SEARCH · Search NASA
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.
Debates about the selection of programming languages often produce cultural collisions that are not easily resolved. This is especially true in the case of Ada and knowledge based programming. The construction of programming tools provides a desirable alternative for resolving the conflict.
The underlying hypothesis of this work is that a rigorous and comprehensive software reuse methodology can bring about a more effective and efficient utilization of constrained resources in the development of large-scale software systems by both government and industry. It is also believed that correct use of this type of software engineering methodology can significantly contribute to the higher levels of reliability that will be required of future operational systems. An overview and discussion of current research in the development and application of two systems that support a rigorous reuse paradigm are presented: the Knowledge-Based Software Engineering Environment (KBSEE) and the Knowledge Acquisition fo the Preservation of Tradeoffs and Underlying Rationales (KAPTUR) systems. Emphasis is on a presentation of operational scenarios which highlight the major functional capabilities of the two systems.
Our purpose was to investigate the effect of automated knowledge-based planning (KBP) on real-world clinical workflow efficiency, assess whether manual refinement of KBP plans improves plan quality across multiple disease sites, and develop a data-driven method to periodically improve KBP automated planning routines.
This Working Paper Series entry represents a collection of presentation visuals associated with the companion report entitled, Knowledge Based Systems: A Critical Survey of Major Concepts, Issues, and Techniques, USL/DBMS NASA/RECON Working Paper Series report number DBMS.NASA/RECON-9. The objectives of the report are to: examine various techniques used to build the KBS; to examine at least one KBS in detail, i.e., a case study; to list and identify limitations and problems with the KBS; to suggest future areas of research; and to provide extensive reference materials.
The general operation of KATE, an artificial intelligence controller, is outlined. A shuttle environmental control system (ECS) demonstration system for KATE is explained. The knowledge base model for this system is derived. An experimental test procedure is given to verify parameters in the model.
Artificial intelligence application requirements demand powerful representation capabilities as well as efficiency for real-time domains. Many tools exist, the most prevalent being expert systems tools such as ART, KEE, OPS5, and CLIPS. Other tools just emerging from the research environment are truth maintenance systems for representing non-monotonic knowledge, constraint systems, object oriented programming, and qualitative reasoning. Unfortunately, as many knowledge engineers have experienced, simply applying a tool to an application requires a large amount of effort to bend the application to fit. Much work goes into supporting work to make the tool integrate effectively. A Knowledge Management Design System (KNOMAD), is described which is a collection of tools built in layers. The layered architecture provides two major benefits; the ability to flexibly apply only those tools that are necessary for an application, and the ability to keep overhead, and thus inefficiency, to a minimum. KNOMAD is designed to manage many knowledge bases in a distributed environment providing maximum flexibility and expressivity to the knowledge engineer while also providing support for efficiency.
Commissioning a new treatment planning system (TPS) involves many time-consuming tasks. We investigated the role that knowledge-based planning (KBP) can play in aiding a clinic's transition to a new TPS. Sixty clinically treated prostate/prostate bed intensity-modulated radiation therapy (IMRT) plans were exported from an in-house TPS and were used to create a KBP model in a newly implemented commercial application. To determine the benefit that KBP may have in a TPS transition, the model was tested on 2 groups of patients. Group 1 consisted of the first 10 prostate/prostate bed patients treated in the commercial TPS after the transition from the in-house TPS. Group 2 consisted of 10 patients planned in the commercial TPS after 8 months of clinical use. The KBP-generated plan was compared with the clinically used plan in terms of plan quality (ability to meet planning objectives and overall dose metrics) and planning efficiency (time required to generate clinically acceptable plans). The KBP-generated plans provided a significantly improved target coverage (p = 0.01) compared with the clinically used plans for Group 1, but yielded plans of comparable target coverage to the clinically used plans for Group 2. For the organs at risk, the KBP-generated plans produced lower doses, on average, for every normal-tissue objective except for the maximum dose to 0.1 cc of rectum. The time needed for the KBP-generated plans ranged from 6 to 15 minutes compared to 30 to 150 and 15 to 60 minutes for manual planning in Groups 1 and 2, respectively. KBP is a promising tool to aid in the transition to a new TPS. Our study indicates that high-quality treatment plans could have been generated in the newly implemented TPS more efficiently compared with not using KBP. Even after 8 months of the clinical use, KBP still showed an increase in plan quality and planning efficiency compared with manual planning.
