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 541 records · Page 30
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Power System Feature-Based Event Classification by Means of Multiple PMU Data

Abstract—Phasor Measurement Units (PMUs) provide time synchronized measurements across the power grid, enabling data driven event detection and classification for enhanced system monitoring and situational awareness. However, variations in event duration, spatial extent, and severity, along with coincident events, pose challenges for conventional classification models that require fixed-size inputs. This paper presents a feature-based framework that aggregates diverse attributes from all available PMUs for each event into a fixed-length vector, facilitating the application of standard machine learning classifiers, including Random Forest, XGBoost, and Multilayer Perceptron. A probabilistic post-processing scheme is further introduced to enable multi-label classification in the presence of overlapping events. Experiments using real-world PMU data demonstrate that the Random Forest model achieves 95% accuracy, while the proposed post-processing method yields an additional 3% improvement.

Nematirad, Reza↗
DOE OSTI2016

Towards catchment classification in data-scarce regions

Assessing spatial variation in hydrologic processes can help to inform freshwater management and advance ecological understanding, yet many areas lack sufficient flow records on which to base classifications. Seeking to address this challenge, we apply concepts developed in data-rich settings to public, global data in order to demonstrate a broadly replicable approach to characterizing hydrologic variation. The proposed approach groups the basins associated with reaches in a river network according to key environmental drivers of hydrologic conditions. This initial study examines Colorado (USA), where long-term streamflow records permit comparison to previously distinguished flow regime types, and the Republic of Ecuador, where data limitations preclude such analysis. The flow regime types assigned to gages in Colorado corresponded reasonably well to the classes distinguished from environmental features. The divisions in Ecuador reflected major known biophysical gradients while also providing a higher resolution supplement to an existing depiction of freshwater ecoregions. Although freshwater policy and management decisions occur amidst uncertainty and imperfect knowledge, this classification framework offers a rigorous and transferrable means to distinguish catchments in data-scarce regions. The maps and attributes of the resulting ecohydrologic classes offer a departure point for additional study and data collection programs such as the placement of stations in under-monitored classes, and the divisions may serve as a preliminary template with which to structure conservation efforts such as environmental flow assessments.

13 HYDRO ENERGY↗
DOE OSTI2019

Gastrointestinal stromal tumor risk classification: spectral CT quantitative parameters

Purpose: To examine the value of spectral CT quantitative parameters in gastrointestinal stromal tumor (GIST) risk classification. Materials and methods: This retrospective study was approved by the institutional review board. The requirement for informed consent was signed. The authors evaluated 86 patients (30 high risk, 22 medium risk, 28 low risk, and 6 very low risk; mean age: 59 years [range 19–83 years]) with pathologically confirmed GIST who underwent plain and triple-phase contrast-enhanced CT with spectral CT imaging mode from March 2015 through September 2017, with manual follow-up. Quantitative parameters including the CT value of 70 keV monochromatic images, the slope of spectral curves, and the normalized iodine concentration (NIC) and water (iodine) concentrations were measured and calculated, and conducted a power analysis of the above data. Results: (1) The CT values at 70 keV of the high-risk group were higher than the intermediate and low groups in each of the enhanced phases (P ≤ 0.001), no significant differences in the intermediate-risk and low-risk groups were noted (P = 0.874, 0.871, 0.831, respectively). (2) The slope of the spectral curve of the high-risk group was higher than those of the intermediate and low groups in each of the enhanced phases (P ≤ 0.001), and there were no significant differences between the intermediate- and low-risk groups (P = 0.069, 0.466, 0.840, respectively). (3) The NIC of the high-risk group significantly differed from the lower risk groups (P ≤ 0.001). There was also no significant difference observed between the intermediate- and low-risk groups (P = 0.671, 0.457, 0.833, respectively). (4) The power analysis results show that only the low-risk group with delay period is 0.530, the rest groups are all greater than 0.999. Conclusion: Dual-energy spectral CT with quantitative analysis may help to increase the accuracy in differentiating the pathological risk classification of GIST between high risk and non-high risk, preoperatively. There were limitations for distinguishing the intermediate- and low-risk groups.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2022

