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 415 records · Page 23
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

A multi-scale convolutional neural network for autonomous anomaly detection and classification in a laser powder bed fusion additive manufacturing process

In-situ detection of processing defects is a critical challenge for Laser Powder Bed Fusion Additive Manufacturing. Many of these defects are related to interactions between the recoater blade, which spreads the powder, and the powder bed. Here this work leverages Deep Learning, specifically a Convolutional Neural Network (CNN), for autonomous detection and classification of many of these spreading anomalies. Importantly, the input layer of the CNN is modified to enable the algorithm to learn both the appearance of the powder bed anomalies as well as key contextual information at multiple size scales. These modifications to the CNN architecture are shown to improve the flexibility and overall classification accuracy of the algorithm while mitigating many human biases. A case study is used to demonstrate the utility of the presented methodology and the overall performance is shown to be superior to that of methodologies previously reported by the authors.

36 MATERIALS SCIENCE↗
DOE OSTI2011

Classification of quantum phases and topology of logical operators in an exactly solved model of quantum codes

Searches for possible new quantum phases and classifications of quantum phases have been central problems in physics. Yet, they are indeed challenging problems due to the computational difficulties in analyzing quantum many-body systems and the lack of a general framework for classifications. While frustration-free Hamiltonians, which appear as fixed point Hamiltonians of renormalization group transformations, may serve as representatives of quantum phases, it is still difficult to analyze and classify quantum phases of arbitrary frustration-free Hamiltonians exhaustively. Here, we address these problems by sharpening our considerations to a certain subclass of frustration-free Hamiltonians, called stabilizer Hamiltonians, which have been actively studied in quantum information science. We propose a model of frustration-free Hamiltonians which covers a large class of physically realistic stabilizer Hamiltonians, constrained to only three physical conditions; the locality of interaction terms, translation symmetries and scale symmetries, meaning that the number of ground states does not grow with the system size. We show that quantum phases arising in two-dimensional models can be classified exactly through certain quantum coding theoretical operators, called logical operators, by proving that two models with topologically distinct shapes of logical operators are always separated by quantum phase transitions.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2026

ClassNMSW- a real-time classification approach for non-recycled municipal solid waste using hyperspectral imaging

Real-time classification of non-recycled municipal solid waste (NMSW) is essential for efficient valorization. This study introduces ClassNMSW, a comprehensive framework for classifying 22 NMSW subclasses under industrial constraints by using hyperspectral imaging (HSI). A primary innovation of this work is the development of a variance-controlled spectral extraction algorithm. Unlike traditional methods that rely on simple averaging, this approach systematically investigates the extent of pixel extraction to minimize the loss of critical chemical information while maximizing data reduction thus ensuring high spectral fidelity with low computational cost. The approach developed in this work integrates automated, computer-vision-based background removal, eliminating the need for the manual thresholding common in current literature. To resolve ambiguities among chemically similar subclasses, a tiered classification and multi-camera fusion strategy (NIR17 and NIR22) is implemented. Results demonstrate that ClassNMSW achieves an object-wise weighted accuracy of 98.70% for single-sensor configurations and 100% under sensor fusion. A novel rolling-window strategy satisfies desired end-to-end latency of <2 s, satisfying the strict deterministic requirements of high-speed industrial sorting environments. The ClassNMSW framework provides a scalable foundation for advancing circularity and resource recovery in large-scale waste valorization operations.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2021

Multiresolution classification of turbulence features in image data through machine learning

During large-scale simulations, intermediate data products such as image databases have become popular due to their low relative storage cost and fast in-situ analysis. Serving as a form of data reduction, these image databases have become more acceptable to perform data analysis on. In this work, we present an image-space detection and classification system for extracting vortices at multiple scales through wavelet-based filtering. A custom image-space descriptor is used to encode a large variety of vortex-types and a machine learning system is trained for fast classification of vortex regions. By combining a radial-based histogram descriptor, a bag of visual words feature descriptor, and a support vector machine, our results show that we are able to detect and classify vortex features at various sizes at multiple scales. Once trained, our framework enables the fast extraction of vortices on new, unknown image datasets for flow analysis.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2011

Integrating Epidermal Growth Factor Receptor Assay With Clinical Parameters Improves Risk Classification for Relapse and Survival in Head-and-Neck Squamous Cell Carcinoma

