SEARCH · Search NASA

Results for “Text 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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5

All sources NASA NTRS DOE OSTI

DOE OSTI2020

Figure Descriptive Text Extraction Using Ontological Representation

Abstract Experimental research publications provide figure form resources including graphs, charts, and any type of images to effectively support and convey methods and results. To describe figures, authors add captions, which are often incomplete, and more descriptions reside in body text. This work presents a method to extract figure descriptive text from the body of scientific articles. We adopted ontological semantics to aid concept recognition of figure-related information, which generates human- and machine-readable knowledge representations from sentences. Our results show that conceptual models bring an improvement in figure descriptive sentence classification over word-based approaches.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2018

Correlating Enzymes to Antimicrobial Resistance in the Protein Data Bank

Antibiotic resistant bacteria are predicted to be the leading cause of death worldwide, with an expected death rate of 10 million people, annually, by 2050. It is vital that antimicrobial resistance (AMR) be understood at the molecular level. The Protein Data Bank (PDB) archive holds over 130,000 3D structures of macromolecular machines that can be analyzed using the RCSB PDB website at RCSB.org. Studying these 3D structures enables scientific research and education in a variety of fields, including drug discovery, nanotechnology, green energy, and disease. In this study, PDB enzymes related to antibiotic inhibitors were identified and further analyzed using additional bioinformatics including The Comprehensive Antibiotic Resistance Database (CARD). CARD holds up to date clinically relevant antibiotic related information. CARD identified 4,688 Genbank IDs (protein accession codes) that are related to AMR. These codes were then put into the Uniprot website which holds protein sequences. As a result, 696 macromolecules related to AMR were found in the PDB. I specifically researched Metallo Beta Lactamases (MBL) because have a large correlation to AMR and have been studied in great detail, with many examples in the PDB. Prominent enzymes in this category include the New Delhi Beta Lactamase which can cleave most if not all antibiotics. This particular “superbug” was found to cleave penicillin, cephalosporin, and carbapenem antibiotics. Using 3D visualizations of beta lactamase enzymes a correlation between zinc ions and spectrum of antibiotic resistance was found. For example, if an enzyme had two zinc ions instead of one it could inhibit broad spectrum antibiotics. In conclusion, the findings of this research presented here will be used to develop novel AMR tab at RCSB.org that will provide antimicrobial details of enzymes that were unavailable before. In the near future a phylogenetic tree of AMR related enzymes and classification details will be implemented. Support or Funding Information RCSB PDB is funded by a grant from the National Science Foundation (DBI‐1338415) , the National Institutes of Health , and the US Department of Energy . This abstract is from the Experimental Biology 2018 Meeting. There is no full text article associated with this abstract published in The FASEB Journal .

Salcedo, Priscilla M.↗

DOE OSTI2020

Bosonic crystalline symmetry protected topological phases beyond the group cohomology proposal

It is demonstrated by explicit construction that three-dimensional bosonic crystalline symmetry protected topological (cSPT) phases are classified by $H^5_\phi(G; \mathbb{Z})⊕H^1_\phi(G; \mathbb{Z})$ for all 230 space groups $\textit{G}$, where $H^n_\phi(G; \mathbb{Z})$ denotes the $\textit{n}$th twisted group cohomology of $\textit{G}$ with $\mathbb{Z}$ coefficients, and $\phi$ indicates that $\textit{g ε G}$ acts nontrivially on coefficients by sending them to their inverses if $\textit{g}$ reverses space-time orientation and acts trivially otherwise. The previously known summand $H^5_\phi(G;\mathbb{Z})$ corresponds only to crystalline phases built without the $E_8$ state or its multiples on 2-cells of space. It is the crystalline analog of the “group cohomology proposal” for classifying bosonic symmetry protected topological (SPT) phases, which takes the form $H^{d + 2}_\phi(G; \mathbb{Z}) ≅ H^{d + 1}_\phi(G; \text{U}(1))$ for finite internal symmetry groups in d spatial dimensions. The new summand $H^1_\phi(G; \mathbb{Z})$ classifies possible configurations of $E_8$ states on 2-cells that can be used to build crystalline phases beyond the group cohomology proposal. The completeness of our classification and the physical meaning of $H^1_\phi(G; \mathbb{Z})$ are established through a combination of dimensional reduction, surface topological order, and explicit cellular construction. The value of $H^1_\phi(G; \mathbb{Z})$ can be easily read off from the international symbol for $\textit{G}$. In this work, our classification agrees with the prediction of the “generalized cohomology hypothesis,” which concerns the general structure of the classification of SPT phases, and therefore provides strong evidence for the validity of the said hypothesis in the realm of crystalline symmetries.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

