Search NASA⌕ Search

SEARCH · Search NASA

Results for “LABELLING”

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 829 records · Page 46

A pre-training and self-training approach for biomedical named entity recognition

Named entity recognition (NER) is a key component of many scientific literature mining tasks, such as information retrieval, information extraction, and question answering; however, many modern approaches require large amounts of labeled training data in order to be effective. This severely limits the effectiveness of NER models in applications where expert annotations are difficult and expensive to obtain. In this work, we explore the effectiveness of transfer learning and semi-supervised self-training to improve the performance of NER models in biomedical settings with very limited labeled data (250-2000 labeled samples). We first pre-train a BiLSTM-CRF and a BERT model on a very large general biomedical NER corpus such as MedMentions or Semantic Medline, and then we fine-tune the model on a more specific target NER task that has very limited training data; finally, we apply semi-supervised self-training using unlabeled data to further boost model performance. We show that in NER tasks that focus on common biomedical entity types such as those in the Unified Medical Language System (UMLS), combining transfer learning with self-training enables a NER model such as a BiLSTM-CRF or BERT to obtain similar performance with the same model trained on 3x-8x the amount of labeled data. We further show that our approach can also boost performance in a low-resource application where entities types are more rare and not specifically covered in UMLS.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Automatic Waveform Quality Control for Surface Waves Using Machine Learning

Surface-wave seismograms are widely used by researchers to study Earth’s interior and earthquakes. To extract information reliably and robustly from a suite of surface waveforms, the signals require quality control screening to reduce artifacts from signal complexity and noise. This process has usually been completed by human experts labeling each waveform visually, which is time consuming and tedious for large data sets. We explore automated approaches to improve the efficiency of waveform quality control processing by investigating logistic regression, support vector machines, K-nearest neighbors, random forests (RF), and artificial neural networks (ANN) algorithms. To speed up signal quality assessment, we trained these five machine learning (ML) methods using nearly 400,000 human-labeled waveforms. The ANN and RF models outperformed other algorithms and achieved a test accuracy of 92%. We evaluated these two best-performing models using seismic events from geographic regions not used for training. The results show that the two trained models agree with labels from human analysts but required only 0.4% of the time. Although the original (human) quality assignments assessed general waveform signal-to-noise, the ANN or RF labels can help facilitate detailed waveform analysis. Our investigations demonstrate the capability of the automated processing using these two ML models to reduce outliers in surface-wave-related measurements without human quality control screening.

58 GEOSCIENCES↗

Laboratory Experiments to Evaluate Matrix Diffusion of Dissolved Organic Carbon Carbon-14 in Southern Nevada Fractured-rock Aquifers

Dissolved inorganic carbon (DIC) carbon-14 ( 14 C) is used to estimate groundwater ages by comparing the DIC 14 C content in groundwater in the recharge area to the DIC 14 C content in the downgradient sampling point. However, because of chemical reactions and physical processes between groundwater and aquifer rocks, the amount of DIC 14 C in groundwater can change and result in 14 C loss that is not because of radioactive decay. This loss of DIC 14 C results in groundwater ages that are older than the actual groundwater ages. Alternatively, dissolved organic carbon (DOC) 14 C in groundwater does not react chemically with aquifer rocks, so DOC 14 C ages are generally younger than DIC 14 C ages. In addition to chemical reactions, 14 C ages may also be altered by the physical process of matrix diffusion. The net effect of a continuous loss of 14 C to the aquifer matrix by matrix diffusion and then radioactive decay is that groundwater appears to be older than it actually is. Laboratory experiments were conducted to measure matrix diffusion coefficients for DOC 14 C in volcanic and carbonate aquifer rocks from southern Nevada. Experiments were conducted using bromide (Br-) as a conservative tracer and 14 C-labeled trimesic acid (TMA) as a surrogate for groundwater DOC. Outcrop samples from six volcanic aquifers and five carbonate aquifers in southern Nevada were used. The average DOC 14 C matrix diffusion coefficient for volcanic rocks was 2.9 x 10 -7 cm 2 /s, whereas the average for carbonate rocks was approximately the same at 1.7 x 10 -7 cm 2 /s. The average Br- matrix diffusion coefficient for volcanic rocks was 10.4 x 10 -7 cm 2 /s, whereas the average for carbonate rocks was less at 6.5 x 10 -7 cm 2 /s. Carbonate rocks exhibited greater variability in DOC 14 C and Br- matrix diffusion coefficients than volcanic rocks. These results confirmed, at the laboratory scale, that the diffusion of DOC 14 C into southern Nevada volcanic and carbonate aquifers is slower than DIC 14 C. Because of the apparent sorption of 14 C-labeled TMA in the experiments, matrix diffusion coefficients are likely even lower. The reasons for the higher than expected Br-/ 14 C-labeled TMA are unknown. Because the molecular size of TMA is on the low end of the range in molecular size for typical humic substances, the matrix diffusion coefficients for the 14 C-labeled TMA likely represent close to the maximum diffusion rates for DOC 14 C in the volcanic and carbonate aquifers in southern Nevada.