Purpose: Epidermal growth factor receptor (EGFR) overexpression has been consistently found to be an independent predictor of local-regional relapse (LRR) after radiotherapy. We assessed the extent by which it can refine risk classification for overall survival (OS) and LRR in patients with head-and-neck squamous cell carcinoma (HNSCC). Methods and Materials: EGFR expression in locally advanced HNSCC was measured by immunohistochemistry in a series of patients randomized to receive accelerated or conventional radiation regimens in a Phase III trial. Subsequently, data of the two series were pooled (N = 533) for conducting a recursive partitioning analysis that incorporated clinical parameters (e.g., performance status, primary site, T and N categories) and four molecular markers (EGFR, p53, Ki-67, and microvessel density). Results: This study confirmed that patients with higher than median levels of tumor EGFR expression had a lower OS (relative risk [RR]: 1.90, p = 0.0010) and a higher LRR (RR: 1.91, p = 0.0163). Of the four markers analyzed, only EGFR was found to contribute to refining classification of patients into three risk classes with distinct OS and LRR outcomes. The addition of EGFR to three clinical parameters could identify patients having up to a fivefold difference in the risk of LRR. Conclusions: Adding pretreatment EGFR expression data to known robust clinical prognostic variables improved the estimation of the probability for OS and LRR after radiotherapy. Its use for stratifying or selecting patients with defined tumor feature and pattern of relapse for enrollment into clinical trials testing specific therapeutic strategy warrants further investigation.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2021

Classification and regression models of audio and vibration signals for machine state monitoring in precision machining systems

Here we present a data-driven method for monitoring machine status in manufacturing processes. Audio and vibration data from precision machining are used for inference in two operating scenarios: (a) variable machine health states (anomaly detection); and (b) settings of machine operation (state estimation). Audio and vibration signals are first processed through Fast Fourier Transform and Principal Component Analysis to extract transformed and informative features. These features are then used in the training of classification and regression models for machine state monitoring. Specifically, three classifiers (K-nearest neighbors, convolutional neural networks and support vector machines) and two regressors (support vector regression and neural network regression) were explored, in terms of their accuracy in machine state prediction. It is shown that the audio and vibration signals are sufficiently rich in information about the machine that 100% state classification accuracy could be accomplished. Data fusion was also explored, showing overall superior accuracy of data-driven regression models.

42 ENGINEERING↗
DOE OSTI2017

Automating cell detection and classification in human brain fluorescent microscopy images using dictionary learning and sparse coding

Background Immunofluorescence (IF) plays a major role in quantifying protein expression in situ and understanding cell function. It is widely applied in assessing disease mechanisms and in drug discovery research. Automation of IF analysis can transform studies using experimental cell models. However, IF analysis of postmortem human tissue relies mostly on manual interaction, often subjected to low-throughput and prone to error, leading to low inter and intra-observer reproducibility. Human postmortem brain samples challenges neuroscientists because of the high level of autofluorescence caused by accumulation of lipofuscin pigment during aging, hindering systematic analyses. We propose a method for automating cell counting and classification in IF microscopy of human postmortem brains. Our algorithm speeds up the quantification task while improving reproducibility. New method Dictionary learning and sparse coding allow for constructing improved cell representations using IF images. These models are input for detection and segmentation methods. Classification occurs by means of color distances between cells and a learned set. Results Our method successfully detected and classified cells in 49 human brain images. We evaluated our results regarding true positive, false positive, false negative, precision, recall, false positive rate and F1 score metrics. We also measured user-experience and time saved compared to manual countings. Comparison with existing methods We compared our results to four open-access IF-based cell-counting tools available in the literature. Lastly, our method showed improved accuracy for all data samples. Conclusion The proposed method satisfactorily detects and classifies cells from human postmortem brain IF images, with potential to be generalized for applications in other counting tasks.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2014

F{sup −}/OH{sup −} substitution in [H{sub 4}tren]{sup 4+} and [H{sub 3}tren]{sup 3+} hydroxyfluorotitanates(IV) and classification of tren cation configurations

