Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “information extraction”

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 37 records · Page 2

Task 7: Image Enhancement and Advanced Information Extraction Techniques, 1385

The author has identified the following significant results. Atmospheric effects in satellite multispectral scanner data can influence results obtained with either manual image interpretation or computer information extraction techniques. The atmosphere attenuates radiation arriving from the surface and adds an extraneous path radiance component. Initial results of an investigation of atmospheric effects in ERTS-1 data are presented. Empirical analyses of ERTS-1 MSS data and simultaneous airborne MSS underflight data for one frame, along with theoretical calculations of atmospheric effects, are discussed. The effect of limited spatial resolution on the accuracy of information extracted from ERTS-1 data also is important. Problems occur when individual resolution elements contain two or more materials. Results from an initial application of Environmental Research Institute of Michigan techniques for estimating proportions of materials within individual elements are presented and discussed. Very accurate determination of surface areas of small lakes is achieved.

Malila, W. A.↗

Optimal vocabulary selection approaches for privacy-preserving deep NLP model training for information extraction and cancer epidemiology

With the use of artificial intelligence and machine learning techniques for biomedical informatics, security and privacy concerns over the data and subject identities have also become an important issue and essential research topic. Without intentional safeguards, machine learning models may find patterns and features to improve task performance that are associated with private personal information. The privacy vulnerability of deep learning models for information extraction from medical textural contents needs to be quantified since the models are exposed to private health information and personally identifiable information. The objective of the study is to quantify the privacy vulnerability of the deep learning models for natural language processing and explore a proper way of securing patients’ information to mitigate confidentiality breaches. The target model is the multitask convolutional neural network for information extraction from cancer pathology reports, where the data for training the model are from multiple state population-based cancer registries. This study proposes the following schemes to collect vocabularies from the cancer pathology reports; (a) words appearing in multiple registries, and (b) words that have higher mutual information. We performed membership inference attacks on the models in high-performance computing environments. The comparison outcomes suggest that the proposed vocabulary selection methods resulted in lower privacy vulnerability while maintaining the same level of clinical task performance.

59 BASIC BIOLOGICAL SCIENCES↗

Detailed design specification for the ALT Shuttle Information Extraction Subsystem (SIES)

The approach and landing test (ALT) shuttle information extraction system (SIES) is described in terms of general requirements and system characteristics output products and processing options, output products and data sources, and system data flow. The ALT SIES is a data reduction system designed to satisfy certain data processing requirements for the ALT phase of the space shuttle program. The specific ALT SIES data processing requirements are stated in the data reduction complex approach and landing test data processing requirements. In general, ALT SIES must produce time correlated data products as a result of standardized data reduction or special purpose analytical processes. The main characteristics of ALT SIES are: (1) the system operates in a batch (non-interactive) mode; (2) the processing is table driven; (3) it is data base oriented; (4) it has simple operating procedures; and (5) it requires a minimum of run time information.

Clouette, G. L.↗

Information extraction and transmission techniques for spaceborne synthetic aperture radar images

Information extraction and transmission techniques for synthetic aperture radar (SAR) imagery were investigated. Four interrelated problems were addressed. An optimal tonal SAR image classification algorithm was developed and evaluated. A data compression technique was developed for SAR imagery which is simple and provides a 5:1 compression with acceptable image quality. An optimal textural edge detector was developed. Several SAR image enhancement algorithms have been proposed. The effectiveness of each algorithm was compared quantitatively.

Frost, V. S.↗

Information Extraction from Cancer Pathology Reports with Graph Convolution Networks for Natural Language Texts

Graph-of-words is a flexible and efficient text representation which addresses well-known challenges, such as word ordering and variation of expressions, to natural language processing. In this paper, we consider the latest graph-based convolutional neural network technique, the Text Graph Convolutional Network (Text GCN), in the context of performing classification tasks on free-form natural language texts. To do this, we designed a study of multi-task information extraction from medical text documents. We implemented multi-task learning in the Text GCN, performed hyperparameter optimization, and measured the clinical task performances. We evaluated micro and macro-F1 scores of four information extraction tasks, including subsite, laterality, behavior, and histological grades from cancer pathology reports. The scores for the Text GCN significantly outperformed our previous studies with convolutional neural networks, suggesting that the Text GCN model is superior to traditional models in task performance.