DOE OSTI2023

Rotational symmetry protected edge and corner states in Abelian topological phases

Spatial symmetries can enrich the topological classification of interacting quantum matter and endow systems with non-trivial strong topological invariants (protected by internal symmetries) with additional "weak" topological indices. In this paper, we study the edge physics of systems with a non-trivial shift invariant, which is protected by either a continuous $\text{U}(1)_r$ or discrete $\text{C}_n$ rotation symmetry, along with internal $\text{U}(1)_c$ charge conservation. Specifically, we construct an interface between two systems which have the same Chern number but are distinguished by their Wen-Zee shift and, through analytic arguments supported by numerics, show that the interface hosts counter-propagating gapless edge modes which cannot be gapped by arbitrary local symmetry-preserving perturbations. Using the Chern-Simons field theory description of two-dimensional Abelian topological orders, we then prove sufficient conditions for continuous rotation symmetry protected gapless edge states using two complementary approaches. One relies on the algebraic Lagrangian sub-algebra framework for gapped boundaries while the other uses a more physical flux insertion argument. For the case of discrete rotation symmetries, we extend the field theory approach to show the presence of fractional corner charges for Abelian topological orders with gappable edges, and compute them in the case where the Abelian topological order is placed on the two-dimensional surface of a Platonic solid. Finally, our work paves the way for studying the edge physics associated with spatial symmetries in symmetry enriched topological phases.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

DOE OSTI2015

Matisse: A Visual Analytics System for Exploring Emotion Trends in Social Media Text Streams

Dynamically mining textual information streams to gain real-time situational awareness is especially challenging with social media systems where throughput and velocity properties push the limits of a static analytical approach. In this paper, we describe an interactive visual analytics system, called Matisse, that aids with the discovery and investigation of trends in streaming text. Matisse addresses the challenges inherent to text stream mining through the following technical contributions: (1) robust stream data management, (2) automated sentiment/emotion analytics, (3) interactive coordinated visualizations, and (4) a flexible drill-down interaction scheme that accesses multiple levels of detail. In addition to positive/negative sentiment prediction, Matisse provides fine-grained emotion classification based on Valence, Arousal, and Dominance dimensions and a novel machine learning process. Information from the sentiment/emotion analytics are fused with raw data and summary information to feed temporal, geospatial, term frequency, and scatterplot visualizations using a multi-scale, coordinated interaction model. After describing these techniques, we conclude with a practical case study focused on analyzing the Twitter sample stream during the week of the 2013 Boston Marathon bombings. The case study demonstrates the effectiveness of Matisse at providing guided situational awareness of significant trends in social media streams by orchestrating computational power and human cognition.

data visualization↗

DOE OSTI2017

Enabling the democratization of the genomics revolution with a fully integrated web-based bioinformatics platform, Version 1.5 and 1.x.

EDGE bioinformatics was developed to help biologists process Next Generation Sequencing data (in the form of raw FASTQ files), even if they have little to no bioinformatics expertise. EDGE is a highly integrated and interactive web-based platform that is capable of running many of the standard analyses that biologists require for viral, bacterial/archaeal, and metagenomic samples. EDGE provides the following analytical workflows: quality trimming and host removal, assembly and annotation, comparisons against known references, taxonomy classification of reads and contigs, whole genome SNP-based phylogenetic analysis, and PCR analysis. EDGE provides an intuitive web-based interface for user input, allows users to visualize and interact with selected results (e.g. JBrowse genome browser), and generates a final detailed PDF report. Results in the form of tables, text files, graphic files, and PDFs can be downloaded. A user management system allows tracking of an individual’s EDGE runs, along with the ability to share, post publicly, delete, or archive their results.

Chain, Patrick↗

DOE OSTI2017

Enabling the democratization of the genomics revolution with a fully integrated web-based bioinformatics platform, Version 1.5 and 1.x.