Three [H{sub 3}tren]{sup 3+} or [H{sub 4}tren]{sup 4+} hydroxyfluorotitanates(IV) are solvothermally synthesized from TiO{sub 2}, tren amine, 40% HF aqueous solution and ethanol under microwave heating at 120 °C and 190 °C. [H{sub 4}tren]·(TiF{sub 4.6}(OH){sub 1.4}){sub 2}·2.7H{sub 2}O (I) and β-[H{sub 3}tren]·(TiF{sub 4.5}(OH){sub 1.5})·(F) (II) are described for the first time. The third compound, α-[H{sub 3}tren]·(TiF{sub 4.7}(OH){sub 1.3})·(F) (III), was previously reported as a pure fluorotitanate. The structure determinations are performed from single crystal (I) and powder (II) X-ray diffraction data. The F{sup −}/OH{sup −} substitution, expected from the presence of water in the reaction medium, is characterized by chemical analyses and {sup 19}F MAS solid state NMR experiments: all three structures are built up from Ti(F,OH){sub 6}{sup 2−} octahedra and “free” fluoride ions or water molecules. “Free” fluoride ions are not affected by F{sup −}/OH{sup −} substitution. The electroneutrality is ensured by triprotonated or tetraprotonated tren amines which adopt specific configurations. Additionally, based on the analysis of [H{sub 3}tren]{sup 3+} or [H{sub 4}tren]{sup 4+} hydroxo/oxo/fluorometalates, a classification of the configurations of tren cations is proposed. - Graphical abstract: The ratio of the relative intensities of the {sup 19}F NMR lines assigned to F atoms belonging to isolated TiF{sub 6−x}(OH){sub x} octahedra and to “free” fluoride ions shows that the F{sup −}/OH{sup −} substitution concerns only F atoms bonded to titanium. - Highlights: • Three tren templated hydroxyfluorotitanates(IV) have been solvothermally synthesized. • They are built up from Ti(F,OH){sub 6}{sup 2−} octahedra and “free” F{sup −} ions or H{sub 2}O molecules. • F{sup −}/OH{sup −} substitution does not affect “free” F{sup −} sites. • [H{sub 4}tren]{sup 4+} and [H{sub 3}tren]{sup 3+} cations adopt specific configurations. • A classification of the configurations of tren cations is proposed.

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

Classification of events from α -induced reactions in the MUSIC detector via statistical and ML methods

The Multi-Sampling Ionization Chamber (MUSIC) detector is typically used to measure nuclear reaction cross sections relevant for nuclear astrophysics, fusion studies, and other applications. From the MUSIC data produced in one experiment scientists carefully extract an order of 10 3 events of interest from about 10 9 total events, where each event can be represented by an 18-dimensional vector. However, the standard data classification process is based on expert driven, manually intensive data analysis techniques that require several months to identify patterns and classify the relevant events from the collected data. Here, to address this issue, we present a method for the classification of events originating from specific α-induced reactions by combining statistical and machine learning methods that require significantly less input from the domain scientist, relative to the standard technique. Here, we applied the new method to two experimental data sets and compared our results with those obtained using traditional methods. With few exceptions, the number of events classified by our method agrees within ±20% with the results obtained using traditional methods. With the present method, which is the first of its kind for the MUSIC data, we have established the foundation for the automated extraction of physical events of interest from experiments using the MUSIC detector.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2011

Metabolic profiling using HPLC allows classification of drugs according to their mechanisms of action in HL-1 cardiomyocytes

Along with hepatotoxicity, cardiotoxic side effects remain one of the major reasons for drug withdrawals and boxed warnings. Prediction methods for cardiotoxicity are insufficient. High content screening comprising of not only electrophysiological characterization but also cellular molecular alterations are expected to improve the cardiotoxicity prediction potential. Metabolomic approaches recently have become an important focus of research in pharmacological testing and prediction. In this study, the culture medium supernatants from HL-1 cardiomyocytes after exposure to drugs from different classes (analgesics, antimetabolites, anthracyclines, antihistamines, channel blockers) were analyzed to determine specific metabolic footprints in response to the tested drugs. Since most drugs influence energy metabolism in cardiac cells, the metabolite 'sub-profile' consisting of glucose, lactate, pyruvate and amino acids was considered. These metabolites were quantified using HPLC in samples after exposure of cells to test compounds of the respective drug groups. The studied drug concentrations were selected from concentration response curves for each drug. The metabolite profiles were randomly split into training/validation and test set; and then analysed using multivariate statistics (principal component analysis and discriminant analysis). Discriminant analysis resulted in clustering of drugs according to their modes of action. After cross validation and cross model validation, the underlying training data were able to predict 50%-80% of conditions to the correct classification group. We show that HPLC based characterisation of known cell culture medium components is sufficient to predict a drug's potential classification according to its mode of action.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2017

Potential Air Pollutant Emissions and Permitting Classifications for Two Biorefinery Process Designs in the United States

Advanced biofuel production facilities (biorefineries), such as those envisioned by the United States (U.S.) Renewable Fuel Standard and U.S. Department of Energy's research and development programs, often lack historical air pollutant emissions data, which can pose challenges for obtaining air emission permits that are required for construction and operation. To help fill this knowledge gap, we perform a thorough regulatory analysis and use engineering process designs to assess the applicability of federal air regulations and quantify air pollutant emissions for two feasibility-level biorefinery designs. We find that without additional emission-control technologies both biorefineries would likely be required to obtain major source permits under the Clean Air Act's New Source Review program. The permitting classification (so-called 'major' or 'minor') has implications for the time and effort required for permitting and therefore affects the cost of capital and the fuel selling price. Consequently, we explore additional technically feasible emission-control technologies and process modifications that have the potential to reduce emissions to achieve a minor source permitting classification. Finally, our analysis of air pollutant emissions and controls can assist biorefinery developers with the air permitting process and inform regulatory agencies about potential permitting pathways for novel biorefinery designs.

