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 307 records · Page 17

What the Logs Can Tell You: Mediation to Implement Feedback in Training

The problem addressed by Mediation to Implement Feedback in Training (MIFT) is to customize the feedback from training exercizes by exploiting knowledge about the training scenario, training objectives, and specific student/teacher needs. We achieve this by inserting an intelligent mediation layer into the information flow from observations collected during training exercises to the display and user interface. Knowledge about training objectives, scenarios, and tasks is maintained in the mediating layer. A designer constraint is that domain experts must be able to extend mediators by adding domain-specific knowledge that supports additional aggregations, abstractions, and views of the results of training exercises. The MIFT mediation concept is intended to be integrated with existing military training exercise management tools and reduce the cost of developing and maintaining separate feedback and evaluation tools for every training simulator and every set of customer needs. The MIFT Architecture is designed as a set of independently reusable components which interact with each other through standardized formalisms such as the Knowledge Interchange Format (KIF) and Knowledge Query and Manipulation Language (KQML).

Maluf, David↗

KEBLM: Knowledge-Enhanced Biomedical Language Models

Pretrained language models (PLMs) have demonstrated strong performance on many natural language processing (NLP) tasks. Despite their great success, these PLMs are typically pretrained only on unstructured free texts without leveraging existing structured knowledge bases that are readily available for many domains, especially scientific domains. As a result, these PLMs may not achieve satisfactory performance on knowledge-intensive tasks such as biomedical NLP. Comprehending a complex biomedical document without domain-specific knowledge is challenging, even for humans. Inspired by this observation, we propose a general framework for incorporating various types of domain knowledge from multiple sources into biomedical PLMs. We encode domain knowledge using lightweight adapter modules, bottleneck feed-forward networks that are inserted into different locations of a backbone PLM. For each knowledge source of interest, we pretrain an adapter module to capture the knowledge in a self-supervised way. We design a wide range of self-supervised objectives to accommodate diverse types of knowledge, ranging from entity relations to description sentences. Once a set of pretrained adapters is available, we employ fusion layers to combine the knowledge encoded within these adapters for downstream tasks. Each fusion layer is a parameterized mixer of the available trained adapters that can identify and activate the most useful adapters for a given input. Our method diverges from prior work by including a knowledge consolidation phase, during which we teach the fusion layers to effectively combine knowledge from both the original PLM and newly-acquired external knowledge using a large collection of unannotated texts. After the consolidation phase, the complete knowledge-enhanced model can be fine-tuned for any downstream task of interest to achieve optimal performance. Extensive experiments on many biomedical NLP datasets show that our proposed framework consistently improves the performance of the underlying PLMs on various downstream tasks such as natural language inference, question answering, and entity linking. These results demonstrate the benefits of using multiple sources of external knowledge to enhance PLMs and the effectiveness of the framework for incorporating knowledge into PLMs. Finally, while primarily focused on the biomedical domain in this work, our framework is highly adaptable and can be easily applied to other domains, such as the bioenergy sector.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

An architecture for intelligent task interruption

In the design of real time systems the capability for task interruption is often considered essential. The problem of task interruption in knowledge-based domains is examined. It is proposed that task interruption can be often avoided by using appropriate functional architectures and knowledge engineering principles. Situations for which task interruption is indispensable, a preliminary architecture based on priority hierarchies is described.

Sharma, D. D.↗

Dynamic reasoning in a knowledge-based system

Any space based system, whether it is a robot arm assembling parts in space or an onboard system monitoring the space station, has to react to changes which cannot be foreseen. As a result, apart from having domain-specific knowledge as in current expert systems, a space based AI system should also have general principles of change. This paper presents a modal logic which can not only represent change but also reason with it. Three primitive operations, expansion, contraction and revision are introduced and axioms which specify how the knowledge base should change when the external world changes are also specified. Accordingly the notion of dynamic reasoning is introduced, which unlike the existing forms of reasoning, provide general principles of change. Dynamic reasoning is based on two main principles, namely minimize change and maximize coherence. A possible-world semantics which incorporates the above two principles is also discussed. The paper concludes by discussing how the dynamic reasoning system can be used to specify actions and hence form an integral part of an autonomous reasoning and planning system.