Pre-trained network-based transfer learning: A small-sample machine learning approach to nuclear power plant classification problem

Some research topics belonging to classification problems in the nuclear industry, such as fault diagnosis and accident identification, can be solved by feature extraction and subsequent application of statistical machine learning classifiers. Recently, deep neural network-based methods with automatic feature extraction and high accuracy have gained wide attention. They usually require large-scale training data, however, plant fault or accident data are scarce or difficult to obtain. Here this paper proposes a convolutional network (CNN)-based transfer learning method to solve this problem. The network's shallow layer is derived from a pre-trained CNN based on the ImageNet database to automatically extract features, and the deep layer is customized to match the classification problem. Data in non-image formats are converted to image formats and subsequently used to train the network. Case studies of rotating machines fault diagnosis show that the proposed method requires only limited training data to achieve high accuracy.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

Class imbalance in out-of-distribution datasets: Improving the robustness of the TextCNN for the classification of rare cancer types

In the last decade, the widespread adoption of electronic health record documentation has created huge opportunities for information mining. Natural language processing (NLP) techniques using machine and deep learning are becoming increasingly widespread for information extraction tasks from unstructured clinical notes. Disparities in performance when deploying machine learning models in the real world have recently received considerable attention. In the clinical NLP domain, the robustness of convolutional neural networks (CNNs) for classifying cancer pathology reports under natural distribution shifts remains understudied. In this research, we aim to quantify and improve the performance of the CNN for text classification on out-of-distribution (OOD) datasets resulting from the natural evolution of clinical text in pathology reports. We identified class imbalance due to different prevalence of cancer types as one of the sources of performance drop and analyzed the impact of previous methods for addressing class imbalance when deploying models in real-world domains. Our results show that our novel class-specialized ensemble technique outperforms other methods for the classification of rare cancer types in terms of macro F1 scores. We also found that traditional ensemble methods perform better in top classes, leading to higher micro F1 scores. Based on our findings, we formulate a series of recommendations for other ML practitioners on how to build robust models with extremely imbalanced datasets in biomedical NLP applications.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

SympGNNs: Symplectic Graph Neural Networks for identifying high-dimensional Hamiltonian systems and node classification

Existing neural network models to learn Hamiltonian systems, such as SympNets, although accurate in low-dimensions, struggle to learn the correct dynamics for high-dimensional many-body systems. Herein, we introduce Symplectic Graph Neural Networks (SympGNNs) that can effectively handle system identification in high-dimensional Hamiltonian systems, as well as node classification. SympGNNs combine symplectic maps with permutation equivariance, a property of graph neural networks. Specifically, we propose two variants of SympGNNs: (i) G-SympGNN and (ii) LA-SympGNN, arising from different parameterizations of the kinetic and potential energy. We demonstrate the capabilities of SympGNN on two physical examples: a 40-particle coupled Harmonic oscillator, and a 2000-particle molecular dynamics simulation in a two-dimensional Lennard-Jones potential. Furthermore, we demonstrate the performance of SympGNN in the node classification task, achieving accuracy comparable to the state-of-the-art. Finally, we also empirically show that SympGNN can overcome the oversmoothing and heterophily problems, two key challenges in the field of graph neural networks.