54 ENVIRONMENTAL SCIENCES↗

Temporal Cyber Attack Detection.

Rigorous characterization of the performance and generalization ability of cyber defense systems is extremely difficult, making it hard to gauge uncertainty, and thus, confidence. This difficulty largely stems from a lack of labeled attack data that fully explores the potential adversarial space. Currently, performance of cyber defense systems is typically evaluated in a qualitative manner by manually inspecting the results of the system on live data and adjusting as needed. Additionally, machine learning has shown promise in deriving models that automatically learn indicators of compromise that are more robust than analyst-derived detectors. However, to generate these models, most algorithms require large amounts of labeled data (i.e., examples of attacks). Algorithms that do not require annotated data to derive models are similarly at a disadvantage, because labeled data is still necessary when evaluating performance. In this work, we explore the use of temporal generative models to learn cyber attack graph representations and automatically generate data for experimentation and evaluation. Training and evaluating cyber systems and machine learning models requires significant, annotated data, which is typically collected and labeled by hand for one-off experiments. Automatically generating such data helps derive/evaluate detection models and ensures reproducibility of results. Experimentally, we demonstrate the efficacy of generative sequence analysis techniques on learning the structure of attack graphs, based on a realistic example. These derived models can then be used to generate more data. Additionally, we provide a roadmap for future research efforts in this area.

97 MATHEMATICS AND COMPUTING↗

225 Ac/ 213 Bi Generator Based on Millifluidics Controlled Electrodeposition

Radioisotopes provide both diagnostic tools and therapeutic treatments for cancer and other diseases. In the US, millions of radioisotope doses are given to patients per year. Radiopharmaceutical generators are widely used to provide such short-lived medical radioisotopes in a clinical setting. These generators work by exploiting chemical differences in a parent/daughter isotope relationship. Actinium-225 (half-life 10 d) is used to provide clinically useful amounts of daughter isotopes 213 Bi (46 m). An integrated millifluidic 225 Ac/ 213 Bi radiopharmaceutical generator device was engineered to produce 213 Bi labeled biomolecules. Using recent LANL successes in additive manufacturing of small-scale fluidic devices, a disposable device was developed that integrates three steps for the production of 213 Bi labeled antibodies: 1) 213 Bi separation from 225 Ac parent, 2) 213 Bi antibody labeling, and 3) purification of the labelled antibody.

213Bi↗

FY21 Progress Report: SRNL Analysis of ICCWR LCM and WAMS data for Corrosion and Cracking