Rao, Anand S.↗

Development of a knowledge acquisition tool for an expert system flight status monitor

Two of the main issues in artificial intelligence today are knowledge acquisition dion and knowledge representation. The Dryden Flight Research Facility of NASA's Ames Research Center is presently involved in the design and implementation of an expert system flight status monitor that will provide expertise and knowledge to aid the flight systems engineer in monitoring today's advanced high-performance aircraft. The flight status monitor can be divided into two sections: the expert system itself and the knowledge acquisition tool. The knowledge acquisition tool, the means it uses to extract knowledge from the domain expert, and how that knowledge is represented for computer use is discussed. An actual aircraft system has been codified by this tool with great success. Future real-time use of the expert system has been facilitated by using the knowledge acquisition tool to easily generate a logically consistent and complete knowledge base.

Disbrow, J. D.↗

Development of a knowledge acquisition tool for an expert system flight status monitor

Two of the main issues in artificial intelligence today are knowledge acquisition and knowledge representation. The Dryden Flight Research Facility of NASA's Ames Research Center is presently involved in the design and implementation of an expert system flight status monitor that will provide expertise and knowledge to aid the flight systems engineer in monitoring today's advanced high-performance aircraft. The flight status monitor can be divided into two sections: the expert system itself and the knowledge acquisition tool. This paper discusses the knowledge acquisition tool, the means it uses to extract knowledge from the domain expert, and how that knowledge is represented for computer use. An actual aircraft system has been codified by this tool with great success. Future real-time use of the expert system has been facilitated by using the knowledge acquisition tool to easily generate a logically consistent and complete knowledge base.

Disbrow, J. D.↗

Aspect-Oriented Programming

Computer science has experienced an evolution in programming languages and systems from the crude assembly and machine codes of the earliest computers through concepts such as formula translation, procedural programming, structured programming, functional programming, logic programming, and programming with abstract data types. Each of these steps in programming technology has advanced our ability to achieve clear separation of concerns at the source code level. Currently, the dominant programming paradigm is object-oriented programming - the idea that one builds a software system by decomposing a problem into objects and then writing the code of those objects. Such objects abstract together behavior and data into a single conceptual and physical entity. Object-orientation is reflected in the entire spectrum of current software development methodologies and tools - we have OO methodologies, analysis and design tools, and OO programming languages. Writing complex applications such as graphical user interfaces, operating systems, and distributed applications while maintaining comprehensible source code has been made possible with OOP. Success at developing simpler systems leads to aspirations for greater complexity. Object orientation is a clever idea, but has certain limitations. We are now seeing that many requirements do not decompose neatly into behavior centered on a single locus. Object technology has difficulty localizing concerns invoking global constraints and pandemic behaviors, appropriately segregating concerns, and applying domain-specific knowledge. Post-object programming (POP) mechanisms that look to increase the expressiveness of the OO paradigm are a fertile arena for current research. Examples of POP technologies include domain-specific languages, generative programming, generic programming, constraint languages, reflection and metaprogramming, feature-oriented development, views/viewpoints, and asynchronous message brokering. (Czarneclu and Eisenecker s book includes a good survey of many of these technologies).

Elrad, Tzilla↗

Online Dectection and Modeling of Safety Boundaries for Aerospace Application Using Bayesian Statistics

The behavior of complex aerospace systems is governed by numerous parameters. For safety analysis it is important to understand how the system behaves with respect to these parameter values. In particular, understanding the boundaries between safe and unsafe regions is of major importance. In this paper, we describe a hierarchical Bayesian statistical modeling approach for the online detection and characterization of such boundaries. Our method for classification with active learning uses a particle filter-based model and a boundary-aware metric for best performance. From a library of candidate shapes incorporated with domain expert knowledge, the location and parameters of the boundaries are estimated using advanced Bayesian modeling techniques. The results of our boundary analysis are then provided in a form understandable by the domain expert. We illustrate our approach using a simulation model of a NASA neuro-adaptive flight control system, as well as a system for the detection of separation violations in the terminal airspace.

Statistics↗

Diagnosis by integrating model-based reasoning with knowledge-based reasoning

Our research investigates how observations can be categorized by integrating a qualitative physical model with experiential knowledge. Our domain is diagnosis of pathologic gait in humans, in which the observations are the gait motions, muscle activity during gait, and physical exam data, and the diagnostic hypotheses are the potential muscle weaknesses, muscle mistimings, and joint restrictions. Patients with underlying neurological disorders typically have several malfunctions. Among the problems that need to be faced are: the ambiguity of the observations, the ambiguity of the qualitative physical model, correspondence of the observations and hypotheses to the qualitative physical model, the inherent uncertainty of experiential knowledge, and the combinatorics involved in forming composite hypotheses. Our system divides the work so that the knowledge-based reasoning suggests which hypotheses appear more likely than others, the qualitative physical model is used to determine which hypotheses explain which observations, and another process combines these functionalities to construct a composite hypothesis based on explanatory power and plausibility. We speculate that the reasoning architecture of our system is generally applicable to complex domains in which a less-than-perfect physical model and less-than-perfect experiential knowledge need to be combined to perform diagnosis.

