Engineering Papers⌕ Search

SEARCH · Engineering Papers

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.

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

At least 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Classifying Cancer Pathology Reports with Hierarchical Self-Attention Networks

We introduce a deep learning architecture, hierarchical self-attention networks (HiSANs), designed for classifying pathology reports and show how its unique architecture leads to a new state-of-the-art in accuracy, faster training, and clear interpretability. We evaluate performance on a corpus of 374,899 pathology reports obtained from the National Cancer Institute's (NCI) Surveillance, Epidemiology, and End Results (SEER) program. Each pathology report is associated with five clinical classification tasks – site, laterality, behavior, histology, and grade. We compare the performance of the HiSAN against other machine learning and deep learning approaches commonly used on medical text data – Naive Bayes, logistic regression, convolutional neural networks, and hierarchical attention networks (the previous state-of-the-art). We show that HiSANs are superior to other machine learning and deep learning text classifiers in both accuracy and macro F-score across all five classification tasks. Compared to the previous state-of-the-art, hierarchical attention networks, HiSANs not only are an order of magnitude faster to train, but also achieve about 1% better relative accuracy and 5% better relative macro F-score.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2012

2012 SARA Students Technical Report

The Service Academy Research Associates (SARA) program provides an opportunity for Midshipmen and Cadets from US Service Academies to participate in research at Los Alamos National Laboratory (LANL), Lawrence Livermore National Laboratory (LLNL), and Sandia National Laboratory for several weeks during the summer as part of their summer training assignments. During the summer of 2012, three Midshipmen were assigned to work with the XCP Division at LANL for approximately 5-6 weeks. As one of the nation's top national security science laboratories, LANL stretches across 36 square miles, has over 2,100 facilities, and employs over 9,000 individuals including a significant number of students and postdocs. LANL's mission is to 'apply science and technology to: ensure the safety, security, and reliability of the US nuclear deterrent, reduce global threats, and solve other emerging national security challenges.' While LANL officially operates under the US Department of Energy (DoE), fulfilling this mission requires mutual cooperation with the US Department of Defense (DoD) as well. LANL's high concentration of knowledge and experience provides interns a chance to perform research in many disciplines, and its connection with the DoD in both operation and personnel gives SARA students insight to career possibilities both during and after military service. SARA students have plenty of opportunity to enjoy hiking, camping, the Los Alamos YMCA, and many other outdoor activities in New Mexico while staying at the Buffalo Thunder Resort, located 20 miles east of the lab. XCP Division is the Computational Physics division of LANL's Weapons Department. Working with XCP Division requires individuals to be Q cleared by the DoE. This means it is significantly more convenient for SARA students to be assigned to XCP Division than their civilian counterparts as the DoD CNWDI clearance held by SARA students is easily transferred to the lab prior to the students arriving at the start of the summer. SARA students working with XCP Division were given a comprehensive introduction into nuclear engineering and physics, nuclear weapons, and radiation transport and detection via texts and lectures at various classification levels. Students also attended tours of several prominent facilities at LANL including TA-41 Ice House, TA-55 PF-4 plutonium facility, the Nicholas C. Metropolis Center for Modeling and Simulation, also known as the Secure Computing Center (SCC), and the Dual-Axis Radiological Hydro Test (DARHT) facility; in addition, SARA students accompanied by LANL staff traveled to Minot AFB in North Dakota for tours of the 5th Bomb Wing and 91st Missile Wing facilities. Students participated in a week long class on the Monte Carlo N Particle (MCNP) code to supplement their understanding of radiation transport simulations. SARA students were then tasked with using this knowledge to model radiation detectors and use MCNP to compare their models to experimental data and previously accepted models.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2026

