Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “classification models”

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 775 records · Page 43
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Comparing Calibration Algorithms for the Rapid Characterization of Pretreated Corn Stover Using Near-Infrared Spectroscopy

Rapid characterization of biomass composition is a key enabling technology for biorefineries—the ability to measure the chemical composition of biomass materials entering the biorefinery as well as the composition of key process intermediate streams would allow real-time process control and the development of robust models to predict process performance. The utility of near-infrared (NIR) spectroscopy for rapid characterization requires multivariate algorithms for building calibration models. The most prevalent algorithm used for building calibration models using NIR spectra is the linear modeling algorithm Partial Least Squares Regression (PLS). Nonlinear regression algorithms (which are typically more computationally intensive than linear modeling approaches) have gained popularity in recent years due to their ability to solve a wide variety of classification and regression problems and the dramatic increase in available computational resources. In this work, we demonstrate that a calibration model can predict the composition of corn stover process intermediate samples pretreated with three different treatments—hot water (HW), dilute acid (DA), and deacetylation followed by dilute acid (DDA). We quantitatively compare three different algorithms for building prediction models based on near-infrared spectroscopy—partial least squares (PLS), support vector machines (SVM), and random forests (RF). We demonstrate the utility of improving model performance by accounting for instrument performance variability using repeated measurements of standard materials (e.g., the “repeatability file” strategy) and investigate its performance with nonlinear regression techniques, and we discuss methods for quantifying the uncertainties of specific predictions among the three methods.

09 BIOMASS FUELS↗
NASA NTRS2024

Jefferson County Ecological Conservation: Quantifying the Effects of Hydrologic Restoration in the Camas National Wildlife Refuge and Mud Lake Wildlife Management Area

Wetlands in the Camas National Wildlife Refuge and Mud Lake Wildlife Management Area, a rare landscape feature in the Intermountain West, are crucial for migratory birds along the Pacific Flyway, yet these wetlands have experienced a noticeable decline in extent and inundation over the last 40+ years. Partners at the U.S. Fish and Wildlife Service and Idaho Department of Fish and Game have ongoing restoration efforts that are yet to be quantified. To assist these partners, we used NASA Earth observations to quantify change in wetland extent and determine if the restoration projects met the intended impact. The QA_PIXEL band from Landsat 5 Thematic Mapper (TM) and Landsat 8 Operational Land Imager (OLI) was used to identify water. Landsat 8 OLI imagery was also used for classifying landcover in ArcGIS Pro for 2016 and 2020 and to forecast landcover in 2060 using TerrSet’s Land Change Modeler. We also compared lidar data from 2011 and 2019 to detect changes in vegetation height, ground elevation, and surface water levels, and Sentinel-2 Multispectral Instrument (MSI) imagery to detect changes in vegetation health. Classification results indicated overall accuracies over 84% and Kappa indices above 0.80, well surpassing random classification performance. From 2016 to 2020 our classifications showed an 825 acre increase in wetland extent, and our forecasted 2060 model showed a 2795 acre decrease. Combining our partners’ knowledge of the area with our analyses, we created a remote sensing workflow to enhance future monitoring and decision-making. This study demonstrated the feasibility of NASA Earth observations in quantifying wetlands, informing restoration projects, and supporting avian conservation.

Cassidy Bromka↗
DOE OSTI2023

Comparison of Supervised and Un-Supervised Machine Learning Algorithms for Threat Detection and Scintillator Performance for Radiation Portal Monitoring

Following the events of September 11, 2001, international border crossing have been equipped with radiation portal monitors (RPMs) to identify illicit radioactive material. Polyvinyl toluene (PVT) scintillators are commonly used due to their low cost and reasonable maintainability, however they offer low spectral resolution. Despite the fact that over twenty years has transpired since this event, radioisotopes are still typically identified by hand-crafted classification algorithms, e.g., total counts or energy windowing, and exhibit relatively poor performance in detecting threats at the low false alarm rates required to support the stream of commerce. While some improvement to performance has been realized via the use of supervised machine learning, these classification algorithms typically utilize simulations in lieu of real data due to the sparsity of data for one or more classes. Accordingly, the performance of these algorithms is somewhat less than optimal when examining experiments or simulations with model mismatch. Consequently, in this work, we examine the application of a number of unsupervised machine learning, anomaly detection based algorithms, to circumvent the inverse crime when analyzing spectroscopy data for RPMs. We also compare anomaly detection results with those obtained via the use of supervised classification detection ML algorithms when model mismatch is introduced between the simulated threat items utilized for training/testing. Finally, we compared the performance of the PVT scintillators to those obtained with higher resolution detectors using both anomaly detection and supervised classification algorithms.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2023

