Search NASA⌕ Search

SEARCH · Search NASA

Results for “Domain knowledge”

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 289 records · Page 16

NOUS: Construction and Querying of Dynamic Knowledge Graphs

The ability to construct domain specific knowledge graphs (KG) and perform question-answering or hypothesis generation is a trans- formative capability. Despite their value, automated construction of knowledge graphs remains an expensive technical challenge that is beyond the reach for most enterprises and academic institutions. We propose an end-to-end framework for developing custom knowl- edge graph driven analytics for arbitrary application domains. The uniqueness of our system lies A) in its combination of curated KGs along with knowledge extracted from unstructured text, B) support for advanced trending and explanatory questions on a dynamic KG, and C) the ability to answer queries where the answer is embedded across multiple data sources.

Choudhury, Sutanay↗

Knowledge-intensive software design systems: Can too much knowledge be a burden?

While acknowledging the considerable benefits of domain-specific, knowledge-intensive approaches to automated software engineering, it is prudent to carefully examine the costs of such approaches, as well. In adding domain knowledge to a system, a developer makes a commitment to understanding, representing, maintaining, and communicating that knowledge. This substantial overhead is not generally associated with domain-independent approaches. In this paper, I examine the downside of incorporating additional knowledge, and illustrate with examples based on our experiences building the SIGMA system. I also offer some guidelines for developers building domain-specific systems.

Keller, Richard M.↗

Knowledge-intensive software design systems: Can too much knowledge be a burden?

While acknowledging the considerable benefits of domain-specific, knowledge-intensive approaches to automated software engineering, it is prudent to carefully examine the costs of such approaches, as well. In adding domain knowledge to a system, a developer makes a commitment to understanding, representing, maintaining, and communicating that knowledge. This substantial overhead is not generally associated with domain-independent approaches. In this paper, I examine the downside of incorporating additional knowledge, and illustrate with examples based on our experience in building the SIGMA system. I also offer some guidelines for developers building domain-specific systems.

Keller, Richard M.↗

Articulation Management for Intelligent Integration of Information

When combining data from distinct sources, there is a need to share meta-data and other knowledge about various source domains. Due to semantic inconsistencies and heterogeneity of representations, problems arise in combining multiple domains when the domains are merged. The knowledge that is irrelevant to the task of interoperation will be included, making the result unnecessarily complex. This heterogeneity problem can be eliminated by mediating the conflicts and managing the intersections of the domains. For interoperation and intelligent access to heterogeneous information, the focus is on the intersection of the knowledge, since intersection will define the required articulation rules. An algebra over domain has been proposed to use articulation rules to support disciplined manipulation of domain knowledge resources. The objective of a domain algebra is to provide the capability for interrogating many domain knowledge resources, which are largely semantically disjoint. The algebra supports formally the tasks of selecting, combining, extending, specializing, and modifying Components from a diverse set of domains. This paper presents a domain algebra and demonstrates the use of articulation rules to link declarative interfaces for Internet and enterprise applications. In particular, it discusses the articulation implementation as part of a production system capable of operating over the domain described by the IDL (interface description language) of objects registered in multiple CORBA servers.

Maluf, David A.↗

Velo: A Knowledge Management Framework for Modeling and Simulation

Modern scientific enterprises are inherently knowledge-intensive. Scientific studies in domains such as geosciences, climate, and biology require the acquisition and manipulation of large amounts of experimental and field data to create inputs for large-scale computational simulations. The results of these simulations are then analyzed, leading to refinements of inputs and models and additional simulations. The results of this process must be managed and archived to provide justifications for regulatory decisions and publications that are based on the models. In this paper we introduce our Velo framework that is designed as a reusable, domain independent knowledge management infrastructure for modeling and simulation. Velo leverages, integrates and extends open source collaborative and content management technologies to create a scalable and flexible core platform that can be tailored to specific scientific domains. We describe the architecture of Velo for managing and associating the various types of data that are used and created in modeling and simulation projects, as well as the framework for integrating domain-specific tools. To demonstrate realizations of Velo, we describe examples from two deployed sites for carbon sequestration and climate modeling. These provide concrete example of the inherent extensibility and utility of our approach.