Cyote-attack Chain Estimator

Attack Chain Estimator (ACE) Application Overview The Attack Chain Estimator (ACE) Application is a sophisticated tool designed for the ingestion, classification, sequencing, and enrichment of cybersecurity threat reports. This application leverages advanced machine learning models and extensive historical data to provide comprehensive insights into cyber threats, specifically targeting Industrial Control Systems (ICS). Purpose The primary functions of the ACE Application include: Ingestion of Cybersecurity Threat Reporting: Capable of ingesting text-based threat reports in markdown or text file format. Supports ingestion of structured data from other sources in STIX/JSON format. Classification of Report’s Text-Based Events: Utilizes a DeBERTa classifier, specifically trained on cybersecurity data, to map the events to MITRE ATT&CK for ICS Tactics and Techniques. Classification is performed using multiple Jupyter notebooks and machine learning workflows hosted as FastAPI microservices: regex_data deberta_base_35_train_hft_classifier_mlflow.ipynb hft_regex_classifier_mlflow.ipynb param_train_hft_classifier_mlflow.ipynb regex_tactic_tech.ipynb Ordering of Tactics, Techniques, and Observable Events: Sequences the identified tactics, techniques, and events to form a coherent attack chain. Enrichment with Historical Attack Chain Details: Enhances the attack chain with details from historical attacks using a Markov model developed from CyOTE Precursor Analysis Report data. The Markov model is available as a FastAPI endpoint for seamless integration. Enrichment with Adversary Emulation Capabilities Data: Integrates adversary emulation capabilities data using MITRE Caldera for OT adversary abilities UUIDs. Export of Output Files: Provides options to export the enriched attack chain in JSON or CSV formats. Routing of Output to Other Applications: Facilitates routing of output to various platforms and applications, including: Threat Intelligence Platforms COREII Scout for Threat Intelligence Analysis COREII Modeling and Simulation for Adversary Emulation Technical Description The ACE Application is an advanced cybersecurity tool designed to provide detailed threat analysis and sequence generation. It is built on a robust architecture that integrates natural language processing, machine learning, and historical data modeling. Key Components: Data Ingestion Module: Handles the input of threat reports and data from various formats, ensuring flexibility in data sources. Classification Engine: Employs DeBERTa-based classifiers hosted as FastAPI microservices to analyze and classify threat report events in accordance with the MITRE ATT&CK framework for ICS. Sequence Generator: Orders the classified events into a logical attack chain, providing clear insight into the sequence of tactics and techniques used in the threat. Enrichment Engine: Integrates historical data and adversary emulation capabilities to enhance the attack chain with valuable context and additional details. The historical data enrichment is powered by a Markov model, which is available as a FastAPI endpoint. Export and Routing Module: Facilitates the export of the enriched attack chain in multiple formats and routes the output to designated applications for further analysis or emulation.

Paul, Tony [Idaho National Laboratory (INL), Idaho↗
DOE OSTI2025

Decoding substance use disorder severity from clinical notes using a large language model

Substance use disorder (SUD) poses a major concern due to its detrimental effects on health and society. SUD identification and treatment depend on a variety of factors such as severity, co-determinants (e.g., withdrawal symptoms), and social determinants of health. Existing diagnostic coding systems used by insurance providers, like the International Classification of Diseases (ICD-10), lack granularity for certain diagnoses, but American clinicians will add this granularity (as that found within the Diagnostic and Statistical Manual of Mental Disorders classification or DSM-5) as supplemental unstructured text in clinical notes. Traditional natural language processing (NLP) methods face limitations in accurately parsing such diverse clinical language. Large language models (LLMs) offer promise in overcoming these challenges by adapting to diverse language patterns. This study investigates the application of LLMs for extracting severity-related information for various SUD diagnoses from clinical notes. We propose a workflow employing zero-shot learning of LLMs with carefully crafted prompts and post-processing techniques. Through experimentation with Flan-T5, an open-source LLM, we demonstrate its superior recall compared to the rule-based approach. Focusing on 11 categories of SUD diagnoses, we show the effectiveness of LLMs in extracting severity information, contributing to improved risk assessment and treatment planning for SUD patients.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

Chinese social media analysis for disease surveillance

Here, it is reported that there are hundreds of thou- sands of deaths caused by seasonal flu all around the world every year. More other diseases such as chickenpox, malaria, etc. are also serious threats to people’s physical and mental health. There are 250,000–500,000 deaths every year around the world. Therefore proper techniques for disease surveillance are highly demanded. Recently, social media analysis is regarded as an efficient way to achieve this goal, which is feasible since growing number of people have been posting their health information on social media such as blogs, personal websites, etc. Previous work on social media analysis mainly focused on English materials but hardly considered Chinese materials, which hinders the application of such technique to Chinese peo- ple. In this paper, we proposed a new method of Chinese social media analysis for disease surveillance. More specifically, we compared different kinds of methods in the process of classification and then proposed a new way to process Chinese text data. The Chinese Sina micro-blog data collected from September to December 2013 are used to validate the effectiveness of the proposed method. The results show that a high classification precision of 87.49 % in average has been obtained. Comparing with the data from the authority, Chinese National Influenza Center, we can predict the outbreak time of flu 5 days earlier.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Provenance infrastructure for multimodal x-ray experiments and reproducible analysis