Deep learning↗
DOE OSTI2015

High Throughput Ambient Mass Spectrometric Approach to Species Identification and Classification from Chemical Fingerprint Signatures

A high throughput method for species identification and classification through chemometric processing of direct analysis in real time (DART) mass spectrometry-derived fingerprint signatures has been developed. The method entails introduction of samples to the open air space between the DART ion source and the mass spectrometer inlet, with the entire observed mass spectral fingerprint subjected to unsupervised hierarchical clustering processing. Moreover, a range of both polar and non-polar chemotypes are instantaneously detected. The result is identification and species level classification based on the entire DART-MS spectrum. In this paper, we illustrate how the method can be used to: (1) distinguish between endangered woods regulated by the Convention for the International Trade of Endangered Flora and Fauna (CITES) treaty; (2) assess the origin and by extension the properties of biodiesel feedstocks; (3) determine insect species from analysis of puparial casings; (4) distinguish between psychoactive plants products; and (5) differentiate between Eucalyptus species. An advantage of the hierarchical clustering approach to processing of the DART-MS derived fingerprint is that it shows both similarities and differences between species based on their chemotypes. Furthermore, full knowledge of the identities of the constituents contained within the small molecule profile of analyzed samples is not required.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Ensemble voting-based fault classification and location identification for a distribution system with microgrids using smart meter measurements

This study presents an ensemble learning approach for fault classification and location identification in a smart distribution network containing photovoltaics (PV)-based microgrid. Lack of available data points and the unbalanced nature of the distribution system make fault handling a challenging task for utilities. The proposed method uses event-driven voltage data from smart meters to classify and locate faults. The ensemble voting classifier is composed of three base learners; random forest, k-nearest neighbours, and artificial neural network. The fault location (FL) task has been formulated as a classification problem where the fault type is classified in the first step and based on the fault type, the faulty bus is identified. The method is tested on IEEE-123 bus system modified with added PV-based microgrid along with dynamic loading conditions and varying fault resistances from 0 to 20 Ω for both unbalanced and balanced fault types. A further sensitivity analysis has been done to test the robustness of the proposed method under various noise levels and data loss errors in the smart meter measurements. The ensemble method shows improved performance and robustness compared to some previously proposed FL methods. Finally, the proposed method has been experimentally validated on a real-time simulation-based testbed using a state-of-the-art digital real-time simulator, industry standard DNP3 communication protocol and a cpu-based control centre running the FL algorithm.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2015

Classification of Malaysia aromatic rice using multivariate statistical analysis

Aromatic rice (Oryza sativa L.) is considered as the best quality premium rice. The varieties are preferred by consumers because of its preference criteria such as shape, colour, distinctive aroma and flavour. The price of aromatic rice is higher than ordinary rice due to its special needed growth condition for instance specific climate and soil. Presently, the aromatic rice quality is identified by using its key elements and isotopic variables. The rice can also be classified via Gas Chromatography Mass Spectrometry (GC-MS) or human sensory panels. However, the uses of human sensory panels have significant drawbacks such as lengthy training time, and prone to fatigue as the number of sample increased and inconsistent. The GC–MS analysis techniques on the other hand, require detailed procedures, lengthy analysis and quite costly. This paper presents the application of in-house developed Electronic Nose (e-nose) to classify new aromatic rice varieties. The e-nose is used to classify the variety of aromatic rice based on the samples odour. The samples were taken from the variety of rice. The instrument utilizes multivariate statistical data analysis, including Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and K-Nearest Neighbours (KNN) to classify the unknown rice samples. The Leave-One-Out (LOO) validation approach is applied to evaluate the ability of KNN to perform recognition and classification of the unspecified samples. The visual observation of the PCA and LDA plots of the rice proves that the instrument was able to separate the samples into different clusters accordingly. The results of LDA and KNN with low misclassification error support the above findings and we may conclude that the e-nose is successfully applied to the classification of the aromatic rice varieties.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2015