Uncertainties are generally classified as either aleatory or epistemic. Aleatory uncertainties are those attributed to random variation, either naturally or through manufacturing processes. Epistemic uncertainties are generally attributed to a lack of knowledge. One type of epistemic uncertainty is called model-form uncertainty. The term model-form means that among the choices to be made during a design process within an analysis, there are different forms of the analysis process, which each give different results for the same configuration at the same flight conditions. Examples of model-form uncertainties include the grid density, grid type, and solver type used within a computational fluid dynamics code, or the choice of the number and type of model elements within a structures analysis. The objectives of this work are to identify and quantify a representative set of model-form uncertainties and to make this information available to designers through an interactive knowledge base (KB). The KB can then be used during probabilistic design sessions, so as to enable the possible reduction of uncertainties in the design process through resource investment. An extensive literature search has been conducted to identify and quantify typical model-form uncertainties present within aerospace design. An initial attempt has been made to assemble the results of this literature search into a searchable KB, usable in real time during probabilistic design sessions. A concept of operations and the basic structure of a model-form uncertainty KB are described. Key operations within the KB are illustrated. Current limitations in the KB, and possible workarounds are explained.
Purpose: To compare the dosimetric difference of the target volume and organs at risk(OARs) between conventional intensity-modulated radiotherapy(C-IMRT) and knowledge-based radiation therapy (KBRT) plans for cervix cancer. Methods: 39 patients with cervical cancer after surgery were randomly selected, 20 patient plans were used to create the model, the other 19 cases used for comparative evaluation. All plans were designed in Eclipse system. The prescription dose was 30.6Gy, 17 fractions, OARs dose satisfied to the clinical requirement. A paired t test was used to evaluate the differences of dose-volume histograms (DVH). Results: Comparaed to C-IMRT plan, the KBRT plan target can achieve the similar target dose coverage, D98,D95,D2,HI and CI had no difference (P≥0.05). The dose of rectum, bladder and femoral heads had no significant differences(P≥0.05). The time was used to design treatment plan was significant reduced. Conclusion: This study shows that postoperative radiotherapy of cervical KBRT plans can achieve the similar target and OARs dose, but the shorter designing time.
Artificial intelligence techniques are applied to the problems of model form and parameter identification of large-scale dynamic systems. The object-oriented knowledge representation is discussed in the context of causal modeling and qualitative reasoning. Structured sets of rules are used for implementing qualitative component simulations, for catching qualitative discrepancies and quantitative bound violations, and for making reconfiguration and control decisions that affect the physical system. These decisions are executed by backward-chaining through a knowledge base of control action tasks. This approach was implemented for two examples: a triple quadrupole mass spectrometer and a two-phase thermal testbed. Results of tests with both of these systems demonstrate that the software replicates some or most of the functionality of a human operator, thereby reducing the need for a human-in-the-loop in the lower levels of control of these complex systems.
The AI Bus architecture is layered, distributed object oriented framework developed to support the requirements of advanced technology programs for an order of magnitude improvement in software costs. The consequent need for highly autonomous computer systems, adaptable to new technology advances over a long lifespan, led to the design of an open architecture and toolbox for building large scale, robust, production quality systems. The AI Bus accommodates a mix of knowledge based and conventional components, running on heterogeneous, distributed real world and testbed environment. The concepts and design is described of the AI Bus architecture and its current implementation status as a Unix C++ library or reusable objects. Each high level semiautonomous agent process consists of a number of knowledge sources together with interagent communication mechanisms based on shared blackboards and message passing acquaintances. Standard interfaces and protocols are followed for combining and validating subsystems. Dynamic probes or demons provide an event driven means for providing active objects with shared access to resources, and each other, while not violating their security.
Purpose: Aims in this study are to (1) develop a computational model observer which reliably tracks the detectability of human observers in low dose computed tomography (CT) images reconstructed with knowledge-based iterative reconstruction (IMR™, Philips Healthcare) and filtered back projection (FBP) across a range of independent variables, (2) use the model to evaluate detectability trends across reconstructions and make predictions of human observer detectability, and (3) perform human observer studies based on model predictions to demonstrate applications of the model in CT imaging. Methods: Detectability (d′) was evaluated in phantom studies across a range of conditions. Images were generated using a numerical CT simulator. Trained observers performed 4-alternative forced choice (4-AFC) experiments across dose (1.3, 2.7, 4.0 mGy), pin size (4, 6, 8 mm), contrast (0.3%, 0.5%, 1.0%), and reconstruction (FBP, IMR), at fixed display window. A five-channel Laguerre–Gauss channelized Hotelling observer (CHO) was developed with internal noise added to the decision variable and/or to channel outputs, creating six different internal noise models. Semianalytic internal noise computation was tested against Monte Carlo and used to accelerate internal noise parameter optimization. Model parameters were estimated from all experiments at once using maximum likelihood on the probability correct, P{sub C}. Akaike information criterion (AIC) was used to compare models of different orders. The best model was selected according to AIC and used to predict detectability in blended FBP-IMR images, analyze trends in IMR detectability improvements, and predict dose savings with IMR. Predicted dose savings were compared against 4-AFC study results using physical CT phantom images. Results: Detection in IMR was greater than FBP in all tested conditions. The CHO with internal noise proportional to channel output standard deviations, Model-k4, showed the best trade-off between fit and model complexity according to AIC{sub c}. With parameters fixed, the model reasonably predicted detectability of human observers in blended FBP-IMR images. Semianalytic internal noise computation gave results equivalent to Monte Carlo, greatly speeding parameter estimation. Using Model-k4, the authors found an average detectability improvement of 2.7 ± 0.4 times that of FBP. IMR showed greater improvements in detectability with larger signals and relatively consistent improvements across signal contrast and x-ray dose. In the phantom tested, Model-k4 predicted an 82% dose reduction compared to FBP, verified with physical CT scans at 80% reduced dose. Conclusions: IMR improves detectability over FBP and may enable significant dose reductions. A channelized Hotelling observer with internal noise proportional to channel output standard deviation agreed well with human observers across a wide range of variables, even across reconstructions with drastically different image characteristics. Utility of the model observer was demonstrated by predicting the effect of image processing (blending), analyzing detectability improvements with IMR across dose, size, and contrast, and in guiding real CT scan dose reduction experiments. Such a model observer can be applied in optimizing parameters in advanced iterative reconstruction algorithms as well as guiding dose reduction protocols in physical CT experiments.
