Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “label quality”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

AI Data Quality Monitoring with Hydra

Hydra is an extensible framework for training and managing AI for near real time monitoring that aims to replace the tedious and repetitive data quality monitoring activities the shift crew and online monitoring coordinator typically perform. It continuously scans incoming data in the form of monitoring plots for signs of problems, flagging them for human review. A web app was developed such that experts can efficiently label images for training. Labels are stored in a database for use in training and model validation. Backed up by a comprehensive database, it utilizes an additional web based front-end for viewing the current monitoring status from anywhere in the world. The system has been in production use for the GlueX experiment at Jefferson Lab for more than 2 years with new features still under active development.

Britton, Thomas↗
NASA NTRS2005

Fluorescent Approaches to High Throughput Crystallography

X-ray crystallography remains the primary method for determining the structure of macromolecules. The first requirement is to have crystals, and obtaining them is often the rate-limiting step. The numbers of crystallization trials that are set up for any one protein for structural genomics, and the rate at which they are being set up, now overwhelm the ability for strictly human analysis of the results. Automated analysis methods are now being implemented with varying degrees of success, but these typically cannot reliably extract intermediate results. By covalently modifying a subpopulation, less than or = 1 %, of a macromolecule solution with a fluorescent probe, the labeled material will add to a growing crystal as a microheterogeneous growth unit. Labeling procedures can be readily incorporated into the final stages of purification. The covalently attached probe will concentrate in the crystal relative to the solution, and under fluorescent illumination the crystals show up as bright objects against a dark background. As crystalline packing is more dense than amorphous precipitate, the fluorescence intensity can be used as a guide in distinguishing different types of precipitated phases, even in the absence of obvious crystalline features, widening the available potential lead conditions in the absence of clear "hits." Non-protein structures, such as salt crystals, will not incorporate the probe and will not show up under fluorescent illumination. Also, brightly fluorescent crystals are readily found against less fluorescent precipitated phases, which under white light illumination may serve to obscure the crystals. Automated image analysis to find crystals should be greatly facilitated, without having to first define crystallization drop boundaries and by having the protein or protein structures all that show up. The trace fluorescently labeled crystals will also emit with sufficient intensity to aid in the automation of crystal alignment using relatively low cost optics, further increasing throughput at synchrotrons. Preliminary experiments show that the presence of the fluorescent probe does not affect the nucleation process or the quality of the X-ray data obtained.

Pusey, Marc L.↗
DOE OSTI2025

Extracting Material Property Measurements from Scientific Literature with Limited Annotations

Extracting material property data from scientific text is pivotal for advancing data-driven research in chemistry and materials science; however, the extensive annotation effort required to produce training data for named entity recognition (NER) models for this task often makes it a barrier to extracting specialized data sets. Here, in this work, we present a comparative study of the conventional, supervised NER methodology to alternative few-shot learning architectures and large language model (LLM)-based approaches that mitigate the need to label large training data sets. We find that the best-performing LLM (GPT-4o) not only excels in directly extracting relevant material properties based on limited examples but also enhances supervised learning through data augmentation. We supplement our findings with error and data quality assessments to provide a nuanced understanding of factors that impact property measurement extraction.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Automated instant labeling chemistry workflow for real-time monitoring of monoclonal antibody N -glycosylation

With the transition toward continuous bioprocessing, process analytical technology (PAT) is becoming necessary for rapid and reliable in-process monitoring during biotherapeutics manufacturing. Bioprocess 4.0 is looking to build end-to-end bioprocesses that include PAT-enabled real-time process control. This is especially important for drug product quality attributes that can change during bioprocessing, such as protein N-glycosylation, a critical quality attribute for most monoclonal antibody (mAb) therapeutics. Glycosylation of mAbs is known to influence their efficacy as therapeutics and is regulated for a majority of mAb products on the market today. Currently, there is no method to truly measure N-glycosylation using on-line PAT, hence making it impractical to design upstream process control strategies. We recently described the N-GLYcanyzer workflow: an integrated PAT unit that measures mAb N-glycosylation within 3 hours of automated sampling from a bioreactor. Here, we integrated Agilent's Instant Procainamide (InstantPC) based chemistry workflow into the N-GLYcanyzer PAT unit to allow for nearly 10× faster near real-time analysis of mAb glycoforms. Furthermore, our methodology is explained in detail to allow for replication of the PAT workflow as well as present a case study demonstrating the use of this PAT to autonomously monitor a mammalian cell perfusion process at the bench scale to gain increased knowledge of mAb glycosylation dynamics during continuous biologics manufacturing using Chinese hamster ovary (CHO) cells.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Identifying Suspect Instrument Intervals Using Midnight Noise Time Histories