09 BIOMASS FUELS↗
DOE OSTI2022

Pose Classification Using Three-Dimensional Atomic Structure-Based Neural Networks Applied to Ion Channel–Ligand Docking

The identification of promising lead compounds showing pharmacological activities toward a biological target is essential in early stage drug discovery. With the recent increase in available small-molecule databases, virtual high-throughput screening using physics-based molecular docking has emerged as an essential tool in assisting fast and cost-efficient lead discovery and optimization. However, the best scored docking poses are often suboptimal, resulting in incorrect screening and chemical property calculation. We address the pose classification problem by leveraging data-driven machine learning approaches to identify correct docking poses from AutoDock Vina and Glide screens. To enable effective classification of docking poses, we present two convolutional neural network approaches: a three-dimensional convolutional neural network (3D-CNN) and an attention-based point cloud network (PCN) trained on the PDBbind refined set. We demonstrate the effectiveness of our proposed classifiers on multiple evaluation data sets including the standard PDBbind CASF-2016 benchmark data set and various compound libraries with structurally different protein targets including an ion channel data set extracted from Protein Data Bank (PDB) and an in-house KCa3.1 inhibitor data set. Our experiments show that excluding false positive docking poses using the proposed classifiers improves virtual high-throughput screening to identify novel molecules against each target protein compared to the initial screen based on the docking scores.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

The System for Classification of Low-Pressure Systems (SyCLoPS): An All-In-One Objective Framework for Large-Scale Data Sets

We propose the first unified objective framework (SyCLoPS) for detecting and classifying all types of low-pressure systems (LPSs) in a given data set. We use the state-of-the-art automated feature tracking software TempestExtremes (TE) to detect and track LPS features globally in ERA5 and compute 16 parameters from commonly found atmospheric variables for classification. A Python classifier is implemented to classify all LPSs at once. The framework assigns 16 different labels (classes) to each LPS data point and designates four different types of high-impact LPS tracks, including tracks of tropical cyclone (TC), monsoonal system, subtropical storm and polar low. The classification process involves disentangling high-altitude and drier LPSs, differentiating tropical and non-tropical LPSs using novel criteria, and optimizing for the detection of the four types of high-impact LPS. A comparison of our labels with those in the International Best Track Archive for Climate Stewardship (IBTrACS) revealed an overall accuracy of 95% in distinguishing between tropical systems, extratropical cyclones, and disturbances. SyCLoPS produces a better TC detection skill compared to the previous algorithms, highlighted by an approximately 6% reduction in the false alarm rate compared to the previous TE algorithm. The vertical cross section composite of the four types of high-impact LPS we detect each shows distinct structural characteristics. Finally, we demonstrate that SyCLoPS is valuable for investigating various aspects of LPSs in climate data, such as the evolution of a single LPS track, patterns of LPS frequencies, and precipitation or wind influence associated with a particular LPS class.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Automated classification of big X-ray diffraction data using deep learning models

Abstract In current in situ X-ray diffraction (XRD) techniques, data generation surpasses human analytical capabilities, potentially leading to the loss of insights. Automated techniques require human intervention, and lack the performance and adaptability required for material exploration. Given the critical need for high-throughput automated XRD pattern analysis, we present a generalized deep learning model to classify a diverse set of materials’ crystal systems and space groups. In our approach, we generate training data with a holistic representation of patterns that emerge from varying experimental conditions and crystal properties. We also employ an expedited learning technique to refine our model’s expertise to experimental conditions. In addition, we optimize model architecture to elicit classification based on Bragg’s Law and use evaluation data to interpret our model’s decision-making. We evaluate our models using experimental data, materials unseen in training, and altered cubic crystals, where we observe state-of-the-art performance and even greater advances in space group classification.