The development of algorithms for machine learning and data analysis for the 3013 Surveillance Program is a collaborative effort by the Savannah River National Laboratory (SRNL) and the University of South Carolina (USC). For corrosion detection, Laser Confocal Microscope (LCM) or Wide Area 3D Measurement System (WAMS) data is extracted from large binary files, with software written to convert the data to physical attributes (e.g., height, color and grayscale values; all as functions of a location in a plane projection). A user-friendly Matlab Graphical User Interface (GUI) that reads data from either LCM or WAMS files was developed to integrate input data with software developed for processing and evaluation. The GUI can selectively download binary data, interrogate data attributes, label data, flag significant features, execute Machine Learning (ML) algorithms, output parameters for trained ML algorithms, report ML model accuracy with respect to labeled data, and generate graphical representations for various analyses. Features can be called out by user-specified thresholds, manual labeling or machine learning algorithms when they have been completed. The ability to rapidly label data is important because of the volume of data required for training machine learning algorithms. The GUI has the flexibility to allow addition of improved ML algorithms, methods for data visualization, and statistical computations. Statistical analyses via the GUI include areas of pits within a defined range of pit depths, correlations between Red-Green-Blue (RGB) or grayscale intensity and relative surface height, covariances between values associated with features, and feature histograms. The development of supervised machine learning algorithms, however, has been hindered by a lack of training data. The machine learning algorithms for crack identification are being refined but require improvements to the true positive rate for crack detection. This shortcoming is an artifact of the limited training data currently available, perhaps more so than the structure of the neural networks. At present, the best results are had from a consensus over an ensemble of randomly generated Deep Neural Network (DNN) or Convolutional Neural Network (CNN) algorithms. Although the consensus accuracy method has yielded optimum true positive and true negative rates in excess of 80%, additional validation testing is necessary. In addition to the suite of LCM data that was initially used, and which represents the majority of the work presented in this report, WAMS image data was also reviewed at a preliminary level. The review included a comparison between image resolution and dynamic range for each method. WAMS (ZON file) image data was found to have a pixel pitch of 3.69μm compared to 1 μm for the LCM (vk4 file) data, which implies a lower resolution for the WAMS images. Conversely, the ratio of dynamic range of the WAMS data to the LCM data was approximately 41:20 for height data, suggesting that information from WAMS should more accurately determine the depth of pits. At present, the significance of the greater dynamic range of the WAMS data relative to the LCM data has not yet been evaluated.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

FY22 Progress Report: SRNL Analysis of ICCWR LCM and WAMS Data for Corrosion and Cracking

Algorithms for machine learning and data analysis for the 3013 Surveillance Program are being developed in an ongoing collaborative effort by the Savannah River National Laboratory (SRNL) and the University of South Carolina (USC). To detect the presence of corrosion and cracking, data is collected from large binary files generated by a Laser Confocal Microscope (LCM) or Wide Area 3D Measurement System (WAMS). Software is being developed to use the physical attributes in the data files (e.g., height, color, and grayscale values; all as functions of a location in a plane projection) to detect the presence of surface corrosion and cracking. A user-friendly Matlab Graphical User Interface (GUI) that reads data from either LCM or WAMS files was developed to integrate input data with software developed for processing and evaluation. The GUI can selectively download binary data, interrogate data attributes, label data for training ML algorithms, flag significant features, execute Machine Learning (ML) algorithms, output parameters from trained ML algorithms, report ML model accuracy with respect to labeled data, and generate graphical representations for various analyses. Surface defects can be called out by setting user-specified thresholds, feature based analysis or machine learning algorithms. Enhancements to data labeling capability have been developed to address this essential precursor to application of ML routines. Efficient labeling is particularly important in view of the very large volume of data required to train ML algorithms.

3013 Corrosion↗

Oxidation of p-[125I]Iodobenzoic Acid and p-[211At]Astatobenzoic Acid Derivatives and Evaluation In Vivo

The alpha particle-emitting radionuclide astatine-211 (211At) is of interest for targeted radiotherapy; however, low in vivo stability of many 211At-labeled cancer-targeting molecules has limited its potential. As an alternative labeling method, we evaluated whether a specific type of astatinated aryl compound that has the At atom in a higher oxidation state might be stable to in vivo deastatination. In the research effort, para-iodobenzoic acid methyl ester and dPEG4-amino acid methyl ester derivatives were prepared as HPLC standards. The corresponding para-stannylbenzoic acid derivatives were also prepared and labeled with 125I and 211At. Oxidization of the [125I]iodo- and [211At]astato-benzamidyl-dPEG4-acid methyl ester derivatives provided materials for in vivo evaluation. A biodistribution was conducted in mice with coinjected oxidized 125I- and 211At-labeled compounds. The oxidized radioiodinated derivative was stable to in vivo deiodination, but unfortunately the oxidized [211At]astatinated benzamide derivative was found to be unstable under the conditions of isolation by radio-HPLC (post animal injection). Another biodistribution study in mice evaluated the tissue concentrations of coinjected [211At]NaAtO3 and [125I]NaIO3. Comparison of the tissue concentrations of the isolated material from the oxidized [211At]benzamide derivative with those of [211At]astatate indicated the species obtained after isolation was likely [211At]astatate.