Threshold selection for classification of MR brain images by clustering method

Given a grey-intensity image, our method detects the optimal threshold for a suitable binarization of MR brain images. In MR brain image processing, the grey levels of pixels belonging to the object are not substantially different from the grey levels belonging to the background. Threshold optimization is an effective tool to separate objects from the background and further, in classification applications. This paper gives a detailed investigation on the selection of thresholds. Our method does not use the well-known method for binarization. Instead, we perform a simple threshold optimization which, in turn, will allow the best classification of the analyzed images into healthy and multiple sclerosis disease. The dissimilarity (or the distance between classes) has been established using the clustering method based on dendrograms. We tested our method using two classes of images: the first consists of 20 T2-weighted and 20 proton density PD-weighted scans from two healthy subjects and from two patients with multiple sclerosis. For each image and for each threshold, the number of the white pixels (or the area of white objects in binary image) has been determined. These pixel numbers represent the objects in clustering operation. The following optimum threshold values are obtained, T = 80 for PD images and T = 30 for T2w images. Each mentioned threshold separate clearly the clusters that belonging of the studied groups, healthy patient and multiple sclerosis disease.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

A novel construct for scaling groundwater–river interactions based on machine-guided hydromorphic classification

Hydrologic exchange between river channels and adjacent subsurface environments is a key process that influences water quality and ecosystem function in river corridors. Predictive numerical models are needed to understand responses of river corridors to environmental change and to support sustainable watershed management. We posit that systematic hydromorphic classification provides a scaling construct that facilitates extrapolation of outputs from local-scale mechanistic models to reduced-order models applicable at reach and watershed scales. This in turn offers the potential to improve large-scale predictions of river corridor hydrobiogeochemical processes. Here we present a new machine-guided hydromorphic classification methodology that addresses the key requirements of this objective, and we demonstrate its application to a segment of the Columbia River in the northwestern United States. The resulting hydromorphic classes form spatially coherent and physically interpretable hydromorphic units that exhibit distinct behaviors in terms of distributions of subsurface residence times (a primary control on critical biogeochemical reactions). This approach forms the basis of ongoing research that is evaluating the formulation of reduced-order models and transferability of results to other river reaches and larger scales.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

‘Flux+Mutability’: a conditional generative approach to one-class classification and anomaly detection

Abstract Anomaly Detection is becoming increasingly popular within the experimental physics community. At experiments such as the Large Hadron Collider, anomaly detection is growing in interest for finding new physics beyond the Standard Model. This paper details the implementation of a novel Machine Learning architecture, called Flux+Mutability, which combines cutting-edge conditional generative models with clustering algorithms. In the ‘flux’ stage we learn the distribution of a reference class. The ‘mutability’ stage at inference addresses if data significantly deviates from the reference class. We demonstrate the validity of our approach and its connection to multiple problems spanning from one-class classification to anomaly detection. In particular, we apply our method to the isolation of neutral showers in an electromagnetic calorimeter and show its performance in detecting anomalous dijets events from standard QCD background. This approach limits assumptions on the reference sample and remains agnostic to the complementary class of objects of a given problem. We describe the possibility of dynamically generating a reference population and defining selection criteria via quantile cuts. Remarkably this flexible architecture can be deployed for a wide range of problems, and applications like multi-class classification or data quality control are left for further exploration.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

DeepAstroUDA: semi-supervised universal domain adaptation for cross-survey galaxy morphology classification and anomaly detection

Abstract Artificial intelligence methods show great promise in increasing the quality and speed of work with large astronomical datasets, but the high complexity of these methods leads to the extraction of dataset-specific, non-robust features. Therefore, such methods do not generalize well across multiple datasets. We present a universal domain adaptation method, DeepAstroUDA , as an approach to overcome this challenge. This algorithm performs semi-supervised domain adaptation (DA) and can be applied to datasets with different data distributions and class overlaps. Non-overlapping classes can be present in any of the two datasets (the labeled source domain, or the unlabeled target domain), and the method can even be used in the presence of unknown classes. We apply our method to three examples of galaxy morphology classification tasks of different complexities (three-class and ten-class problems), with anomaly detection: (1) datasets created after different numbers of observing years from a single survey (Legacy Survey of Space and Time mock data of one and ten years of observations); (2) data from different surveys (Sloan Digital Sky Survey (SDSS) and DECaLS); and (3) data from observing fields with different depths within one survey (wide field and Stripe 82 deep field of SDSS). For the first time, we demonstrate the successful use of DA between very discrepant observational datasets. DeepAstroUDA is capable of bridging the gap between two astronomical surveys, increasing classification accuracy in both domains (up to 40 % on the unlabeled data), and making model performance consistent across datasets. Furthermore, our method also performs well as an anomaly detection algorithm and successfully clusters unknown class samples even in the unlabeled target dataset.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2018