Yoon, Hong-Jun↗

Information extraction techniques for multi-spectral scanner data

Multispectral data recognition and information extraction problems considered are: (1) signature extension for improved recognition processing over large areas; (2) choice of density functions for recognition decision rules; (3) channel selection for cost reduction; and (4) radiation balance mapping for interpretation of wide spectrum scanner data. The formulation of a simulation model and reprocessing of both aircraft and space data reduces scan angle variations and extends signatures from one altitude to another. Comparison of the usefulness of empirical density functions and that of Gaussian density functions for recognition processing establishes the advantages of normal assumption for individual fields in processing of multispectral scanner data. Also reported is a procedure for producing radiation balance maps from wide spectra by analyzing energy budgets of vegetation and other surface materials through partitioning net absorbed radiant energy and estimating incoming power density at both short and long wavelengths.

Malila, W. A.↗

Question-answering system extracts information on injection drug use from clinical notes

Background. Injection drug use (IDU) can increase mortality and morbidity. Therefore, identifying IDU early and initiating harm reduction interventions can benefit individuals at risk. However, extracting IDU behaviors from patients’ electronic health records (EHR) is difficult because there is no other structured data available, such as International Classification of Disease (ICD) codes, and IDU is most often documented in unstructured free-text clinical notes. Although natural language processing can efficiently extract this information from unstructured data, there are no validated tools. Methods. Here, to address this gap in clinical information, we design a question-answering (QA) framework to extract information on IDU from clinical notes for use in clinical operations. Our framework involves two main steps: (1) generating a gold-standard QA dataset and (2) developing and testing the QA model. We use 2323 clinical notes of 1145 patients curated from the US Department of Veterans Affairs (VA) Corporate Data Warehouse to construct the gold-standard dataset for developing and evaluating the QA model. We also demonstrate the QA model’s ability to extract IDU-related information from temporally out-of-distribution data. Results. Here, we show that for a strict match between gold-standard and predicted answers, the QA model achieves a 51.65% F1 score. For a relaxed match between the gold-standard and predicted answers, the QA model obtains a 78.03% F1 score, along with 85.38% Precision and 79.02% Recall scores. Moreover, the QA model demonstrates consistent performance when subjected to temporally out-of-distribution data. Conclusions. Our study introduces a QA framework designed to extract IDU information from clinical notes, aiming to enhance the accurate and efficient detection of people who inject drugs, extract relevant information, and ultimately facilitate informed patient care.

60 APPLIED LIFE SCIENCES↗

Cybersecurity Automated Information Extraction Techniques: Drawbacks of Current Methods, and Enhanced Extractors

We address a crucial element of applied information extraction—accurate identification of basic security entities in text-—by evaluating previous methods and presenting new labelers. Our survey reveals that the previous efforts have not been tested on documents similar to the targeted sources (news articles, blogs, tweets, etc.) and that no sufficiently large publicly available annotated corpus of these documents exists. By assembling a representative test corpus, we perform a quantitative evaluation of previous methods in a realistic setting, revealing an overall lack of recall, and giving insight to the models' beneficial and inhibiting elements. In particular, our results show that many previous efforts overfit to the non-representative test corpora in this domain. Informed by this evaluation, we present three novel cyber entity extractors, which seek to leverage the available labeled data but remain worthwhile on the more diverse documents encountered in the wild. Each new model increases the state of the art in recall, with maximal or near maximal F1 score. Our results establish that the state of the art in cyber entity tagging is characterized by F1 = 0.61.

Bridges, Robert↗

Extracting information from X-ray diffraction patterns containing Laue oscillations

The presence of Laue oscillations in a film grown on a solid surface is broadly taken as indicating a high quality, crystallographically aligned film of the targeted compound. In this paper we briefly review the origins of both Laue oscillations and Kiessig fringes and show how they can be used together to determine if extra thickness exists above or below the coherently diffracting domains. The differences between experimental and “ideal” films are discussed and the effect of structural features (roughness, different thickness coherently diffracting domains and thickness in addition to the coherently diffracting domains) are illustrated with experimental and simulated data for metal and mixed-metal chalcogenide films of titanium, bismuth, vanadium/iron, and bismuth/molybdenum. Examples are given showing how quantitative information can be extracted from experimental diffraction patterns.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Information Extraction for System-Software Safety Analysis: Calendar Year 2008 Year-End Report

This annual report describes work to integrate a set of tools to support early model-based analysis of failures and hazards due to system-software interactions. The tools perform and assist analysts in the following tasks: 1) extract model parts from text for architecture and safety/hazard models; 2) combine the parts with library information to develop the models for visualization and analysis; 3) perform graph analysis and simulation to identify and evaluate possible paths from hazard sources to vulnerable entities and functions, in nominal and anomalous system-software configurations and scenarios; and 4) identify resulting candidate scenarios for software integration testing. There has been significant technical progress in model extraction from Orion program text sources, architecture model derivation (components and connections) and documentation of extraction sources. Models have been derived from Internal Interface Requirements Documents (IIRDs) and FMEA documents. Linguistic text processing is used to extract model parts and relationships, and the Aerospace Ontology also aids automated model development from the extracted information. Visualizations of these models assist analysts in requirements overview and in checking consistency and completeness.

