SEARCH · Engineering Papers

Results for “Information Automation”

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 37 records · Page 2

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Using ensembles and distillation to optimize the deployment of deep learning models for the classification of electronic cancer pathology reports

One of the goals of the Surveillance, Epidemiology, and End Results (SEER) program is to estimate incidence, prevalence, and mortality of all cancers. To that end, cancer registries across the country maintain a massive database of cancer pathology reports which contain rich information to understand cancer trends. However, these reports are stored in the form of unstructured text, and human annotators are required to read and extract relevant information. In this article, we show that existing deep learning models for automating information extraction from cancer pathology reports can be significantly improved by using ensemble model distillation. We found that by training multiple predictive models and transferring their knowledge to a single, low-resource model, we can reduce the number of highly confident wrong predictions. Our results show that our implemented methods could save 1000s of manual annotation hours.

60 APPLIED LIFE SCIENCES↗

NASA NTRS1990

Management of information in a research and development agency

The NASA program for managing scientific and technical information (STI) is examined, noting the technological, managerial, educational, and legal aspects of transferring and disseminating information. A definition of STI is introduced and NASA's STI-related management programs are outlined. Consideration is given to the role of STI management in NASA mission programs, research efforts supporting the management and use of STI, STI program interfaces, and the Automated Information Management Program to eliminate redundant automation efforts in common administrative functions. The infrastructure needed to manage the broad base of NASA information and the interfaces between NASA's STI management and external organizations are described.

Keene, Wallace O.↗

NASA NTRS1990

Management of information in a research and development agency

Keene, Wallace O.↗

NASA NTRS2000

A Distributed Multi-Agent System for Collaborative Information Management and Learning

In this paper, we present DIAMS, a system of distributed, collaborative agents to help users access, manage, share and exchange information. A DIAMS personal agent helps its owner find information most relevant to current needs. It provides tools and utilities for users to manage their information repositories with dynamic organization and virtual views. Flexible hierarchical display is integrated with indexed query search-to support effective information access. Automatic indexing methods are employed to support user queries and communication between agents. Contents of a repository are kept in object-oriented storage to facilitate information sharing. Collaboration between users is aided by easy sharing utilities as well as automated information exchange. Matchmaker agents are designed to establish connections between users with similar interests and expertise. DIAMS agents provide needed services for users to share and learn information from one another on the World Wide Web.

Chen, James R.↗

NASA NTRS1988

IDEAL: A methology for developing information systems

As a result of improved capabilities obtained through current computer technologies, application programs and expert systems, Enterprises are being designed or upgraded to be highly integrated and automated information systems. To design or modify Enterprises, it is necessary to first define what functions are to be performed within the Enterprise, identify which functions are potential candidates for automation, and what automated or expert systems are available, or must be developed, to accomplish the selected function. Second, it is necessary to define and analyze the informational requirements for each function along with the informational relationships among the functions so that a database structure can be established to support the Enterprise. To perform this type of system design, an integrated set of analysis tools is required to support the information analysis process. The IDEAL (Integrated Design and Engineering Analysis Languages) methodology provides this integrated set of tools and is discussed.

Evers, Ken H.↗

NASA NTRSDate not supplied

Managing the Digital Thread for Structural Applications With Fit for Purpose Materials

With the increased emphasis on reducing the cost and time to market of new materials, the need for analytical tools that enable the virtual design and optimization of materials throughout their processing - internal structure - property - performance envelope, along with the capturing and storing of the associated material and model information across its lifecycle, has become critical. This need is also fueled by the demands for higher efficiency in material testing; consistency, quality and traceability of data; product design; engineering analysis; as well as control of access to proprietary or sensitive information. Consequently, at NASA Glenn Research Center a robust information management system that manages the digital thread across the full material life (i.e., capture, analysis, maintenance, and dissemination of data) cycle directed at the design of ‘fit-for-purpose materials’ is under development. To this end the Application Table has been incorporated within NASA Glenn Research Center’s ICME Information Management framework within the ANSYS Granta MI tool. The Application Table provides a place where material and structural application information/requirements can be linked to marry the “design-the-material” (structural engineering) and the “design-with-material” (material science) paradigms and thereby enable application-driven design and optimization of materials and structures. In additional several associated toolsets, specifically: AIMAOS (Automated Information Management Across Organizations and Scales), Py MILab, and JARIMIS (Just A Rather Intelligent Material Interrogation System) are also under development to assist in the judicious automation of this process. AIMOAS offers users an interactive graphical user interface for connecting material information management systems with both commercial and in-house simulation tools at various length scales to enable such automation in the handoff across scales and maintenance of material digital twins and the digital thread. Py MILab, is an automatic framework for the capture, analysis, maintenance, and storage of material test data. Py MILab uses a modular approach for capturing raw data, analyzing the data, and storing the data in a database, interfaced by neutral file structures, to promote plug-and-play capabilities for various analysis types. Finally, JARIMIS is an expert system that integrates various materials informatics tools (e.g., MicroNet, Surrogate ML models, ANSYS Granta MI, etc.) to enable inverse design of materials and facilitate the application of machine learning (ML) and data science with human in the loop decision making to rapidly discover and optimize new materials.