Domain-Adapted Convolutional Networks for Satellite Image Classification: A Large-Scale Interactive Learning Workflow

Satellite imagery often exhibits large spatial extent areas that encompass object classes with considerable variability. This often limits large-scale model generalization with machine learning algorithms. Notably, acquisition conditions, including dates, sensor position, lighting condition, and sensor types, often translate into class distribution shifts introducing complex nonlinear factors and hamper the potential impact of machine learning classifiers. Here, this article investigates the challenge of exploiting satellite images using convolutional neural networks (CNN) for settlement classification where the class distribution shifts are significant. We present a large-scale human settlement mapping workflow based-off multiple modules to adapt a pretrained CNN to address the negative impact of distribution shift on classification performance. To extend a locally trained classifier onto large spatial extents areas we introduce several submodules: First, a human-in-the-loop element for relabeling of misclassified target domain samples to generate representative examples for model adaptation; second, an efficient hashing module to minimize redundancy and noisy samples from the mass-selected examples; and third, a novel relevance ranking module to minimize the dominance of source example on the target domain. The workflow presents a novel and practical approach to achieve large-scale domain adaptation with binary classifiers that are based-off CNN features. Experimental evaluations are conducted on areas of interest that encompass various image characteristics, including multisensors, multitemporal, and multiangular conditions. Domain adaptation is assessed on source–target pairs through the transfer loss and transfer ratio metrics to illustrate the utility of the workflow.

47 OTHER INSTRUMENTATION↗
DOE OSTI2018

A complete electrical shock hazard classification system and its application

Current electrical safety standards evolved to address the hazards of 60-Hz power that are faced primarily by electricians, linemen, and others performing facility and utility work. As a result, this leaves a substantial gap in the management of electrical hazards in Research and Development (R&D) and specialized high voltage and high power equipment. We find substantial use of direct current (dc) electrical energy, and the use of capacitors, inductors, batteries, and radiofrequency (RF) power. The electrical hazards of these forms of electricity and their systems are different than for 50/60 Hz power. This paper proposes a method of classifying all of the electrical shock hazards found in all types of R&D and utilization equipment. Examples of the variation of these hazards from NFPA 70E include (a) high voltage can be harmless, if the available current is sufficiently low, (b) low voltage can be harmful if the available current/power is high, (c) high voltage capacitor hazards are unique and include severe reflex action, affects on the heart, and tissue damage, and (d) arc flash hazard analysis for dc and capacitor systems are not provided in existing standards. This work has led to a comprehensive electrical hazard classification system that is based on various research conducted over the past 100 years, on analysis of such systems in R&D, and on decades of experience. Lastly, the new comprehensive electrical shock hazard classification system uses a combination of voltage, shock current available, fault current available, power, energy, and waveform to classify all forms of electrical hazards.

42 ENGINEERING↗
DOE OSTI2023

Use of Convolutional Neural Network Image Classification and High-Speed Ion Probe Data Toward Real-Time Detonation Characterization in a Water-Cooled Rotating Detonation Engine