Malin, Jane T.↗

Automatic information extraction for land use and agricultural applications

Description of some current work in interpretation technique development for automatic computer-aided image information extraction related to various application areas, including land use mapping and agricultural survey and monitoring. In particular, the application of a fast template matching algorithm, employing the sequential similarity detection principle, to image registration, linear feature detection, and the extraction and enumeration of scene objects is discussed and illustrated.

Bond, A. D.↗

Information extraction from digital images of the earth and the planets

An overview is presented of recent developments at the JPL Image Processing Laboratory which emphasize the utilization of a digital computer to automate the process of information extraction from digital imagery. Consideration is given to: (1) the analysis of Viking Orbiter stereo imagery to determine elevation profiles of the Mars surface, (2) the use of Viking Lander stereo imagery to determine nonhazardous surface sample acquisition strategies, (3) the correlation of Landsat imagery with geographically referenced cultural data to determine land use trends, and (4) the generation of mosaics using digital computer techniques.

Green, W. B.↗

Structured information extraction from scientific text with large language models

Extracting structured knowledge from scientific text remains a challenging task for machine learning models. Here, we present a simple approach to joint named entity recognition and relation extraction and demonstrate how pretrained large language models (GPT-3, Llama-2) can be fine-tuned to extract useful records of complex scientific knowledge. We test three representative tasks in materials chemistry: linking dopants and host materials, cataloging metal-organic frameworks, and general composition/phase/morphology/application information extraction. Records are extracted from single sentences or entire paragraphs, and the output can be returned as simple English sentences or a more structured format such as a list of JSON objects. This approach represents a simple, accessible, and highly flexible route to obtaining large databases of structured specialized scientific knowledge extracted from research papers.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Model-based Hyperparameter Optimization of Convolutional Neural Networks for Information Extraction from Cancer Pathology Reports on HPC

Finding optimal hyperparameters is necessary to identify the best performing deep learning models but the process is costly. In this paper, we applied model-based optimization, also known as Bayesian optimization, using the CANDLE framework implemented on a High-Performance Computing environment. As a use case we selected information extraction from cancer pathology reports using a multi-task convolutional neural network, and hierarchical convolutional attention network to be optimized. We utilized a synthesized text corpus of 8,000 training cases and 2,000 validation cases with four types of clinical task labels including primary cancer site, laterality, behavior, and histological grade. We demonstrated that hyperparameter optimization using the CANDLE framework is a feasible approach with respect to both scalability and clinical task performance.

Yoon, Hong-Jun↗

Digital image processing for information extraction.

The modern digital computer has made practical image processing techniques for handling nonlinear operations in both the geometrical and the intensity domains, various types of nonuniform noise cleanup, and the numerical analysis of pictures. An initial requirement is that a number of anomalies caused by the camera (e.g., geometric distortion, MTF roll-off, vignetting, and nonuniform intensity response) must be taken into account or removed to avoid their interference with the information extraction process. Examples illustrating these operations are discussed along with computer techniques used to emphasize details, perform analyses, classify materials by multivariate analysis, detect temporal differences, and aid in human interpretation of photos.

Billingsley, F. C.↗

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↗

Addressing quantum’s “fine print” with efficient state preparation and information extraction for quantum algorithms and geologic fracture networks

Abstract Quantum algorithms provide an exponential speedup for solving certain classes of linear systems, including those that model geologic fracture flow. However, this revolutionary gain in efficiency does not come without difficulty. Quantum algorithms require that problems satisfy not only algorithm-specific constraints, but also application-specific ones. Otherwise, the quantum advantage carefully attained through algorithmic ingenuity can be entirely negated. Previous work addressing quantum algorithms for geologic fracture flow has illustrated core algorithmic approaches while incrementally removing assumptions. This work addresses two further requirements for solving geologic fracture flow systems with quantum algorithms: efficient system state preparation and efficient information extraction. Our approach to addressing each is consistent with an overall exponential speed-up.

58 GEOSCIENCES↗