59 BASIC BIOLOGICAL SCIENCES↗

Self-supervised Representation Learning for Astronomical Images

Sky surveys are the largest data generators in astronomy, making automated tools for extracting meaningful scientific information an absolute necessity. We show that, without the need for labels, self-supervised learning recovers representations of sky survey images that are semantically useful for a variety of scientific tasks. These representations can be directly used as features, or fine-tuned, to outperform supervised methods trained only on labeled data. We apply a contrastive learning framework on multiband galaxy photometry from the Sloan Digital Sky Survey (SDSS), to learn image representations. We then use them for galaxy morphology classification and fine-tune them for photometric redshift estimation, using labels from the Galaxy Zoo 2 data set and SDSS spectroscopy. In both downstream tasks, using the same learned representations, we outperform the supervised state-of-the-art results, and we show that our approach can achieve the accuracy of supervised models while using 2-4 times fewer labels for training. The codes, trained models, and data can be found at https://portal.nersc.gov/project/dasrepo/self-supervised-learning-sdss.

79 ASTRONOMY AND ASTROPHYSICS↗

Analytical Validation of Accelerator Mass Spectrometry for Pharmaceutical Development: the Measurement of Carbon-14 Isotope Ratio.

Accelerator mass spectrometry (AMS) is an isotope based measurement technology that utilizes carbon-14 labeled compounds in the pharmaceutical development process to measure compounds at very low concentrations, empowers microdosing as an investigational tool, and extends the utility of {sup 14}C labeled compounds to dramatically lower levels. It is a form of isotope ratio mass spectrometry that can provide either measurements of total compound equivalents or, when coupled to separation technology such as chromatography, quantitation of specific compounds. The properties of AMS as a measurement technique are investigated here, and the parameters of method validation are shown. AMS, independent of any separation technique to which it may be coupled, is shown to be accurate, linear, precise, and robust. As the sensitivity and universality of AMS is constantly being explored and expanded, this work underpins many areas of pharmaceutical development including drug metabolism as well as absorption, distribution and excretion of pharmaceutical compounds as a fundamental step in drug development. The validation parameters for pharmaceutical analyses were examined for the accelerator mass spectrometry measurement of {sup 14}C/C ratio, independent of chemical separation procedures. The isotope ratio measurement was specific (owing to the {sup 14}C label), stable across samples storage conditions for at least one year, linear over 4 orders of magnitude with an analytical range from one tenth Modern to at least 2000 Modern (instrument specific). Further, accuracy was excellent between 1 and 3 percent while precision expressed as coefficient of variation is between 1 and 6% determined primarily by radiocarbon content and the time spent analyzing a sample. Sensitivity, expressed as LOD and LLOQ was 1 and 10 attomoles of carbon-14 (which can be expressed as compound equivalents) and for a typical small molecule labeled at 10% incorporated with {sup 14}C corresponds to 30 fg equivalents. AMS provides an sensitive, accurate and precise method of measuring drug compounds in biological matrices.

07 ISOTOPE AND RADIATION SOURCES↗

A semi-supervised machine learning detector for physics events in tokamak discharges

Databases of physics events have been used in various fusion research applications, including the development of scaling laws and disruption avoidance algorithms, yet they can be time-consuming and tedious to construct. This paper presents a novel application of the label spreading semi-supervised learning algorithm to accelerate this process by detecting distinct events in a large dataset of discharges, given few manually labeled examples. A high detection accuracy (>85%) for H-L back transitions and initially rotating locked modes is demonstrated on a dataset of hundreds of discharges from DIII-D with manually identified events for which only 3 discharges are initially labeled by the user. Lower yet reasonable performance (~75%) is also demonstrated for the core radiative collapse, an event with a much lower prevalence in the dataset. Additionally, analysis of the performance sensitivity indicates that the same set of algorithmic parameters is optimal for each event. This suggests that the method can be applied to detect a variety of other events not included in this paper, given that the event is well described by a set of 0D signals robustly available on many discharges. Procedures for analysis of new events are demonstrated, showing automatic event detection with increasing fidelity as the user strategically adds manually labeled examples. Detections on Alcator C-Mod and EAST are also shown, demonstrating the potential for this to be used on a multi-tokamak dataset.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Methods for analyzing nucleic acid sequences