Autonomous Cyber Defense Against Dynamic Multi-strategy Infrastructural DDoS Attacks

Dynamic Infrastructural Distributed Denial of Service (I-DDoS) attacks constantly change attack vectors to congest core backhaul links and disrupt critical network availability while evading end-system defenses. To effectively counter these highly dynamic attacks, defense mechanisms need to exhibit adaptive decision strategies for real-time mitigation. This paper presents a novel Autonomous DDoS Defense framework that employs model-based reinforcement agents. The framework continuously learns attack strategies, predicts attack actions, and dynamically determines the optimal composition of defense tactics such as filtering, limiting, and rerouting for flow diversion. Our contributions include extending the underlying formulation of the Markov Decision Process (MDP) to address simultaneous DDoS attack and defense behavior, and accounting for environmental uncertainties. We also propose a fine-grained action mitigation approach robust to classification inaccuracies in Intrusion Detection Systems (IDS). Additionally, our reinforcement learning model demonstrates resilience against evasion and deceptive attacks. Evaluation experiments using real-world and simulated DDoS traces demonstrate that our autonomous defense framework ensures the delivery of approximately 96 - 98% of benign traffic despite the diverse range of attack strategies.

Dutta, Ashutosh↗
DOE OSTI2021

Tensorized Feature Spaces for Feature Explosion

In this paper 1 1 This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-000R22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan) This research used resources of the Oak Ridge Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC05-000R22725., we present a novel framework that uses tensor factorization to generate richer feature spaces for pixel classification in hyperspectral images. In particular, we assess the performance of different tensor rank decomposition methods as compared to the traditional kernel-based approaches for the hyperspectral image classification problem. We propose Orion, which takes as input a hyperspectral image tensor and a rank and outputs an enhanced feature space from the factor matrices of the decomposed tensor. Our method is a feature explosion technique that inherently maps low dimensional input space in $\mathbb{R}^{K}$ to high dimensional space in $\mathbb{R}^{R}$ , where $R\gg K$ , say in the order of 1000x, like a kernel. We show how the proposed method exploits the multi-linear structure of hyperspectral three dimensional tensor. We demonstrate the effectiveness of our method with experiments on three publicly available hyperspectral datasets with labeled pixels and compare their classification performance against traditional linear and non-linear supervised learning methods such as SVM with Linear, Polynomial, RBF kernels, and the Multi-Layer Perceptron model. Finally, we explore the relationship between the rank of the tensor decomposition and the classification accuracy using several hyperspectral datasets with ground truth.

Pasricha, Ravdeep Singh↗
NASA NTRS1998

Testing Models for Perceptual Discrimination Using Repeatable Noise

Adding noise to stimuli to be discriminated allows estimation of observer classification functions based on the correlation between observer responses and relevant features of the noisy stimuli. Examples will be presented of stimulus features that are found in auditory tone detection and visual Vernier acuity. Using the standard signal detection model (Thurstone scaling), we derive formulas to estimate the proportion of the observer's decision variable variance that is controlled by the added noise. One is based on the probability of agreement of the observer with him/herself on trials with the same noise sample. Another is based on the relative performance of the observer and the model. When these do not agree, the model can be rejected. A second derivation gives the probability of agreement of observer and model when the observer follows the model except for internal noise. Agreement significantly less than this amount allows rejection of the model.

Ahumada, Albert J., Jr.↗
NASA NTRS1998

Masking by Gratings Predicted by an Image Sequence Discriminating Model: Testing Models for Perceptual Discrimination Using Repeatable Noise

Adding noise to stimuli to be discriminated allows estimation of observer classification functions based on the correlation between observer responses and relevant features of the noisy stimuli. Examples will be presented of stimulus features that are found in auditory tone detection and visual vernier acuity. using the standard signal detection model (Thurstone scaling), we derive formulas to estimate the proportion of the observers decision variable variance that is controlled by the added noise. one is based on the probability of agreement of the observer with him/herself on trials with the same noise sample. Another is based on the relative performance of the observer and the model. When these do not agree, the model can be rejected. A second derivation gives the probability of agreement of observer and model when the observer follows the model except for internal noise. Agreement significantly less than this amount allows rejection of the model.