Exploring relationships between material structures and desired properties for material discovery and synthesis requires mining machine-readable databases and linking experimental data with sufficiently rich annotations. There are vast gaps both in these data sources and in the connections between them. We present a provenance-based data management and analysis framework that enables capturing, persisting, and reanalyzing experimental data from the BNL National Synchrotron Light Source II (NSLS-II). Our system leverages NSLS-II Bluesky for experimental data acquisition, captures analysis parameters, and enriches the search space with results from the scientific literature. We describe in detail the challenges and benefits of data-driven approaches when comparing computational and experimental data, such as the multiple possible scenarios of interest in often ill-posed inverse problems and missing data. Our infrastructure utilizes the NSLS-II event model and includes discovery mechanisms across multiple beamlines. A text and data mining module using natural language processing classification techniques extracts relevant information from the literature that is added to data sources. We describe a provenance acquisition and analysis rerun workflow based on a directed acyclic graph that keeps track of process and data provenance and allows to replay analysis.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Topological Interpretability for Deep Learning

With the growing adoption of AI-based systems across everyday life, the need to understand their decision-making mechanisms is correspondingly increasing. The level at which we can trust the statistical inferences made from AI-based decision systems is an increasing concern, especially in high-risk systems such as criminal justice or medical diagnosis, where incorrect inferences may have tragic consequences. Despite their successes in providing solutions to problems involving real-world data, deep learning (DL) models cannot quantify the certainty of their predictions. These models are frequently quite confident, even when their solutions are incorrect. This work presents a method to infer prominent features in two DL classification models trained on clinical and non-clinical text by employing techniques from topological and geometric data analysis. We create a graph of a model's feature space and cluster the inputs into the graph's vertices by the similarity of features and prediction statistics. We then extract subgraphs demonstrating high-predictive accuracy for a given label. These subgraphs contain a wealth of information about features that the DL model has recognized as relevant to its decisions. We infer these features for a given label using a distance metric between probability measures, and demonstrate the stability of our method compared to the LIME and SHAP interpretability methods. This work establishes that we may gain insights into the decision mechanism of a DL model. This method allows us to ascertain if the model is making its decisions based on information germane to the problem or identifies extraneous patterns within the data.

Spannaus, Adam↗
DOE OSTI2021

An Introduction to Word Embeddings and Language Models

Language models have advanced at a phenomenal pace over the past decade. This document provides a short introduction to terminology, word embeddings (aka low-dimensional representations), and popular large-scale language models (LMs). Word embeddings are used to represent words as numerical vectors and are context-independent, meaning a word can only have a single representation (e.g., club can only be club sandwich, not golf club ). Language models can determine the probability of a given sequence of words occurring in a sentence and can provide context to distinguish between words and phrases that sound similar. LMs are context-dependent (e.g., club can be club sandwich or golf club ) and largely fall in two main classes – autoregressive and autoencoding models. Autoregressive models are pretrained on the classic language modeling task: guess the next token having read all the previous ones. Those models can be fine-tuned and achieve great results on many tasks, the most natural application is text generation. A typical example of such models is GPT, but others include GPT-2, GPT-3, CTLR, TRANSFORMER-XL, REFORMER, XLNET. Autoencoding models are pretrained by corrupting the input tokens in some way and trying to reconstruct the original sentence. They can be fine-tuned and achieve great results on many tasks such as text generation, but their most natural application is sentence classification or token classification. A typical example of such models is BERT, but others include ROBERTA, ALBERT, XML, XML-ROBERTA, FLAUBERT AND LONGFORMER.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

A systematic review of validated suicide outcome classification in observational studies

Abstract Background Suicidal outcomes, including ideation, attempt, and completed suicide, are an important drug safety issue, though few epidemiological studies address the accuracy of suicidal outcome ascertainment. Our primary objective was to evaluate validated methods for suicidal outcome classification in electronic health care database studies. Methods We performed a systematic review of PubMed and EMBASE to identify studies that validated methods for suicidal outcome classification published 1 January 1990 to 15 March 2016. Abstracts and full texts were screened by two reviewers using prespecified criteria. Sensitivity, specificity, and predictive value for suicidal outcomes were extracted by two reviewers. Methods followed PRISMA-P guidelines, PROSPERO Protocol: 2016: CRD42016042794. Results We identified 2202 citations, of which 34 validated the accuracy of measuring suicidal outcomes using International Classification of Diseases (ICD) codes or algorithms, chart review or vital records. ICD E-codes (E950-9) for suicide attempt had 2–19% sensitivity, and 83–100% positive predictive value (PPV). ICD algorithms that included events with ‘uncertain’ intent had 4–70% PPV. The three best-performing algorithms had 74–92% PPV, with improved sensitivity compared with E-codes. Read code algorithms had 14–68% sensitivity and 0–56% PPV. Studies estimated 19–80% sensitivity for chart review, and 41–97% sensitivity and 100% PPV for vital records. Conclusions Pharmacoepidemiological studies measuring suicidal outcomes often use methodologies with poor sensitivity or predictive value or both, which may result in underestimation of associations between drugs and suicidal behaviour. Studies should validate outcomes or use a previously validated algorithm with high PPV and acceptable sensitivity in an appropriate population and data source.