With an intense work ethic, and high levels of devotion to their craft, seismologists continue to battle the elements and wrestle with complex logistics in their efforts to field instrumentation over the entire globe. We are fortunate to see data volumes accelerating in size, and quality continuing to improve; for example, universal timing issues can now be considered rare. However, instrument response issues are still common, and can hinder research that seeks to understand amplitudes of seismic wavefields. We are interested in using the accumulations of seismic data to develop models that will predict high frequency (0.2-20 Hz, and higher) signal amplitudes for explosion monitoring purposes over broad areas, which requires large data sets and extensive quality control. To identify response and station health issues, we have collected noise time histories for global seismic data, focusing on measurements near (but not restricted to) midnight to eliminate diurnal variations, and have manually determined time intervals that appear inconsistent with background behavior. We assign descriptive labels, but do not attempt to diagnose causes. We use these intervals to discard data. To date, we have examined 39,260 channels from 11,105 stations, heavily weighted toward IRIS holdings, dates through 2017 (depending on station, roughly the date we started our manual review), bands between 1 and 8 Hz, finding 24,733 anomalous time intervals. The great majority (90%) of these intervals appear to be shifts of constant offset, often bounded by times of known instrument changes, likely the result of poor documentation of response parameters at one of many stages between the field and the plotter. We hope these results can be of use to our colleagues, and would encourage community efforts to diagnose anomalous behavior, and fix poor responses. We also hope these results will support automation efforts, including application of supervised learning techniques.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Characterization of Gramicidin A in Triblock and Diblock Polymersomes and Hybrid Vesicles via Continuous Wave Electron Paramagnetic Resonance Spectroscopy

Studying membrane proteins in a native environment is crucial to understanding their structural and/or functional studies. Often, widely accepted mimetic systems have limitations that prevent the study of some membrane proteins. Micelles, bicelles, and liposomes are common biomimetic systems but have problems with membrane compatibility, limited lipid composition, and heterogeneity. To overcome these limitations, polymersomes and hybrid vesicles have become popular alternatives. Polymersomes form from amphiphilic triblock or diblock copolymers and are considered more robust than liposomes. Hybrid vesicles are a combination of lipids and block copolymers that form vesicles composed of a mixture of the two. These hybrid vesicles are appealing because they have the native lipid environment of bilayers but also the stability and customizability of polymersomes. Gramicidin A was incorporated into these polymersomes and characterized using continuous wave electron paramagnetic resonance (CW-EPR) and transmission electron microscopy (TEM). EPR spectroscopy is a powerful biophysical technique used to study the structure and dynamic properties of membrane proteins in their native environment. Spectroscopic studies of gramicidin A have been limited to liposomes; in this study, the membrane peptide is studied in both polymersomes and hybrid vesicles using CW-EPR spectroscopy. Lineshape analysis of spin-labeled gramicidin A revealed linewidth broadening, suggesting that the thicker polymersome membranes restrict the motion of the spin label more when compared to liposome membranes. Statement of Significance: Understanding membrane proteins’ structures and functions is critical in the study of many diseases. In order to study them in a native environment, membrane mimetics must be developed that can be suitable for obtaining superior biophysical data quality to characterize structural dynamics while maintaining their native functions and structures. Many currently widely accepted methods have limitations, such as a loss of native structure and function, heterogeneous vesicle formation, restricted lipid types for the vesicle formation for many proteins, and experimental artifacts, which leaves rooms for the development of new biomembrane mimetics. The triblock and diblock polymersomes and hybrid versicles utilized in this study may overcome these limitations and provide the stability and customizability of polymersomes, keeping the biocompatibility and functionality of liposomes for EPR studies of membrane proteins.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Improving radiograph analysis throughput through transfer learning and object detection