Ahumada, Albert J., Jr.↗
NASA NTRS2014

Neural Network Machine Learning and Dimension Reduction for Data Visualization

Neural network machine learning in computer science is a continuously developing field of study. Although neural network models have been developed which can accurately predict a numeric value or nominal classification, a general purpose method for constructing neural network architecture has yet to be developed. Computer scientists are often forced to rely on a trial-and-error process of developing and improving accurate neural network models. In many cases, models are constructed from a large number of input parameters. Understanding which input parameters have the greatest impact on the prediction of the model is often difficult to surmise, especially when the number of input variables is very high. This challenge is often labeled the "curse of dimensionality" in scientific fields. However, techniques exist for reducing the dimensionality of problems to just two dimensions. Once a problem's dimensions have been mapped to two dimensions, it can be easily plotted and understood by humans. The ability to visualize a multi-dimensional dataset can provide a means of identifying which input variables have the highest effect on determining a nominal or numeric output. Identifying these variables can provide a better means of training neural network models; models can be more easily and quickly trained using only input variables which appear to affect the outcome variable. The purpose of this project is to explore varying means of training neural networks and to utilize dimensional reduction for visualizing and understanding complex datasets.

Liles, Charles A.↗
NASA NTRS2020

Robust Algorithm for Estimating Total Suspended Solids (TSS) in Inland and Nearshore Coastal Waters

One of the challenging tasks in modern aquatic remote sensing is the retrieval of near-surface concentrations of Total Suspended Solids (TSS). This study aims to present a Statistical, inherent Optical property (IOP) -based, and muLti-conditional Inversion proceDure (SOLID) for enhanced retrievals of satellite-derived TSS under a wide range of in-water bio-optical conditions in rivers, lakes, estuaries, and coastal waters. In this study, using a large in situ database (N > 3500), the SOLID model is devised using a three-step procedure: (a) water-type classification of the input remote sensing reflectance (R(sub rs)), (b) retrieval of particulate backscattering (b(sub bp)) in the red or near-infrared (NIR) regions using semi-analytical, machine-learning, and empirical models, and (c) estimation of TSS from b(sub bp) via water-type-specific empirical models. Using an independent subset of our in situ data (N = 2729) with TSS ranging from 0.1 to 2626.8 [g/m (exp 3)], the SOLID model is thoroughly examined and compared against several state-of-the-art algorithms (Miller and McKee, 2004; Nechad et al., 2010; Novoa et al., 2017; Ondrusek et al., 2012; Petus et al., 2010). We show that SOLID outperforms all the other models to varying degrees, i.e., from 10 to > 100%, depending on the statistical attributes (e.g., global versus water-type-specific metrics). For demonstration purposes, the model is implemented for images acquired by the MultiSpectral Imager aboard Sentinel-2A/B over the Chesapeake Bay, San-Francisco-Bay-Delta Estuary, Lake Okeechobee, and Lake Taihu. To enable generating consistent, multimission TSS products, its performance is further extended to, and evaluated for, other missions, such as the Ocean and Land Color Instrument (OLCI), Moderate Resolution Imaging Spectroradiometer (MODIS), Visible Infrared Imaging Radiometer Suite (VIIRS), and Operational Land Imager (OLI). Sensitivity analyses on uncertainties induced by the atmospheric correction indicate that 10% uncertainty in Rrs leads to < 20% uncertainty in TSS retrievals from SOLID. While this study suggests that SOLID has a potential for producing TSS products in global coastal and inland waters, our statistical analysis certainly verifies that there is still a need for improving retrievals across a wide spectrum of particle loads.