99 GENERAL AND MISCELLANEOUS↗

Deep Domain Adaptation based Cloud Type Detection using Active and Passive Satellite Data

Domain adaptation techniques have been developed to handle data from multiple sources or domains. Most existing domain adaptation models assume that source and target domains are homogeneous, i.e., they have the same feature space. Nevertheless, many real world applications often deal with data from heterogeneous domains that come from completely different feature spaces. In our remote sensing application, data in source domain (from an active spaceborne Lidar sensor CALIOP onboard CALIPSO satellite) contain 25 attributes, while data in target domain (from a passive spectroradiometer sensor VIIRS onboard Suomi-NPP satellite) contain 20 different attributes. CALIOP has better representation capability and sensitivity to aerosol types and cloud phase, while VIIRS has wide swaths and better spatial coverage but has inherent weakness in differentiating atmospheric objects on different vertical levels. To address this mismatch of features across the domains/sensors, we propose a novel end-to-end deep domain adaptation with domain mapping and correlation alignment (DAMA) to align the heterogeneous source and target domains in active and passive satellite remote sensing data. It can learn domain invariant representation from source and target domains by transferring knowledge across these domains, and achieve additional performance improvement by incorporating weak label information into the model (DAMA-WL). Our experiments on a collocated CALIOP and VIIRS dataset show that DAMA and DAMA-WL can achieve higher classification accuracy in predicting cloud types.

domain adaptation↗

The KASE approach to domain-specific software systems

Designing software systems, like all design activities, is a knowledge-intensive task. Several studies have found that the predominant cause of failures among system designers is lack of knowledge: knowledge about the application domain, knowledge about design schemes, knowledge about design processes, etc. The goal of domain-specific software design systems is to explicitly represent knowledge relevant to a class of applications and use it to partially or completely automate various aspects of the designing systems within that domain. The hope is that this would reduce the intellectual burden on the human designers and lead to more efficient software development. In this paper, we present a domain-specific system built on top of KASE, a knowledge-assisted software engineering environment being developed at the Stanford Knowledge Systems Laboratory. We introduce the main ideas underlying the construction of domain specific systems within KASE, illustrate the application of the idea in the synthesis of a system for tracking aircraft from radar signals, and discuss some of the issues in constructing domain-specific systems.

Bhansali, Sanjay↗

Description of research interests and current work related to automating software design

Enclosed is a list of selected and recent publications. Most of these publications concern applied research in the areas of software engineering and human-computer interaction. It is felt that domain-specific knowledge plays a major role in software development. Additionally, it is believed that improvements in the general software development process (e.g., object-oriented approaches) will have to be combined with the use of large domain-specific knowledge bases.

Kaindl, Hermann↗

Velo: Riding the Knowledge Management Wave for Simulation and Modeling

Modern scientific enterprises are inherently knowledge-intensive. In general, scientific studies in domains such as geosciences, climate, and biology require the acquisition and manipulation of large amounts of experimental and field data in order to create inputs for large-scale computational simulations. The results of these simulations must then be analyzed, leading to refinements of inputs and models and further simulations. Further, these results must be managed and archived to provide justifications for publications and regulatory decisions that are based on these models. In this paper we describe our Velo framework that is designed as a reusable, domain independent knowledge management infrastructure for modeling and simulation. Velo leverages, integrates, and extends open source collaborative and content management technologies to create a scalable and flexible core platform that can be tailored to specific scientific domains. In this paper we describe the architecture of Velo for managing and associating the various types of data that are used and created in modeling and simulation projects, as well as the framework for integrating domain-specific tools. To demonstrate a realization of Velo, we describe the Geologic Sequestration Software Suite (GS3) that has been developed to support geologic sequestration modeling. This provides a concrete example of the inherent extensibility and utility of our approach.

99 GENERAL AND MISCELLANEOUS↗

Knowledge and regularity in planning

The field of planning has focused on several methods of using domain-specific knowledge. The three most common methods, use of search control, use of macro-operators, and analogy, are part of a continuum of techniques differing in the amount of reused plan information. This paper describes TALUS, a planner that exploits this continuum, and is used for comparing the relative utility of these methods. We present results showing how search control, macro-operators, and analogy are affected by domain regularity and the amount of stored knowledge.

Allen, John A.↗

Problem solving with uncertain knowledge

Systems capable of expert level performance are built. The system represents domain-specific knowledge such as knowledge about geology, medicine, etc., and enables a process in which it uses such knowledge in an understandable line of reasoning. The MYCIN system, one example of such a system, is used as illustration.