As rotating detonation engines (RDEs) progress in maturity, the importance of monitoring advancements toward development of active control becomes more critical. Experimental RDE data processing at time scales which satisfy real-time diagnostics will likely require the use of machine learning. This study aims to develop and deploy a novel real-time monitoring technique capable of determining detonation wave number, direction, frequency, and individual wave speeds throughout experimental RDE operational windows. To do so, the diagnostic integrates image classification by a convolutional neural network (CNN) and ionization current signal analysis. Wave mode identification through single-image CNN classification bypasses the need to evaluate sequential images and offers instantaneous identification of the wave mode present in the RDE annulus. Here, real-time processing speeds are achieved due to low data volumes required by the methodology, namely one short-exposure image and a short window of sensor data to generate each diagnostic output. The diagnostic acquires live data using a modified experimental setup alongside Pylon and PyDAQmx libraries within a python data acquisition environment. Lab-deployed diagnostic results are presented across varying wave modes, operating conditions, and data quality, currently executed at 3–4 Hz with a variety of iteration speed optimization options to be considered as future work. These speeds exceed that of conventional techniques and offer a proven structure for real-time RDE monitoring. The demonstrated ability to analyze detonation wave presence and behavior during RDE operation will certainly play a vital role in the development of RDE active control, necessary for RDE technology maturation toward industrial integration.

42 ENGINEERING↗
DOE OSTI2016

SU-D-207B-02: Early Grade Classification in Meningioma Patients Combining Radiomics and Semantics Data

Purpose: The clinical management of meningioma is guided by its grade and biologic behavior. Currently, diagnosis of tumor grade follows surgical resection and histopathologic review. Reliable techniques for pre-operative determination of tumor behavior are needed. We investigated the association between imaging features extracted from preoperative gadolinium-enhanced T1-weighted MRI and meningioma grade. Methods: We retrospectively examined the pre-operative MRI for 139 patients with de novo WHO grade I (63%) and grade II (37%) meningiomas. We investigated the predictive power of ten semantic radiologic features as determined by a neuroradiologist, fifteen radiomic features, and tumor location. Conventional (volume and diameter) imaging features were added for comparison. AUC was computed for continuous and χ{sup 2} for discrete variables. Classification was done using random forest. Performance was evaluated using cross validation (1000 iterations, 75% training and 25% validation). All p-values were adjusted for multiple testing. Results: Significant association was observed between meningioma grade and tumor location (p<0.001) and two semantic features including intra-tumoral heterogeneity (p<0.001) and overt hemorrhage (p=0.01). Conventional (AUC 0.61–0.67) and eleven radiomic (AUC 0.60–0.70) features were significant from random (p<0.05, Noether test). Median AUC values for classification of tumor grade were 0.57, 0.71, 0.72 and 0.77 respectively for conventional, radiomic, location, and semantic features after using random forest. By combining all imaging data (semantic, radiomic, and location), the median AUC was 0.81, which offers superior predicting power to that of conventional imaging descriptors for meningioma as well as radiomic features alone (p<0.05, permutation test). Conclusion: We demonstrate a strong association between radiologic features and meningioma grade. Pre-operative prediction of tumor behavior based on imaging features offers promise for guiding personalized medicine and improving patient management.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2017

Cloud Type Classification (cldtype) Value-Added Product

The Cloud Type (cldtype) value-added product (VAP) provides an automated cloud type classification based on macrophysical quantities derived from vertically pointing lidar and radar. Up to 10 layers of clouds are classified into seven cloud types based on predetermined and site-specific thresholds of cloud top, base and thickness. Examples of thresholds for selected U.S. Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) Climate Research Facility sites are provided in Tables 1 and 2. Inputs for the cldtype VAP include lidar and radar cloud boundaries obtained from the Active Remotely Sensed Cloud Location (ARSCL) and Surface Meteorological Systems (MET) data. Rain rates from MET are used to determine when radar signal attenuation precludes accurate cloud detection. Temporal resolution and vertical resolution for cldtype are 1 minute and 30 m respectively and match the resolution of ARSCL. The cldtype classification is an initial step for further categorization of clouds. It was developed for use by the Shallow Cumulus VAP to identify potential periods of interest to the LASSO model and is intended to find clouds of interest for a variety of users.

54 ENVIRONMENTAL SCIENCES↗