions with surrounding materials, we can improve classification accuracy over static spectral analysis. This research rigorously examines the temporal content of list-mode data through exploratory data analysis via correlation discovery and information theory. We further propose a basic classification model that can utilize spectral or temporal data (or both) to determine if the incorporation of temporal information can improve radioisotope identification. The findings suggest that the temporal information present in list-mode gamma-ray data has merit and should be further investigated.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS1989

Image-based terrain modeling with thematic mapper applied to resolving the limit of Holocene Lake expansion in the Great Salt Lake Desert, Utah, part 1

The LANDSAT Thematic Mapper (TM) scanner records reflected solar energy from the earth's surface in six wavelength regions, or bands, and one band that records emitted energy in the thermal region, giving a total of seven bands. Useful research was extracted about terrain morphometry from remote sensing measurements and this information is used in an image-based terrain model for selected coastal geomorphic features in the Great Salt Lake Desert (GSLD). Technical developments include the incorporation of Aerial Profiling of Terrain System (APTS) data in satellite image analysis, and the production and use of 3-D surface plots of TM reflectance data. Also included in the technical developments is the analysis of the ground control point spatial distribution and its affects on geometric correction, and the terrain mapping procedure; using satellite data in a way that eliminates the need to degrade the data by resampling. The most common approach for terrain mapping with multispectral scanner data includes the techniques of pattern recognition and image classification, as opposed to direct measurement of radiance for identification of terrain features. The research approach in this investigation was based on an understanding of the characteristics of reflected light resulting from the variations in moisture and geometry related to terrain as described by the physical laws of radiative transfer. The image-based terrain model provides quantitative information about the terrain morphometry based on the physical relationship between TM data, the physical character of the GSLD, and the APTS measurements.

Merola, John A.↗
DOE OSTI2023

A machine learning approach for identifying variables associated with risk of developing neutralizing antidrug antibodies to factor VIII

A key unmet need in the management of hemophilia A (HA) is the lack of clinically validated markers that are associated with the development of neutralizing antibodies to Factor VIII (FVIII) (commonly referred to as inhibitors). This study aimed to identify relevant biomarkers for FVIII inhibition using Machine Learning (ML) and Explainable AI (XAI) using the My Life Our Future (MLOF) research repository. The dataset includes biologically relevant variables such as age, race, sex, ethnicity, and the variants in the F8 gene. In addition, we previously carried out Human Leukocyte Antigen Class II (HLA-II) typing on samples obtained from the MLOF repository. Using this information, we derived other patient-specific biologically and genetically important variables. These included identifying the number of foreign FVIII derived peptides, based on the alignment of the endogenous FVIII and infused drug sequences, and the foreign-peptide HLA-II molecule binding affinity calculated using NetMHCIIpan. The data were processed and trained with multiple ML classification models to identify the top performing models. The top performing model was then chosen to apply XAI via SHAP, (SHapley Additive exPlanations) to identify the variables critical for the prediction of FVIII inhibitor development in a hemophilia A patient. Using XAI we provide a robust and ranked identification of variables that could be predictive for developing inhibitors to FVIII drugs in hemophilia A patients. These variables could be validated as biomarkers and used in making clinical decisions and during drug development. The top five variables for predicting inhibitor development based on SHAP values are: (i) the baseline activity of the FVIII protein, (ii) mean affinity of all foreign peptides for HLA DRB 3, 4, & 5 alleles, (iii) mean affinity of all foreign peptides for HLA DRB1 alleles), (iv) the minimum affinity among all foreign peptides for HLA DRB1 alleles, and (v) F8 mutation type.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Compressing deep neural networks on FPGAs to binary and ternary precision with hls4ml

We present the implementation of binary and ternary neural networks in the hls4ml library, designed to automatically convert deep neural network models to digital circuits with FPGA firmware. Starting from benchmark models trained with floating point precision, we investigate different strategies to reduce the network's resource consumption by reducing the numerical precision of the network parameters to binary or ternary. We discuss the trade-off between model accuracy and resource consumption. In addition, we show how to balance between latency and accuracy by retaining full precision on a selected subset of network components. As an example, we consider two multiclass classification tasks: handwritten digit recognition with the MNIST data set and jet identification with simulated proton-proton collisions at the CERN Large Hadron Collider. The binary and ternary implementation has similar performance to the higher precision implementation while using drastically fewer FPGA resources.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