Chain, Patrick↗

DOE OSTI2025

Old Woman Creek Wetland Sediment and Electrochemical Sensor Microbial Community, 2023

We are developing a technique to monitor microbiological activities referred to as zero resistance ammetry, which entails the deployment of graphite electrodes in sediments. Measurement of current between electrodes of contrasting redox regimes and/or predominant terminal electron accepting processes can be used as an indicator of the extents of microbiological activity. We deployed an electrode array at depths of 2 mm, 4 mm, 76 mm, 78 mm, 152 mm, 154 mm, 227 mm, and 229 mm below the wetland sediment water interface in the Old Woman Creek National Estuarine Research Center, Huron, OH, USA (Lat. = 41.380833, Long. = -82.508889). A core was collected from adjacent sediment and subsamples were collected from depth intervals of 0 – 25 mm, 25 – 127 mm, 127 – 128 mm, and below 178 mm. To determine if the microbial communities attached to the electrodes were reflective of the adjacent sediment-associated microbial community, we conducted a 16S rRNA gene-based (V4 region) survey of these respective materials. This data package contains the results of these surveys, including metadata on the depths from which samples were collected (samples.csv), DNA extraction and sequencing information (OWC_DEPTH_AMPLICON_SEQUENCING_METADATA), sequence processing information (OWC_DEPTH_BIOINFORMATIC_METADATA.csv), an operational taxonomic unit (OTU) table (OWC_DEPTH_97OTUS_TABLE.csv), and nucleotide sequences of OTUs (OWC_DEPTH_97OTUS_SEQS.fasta). All files can be opened using a text-editing application. The fasta file is compatible with bioinformatics applications.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Semantic Stealth: Crafting Covert Adversarial Patches for Sentiment Classifiers Using Large Language Models

Deep learning models have been shown to be vulnerable to adversarial attacks, in which perturbations to their inputs cause the model to produce incorrect predictions. As opposed to adversarial attacks in computer vision, where small changes introduced to pixel values can drastically alter a model's output while remaining imperceptible to humans, text-based attacks are difficult to conceal due to the discrete nature of tokens. Consequently, unconstrained gradient-based attacks often produce adversarial examples that lack semantic meaning, rendering them detectable through visual inspection or perplexity filters. In contrast to methods that rely on gradient-based optimization in the embedding space, we propose an approach that leverages a Large Language Model's ability to generate grammatically correct and semantically meaningful text to craft adversarial patches that seamlessly blend in with the original input text. These patches can be used to alter the behavior of a target model, such as a text classifier. Since our approach does not rely on gradient backpropagation, it only requires access to the target model's confidence scores, making it a grey-box attack. We demonstrate the feasibility of our approach using open-source LLMs, including Intel's Neural Chat, Llama2, and Mistral-Instruct, to generate adversarial patches capable of altering the predictions of a distilBERT model fine-tuned on the IMDB reviews dataset for sentiment classification.

Roa Carvajal, Maria↗

DOE OSTI2018

Toward Uncertainty Quantification for Supervised Classification

Our goal is to develop a general theoretical basis for quantifying uncertainty in supervised machine learning models. Current machine learning accuracy-based validation metrics indicate how well a classifier performs on a given data set as a whole. However, these metrics do not tell us a model's efficacy in predicting particular samples. We quantify uncertainty by constructing probability distributions of the predictions made by an ensemble of classifiers. This report details our initial investigations into uncertainty quantification for supervised machine learning. We apply an uncertainty analysis to the problem of malicious website detection. Machine learning models can be trained to find suspicious characteristics in the text of a website's Uniform Resource Locator (URL). However, given the vast numbers of URLs and the ever changing tactics of malicious actors, it will always be possible to find sets of websites which are outliers with respect to a model's hypothesis. Therefore, we seek to understand a model's per-sample reliability when classifying URL data. Acknowledgements This work was funded by the Sandia National Laboratories Laboratory Directed Research and Development (LDRD) program.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2013