Swain, Richard S.↗
DOE OSTI2015

Theoretical Synthesis of Mixed Materials for CO2 Capture Applications

These pages provide an example of the layout and style required for the preparation of four-page papers for the TechConnect World 2015 technical proceedings.Documents must be submitted in electronic (Adobe PDFfile) format. Please study the enclosed materials beforebeginning the final preparation of your paper. Proofread your paper carefully before submitting (it will appear in the published volume in exactly the same form). Your PDF manuscript must be uploaded online by April 11th, 2015.You will receive no proofs. Begin your paper with an abstract of no more than 18 lines. Thoroughly summarize your article in this section since this text will be used for on-line listing and classification of the publication.

provide up to five comma separated, keywords for i↗
DOE OSTI2018

PathRepHAN: Hierarchical attention networks for pathology report classification

Developers at ORNL explored how a deep learning (DL) approach based on hierarchical attention networks (HANs) can improve model performance for multiple information extraction tasks from unstructured cancer pathology reports compared to conventional methods that do not sufficiently capture syntactic and semantic contexts from free-text documents. The HAN was implemented for 2 information extraction tasks: (1) primary site, matched to 12 International Classification of Diseases for Oncology topography codes (7 breast, 5 lung primary sites), and (2) histological grade classification, matched to G1–G4. Our results demonstrate that for both information tasks, HAN performed significantly better compared to the conventional ML and DL techniques.

Ramanathan, Arvind↗
DOE OSTI2019

Selective Information Extraction Strategies for Cancer Pathology Reports with Convolutional Neural Networks

To trust model predictions, it is important to ensure new data scored by the model comes from the same population used for model training. If the model is used to score new data different than the model’s training data, then predictions and model performance metrics cannot be trusted. Identifying and excluding these anomalous data points is an important task when using models in the real world. Traditional machine learning algorithms and classifiers don’t have the capability to abstain in this case. Here we propose a data-novelty detection algorithm for the Convolutional Neural Network classifier, yielding a rejection score for each new data point scored. It is a post-modeling procedure which examines the distribution of convolution filters to determine if the prediction should be trusted. We apply this algorithm to an information extraction model for a natural language text corpus. We evaluated the algorithm performance using a primary cancer site classification model applied to cancer pathology reports. Results demonstrate that the algorithm is an effective way to exclude cancer pathology reports from model scoring when they do not contain the expected information necessary to accurately classify the primary cancer type.

Yoon, Hong-Jun↗
DOE OSTI2010

ParaText : scalable solutions for processing and searching very large document collections : final LDRD report.

This report is a summary of the accomplishments of the 'Scalable Solutions for Processing and Searching Very Large Document Collections' LDRD, which ran from FY08 through FY10. Our goal was to investigate scalable text analysis; specifically, methods for information retrieval and visualization that could scale to extremely large document collections. Towards that end, we designed, implemented, and demonstrated a scalable framework for text analysis - ParaText - as a major project deliverable. Further, we demonstrated the benefits of using visual analysis in text analysis algorithm development, improved performance of heterogeneous ensemble models in data classification problems, and the advantages of information theoretic methods in user analysis and interpretation in cross language information retrieval. The project involved 5 members of the technical staff and 3 summer interns (including one who worked two summers). It resulted in a total of 14 publications, 3 new software libraries (2 open source and 1 internal to Sandia), several new end-user software applications, and over 20 presentations. Several follow-on projects have already begun or will start in FY11, with additional projects currently in proposal.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2022

Towards Automatic Mapping of Vulnerabilities to Attack Patterns using Large Language Models

With the advent of new devices and applications, cyber attack surface is continuously evolving due to the emergence of new attack techniques and vulnerabilities. Hence, security management tool must assess the cyber risk of an enterprise at regular interval basis through comprehensively identifying associations among attack techniques, weakness, and vulnerabilities. However, existing repositories providing such associations are incomplete (i.e., missing associations), inducing the likelihood of undermining the risk of particular set of attack techniques. Moreover, such associations still rely on manual interpretation, which is slow compared to attack speed and ineffective for the increasing list of vulnerabilities and attack actions. Therefore, there is an urge to develop methodologies for automatically associating vulnerabilities to all relevant attack techniques. In this paper, we present a framework, named VWC-MAP, that can automatically identify all relevant attack techniques of a vulnerability via weakness based on their text descriptions, applying natural language process (NLP) techniques. To achieve that, we present a novel two-tiered classification approach, where the first tier classifies vulnerabilities to weakness, and the second tier classifies weakness to attack techniques. This research has improved the scalability of the current state-of-the-art tool to make vulnerability to weakness mapping significantly faster. Moreover, this paper presents two novel approaches for weakness to attack technique mapping applying Text-to-Text and link prediction techniques. Our experiment results cross-validated through cyber-security experts show that VWC-MAP can associate vulnerabilities to weakness types with 87% accuracy and to new attack patterns with 80% accuracy.