TranSyT , an innovative framework for identifying transport systems

The importance and rate of development of genome-scale metabolic models have been growing for the last few years, increasing the demand for software solutions that automate several steps of this process. However, since TRIAGE’s release, software development for the automatic integration of transport reactions into models has stalled. Here, in this paper, we present the Transport Systems Tracker (TranSyT). Unlike other transport systems annotation software, TranSyT does not rely on manual curation to expand its internal database, which is derived from highly curated records retrieved from the Transporters Classification Database and complemented with information from other data sources. TranSyT compiles information regarding transporter families and proteins, and derives reactions into its internal database, making it available for rapid annotation of complete genomes. All transport reactions have GPR associations and can be exported with identifiers from four different metabolite databases. TranSyT is currently available as a plugin for merlin v4.0 and an app for KBase.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

A catalogue of white dwarfs in Gaia EDR3

ABSTRACT We present a catalogue of white dwarf candidates selected from Gaia Early Data Release 3 (EDR3). We applied several selection criteria in absolute magnitude, colour, and Gaia quality flags to remove objects with unreliable measurements while preserving most stars compatible with the white dwarf locus in the Hertzsprung–Russell diagram. We then used a sample of over 30 000 spectroscopically confirmed white dwarfs and contaminants from the Sloan Digital Sky Survey (SDSS) to map the distribution of these objects in the Gaia absolute magnitude–colour space. Finally, we adopt the same method presented in our previous work on Gaia Data Release 2 (DR2) to calculate a probability of being a white dwarf (PWD) for ≃1.3 million sources that passed our quality selection. The PWD values can be used to select a sample of ${\simeq} 359\,000$ high-confidence white dwarf candidates. We calculated stellar parameters (effective temperature, surface gravity, and mass) for all these stars by fitting Gaia astrometry and photometry with synthetic pure-H, pure-He, and mixed H–He atmospheric models. We estimate an upper limit of 93 per cent for the overall completeness of our catalogue for white dwarfs with G ≤ 20 mag and effective temperature (Teff) > 7000 K, at high Galactic latitudes (|b| > 20°). Alongside the main catalogue we include a reduced proper motion extension containing ${\simeq} 10\,200$ white dwarf candidates with unreliable parallax measurements that could, however, be identified on the basis of their proper motion. We also performed a cross-match of our catalogues with SDSS Data Release 16 (DR16) spectroscopy and provide spectral classification based on visual inspection for all resulting matches.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Effects of Substance Use and Antisocial Personality on Neuroimaging-Based Machine Learning Prediction of Schizophrenia

Abstract Background and hypothesis Neuroimaging-based machine learning (ML) algorithms have the potential to aid the clinical diagnosis of schizophrenia. However, literature on the effect of prevalent comorbidities such as substance use disorder (SUD) and antisocial personality (ASPD) on these models’ performance has remained unexplored. We investigated whether the presence of SUD or ASPD affects the performance of neuroimaging-based ML models trained to discern patients with schizophrenia (SCH) from controls. Study design We trained an ML model on structural MRI data from public datasets to distinguish between SCH and controls (SCH = 347, controls = 341). We then investigated the model’s performance in two independent samples of individuals undergoing forensic psychiatric examination: sample 1 was used for sensitivity analysis to discern ASPD (N = 52) from SCH (N = 66), and sample 2 was used for specificity analysis to discern ASPD (N = 26) from controls (N = 25). Both samples included individuals with SUD. Study results In sample 1, 94.4% of SCH with comorbid ASPD and SUD were classified as SCH, followed by patients with SCH + SUD (78.8% classified as SCH) and patients with SCH (60.0% classified as SCH). The model failed to discern SCH without comorbidities from ASPD + SUD (AUC = 0.562, 95%CI = 0.400–0.723). In sample 2, the model’s specificity to predict controls was 84.0%. In both samples, about half of the ASPD + SUD were misclassified as SCH. Data-driven functional characterization revealed associations between the classification as SCH and cognition-related brain regions. Conclusion Altogether, ASPD and SUD appear to have effects on ML prediction performance, which potentially results from converging cognition-related brain abnormalities between SCH, ASPD, and SUD.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors

This software offers methods and functions for training calibrated out-of-distribution detectors for medical image classification tasks. It includes functionalities for training, synthesizing data augmentations, calibration, and out-of-distribution detection. Developed using PyTorch, this software is compatible with standard neural network architectures used for imaging data. Additionally, it provides capabilities to compute evaluation metrics for assessing the performance and quality of the detectors.