The present invention is directed to a method of sequencing a target nucleic acid. The method provides a complex comprising a polymerase enzyme, a target nucleic acid molecule, and a primer, wherein the complex is immobilized on a support Fluorescent label is attached to a terminal phosphate group of the nucleotide or nucleotide analog. The growing nucleic acid strand is extended by using the polymerase to add a nucleotide analog to the nucleic acid strand. The nucleotide analog added to the oligonucleotide primer as a result of the polymerizing step is identified. The time duration of the signal from labeled nucleotides or nucleotide analogs that become incorporated is distinguished from freely diffusing labels by a longer retention in the observation volume for the nucleotides or nucleotide analogs that become incorporated than for the freely diffusing labels.

59 BASIC BIOLOGICAL SCIENCES↗

AVOID BECOMING A VICTIM OF COUNTERFEIT ITEMS

In today's globalized economy, we cannot live without imported products. Most people do not realize how thin the safety net of regulation and inspection really is. Less than three percent of imported products receive any form of government inspection prior to sale. Avoid flea markets, street vendors and deep discount stores. The sellers of counterfeit wares know where to market their products. They look for individuals who are hungry for a brand name item but do not want to pay a brand name price for it. The internet provides anonymity to the sellers of counterfeit products. Unlike Europe, U.S. law does not hold internet-marketing organizations, responsible for the quality of the products sold on their websites. These organizations will remove an individual vendor when a sufficient number of complaints are lodged, but they will not take responsibility for the counterfeit products you may have purchased. EBay has a number of counterfeit product guides to help you avoid being a victim of the sellers of these products. Ten percent of all medications taken worldwide are counterfeit. If you do buy medications on-line, be sure that the National Association of Boards of Pharmacy Verified Internet Pharmacy Practice Sites (VIPPS) recommends the pharmacy you choose to use. Inspect all medication purchases and report any change in color, shape, imprinting or odor to your pharmacist. If you take generic medications these attributes may change from one manufacturer to another. Your pharmacist should inform you of any changes when you refill your prescription. If they do not, get clarification prior to taking the medication. Please note that the Federal Drug Administration (FDA) does not regulate supplements. The FDA only steps in when a specific supplement proves to cause physical harm or contains a regulated ingredient. Due to counterfeiting, Underwriters Laboratories (UL) changed their label design three times since 1996. The new gold label should be attached to the cord or body of most office and home electrical products (please see the picture to the left). Holiday lights may have the UL marking in red or green instead of the universal black. A red UL mark indicates the product is approved for outdoor as well as indoor service. The green UL mark indicates the product is only to be used indoors. A small number of home electrical products may bear an Interteck (ETL) approval. This label is also acceptable. An Interteck label includes black print on a white background bearing the circular ETL logo. Most manufacturers are proud of their products and strive to gain name recognition as well as foster repeat business. This is not true of counterfeiters. The very first thing most counterfeiters try to do is make their products untraceable. Their products may bear the nation of origin but that is all. This is a common practice with metal components such as pipe fittings and flanges. This is also true of hoisting and rigging equipment such as shackles, turnbuckles and chain. Sadly, this has also occurred with the purchase of some safety equipment such as arc-flash retardant coveralls. Learn the national standards associated with products you are purchasing. Clearly specify these requirements on the procurements you make.

99 GENERAL AND MISCELLANEOUS↗

Chip-based in situ hybridization for identification of bacteria from the human microbiome.