SIGN Fracture Care International partners with surgeons in low-resource hospitals worldwide to provide access to effective orthopedic care by donating educational materials and innovatively designed surgical implants. Over two decades, SIGN’s Online Surgical Database (SOSD) has grown to contain over 500,000 medical images, with radiographs holding the majority share. One challenge in working with hospitals worldwide is that both the radiographs uploaded to the SOSD and the data entry accompanying the uploads vary in quality. To improve the accuracy of data in the SOSD, we trained a model to detect surgical implants in radiographs. We first developed a tool to automatically detect radiographs, then trained an object detection model to determine the number and placement of surgical implants visible in the radiograph. Active learning was used to generate a training set containing 2,510 radiographs with screws, nails, and plates labeled by bounding boxes. Training a model to simultaneously recognize all three classes of implants gave a low average precision (AP) for the plate class, likely due to the low number of plate instances in our training set and the large variety of surgical plates used by SIGN-partnered surgeons. Applying standard image augmentation techniques to increase the plate count in our training set did not appreciably increase the AP of plate detection. To improve plate detection, we redrew the bounding boxes to account for correlations between the screw and plate classes. Training one model to detect nails and screws and a separate model to detect plates increased the AP of plate detection by 78.8 percentage points. The AP of each class was 80.7% for screws, 93.6% for nails, and 92.6% for plates; meanwhile, the sensitivity was 92% for screws, 86% for nails, and 81% for plates. We show that object detection methods can be used to detect surgical implants in radiographs of varying quality; however, the detection ability is dependent on the type of implant, and some implants, in our case plates, must be treated differently than others. Such tools can improve the throughput of radiograph analysis, assisting physicians and surgeons with the treatment of bone fractures.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Artificial neural network approach for multiphase segmentation of battery electrode nano-CT images

The segmentation of tomographic images of the battery electrode is a crucial processing step, which will have an additional impact on the results of material characterization and electrochemical simulation. However, manually labeling X-ray CT images (XCT) is time-consuming, and these XCT images are generally difficult to segment with histographical methods. We propose a deep learning approach with an asymmetrical depth encode-decoder convolutional neural network (CNN) for real-world battery material datasets. This network achieves high accuracy while requiring small amounts of labeled data and predicts a volume of billions voxel within few minutes. While applying supervised machine learning for segmenting real-world data, the ground truth is often absent. The results of segmentation are usually qualitatively justified by visual judgement. We try to unravel this fuzzy definition of segmentation quality by identifying the uncertainty due to the human bias diluted in the training data. Further CNN trainings using synthetic data show quantitative impact of such uncertainty on the determination of material’s properties. Nano-XCT datasets of various battery materials have been successfully segmented by training this neural network from scratch. We will also show that applying the transfer learning, which consists of reusing a well-trained network, can improve the accuracy of a similar dataset.

25 ENERGY STORAGE↗
DOE OSTI2023

Using deep transfer learning and satellite imagery to estimate urban air quality in data-poor regions

Urban air pollution is a critical public health challenge in low-and-middle-income countries (LMICs). At the same time, LMICs tend to be data-poor, lacking adequate infrastructure to monitor air quality (AQ). As LMICs undergo rapid urbanization, the socio-economic burden of poor AQ will be immense. Here we present a globally scalable two-step deep learning (DL) based approach for AQ estimation in LMIC cities that mitigates the need for extensive AQ infrastructure on the ground. We train a DL model that can map satellite imagery to AQ in high-income countries (HICs) with sufficient ground data, and then adapt the model to learn meaningful AQ estimates in LMIC cities using transfer learning. The trained model can explain up to 54% of the variation in the AQ distribution of the target LMIC city without the need for target labels. The approach is demonstrated for Accra in Ghana, Africa, with AQ patterns learned and adapted from two HIC cities, specifically Los Angeles and New York.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRSDate not supplied

Revolutionizing Earth Science with Generalized AI Models

Foundation Models (FM) are generalized Artificial Intelligence (AI) models that are designed to replace a task or an application-specific model and can be used for many downstream applications. These FM can be built on any sequence data and are trained utilizing self-supervised approaches. The obstacle of creating a sizable labeled dataset for training is removed by using self-supervised learning. Most FM employ transformer design that takes advantage of the idea of self-attention, allowing the network to represent the impact of distant data points on one another in space and time. The FM models show emergent qualities that are induced from the data. FM can become a valuable tool for Earth science researchers. Due to the size of these models, downstream applications built fine-tuning these FM perform better and exhibit greater accuracy than models created from scratch. FM significantly lowers the entry barrier in terms of both the time and effort required to develop various downstream applications. For some scientific datasets, such as optical remote sensing data, FM can speed up processes like classification, object detection and prediction. By eliminating the training data bottleneck and maximizing the usage of science data, FM can make it simpler to integrate AI into scientific research. Initial results for three different FMs will be presented.