AKARI INFRARED CAMERA SURVEY OF THE LARGE MAGELLANIC CLOUD. II. THE NEAR-INFRARED SPECTROSCOPIC CATALOG

We performed a near-infrared spectroscopic survey toward an area of {approx}10 deg{sup 2} of the Large Magellanic Cloud (LMC) with the infrared satellite AKARI. Observations were carried out as part of the AKARI Large-area Survey of the Large Magellanic Cloud (LSLMC). The slitless multi-object spectroscopic capability of the AKARI/IRC enabled us to obtain low-resolution (R {approx} 20) spectra in 2-5 {mu}m for a large number of point sources in the LMC. As a result of the survey, we extracted about 2000 infrared spectra of point sources. The data are organized as a near-infrared spectroscopic catalog. The catalog includes various infrared objects such as young stellar objects (YSOs), asymptotic giant branch (AGB) stars, supergiants, and so on. It is shown that 97% of the catalog sources have corresponding photometric data in the wavelength range from 1.2 to 11 {mu}m, and 67% of the sources also have photometric data up to 24 {mu}m. The catalog allows us to investigate near-infrared spectral features of sources by comparison with their infrared spectral energy distributions. In addition, it is estimated that about 10% of the catalog sources are observed at more than two different epochs. This enables us to study a spectroscopic variability of sources by using the present catalog. Initial results of source classifications for the LSLMC samples are presented. We classified 659 LSLMC spectra based on their near-infrared spectral features by visual inspection. As a result, it is shown that the present catalog includes 7 YSOs, 160 C-rich AGBs, 8 C-rich AGB candidates, 85 O-rich AGBs, 122 blue and yellow supergiants, 150 red super giants, and 128 unclassified sources. Distributions of the classified sources on the color-color and color-magnitude diagrams are discussed in the text. Continuous wavelength coverage and high spectroscopic sensitivity in 2-5 {mu}m can only be achieved by space observations. This is an unprecedented large-scale spectroscopic survey toward the LMC in the near-infrared. A large number of near-infrared spectral data provided by the survey possess scientific potential that can be applied to various studies. In this paper, we present the details of the spectroscopic survey and the catalog, and discuss its scientific applications.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2024

Deep Generative Models in Energy System Applications: Review, Challenges, and Future Directions

In recent years, with the advent of mature machine learning products like ChatGPT, Stable Diffusion, and Sora, the world has witnessed tremendous changes driven by the rapid development of generative artificial intelligence (GAI). Beyond applications in text, speech, image, and video creation, deep generative models (DGMs) underpinning these cutting-edge technologies have also been employed by domain researchers to address scientific and engineering challenges. This paper aims to fill a gap in the research community by providing a systematic review of how DGMs have been utilized in energy system applications. After introducing four most popular DGMs, we review and categorize 196 research articles into five focus areas: data generation, forecasting, situational awareness, modeling, and optimal decision-making. Through this classification, we uncover trends in how DGMs are employed for each type of problem, highlighting GAI techniques that contribute to breakthroughs over traditional methods. We discuss limitations in existing literature, engineering challenges, and propose future directions, all tailored to the unique nature of problems in energy system engineering. Our goal is to offer insights for energy system domain researchers, providing a comprehensive view of existing studies and potential future opportunities.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2024

A Decision Support System to Compile Environmental Mitigations from Hydropower Licensing Documents

The process of deciphering, extracting, and compiling information from texts dense with domain-specific terminology and technical jargon is a challenging endeavor. It demands considerable expertise and deep knowledge in the respective field, resulting in a labor-intensive process when executed by humans. Furthermore, the task of identifying multiple class labels in extensive texts presents a challenge due to intra- and inter-reader variability, making the process time-consuming and costly.We’re introducing a user-friendly graphical interface, fortified with a BERT model-powered decision support system. This advanced system aims to augment efficiency, curtail data collection time, and sustain high precision in data acquisition. It is instrumental in deciphering and synthesizing intricate texts teeming with a spectrum of expressions, even within similar mitigation categories. Such tasks traditionally demand substantial human effort and specialized knowledge in the domain.Our system is specifically engineered for the task of extracting environmental mitigation information to promote sustainable hydropower development from licenses issued by the Federal Energy Regulatory Commission (FERC). These license documents are comprehensive, each containing over 15,000 words and requiring the identification of 135 different class labels. We anticipate that our system will boost reading speed, improve the consistency of classification outputs among readers, and contribute to the development of a robust scientific database of environmental mitigations associated with the 2,000+ non-federal hydropower facilities licensed by FERC in the United States.

Yoon, Hong-Jun [ORNL] (ORCID:0000000254505878)↗

DOE OSTI2026

Soft symmetries of topological orders

(2+1)D topological orders possess emergent symmetries given by a group $\text{Aut}(\mathcal{C})$, which consists of the braided tensor autoequivalences of the modular tensor category $\mathcal{C}$ that describes the anyons. In this paper we discuss cases where $\text{Aut}(\mathcal{C})$ has elements that neither permute anyons nor are associated to any symmetry fractionalization but are still non-trivial, which we refer to as soft symmetries. We point out that one can construct topological defects corresponding to such exotic symmetry actions by decorating with a certain class of gauged SPT states that cannot be distinguished by their torus partition function. This gives a physical interpretation to work by Davydov on soft braided tensor autoequivalences. This has a number of important implications for the classification of gapped boundaries, non-invertible spontaneous symmetry breaking, and the general classification of symmetry-enriched topological phases of matter. Here, we also demonstrate analogous phenomena in higher dimensions, such as (3+1)D gauge theory with gauge group given by the quaternion group $Q_8$.