Digital Transformation↗

NASA NTRS1994

Interviews with the Apollo lunar surface astronauts in support of planning for EVA systems design

Focused interviews were conducted with the Apollo astronauts who landed on the moon. The purpose of these interviews was to help define extravehicular activity (EVA) system requirements for future lunar and planetary missions. Information from the interviews was examined with particular attention to identifying areas of consensus, since some commonality of experience is necessary to aid in the design of advanced systems. Results are presented under the following categories: mission approach; mission structure; suits; portable life support systems; dust control; gloves; automation; information, displays, and controls; rovers and remotes; tools; operations; training; and general comments. Research recommendations are offered, along with supporting information.

Connors, Mary M.↗

DOE OSTI2024

Path-BigBird: An AI-Driven Transformer Approach to Classification of Cancer Pathology Reports

PURPOSE Surgical pathology reports are critical for cancer diagnosis and management. To accurately extract information about tumor characteristics from pathology reports in near real time, we explore the impact of using domain-specific transformer models that understand cancer pathology reports. METHODS We built a pathology transformer model, Path-BigBird, by using 2.7 million pathology reports from six SEER cancer registries. We then compare different variations of Path-BigBird with two less computationally intensive methods: Hierarchical Self-Attention Network (HiSAN) classification model and an offthe-shelf clinical transformer model (Clinical BigBird). We use five pathology information extraction tasks for evaluation: site, subsite, laterality, histology, and behavior. Model performance is evaluated by using macro and micro F 1 scores. RESULTS We found that Path-BigBird and Clinical BigBird outperformed the HiSAN in all tasks. Clinical BigBird performed better on the site and laterality tasks. Versions of the Path-BigBird model performed best on the two most difficult tasks: subsite (micro F 1 score of 72.53, macro F 1 score of 35.76) and histology (micro F 1 score of 80.96, macro F 1 score of 37.94). The largest performance gains over the HiSAN model were for histology, for which a Path-BigBird model increased the micro F 1 score by 1.44 points and the macro F 1 score by 3.55 points. Overall, the results suggest that a Path-BigBird model with a vocabulary derived from wellcurated and deidentified data is the best-performing model. CONCLUSION The Path-BigBird pathology transformer model improves automated information extraction from pathology reports. Although Path-BigBird outperforms Clinical BigBird and HiSAN, these less computationally expensive models still have utility when resources are constrained.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2023