Rahul Ramachandran↗
DOE OSTI2022

Direction-optimizing Label Propagation Framework for Structure Detection in Graphs: Design, Implementation, and Experimental Analysis

Label Propagation is not only a well-known machine learning algorithm for classification but also an effective method for discovering communities and connected components in networks. We propose a new Direction-optimizing Label Propagation Algorithm (DOLPA) framework that enhances the performance of the standard Label Propagation Algorithm (LPA), increases its scalability, and extends its versatility and application scope. As a central feature, the DOLPA framework relies on the use of frontiers and alternates between label push and label pull operations to attain high performance. It is formulated in such a way that the same basic algorithm can be used for finding communities or connected components in graphs by only changing the objective function used. Additionally, DOLPA has parameters for tuning the processing order of vertices in a graph to reduce the number of edges visited and improve the quality of solution obtained. We present the design and implementation of the enhanced algorithm as well as our shared-memory parallelization of it using OpenMP. We also present an extensive experimental evaluation of our implementations using the LFR benchmark and real-world networks drawn from various domains. Compared with an implementation of LPA for community detection available in a widely used network analysis software, we achieve at most five times the F-Score while maintaining similar runtime for graphs with overlapping communities. We also compare DOLPA against an implementation of the Louvain method for community detection using the same LFR-graphs and show that DOLPA achieves about three times the F-Score at just 10% of the runtime. For connected component decomposition, our algorithm achieves orders of magnitude speedups over the basic LP-based algorithm on large-diameter graphs, up to 13.2× speedup over the Shiloach-Vishkin algorithm, and up to 1.6× speedup over Afforest on an Intel Xeon processor using 40 threads.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Power Prediction of Airborne Wind Energy Systems Using Multivariate Machine Learning

Kites can be used to harvest wind energy at higher altitudes while using only a fraction of the material required for conventional wind turbines. In this work, we present the kite system of Kyushu University and demonstrate how experimental data can be used to train machine learning regression models. The system is designed for 7 kW traction power and comprises an inflatable wing with suspended kite control unit that is either tethered to a fixed ground anchor or to a towing vehicle to produce a controlled relative flow environment. A measurement unit was attached to the kite for data acquisition. To predict the generated tether force, we collected input–output samples from a set of well-designed experimental runs to act as our labeled training data in a supervised machine learning setting. We then identified a set of key input parameters which were found to be consistent with our sensitivity analysis using Pearson input–output correlation metrics. Finally, we designed and tested the accuracy of a neural network, among other multivariate regression models. The quality metrics of our models show great promise in accurately predicting the tether force for new input/feature combinations and potentially guide new designs for optimal power generation.

17 WIND ENERGY↗
NASA NTRS2011

Development of a Novel Self-Enclosed Sample Preparation Device for DNA/RNA Isolation in Space

Modern biology techniques present potentials for a wide range of molecular, cellular, and biochemistry applications in space, including detection of infectious pathogens and environmental contaminations, monitoring of drug-resistant microbial and dangerous mutations, identification of new phenotypes of microbial and new life species. However, one of the major technological blockades in enabling these technologies in space is a lack of devices for sample preparation in the space environment. To overcome such an obstacle, we constructed a prototype of a DNA/RNA isolation device based on our novel designs documented in the NASA New Technology Reporting System (MSC-24811-1/3-1). This device is self-enclosed and pipette free, purposely designed for use in the absence of gravity. Our design can also be modified easily for preparing samples in space for other applications, such as flowcytometry, immunostaining, cell separation, sample purification and separation according to its size and charges, sample chemical labeling, and sample purification. The prototype of our DNA/RNA isolation device was tested for efficiencies of DNA and RNA isolation from various cell types for PCR analysis. The purity and integrity of purified DNA and RNA were determined as well. Results showed that our developed DNA/RNA isolation device offers similar efficiency and quality in comparison to the samples prepared using the standard protocol in the laboratory.

Zhang, Ye↗
DOE OSTI2021

TMTpro Complementary Ion Quantification Increases Plexing and Sensitivity for Accurate Multiplexed Proteomics at the MS2 Level

Multiplexed proteomics is a powerful tool to assay cell states in health and disease, but accurate quantification of relative protein changes is impaired by interference from co-isolated peptides. Most widely, this issue is alleviated by MS3-based quantification, reducing sensitivity and requiring specialized instrumentation. An alternative approach is quantification by complementary ions, which allows accurate and precise multiplexed quantification at the MS2 level and is compatible with the most widely distributed instruments. However, complementary ions of the popular TMT tag form inefficiently and plexing is limited to five channels. In this work, we evaluate and optimize complementary ion quantification for the recently released TMTPro tag, which increases plexing capacity to 8 channels (TMTProC). We find that the beneficial fragmentation properties increase quantification signal five-fold compared to TMT. This increased sensitivity results in ~50% more proteins quantified compared to TMTPro-MS3 and even slightly outperforms TMTPro-MS2. Furthermore, TMTProC quantification is more accurate than TMTPro-MS2 and even superior to TMTPro-MS3. To demonstrate the power of TMTProC, we analyzed a human and yeast interference sample and were able to quantify 13,290 proteins in 24 fractions. Thus, TMTProC advances multiplexed proteomics data quality and widens access to accurate multiplexed proteomics beyond laboratories with MS3-capable instrumentation.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Evaluation of Differential Peptide Loading on Tandem Mass Tag-Based Proteomic and Phosphoproteomic Data Quality