Bylander, Tom↗

Determining robot actions for tasks requiring sensor interaction

The performance of non-trivial tasks by a mobile robot has been a long term objective of robotic research. One of the major stumbling blocks to this goal is the conversion of the high-level planning goals and commands into the actuator and sensor processing controls. In order for a mobile robot to accomplish a non-trivial task, the task must be described in terms of primitive actions of the robot's actuators. Most non-trivial tasks require the robot to interact with its environment; thus necessitating coordination of sensor processing and actuator control to accomplish the task. The main contention is that the transformation from the high level description of the task to the primitive actions should be performed primarily at execution time, when knowledge about the environment can be obtained through sensors. It is proposed to produce the detailed plan of primitive actions by using a collection of low-level planning components that contain domain specific knowledge and knowledge about the available sensors, actuators, and sensor/actuator processing. This collection will perform signal and control processing as well as serve as a control interface between an actual mobile robot and a high-level planning system. Previous research has shown the usefulness of high-level planning systems to plan the coordination of activities such to achieve a goal, but none have been fully applied to actual mobile robots due to the complexity of interacting with sensors and actuators. This control interface is currently being implemented on a LABMATE mobile robot connected to a SUN workstation and will be developed such to enable the LABMATE to perform non-trivial, sensor-intensive tasks as specified by a planning system.

Budenske, John↗

GraphAide: Advanced Graph-Assisted Query and Reasoning System

Curating knowledge from multiple siloed sources that contain both structured and unstructured data is a major challenge in many real-world applications. Pattern matching and querying represent fundamental tasks in modern data analytics that leverage this curated knowledge. The development of such applications necessitates overcoming several research challenges, including data extraction, named entity recognition, data modeling, and designing query interfaces. Moreover, the explainability of these functionalities is critical for their broader adoption. The emergence of Large Language Models (LLMs) has accelerated the development lifecycle of new capabilities. Nonetheless, there is an ongoing need for domain-specific tools tailored to user activities. The creation of digital assistants has gained considerable traction in recent years, with LLMs offering a promising avenue to develop such assistants utilizing domain-specific knowledge and assumptions. In this context, we introduce an advanced query and reasoning system, GraphAide, which constructs a knowledge graph (KG) from diverse sources and allows to query and reason over the resulting KG. GraphAide harnesses both the KG and LLMs to rapidly develop domain-specific digital assistants. It integrates design patterns from retrieval augmented generation (RAG) and the semantic web to create an agentic LLM application. GraphAide underscores the potential for streamlined and efficient development of specialized digital assistants, thereby enhancing their applicability across various domains.

Purohit, Sumit [BATTELLE (PACIFIC NW LAB)] (ORCID:↗

Science Literacy Project, August 2006 - August 2008

Ball State University (BSU) was the recipient of a U.S. Department of Energy award to develop educational games teaching science and math. The Science Media Program will merge Ball State University’s nationally recognized capabilities in education, technology, and communication to develop new, interactive, game-based media for the teaching and learning of science and scientific principles for K-12 students. BSU established a team of educators, researchers, scientists, animators, designers, technology specialists, and hired a professional media developer company (Outside Source Design) from Indianapolis. After six months discussions and assessments the project team selected the following 8 games in Math, Physics, Chemistry, and Biology, 2 from each discipline. The assembled teams were innovative and unique. This new model of development and production included a process that integrated all needed knowledge and expertise for the development of high quality science and math games for K-12 students. This new model has potential to be used by others for the development of the educational games. The uniqueness of the model is to integrate domain experts’ knowledge with researchers/quality control group, and combine a professional development team from the game development company with the academic game development team from Computer Science and Art departments at Ball State University. The developed games went through feasibility tests with selected students for improvement before use in the research activities.