As the hardware trends for artificial intelligence (AI) involve more and more complexity, the process of optimizing the computer system design for a particular problem will also increase in complexity. Space applications of knowledge based systems (KBS) will often require an ability to perform both numerically intensive vector computations and real time symbolic computations. Although parallel machines can theoretically achieve the speeds necessary for most of these problems, if the application itself is not highly parallel, the machine's power cannot be utilized. A scheme is presented which will provide the computer systems engineer with a tool for analyzing machines with various configurations of array, symbolic, scaler, and multiprocessors. High speed networks and interconnections make customized, distributed, intelligent systems feasible for the application of AI in space. The method presented can be used to optimize such AI system configurations and to make comparisons between existing computer systems. It is an open question whether or not, for a given mission requirement, a suitable computer system design can be constructed for any amount of money.
Features and applications of the script-based flight monitor SECURE are described. Implemented on an on-board computer, SECURE treats a flight as a regular sequence of contexts (situations) defined in a knowledge base with a hierarchical structure for successively more finely delineated flight phases, i.e., takeoff, cruise and landing. SECURE provides normalcy references for flight monitoring and allows context identification, which allows the presentation of checklists. An implementation of SECURE, written in MACLISP, on a DC-10 flight simulator is described.
Expert Systems which support knowledge representation by qualitative modeling techniques experience problems, when called upon to support integrated views embodying description and explanation, especially when other factors such as multiple causality, competing rule model resolution, and multiple uses of knowledge representation are included. A series of prototypes are being developed to demonstrate the feasibility of automating the process of systems engineering, design and configuration, and diagnosis and fault management. A study involves not only a generic knowledge representation; it must also support multiple views at varying levels of description and interaction between physical elements, systems, and subsystems. Moreover, it will involve models of description and explanation for each level. This multiple model feature requires the development of control methods between rule systems and heuristics on a meta-level for each expert system involved in an integrated and larger class of expert system. The broadest possible category of interacting expert systems is described along with a general methodology for the knowledge representation and control of mutually exclusive rule systems.
The Expert Systems Validation Associate (EVA), a validation system under development at the Lockheed Artificial Intelligence Center for more than a year, provides a wide range of validation tools to check the correctness, consistency and completeness of a knowledge-based system. A declarative meta-language (higher-order language), is used to create a generic version of EVA to validate applications written in arbitrary expert system shells. The architecture and functionality of EVA are presented. The functionality includes Structure Check, Logic Check, Extended Structure Check (using semantic information), Extended Logic Check, Semantic Check, Omission Check, Rule Refinement, Control Check, Test Case Generation, Error Localization, and Behavior Verification.
It is only recently that research in Artificial Intelligence (AI) is accomplishing practical results. Most of these results can be attributed to the design and use of expert systems (or Knowledge-Based Systems, KBS) - problem-solving computer programs that can reach a level of performance comparable to that of a human expert in some specialized problem domain. But many computer systems designed to see images, hear sounds, and recognize speech are still in a fairly early stage of development. In this report, a preliminary survey of recent work in the KBS is reported, explaining KBS concepts and issues and techniques used to construct them. Application considerations to construct the KBS and potential KBS research areas are identified. A case study (MYCIN) of a KBS is also provided.
A computer program that belongs to the class known among software experts as output truth-maintenance-systems (output TMSs) has been devised as one of a number of software tools for reducing the size of the knowledge base that must be searched during execution of artificial- intelligence software of the rule-based inference-engine type in a case in which data are missing. This program determines whether the consequences of activation of two or more rules can be combined without causing a logical inconsistency. For example, in a case involving hypothetical scenarios that could lead to turning a given device on or off, the program determines whether a scenario involving a given combination of rules could lead to turning the device both on and off at the same time, in which case that combination of rules would not be included in the scenario.