Total suspended solids↗
NASA NTRS2009

Watershed and Hydrodynamic Modeling for Evaluating the Impact of Land Use Change on Submerged Aquatic Vegetation and Seagrasses in Mobile Bay

There is a continued need to understand how human activities along the northern Gulf of Mexico coast are impacting the natural ecosystems. The gulf coast is experiencing rapid population growth and associated land cover/land use change. Mobile Bay, AL is a designated pilot region of the Gulf of Mexico Alliance (GOMA) and is the focus area of many current NASA and NOAA studies, for example. This is a critical region, both ecologically and economically to the entire United States because it has the fourth largest freshwater inflow in the continental USA, is a vital nursery habitat for commercially and recreational important fisheries, and houses a working waterfront and port that is expanding. Watershed and hydrodynamic modeling has been performed for Mobile Bay to evaluate the impact of land use change in Mobile and Baldwin counties on the aquatic ecosystem. Watershed modeling using the Loading Simulation Package in C++ (LSPC) was performed for all watersheds contiguous to Mobile Bay for land use Scenarios in 1948, 1992, 2001, and 2030. The Prescott Spatial Growth Model was used to project the 2030 land use scenario based on observed trends. All land use scenarios were developed to a common land classification system developed by merging the 1992 and 2001 National Land Cover Data (NLCD). The LSPC model output provides changes in flow, temperature, sediments and general water quality for 22 discharge points into the Bay. These results were inputted in the Environmental Fluid Dynamics Computer Code (EFDC) hydrodynamic model to generate data on changes in temperature, salinity, and sediment concentrations on a grid with four vertical profiles throughout the Bay s aquatic ecosystems. The models were calibrated using in-situ data collected at sampling stations in and around Mobile bay. This phase of the project has focused on sediment modeling because of its significant influence on light attenuation which is a critical factor in the health of submerged aquatic vegetation. The impact of land use change on sediment concentrations was evaluated by analyzing the LSPC and EFDC sediment simulations for the four land use scenarios. Such analysis was also performed for storm and non-storm periods. In- situ data of total suspended sediments (TSS) and light attenuation were used to develop a regression model to estimate light attenuation from TSS. This regression model was used to derive marine light attenuation estimates throughout Mobile bay using the EFDC TSS outputs. The changes in sediment concentrations and associated impact on light attenuation in the aquatic ecosystem were used to perform an ecological analysis to evaluate the impact on seagreasses and Submerged Aquatic Vegetation (SAV) habitat. This is the key product benefiting the Mobile Bay coastal environmental managers that integrates the influences of sediments due to land use driven flow changes with the restoration potential of SAVs.

Estes, Maurice G.↗
DOE OSTI2024

Quantum Vision Transformers for Quark–Gluon Classification

We introduce a hybrid quantum-classical vision transformer architecture, notable for its integration of variational quantum circuits within both the attention mechanism and the multi-layer perceptrons. The research addresses the critical challenge of computational efficiency and resource constraints in analyzing data from the upcoming High Luminosity Large Hadron Collider, presenting the architecture as a potential solution. In particular, we evaluate our method by applying the model to multi-detector jet images from CMS Open Data. The goal is to distinguish quark-initiated from gluon-initiated jets. We successfully train the quantum model and evaluate it via numerical simulations. Using this approach, we achieve classification performance almost on par with the one obtained with the completely classical architecture, considering a similar number of parameters.

Comajoan Cara, Marçal (ORCID:0009000126263752)↗
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 OSTI2023

Machine learning methods for fission product identification from Bragg curves

A fission time projection chamber (fission-TPC) was developed to provide precise neutron-induced fission measurements for several major actinides. As fission fragments lose energy in one of the gas volumes of the fission-TPC, energy loss information is captured and may be used to determine fission product yields as the stopping power of an ion is dependent on the atomic number. The work presented here demonstrates the ability to apply machine learning techniques for Bragg curve classification. A set of one million energy loss curves for 24 different fission-fragment elements was generated using common stopping power software. A ResNet architecture optimized for 1D data was used to train, test, and validate a model for light and heavy fission fragments using the simulated data. The resultant classification accuracy for the light and heavy fragments indicates that this could be a viable method for elemental classification of data from the fission-TPC.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2026

Morphology-Based Building Use-Type Modeling: Learnability-First Schema Discovery

This technical memorandum documents an update to the building use-type classification workflow, used in LandScan Mosaic, that replaces a fixed, semantically defined class schema with a learnability-first schema discovery procedure. Historically, the target label schema was specified a priori (e.g., predicting a chosen set of use-type codes), and model training and evaluation were performed within that fixed label space. In the updated workflow, the pipeline first evaluates which non-residential distinctions are learnable under spatial generalization and then collapses ambiguous classes into data-driven groupings before finalizing the schema used for production training.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1991