59 BASIC BIOLOGICAL SCIENCES↗

Solving the puzzle of Fe homeostasis by integrating molecular, mathematical, and societal models

To ensure optimal utilization and bioavailability, iron uptake, transport, subcellular localization, and assimilation are tightly regulated in plants. In this work, we examine recent advances in our understanding of cellular responses to Fe deficiency. We then use intracellular mechanisms of Fe homeostasis to discuss how formalizing cell biology knowledge via a mathematical model can advance discovery even when quantitative data is limited. Using simulation-based inference to identify plausible systems mechanisms that conform to known emergent phenotypes can yield novel, testable hypotheses to guide targeted experiments. However, this approach relies on the accurate encoding of domain-expert knowledge in exploratory mathematical models. We argue that this would be facilitated by fostering more “systems thinking” life scientists and that diversifying your research team may be a practical path to achieve that goal.

59 BASIC BIOLOGICAL SCIENCES↗

Methods and principles for determining task dependent interface content

Computer generated information displays provide a promising technology for offsetting the increasing complexity of the National Airspace System. To realize this promise, however, we must extend and adapt the domain-dependent knowledge that informally guides the design of traditional dedicated displays. In our view, the successful exploitation of computer generated displays revolves around the idea of information management, that is, the identification, organization, and presentation of relevant and timely information in a complex task environment. The program of research that is described leads to methods and principles for information management in the domain of commercial aviation. The multi-year objective of the proposed program of research is to develop methods and principles for determining task dependent interface content.

Shalin, Valerie L.↗

MOORE: A prototype expert system for diagnosing spacecraft problems

MOORE is a rule-based, prototype expert system that assists in diagnosing operational Tracking and Data Relay Satellite (TDRS) problems. It is intended to assist spacecraft engineers at the TDRS ground terminal in trouble shooting problems that are not readily solved with routine procedures, and without expert counsel. An additional goal of the prototype system is to develop in-house expert system and knowledge engineering skills. The prototype system diagnoses antenna pointing and earth pointing problems that may occur within the TDRS Attitude Control System (ACS). Plans include expansion to fault isolation of problems in the most critical subsystems of the TDRS spacecraft. Long term benefits are anticipated with use of an expert system during future TDRS programs with increased mission support time, reduced problem solving time, and retained expert knowledge and experience. Phase 2 of the project is intended to provide NASA the necessary expertise and capability to define requirements, evaluate proposals, and monitor the development progress of a highly competent expert system for NASA's Tracking Data Relay Satellite. Phase 2 also envisions addressing two unexplored applications for expert systems, spacecraft integration and tests (I and T) and support to launch activities. The concept, goals, domain, tools, knowledge acquisition, developmental approach, and design of the expert system. It will explain how NASA obtained the knowledge and capability to develop the system in-house without assistance from outside consultants. Future plans will also be presented.

Howlin, Katherine↗

Experimental mapping of soluble protein domains using a hierarchical approach

Exploring the function and 3D space of large multidomain protein targets often requires sophisticated experimentation to obtain the targets in a form suitable for structure determination. Screening methods capable of selecting well-expressed, soluble fragments from DNA libraries exist, but require the use of automation to maximize chances of picking a few good candidates. Here, we describe the use of an insertion dihydrofolate reductase (DHFR) vector to select in-frame fragments and a split-GFP assay technology to filter-out constructs that express insoluble protein fragments. With the incorporation of an IPCR step to create high density, focused sublibraries of fragments, this cost-effective method can be performed manually with no a priori knowledge of domain boundaries while permitting single amino acid resolution boundary mapping. We used it on the well-characterized p85a subunit of the phosphoinositide-3-kinase to demonstrate the robustness and efficiency of our methodology. We then successfully tested it onto the polyketide synthase PpsC from Mycobacterium tuberculosis, a potential drug target involved in the biosynthesis of complex lipids in the cell envelope. X-ray quality crystals from the acyl-transferase (AT), dehydratase (DH) and enoyl-reductase (ER) domains have been obtained.

59 BASIC BIOLOGICAL SCIENCES↗

The role of knowledge structures in fault diagnosis

The use of human memory and knowledge structures to direct fault diagnosis performance was investigated. The performances of 20 pilots with instrument flight ratings were studied in a fault diagnosis task. The pilots were read a scenario which described flight conditions under which the symptoms which are indicative of a problem were detected. They were asked to think out loud as they requested and interpreted various pieces of information to diagnose the cause of the problem. Only 11 of the 20 pilots successfully diagnosed the problem. Pilot performance on this fault diagnosis task was modeled in the use of domain specific knowledge organized in a frame system. Eighteen frames, with a common structure, were necessary to account for the data from all twenty subjects.

Smith, P. J.↗