Deep learning uncertainty quantification for clinical text classification

Machine learning algorithms are expected to work side-by-side with humans in decision-making pipelines. Thus, the ability of classifiers to make reliable decisions is of paramount importance. Deep neural networks (DNNs) represent the state-of-the-art models to address real-world classification. Although the strength of activation in DNNs is often correlated with the network’s confidence, in-depth analyses are needed to establish whether they are well calibrated. In this paper, we demonstrate the use of DNN-based classification tools to benefit cancer registries by automating information extraction of disease at diagnosis and at surgery from electronic text pathology reports from the US National Cancer Institute (NCI) Surveillance, Epidemiology, and End Results (SEER) population-based cancer registries. In particular, we introduce multiple methods for selective classification to achieve a target level of accuracy on multiple classification tasks while minimizing the rejection amount—that is, the number of electronic pathology reports for which the model’s predictions are unreliable. We evaluate the proposed methods by comparing our approach with the current in-house deep learning-based abstaining classifier. Overall, all the proposed selective classification methods effectively allow for achieving the targeted level of accuracy or higher in a trade-off analysis aimed to minimize the rejection rate. On in-distribution validation and holdout test data, with all the proposed methods, we achieve on all tasks the required target level of accuracy with a lower rejection rate than the deep abstaining classifier (DAC). Interpreting the results for the out-of-distribution test data is more complex; nevertheless, in this case as well, the rejection rate from the best among the proposed methods achieving 97% accuracy or higher is lower than the rejection rate based on the DAC. We show that although both approaches can flag those samples that should be manually reviewed and labeled by human annotators, the newly proposed methods retain a larger fraction and do so without retraining—thus offering a reduced computational cost compared with the in-house deep learning-based abstaining classifier.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

First Impressions: Early-time Classification of Supernovae Using Host-galaxy Information and Shallow Learning

Substantial effort has been devoted to the characterization of transient phenomena from photometric information. Automated approaches to this problem have taken advantage of complete phase coverage of an event, limiting their use for triggering rapid follow-up of ongoing phenomena. In this work, we introduce a neural network with a single recurrent layer designed explicitly for early photometric classification of supernovae (SNe). Our algorithm leverages transfer learning to account for model misspecification, host-galaxy photometry to solve the data-scarcity problem soon after discovery, and a custom weighted loss to prioritize accurate early classification. We first train our algorithm using state-of-the-art transient and host-galaxy simulations, then adapt its weights and validate it on the spectroscopically confirmed SNe Ia, SNe II, and SNe Ib/c from the Zwicky Transient Facility Bright Transient Survey. On observed data, our method achieves an overall accuracy of 82% ± 2% within 3 days of an event’s discovery, and an accuracy of 87% ± 5% within 30 days of discovery. At both early and late phases, our method achieves comparable or superior results to the leading classification algorithms with a simpler network architecture. These results help pave the way for rapid photometric and spectroscopic follow-up of scientifically valuable transients discovered in massive synoptic surveys.

79 ASTRONOMY AND ASTROPHYSICS↗

NASA NTRS1982

Research in satellite-aided crop inventory and monitoring

Automated information extraction procedures for analysis of multitemporal LANDSAT data in non-U.S. crop inventory and monitoring are reviewed. Experiments to develope and evaluate crop area estimation technologies for spring small grains, summer crops, corn, and soybeans are discussed.

Erickson, J. D.↗

NASA NTRS1982

Research in satellite-aided crop inventory and monitoring

Automated information extraction procedures for analysis of multitemporal Landsat data in non-U.S. crop inventory and monitoring are reviewed. Experiments to develop and evaluate crop area estimation technologies for spring small grains, summer crops, corn, and soybeans are discussed. Previously announced in STAR as N82-32793

Erickson, J. D.↗

NASA NTRS1989

Continuation of research in software for space operations support

Software technologies relevant to workstation executives are discussed. Evaluations of problems, potential or otherwise, seen with IBM's Workstation Executive (WEX) 2.5 preliminary design and applicable portions of the 2.5 critical design are presented. Diverse graphics requirements of the Johnson Space Center's Mission Control Center Upgrade (MCCU) are also discussed. The key is to use tools that are portable, compatible with the X window system, and best suited to the requirements of the associated application. This will include a User Interface Language (UIL), an interactive display builder, and a graphic plotting/modeling system. Work sheets are provided for POSIX 1003.4 real-time extensions and the requirements for the Center's automated information systems security plan, referred to as POSIX 1003.6, are discussed.

Collier, Mark D.↗

NASA NTRS1990

Weather data dissemination to aircraft

Documentation exists that shows weather to be responsible for approximately 40 percent of all general aviation accidents with fatalities. Weather data products available on the ground are becoming more sophisticated and greater in number. Although many of these data are critical to aircraft safety, they currently must be transmitted verbally to the aircraft. This process is labor intensive and provides a low rate of information transfer. Consequently, the pilot is often forced to make life-critical decisions based on incomplete and outdated information. Automated transmission of weather data from the ground to the aircraft can provide the aircrew with accurate data in near-real time. The current National Airspace System Plan calls for such an uplink capability to be provided by the Mode S Beacon System data link. Although this system has a very advanced data link capability, it will not be capable of providing adequate weather data to all airspace users in its planned configuration. This paper delineates some of the important weather data uplink system requirements, and describes a system which is capable of meeting these requirements. The proposed system utilizes a run-length coding technique for image data compression and a hybrid phase and amplitude modulation technique for the transmission of both voice and weather data on existing aeronautical Very High Frequency (VHF) voice communication channels.