Pattern-recognition techniques applied to performance monitoring of the DSS 13 34-meter antenna control assembly

The results of applying pattern recognition techniques to diagnose fault conditions in the pointing system of one of the Deep Space network's large antennas, the DSS 13 34-meter structure, are discussed. A previous article described an experiment whereby a neural network technique was used to identify fault classes by using data obtained from a simulation model of the Deep Space Network (DSN) 70-meter antenna system. Described here is the extension of these classification techniques to the analysis of real data from the field. The general architecture and philosophy of an autonomous monitoring paradigm is described and classification results are discussed and analyzed in this context. Key features of this approach include a probabilistic time-varying context model, the effective integration of signal processing and system identification techniques with pattern recognition algorithms, and the ability to calibrate the system given limited amounts of training data. Reported here are recognition accuracies in the 97 to 98 percent range for the particular fault classes included in the experiments.

Mellstrom, J. A.↗
NASA NTRS2014

A Framework for Land Cover Classification Using Discrete Return LiDAR Data: Adopting Pseudo-Waveform and Hierarchical Segmentation

Acquiring current, accurate land-use information is critical for monitoring and understanding the impact of anthropogenic activities on natural environments.Remote sensing technologies are of increasing importance because of their capability to acquire information for large areas in a timely manner, enabling decision makers to be more effective in complex environments. Although optical imagery has demonstrated to be successful for land cover classification, active sensors, such as light detection and ranging (LiDAR), have distinct capabilities that can be exploited to improve classification results. However, utilization of LiDAR data for land cover classification has not been fully exploited. Moreover, spatial-spectral classification has recently gained significant attention since classification accuracy can be improved by extracting additional information from the neighboring pixels. Although spatial information has been widely used for spectral data, less attention has been given to LiDARdata. In this work, a new framework for land cover classification using discrete return LiDAR data is proposed. Pseudo-waveforms are generated from the LiDAR data and processed by hierarchical segmentation. Spatial featuresare extracted in a region-based way using a new unsupervised strategy for multiple pruning of the segmentation hierarchy. The proposed framework is validated experimentally on a real dataset acquired in an urban area. Better classification results are exhibited by the proposed framework compared to the cases in which basic LiDAR products such as digital surface model and intensity image are used. Moreover, the proposed region-based feature extraction strategy results in improved classification accuracies in comparison with a more traditional window-based approach.

Light Detection & Ranging (LIDAR)↗
DOE OSTI2025

Development of chemometric models to classify solid-state U materials by micro-Raman spectroscopy

Discerning uranium (U) particles found in environmental sampling is of interest for monitoring the peaceful use of nuclear material. In this study, a soft independent modeling of class analogy (SIMCA) library was successfully developed for the classification of a four-class system consisting of α-U 3 O 8 , UO 2 , UO 2 (NO 3 ) 2 ·6H 2 O (UNH), and UO 2 O 2 ·4H 2 O (studtite) by Raman spectroscopy in the presence of matrix particulates and additional outliers. Spectral variability between numerous particles of each type revealed appreciable differences as a function of particle size with respect to hydration state and potential oxide phase within each class. Interclass variability was accounted for using both unsupervised and supervised chemometric models. The supervised SIMCA model displayed reasonable sensitivity for each U class and a high degree of specificity by returning whether a spectrum belonged to one class or not. This work demonstrates how Raman spectral features and chemometrics can be used to distinguish U materials from one another and from matrix materials such as flint clay. Combining the outlined chemometric approach with Raman mapping sequences could provide a rapid, nondestructive technique to characterize the chemical composition of a diverse collection of U compounds amid background samples for environmental sampling, nuclear forensics, and industrial applications.

Actinide↗
DOE OSTI2023

Higgs event classification using Machine Learning

The Higgs boson is a fundamental particle in the Standard Model of particle physics, theorized in the 1960s and later discovered in 2012 at the Large Hadron Collider (LHC). It plays a pivotal role in the mechanism of mass generation for other particles. This poster focuses on the application of Machine Learning algorithms to efficiently classify Higgs boson events.

Khan, Mysha Jahin↗