Das, Siddhartha Shankar↗
DOE OSTI2022

A meta-analysis of semantic classification of citations

The aim of this literature review is to examine the current state of the art in the area of citation classification. In particular, we investigate the approaches for characterizing citations based on their semantic type. We conduct this literature review as a meta-analysis covering 60 scholarly articles in this domain. Although we included some of the manual pioneering works in this review, more emphasis is placed on the later automated methods, which use Machine Learning and Natural Language Processing (NLP) for analyzing the fine-grained linguistic features in the surrounding text of citations. The sections are organized based on the steps involved in the pipeline for citation classification. Specifically, we explore the existing classification schemes, data sets, pre-processing methods, extraction of contextual and non-contextual features, and the different types of classifiers and evaluation approaches. The review highlights the importance of identifying the citation types for research evaluation, the challenges faced by the researchers in the process, and the existing research gaps in this field.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2023

Attention-Augmented Parametric Kernel Graph Neural Network (APKGNN) for Node Classification

We present a new graph neural network, the Attention-based Parametric-Kernel augmented Graph Neural Network (APKGNN), developed for node classification tasks. Despite extensive work on modeling multi-faceted relationships between connected nodes of a graph, the effect of attention on edge features mapped to relationships has not yet been analyzed through learning representation. This study derives such an attention vector by first calculating node features corresponding to endpoints of an edge and then aggregating these with extracted local intrinsic patches of a given graph to generate augmented local patch vectors. This process uses a parametric kernel based on Gaussian mixture models (GMMs) to embed local neighborhoods of the graph in local patches. The patch vectors then convolve with the above node features to produce an updated node representation. We show that this new learning representation (APKGNN) achieves higher node classification accuracy on tasks - both standard benchmarks (Cora, PubMed, Citeseer) and new experimental short text corpora where nodes correspond to text documents and words. This implementation of the GNN convolution layer outperforms state-of-the-art (SOTA) algorithms, achieving higher training, validation, and test accuracy by a significant margin on three standard benchmark data sets under both SOTA experimental settings and those for new testbeds.

Bose, Avishek↗
DOE OSTI2012

Managing the Drivers of Air Flow and Water Vapor Transport in Existing Single-Family Homes

This report is a revision of an earlier report titled: Measure Guideline: Managing the Drivers of Air Flow and Water Vapor Transport in Existing Single-Family Homes. Revisions include: Information in the text box on page 1 was revised to reflect the most accurate information regarding classifications as referenced in the 2012 International Residential Code. “Measure Guideline” was dropped from the title of the report. An addition was made to the reference list.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Leveraging large language models to automate the identification of healthcare access barriers for veterans

Objective: To develop and evaluate an automated system for identifying healthcare barriers focusing on transportation issues in veterans’ clinical notes using large language models (LLMs) and to assess the impact of different prompting strategies on classification performance and explanation consistency. Methods: We developed a hybrid system combining pattern matching for templated notes with LLM analysis for free-text notes. Using 2000 manually annotated clinical notes, we compared four prompting strategies (dual-role short, dual-role long, analysis-first, analysis-only) across Mistral-7B and Llama-3.1 models. We evaluated classification performance using standard metrics and assessed explanation consistency through embedding similarity analysis. Results: The analysis-first strategy achieved superior performance, with Mistral-7B reaching an F1 score of 0.914, outperforming traditional machine learning approaches (GBM: 0.786, BERT: 0.811). LLMs demonstrated higher explanation consistency within models (mean cosine similarity 0.887–0.908) compared to cross-model similarities (0.767–0.872). Pattern matching successfully handled 6.7% of templated notes deterministically. Mistral-7B showed greater internal consistency but higher abstention rates compared to Llama-3.1. Conclusion: Requiring LLMs to analyze evidence before classification improves both accuracy and explanation consistency for identifying transportation barriers in clinical notes. This approach enables automated barrier detection at scale while providing clinically relevant explanations, supporting both population-level healthcare planning and individual patient care decisions.

Healthcare access barriers↗