Chemistry↗
DOE OSTI2022

An image classification deep-learning algorithm for shrapnel detection from ultrasound images

Ultrasound imaging is essential for non-invasively diagnosing injuries where advanced diagnostics may not be possible. However, image interpretation remains a challenge as proper expertise may not be available. In response, artificial intelligence algorithms are being investigated to automate image analysis and diagnosis. Here, we highlight an image classification convolutional neural network for detecting shrapnel in ultrasound images. As an initial application, different shrapnel types and sizes were embedded first in a tissue mimicking phantom and then in swine thigh tissue. The algorithm architecture was optimized stepwise by minimizing validation loss and maximizing F1 score. The final algorithm design trained on tissue phantom image sets had an F1 score of 0.95 and an area under the ROC curve of 0.95. It maintained higher than a 90% accuracy for each of 8 shrapnel types. When trained only on swine image sets, the optimized algorithm format had even higher metrics: F1 and area under the ROC curve of 0.99. Overall, the algorithm developed resulted in strong classification accuracy for both the tissue phantom and animal tissue. This framework can be applied to other trauma relevant imaging applications such as internal bleeding to further simplify trauma medicine when resources and image interpretation are scarce.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2019

Exploring End-to-end Deep Learning Applications for Event Classification at CMS

An essential part of new physics searches at the Large Hadron Collider (LHC) at CERN involves event classification, or distinguishing potential signal events from those coming from background processes. Current machine learning techniques accomplish this using traditional hand-engineered features like particle 4-momenta, motivated by our understanding of particle decay phenomenology. While such techniques have proven useful for simple decays, they are highly dependent on our ability to model all aspects of the phenomenology and detector response. Meanwhile, powerful deep learning algorithms are capable of not only training on high-level features, but of performing feature extraction. In computer vision, convolutional neural networks have become the state-of-the-art for many applications. Motivated by their success, we apply deep learning algorithms to low-level detector data from the 2012 CMS Simulated Open Data to directly learn useful features, in what we call, end-to-end event classification. We demonstrate the power of this approach in the context of a physics search and offer solutions to some of the inherent challenges, such as image construction, image sparsity, combining multiple sub-detectors, and de-correlating the classifier from the search observable, among others.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2019

Scalable Bayesian Nonparametric Clustering and Classification

We develop a scalable multi-step Monte Carlo algorithm for inference under a large class of nonparametric Bayesian models for clustering and classification. Each step is “embarrassingly parallel” and can be implemented using the same Markov chain Monte Carlo sampler. The simplicity and generality of our approach makes inference for a wide range of Bayesian nonparametric mixture models applicable to large datasets. Specifically, we apply the approach to inference under a product partition model with regression on covariates. We show results for inference with two motivating data sets: a large set of electronic health records (EHR) and a bank telemarketing dataset. We find interesting clusters and competitive classification performance relative to other widely used competing classifiers. Supplementary materials for this article are available online.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2012

SPECTRAL CLASSIFICATION OF THE BRIGHTEST OBJECTS IN THE GALACTIC STAR-FORMING REGION W40

We present high signal-to-noise, moderate resolution (R Almost-Equal-To 2000) near-infrared spectra, as well as 10 {mu}m imaging, for the brightest members of the central stellar cluster in the W40 H II region, obtained using the SpeX and MIRSI instruments at NASA's Infrared Telescope Facility. Using these observations combined with archival Spitzer Space Telescope data, we have determined the spectral classifications, extinction, distances, and spectral energy distributions (SEDs) for the brightest members of the cluster. Of the eight objects observed, we identify four main-sequence (MS) OB stars (one late-O, three early-B), two Herbig Ae/Be stars, and two low-mass young stellar objects (Class II). Strong He I absorption at 1.083 {mu}m in the MS star spectra strongly suggests that at least some of these sources are in fact close binaries. Two out of the four MS stars also show significant infrared excesses typical of circumstellar disks. Extinctions and distances were determined for each MS star by fitting model stellar atmospheres to the SEDs. We estimate a distance to the cluster of between 455 and 535 pc, which agrees well with earlier (but far less precise) distance estimates. We conclude that the late-O star we identify is the dominant source of Lyman continuum luminosity needed to power the W40 H II region and is the likely source of the stellar wind that has blown a large ( Almost-Equal-To 4 pc) pinched-waist bubble observed in wide-field mid-IR images. We also suggest that 3.6 cm radio emission observed from some of the sources in the cluster is likely not due to emission from ultracompact H II regions, as suggested in other work, due to size constraints based on our derived distance to the cluster. Finally, we also present a discussion of the curious source IRS 3A, which has a very strong mid-IR excess (despite its B3 MS classification) and appears to be embedded in a dusty envelope roughly 2700 AU in size.

79 ASTRONOMY AND ASTROPHYSICS↗