Mcfarland, Richard H.↗

NASA NTRS1991

Heterogeneous distributed databases: A case study

Alternatives are reviewed for accessing distributed heterogeneous databases and a recommended solution is proposed. The current study is limited to the Automated Information Systems Center at the Naval Sea Combat Systems Engineering Station at Norfolk, VA. This center maintains two databases located on Digital Equipment Corporation's VAX computers running under the VMS operating system. The first data base, ICMS, resides on a VAX11/780 and has been implemented using VAX DBMS, a CODASYL based system. The second database, CSA, resides on a VAX 6460 and has been implemented using the ORACLE relational database management system (RDBMS). Both databases are used for configuration management within the U.S. Navy. Different customer bases are supported by each database. ICMS tracks U.S. Navy ships and major systems (anti-sub, sonar, etc.). Even though the major systems on ships and submarines have totally different functions, some of the equipment within the major systems are common to both ships and submarines.

Stewart, Tracy R.↗

NASA NTRS1990

Space Station Freedom - Configuration management approach to supporting concurrent engineering and total quality management

Some experiences of NASA configuration management in providing concurrent engineering support to the Space Station Freedom program for the achievement of life cycle benefits and total quality are discussed. Three change decision experiences involving tracing requirements and automated information systems of the electrical power system are described. The potential benefits of concurrent engineering and total quality management include improved operational effectiveness, reduced logistics and support requirements, prevention of schedule slippages, and life cycle cost savings. It is shown how configuration management can influence the benefits attained through disciplined approaches and innovations that compel consideration of all the technical elements of engineering and quality factors that apply to the program development, transition to operations and in operations. Configuration management experiences involving the Space Station program's tiered management structure, the work package contractors, international partners, and the participating NASA centers are discussed.

Gavert, Raymond B.↗

NASA NTRS1991

Quality and security - They work together

This paper describes the importance of considering computer security as part of software quality assurance practice. The intended audience is primarily those professionals involved in the design, development, and quality assurance of software. Many issues are raised which point to the need ultimately for integration of quality assurance and computer security disciplines. To address some of the issues raised, the NASA Automated Information Security program is presented as a model which may be used for improving interactions between the quality assurance and computer security community of professionals.

Carr, Richard↗

NASA NTRS1991

Analysis of methods

Information is one of an organization's most important assets. For this reason the development and maintenance of an integrated information system environment is one of the most important functions within a large organization. The Integrated Information Systems Evolution Environment (IISEE) project has as one of its primary goals a computerized solution to the difficulties involved in the development of integrated information systems. To develop such an environment a thorough understanding of the enterprise's information needs and requirements is of paramount importance. This document is the current release of the research performed by the Integrated Development Support Environment (IDSE) Research Team in support of the IISEE project. Research indicates that an integral part of any information system environment would be multiple modeling methods to support the management of the organization's information. Automated tool support for these methods is necessary to facilitate their use in an integrated environment. An integrated environment makes it necessary to maintain an integrated database which contains the different kinds of models developed under the various methodologies. In addition, to speed the process of development of models, a procedure or technique is needed to allow automatic translation from one methodology's representation to another while maintaining the integrity of both. The purpose for the analysis of the modeling methods included in this document is to examine these methods with the goal being to include them in an integrated development support environment. To accomplish this and to develop a method for allowing intra-methodology and inter-methodology model element reuse, a thorough understanding of multiple modeling methodologies is necessary. Currently the IDSE Research Team is investigating the family of Integrated Computer Aided Manufacturing (ICAM) DEFinition (IDEF) languages IDEF(0), IDEF(1), and IDEF(1x), as well as ENALIM, Entity Relationship, Data Flow Diagrams, and Structure Charts, for inclusion in an integrated development support environment.

Mayer, Richard J.↗