Global and phosphoproteome profiling has demonstrated great utility for the analysis of clinical specimens. One major barrier to the broad clinical application of proteomic profiling is the large amount of biological material required, particularly for phosphoproteomics—currently on the order of 25 mg wet tissue weight, depending on tissue type. For hematopoietic cancers such as acute myeloid leukemia (AML), the sample requirement is in excess of 10 million (1E7) peripheral blood mononuclear cells (PBMCs). Throughout the course of a prospective study, this requirement will certainly exceed what is obtainable from many of the individual patients/timepoints. For this reason, we were interested in examining the impact of differential peptide loading across multiplex channels on proteomic data quality. Methods: To achieve this, we tested a range of channel loading amounts (20, 40, 100, 200, and 400 µg of tryptic peptides, or approximately the material obtainable from 5E5, 1E6, 2.5E6, 5E6, and 1E7 AML patient cells) to assess proteome coverage, quantification reproducibility and accuracy in experiments utilizing isobaric tandem mass tag (TMT) labeling. As expected, we found that fewer missing values are observed in TMT channels with higher peptide loading amounts compared to those with lower loading. Moreover, channels with lower loading amounts have greater quantitative variability than channels with higher loading amounts. Statistical analysis of the differences in means among the five loading groups showed that the 20 µg loading group was significantly different from the 400 µg loading group. However, no significant differences were detected among the 40, 100, 200 and 400 µg loading groups. Conclusions: These assessment data demonstrate the practical limits of loading differential quantities of peptides across channels in TMT multiplexes, and provide a basis for designing the optimal clinical proteomics study when specimen quantities are limited.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Hydra: Computer Vision for Online Data Quality Monitoring

Hydra is a system utilizing computer vision for near real-time data quality monitoring. Currently operational across all of Jefferson Lab’s experimental halls, it reduces the workload of shift takers by autonomously monitoring diagnostic plots during experiments. Hydra uses "off-the-shelf" supervised learning technologies and is supported by a comprehensive MySQL database. To simplify access, web apps have been developed to facilitate both labeling and monitoring of Hydra’s inferences. Hydra can connect with the alarm system and incorporates complete historical tracking, enabling it to identify issues that shift takers could miss. When issues are detected, a natural first question is: "Why does Hydra think there is a problem?" To answer, Hydra employs Gradient-weighted Class Activation Maps (GradCAM) to identify regions of the image that are important for the specific classification. This interpretive layer enhances transparency and trustworthiness, which is essential for integration with experiment workflows and operation. The Hydra system, results, and sociological considerations for deployment will be discussed.

Jeske, Torri↗
DOE OSTI2026

Two-Stage Wildlife Event Classification for Edge Deployment

Camera-based wildlife monitoring is often overwhelmed by non-target triggers and slowed by manual review or cloud-dependent inference, which can prevent timely intervention for high stakes human–wildlife conflicts. Our key contribution is a deployable, fully offline edge vision sensor that achieves near-real-time, highly accurate wildlife event classification by combining detector-based empty-image suppression with a lightweight classifier trained with a staged transfer-learning curriculum. Specifically, Stage 1 uses a pretrained You Only Look Once (YOLO)-family detector for permissive animal localization and empty-trigger suppression, and Stage 2 uses a lightweight EfficientNet-based binary classifier to confirm puma on detector crops and gate downstream actions. Our design is robust to low-quality nighttime monochrome imagery (motion blur, low contrast, illumination artifacts, and partial-body captures) and operates using commercially available components in connectivity-limited settings. In field deployments running since May 2025, end-to-end latency from camera trigger to action command is approximately 4 s. Ablation studies using a dataset of labeled wildlife images (pumas, not pumas) show that the two-stage approach substantially reduces false alarms in identifying pumas relative to a full-image classifier while maintaining high recall. On the held-out test set (N = 1434 events), the proposed two-stage cascade achieves precision 0.983, recall 0.975, F1 0.979, accuracy 0.986, and balanced accuracy 0.983, with only 8 false positives and 12 false negatives. The system can be easily adapted for other species, as demonstrated by rapid retraining of the second stage to classify ringtails. Downstream responses (e.g., notifications and optional audio/light outputs) provide flexible actuation capabilities that can be configured to support intervention.

58 GEOSCIENCES↗