Narayanaswamy, VivekSivaraman↗
DOE OSTI2024

Multivariate Time Series Intermittent Fault Detectionin Controller Area Network CAN

Fault detection in Controller Area Network (CAN) systems is crucial for ensuring the reliability and safety of automotive and industrial applications. This study investigates and compares the effectiveness of time series classification models for supervised fault detection in CAN data. This repository contains the code and data for our benchmarking experiment aimed at detecting intermittent faults in automotive Controller Area Network (CAN) data. The goal of this project is to compare various machine learning (ML) and deep learning (DL) models using different Time Series Cross-Validation (TSCV) techniques to evaluate their effectiveness in a streaming environment for fault detection.

Hespeler, Steven [Oak Ridge National Laboratory (O↗
DOE OSTI2022

Perfecting Our Set of Spectrophotometric Standard DA White Dwarfs

We verified for photometric stability a set of DA white dwarfs with Hubble Space Telescope magnitudes from the near-ultraviolet to the near-infrared and ground-based spectroscopy by using time-spaced observations from the Las Cumbres Observatory network of telescopes. The initial list of 38 stars was whittled to 32 final ones, which comprise a high-quality set of spectrophotometric standards. These stars are homogeneously distributed around the sky and are all fainter than r ~ 16.5 mag. Their distribution is such that at least two of them would be available to be observed from any observatory on the ground at any time at airmass less than 2. Light curves and different variability indices from the Las Cumbres Observatory data were used to determine the stability of the candidate standards. When available, Pan-STARRS1, Zwicky Transient Facility, and TESS data were also used to confirm the star classification. Our analysis showed that four DA white dwarfs may exhibit evidence of photometric variability, while a fifth is cooler than our established lower temperature limit, and a sixth star might be a binary. In some instances, due to the presence of faint nearby red sources, care should be used when observing a few of the spectrophotometric standards with ground-based telescopes. Light curves and finding charts for all the stars are provided.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Applications of Machine Learning to Predicting Core-collapse Supernova Explosion Outcomes

Most existing criteria derived from progenitor properties of core-collapse supernovae are not very accurate in predicting explosion outcomes. We present a novel look at identifying the explosion outcome of core-collapse supernovae using a machine-learning approach. Informed by a sample of 100 2D axisymmetric supernova simulations evolved with F ornax , we train and evaluate a random forest classifier as an explosion predictor. Furthermore, we examine physics-based feature sets including the compactness parameter, the Ertl condition, and a newly developed set that characterizes the silicon/oxygen interface. With over 1500 supernovae progenitors from 9-27 M ⊙ , we additionally train an autoencoder to extract physics-agnostic features directly from the progenitor density profiles. We find that the density profiles alone contain meaningful information regarding their explodability. Both the silicon/oxygen and autoencoder features predict the explosion outcome with ≈90% accuracy. In anticipation of much larger multidimensional simulation sets, we identify future directions in which machine-learning applications will be useful beyond the explosion outcome prediction.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1973

An objective technique to estimate percentage of an ERTS-1 water boundary resolution element covered by water

The author has identified the following significant results. An objective technique was developed to measure the surface area of water bodies. Nineteen water bodies in the Houston and Galveston, Texas area were selected as a basis for the technique development. The actual surface area of each body was determined from rectified and enlarged NASA aircraft photography. A clustering algorithm was used to produce classification maps of the region from ERTS-1 data. Certain classes were identified as being 100% water. Other classes were identified as being mixtures of water with land or vegetation. The number of picture elements falling on each water body and its boundary were counted. A linear regression analysis was performed to relate the total number of picture elements and boundary elements counted to the actual surface area. The standard error of the estimate was 6.7 acres. The absolute error was not a function of the actual surface area of the water body.

Erb, R. B.↗