Gauge theory techniques↗

DOE OSTI2025

Demystifying the Resilience of Large Language Models: An End-to-End Perspective

Deep neural networks are known to be resilient to random bit-wise faults in their parameters. However, this resilience has primarily been established through evaluations of classification models. The extent to which this claim holds for large-language models remains underexplored. In this work, we conduct an extensive measurement study on the impact of random bitwise faults in commercial-scale language models. We perform an in-depth analysis of the resulting generation outputs. We first expose that these language models are not truly resilient to random bit-flips. While aggregate metrics such as accuracy may suggest resilience, an in-depth inspection of the generated outputs shows significant degradation in text quality. Our analysis also shows that tasks requiring more complex reasoning suffer more from performance and quality degradation. Moreover, we extend our analysis to models with augmented reasoning capabilities, such as Chain-of-Thought or Mixture of Experts architectures, and characterize their failure scenarios under random bit-flips.

Sun, Yu↗

DOE OSTI2013

MultiFacet: A Faceted Interface for Browsing Large Multimedia Collections

Faceted browsing is a common technique for exploring collections where the data can be grouped into a number of pre-defined categories, most often generated from textual metadata. Historically, faceted browsing has been applied to a single data type such as text or image data. However, typical collections contain multiple data types, such as information from web pages that contain text, images, and video. Additionally, when browsing a collection of images and video, facets are often created based on the metadata which may be incomplete, inaccurate, or missing altogether instead of the actual visual content contained within those images and video. In this work we address these limitations by presenting MultiFacet, a faceted browsing interface that supports multiple data types. MultiFacet constructs facets for images and video in a collection from the visual content using computer vision techniques. These visual facets can then be browsed in conjunction with text facets within a single interface to reveal relationships and phenomena within multimedia collections. Additionally, we present a use case based on real-world data, demonstrating the utility of this approach towards browsing a large multimedia data collection.

content-based image retrieval↗

DOE OSTI2023

Chaconne: A Statistical Approach to Nonlocal Compression for Supervised Learning, Semi-Supervised Learning, and Anomaly Detection

This project developed a novel statistical understanding of compression analytics (CA), which has challenged and clarified some core assumptions about CA, and enabled the development of novel techniques that address vital challenges of national security. Specifically, this project has yielded the development of novel capabilities including 1. Principled metrics for model selection in CA, 2. Techniques for deriving/applying optimal classification rules and decision theory to supervised CA, including how to properly handle class imbalance and differing costs of misclassification, 3. Two techniques for handling nonlocal information in CA, 4. A novel technique for unsupervised CA that is agnostic with regard to the underlying compression algorithm, 5. A framework for semisupervised CA when a small number of labels are known in an otherwise large unlabeled dataset. 6. The academic alliance component of this project has focused on the development of a novel exemplar-based Bayesian technique for estimating variable length Markov models (closely related to PPM [prediction by partial matching] compression techniques). We have developed examples illustrating the application of our work to text, video, genetic sequences, and unstructured cybersecurity log files.

99 GENERAL AND MISCELLANEOUS↗

DOE OSTI2017

Measuring, Predicting and Visualizing Short-Term Change in Word Representation and Usage in VKontakte Social Network

Language in social media is extremely dynamic: new words emerge, trend and disappear, while the meaning of existing words can fluctuate over time. This work addresses several important tasks of visualizing and predicting short term text representation shift, i.e. the change in a word’s contextual semantics. We study the relationship between short-term concept drift and representation shift on a large social media corpus – VKontakte collected during the Russia-Ukraine crisis in 2014 – 2015. We visualize short-term representation shift for example keywords and build predictive models to forecast short-term shifts in meaning from previous meaning as well as from concept drift. We show that short-term representation shift can be accurately predicted up to several weeks in advance and that visualization provides insight into meaning change. Our approach can be used to explore and characterize specific aspects of the streaming corpus during crisis events and potentially improve other downstream classification tasks including real-time event forecasting in social media.

concept drift↗