Buchanan, B.↗

Implementation of a frame-based representation in CLIPS

Knowledge representation is one of the major concerns in expert systems. The representation of domain-specific knowledge should agree with the nature of the domain entities and their use in the real world. For example, architectural applications deal with objects and entities such as spaces, walls, and windows. A natural way of representing these architectural entities is provided by frames. This research explores the potential of using the expert system shell CLIPS, developed by NASA, to implement a frame-based representation that can accommodate architectural knowledge. These frames are similar but quite different from the 'template' construct in version 4.3 of CLIPS. Templates support only the grouping of related information and the assignment of default values to template fields. In addition to these features frames provide other capabilities including definition of classes, inheritance between classes and subclasses, relation of objects of different classes with 'has-a', association of methods (demons) of different types (standard and user-defined) to fields (slots), and creation of new fields at run-time. This frame-based representation is implemented completely in CLIPS. No change to the source code is necessary.

Assal, Hisham↗

Model-based software design

Domain-specific knowledge is required to create specifications, generate code, and understand existing systems. Our approach to automating software design is based on instantiating an application domain model with industry-specific knowledge and then using that model to achieve the operational goals of specification elicitation and verification, reverse engineering, and code generation. Although many different specification models can be created from any particular domain model, each specification model is consistent and correct with respect to the domain model.

Iscoe, Neil↗

Automated analysis of complex data

We have examined some of the issues involved in automating exploratory data analysis, in particular the tradeoff between control and opportunism. We have proposed an opportunistic planning solution for this tradeoff, and we have implemented a prototype, Igor, to test the approach. Our experience in developing Igor was surprisingly smooth. In contrast to earlier versions that relied on rule representation, it was straightforward to increment Igor's knowledge base without causing the search space to explode. The planning representation appears to be both general and powerful, with high level strategic knowledge provided by goals and plans, and the hooks for domain-specific knowledge are provided by monitors and focusing heuristics.

Saintamant, Robert↗

A Knowledge-Based System Developer for aerospace applications

A prototype Knowledge-Based System Developer (KBSD) has been developed for aerospace applications by utilizing artificial intelligence technology. The KBSD directly acquires knowledge from domain experts through a graphical interface then builds expert systems from that knowledge. This raises the state of the art of knowledge acquisition/expert system technology to a new level by lessening the need for skilled knowledge engineers. The feasibility, applicability , and efficiency of the proposed concept was established, making a continuation which would develop the prototype to a full-scale general-purpose knowledge-based system developer justifiable. The KBSD has great commercial potential. It will provide a marketable software shell which alleviates the need for knowledge engineers and increase productivity in the workplace. The KBSD will therefore make knowledge-based systems available to a large portion of industry.

Shi, George Z.↗

LLMs for Mfg.—On the State of Large Language Models and Applications to Manufacturing

Additive Manufacturing (AM), referred to as 3D printing, has emerged as a key pillar of Industry 4.0 enabling layer-by-layer fabrication of intricate geometries from CAD models. In parallel, Large Language Models (LLMs), deep learning models for natural language generation trained on vast text corpora, have demonstrated unprecedented capabilities in understanding and generating human-like text. The convergence of these trends opens new opportunities at the intersection of AM and AI/ML, where LLMs can assist engineers and researchers in design, manufacture planning, and knowledge discovery. Recent academic work has begun to explore LLM applications in AM and adjacent fields, such as material science, mechanical engineering, and design for additive manufacturing. This exploration ranges from intelligent process planning to domain-specific knowledge retrieval. This survey provides a comprehensive review of current developments, focusing on peer-reviewed literature contributions that apply, adapt, and advance LLMs in general and domain-specific domains. We analyze state-of-the-art (SOTA) techniques, such as fine-tuning foundational models for specific domains, retrieval-augmented generation (RAG) pipelines, knowledge graph integration, and delve into the architectures and evaluation methods employed. The goal of this survey is to inform researchers and practitioners of the current capabilities and limitations of LLMs in general and in domain-specific applications, and to outline how these models are being tailored to meet the requirements of these applications.

36 MATERIALS SCIENCE↗

Progress in knowledge representation research

Brief descriptions are given of research being carried out in the field of knowledge representation. Dynamic simulation and modelling of planning systems with real-time sensor inputs; development of domain-independent knowledge representation tools which can be used in the development of application-specific expert and planning systems; and development of a space-borne very high speed integrated circuit processor are among the projects discussed.

Lum, Henry↗