The emerging field of metagenomics seeks to assess the genetic diversity of complex mixed populations of bacteria, such as those found at different sites within the human body. A single person's mouth typically harbors up to 100 bacterial species, while surveys of many people have found more than 700 different species, of which {approx}50% have never been cultivated. In typical metagenomics studies, the cells themselves are destroyed in the process of gathering sequence information, and thus the connection between genotype and phenotype is lost. A great deal of sequence information may be generated, but it is impossible to assign any given sequence to a specific cell. We seek non-destructive, culture-independent means of gathering sequence information from selected individual cells from mixed populations. As a first step, we have developed a microfluidic device for concentrating and specifically labeling bacteria from a mixed population. Bacteria are electrophoretically concentrated against a photopolymerized membrane element, and then incubated with a specific fluorescent label, which can include antibodies as well as specific or non-specific nucleic acid stains. Unbound stain is washed away, and the labeled bacteria are released from the membrane. The stained cells can then be observed via epifluorescence microscopy, or counted via flow cytometry. We have tested our device with three representative bacteria from the human microbiome: E. coli (gut, Gram-negative), Lactobacillus acidophilus (mouth, Gram-positive), and Streptococcus mutans (mouth, Gram-positive), with results comparable to off-chip labeling techniques.

59 BASIC BIOLOGICAL SCIENCES↗

Conformational Exchange in a Membrane Transport Protein Is Altered in Protein Crystals

Successful macromolecular crystallography requires solution conditions that may alter the conformational sampling of a macromolecule. Here, site-directed spin labeling is used to examine a conformational equilibrium within BtuB, the Escherichia coli outer membrane transporter for vitamin B{sub 12}. Electron paramagnetic resonance (EPR) spectra from a spin label placed within the N-terminal energy coupling motif (Ton box) of BtuB indicate that this segment is in equilibrium between folded and unfolded forms. In bilayers, substrate binding shifts this equilibrium toward the unfolded form; however, EPR spectra from this same spin-labeled mutant indicate that this unfolding transition is blocked in protein crystals. Moreover, crystal structures of this spin-labeled mutant are consistent with the EPR result. When the free energy difference between substates is estimated from the EPR spectra, the crystal environment is found to alter this energy by 3 kcal/mol when compared to the bilayer state. Approximately half of this energy change is due to solutes or osmolytes in the crystallization buffer, and the remainder is contributed by the crystal lattice. These data provide a quantitative measure of how a conformational equilibrium in BtuB is modified in the crystal environment, and suggest that more-compact, less-hydrated substates will be favored in protein crystals.

59 BASIC BIOLOGICAL SCIENCES↗

Polynucleotide barcoding

A polynucleotide is barcoded using a method whereby an isolated, individual polynucleotide is immobilized on a solid phase and stretched, targets are labeled using target-specific hybridization probes, and an individual label of an unamplified probe at each of the labeled targets is optically detected. The order of the labels is determined to form a barcode representation of the polynucleotide wherein the targets and their relative positions are represented.

Selvin, Paul R.↗

Vehicle track detection in synthetic aperture radar imagery

The various technologies presented herein relate to detecting one or more vehicle tracks in radar imagery. A CCD image can be generated from a first SAR image and a second SAR image captured for a common scene, wherein the second SAR image may include a vehicle track that is not present in the first SAR image. A Radon transform (RT) process can be applied to each pixel in the CCD image, and further, a radial derivative (RDRT) can be determined for each pixel from RT values derived for each pixel. Each pixel can be labelled as being related to a track, or not, based upon a unary cost obtained from the RDRT value of that pixel, combined with a probability of the pixel label based upon labels applied to neighboring pixels. A labelled representation of the CCD image can be generated based upon the determination of “track” or “not track”.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Incorporating historical data and past analyses for improved tensile property prediction of 9% Cr steel

Data-driven analytical clustering and visualization techniques were applied to the dataset of 9% Cr experimental alloy data generated through the eXtremeMAT project. Techniques and results were compared with the resulting clusters obtained through similar analytical techniques on previous and reduced versions of the dataset. The principal components were generated in order to reduce the dimensionality of the complex dataset and to visualize the underlying trends in the data. Partitioning around medoids was performed on the resulting principal components to determine relevant clusters. Domain knowledge labels were further applied to the principal components to compare the labels with the trends identified through the clustering methods. The resulting clusters show the addition of the new data into the dataset, and show where alignment between the domain knowledge labels and partitioning around medoids (PAM) clusters show where the labels are appropriate. The clusters can be used to compare the tensile properties of the alloys, and to reduce the variation in the dataset.

Alloy design, Mechanical Properties, data analysis↗