![]() |
|||
![]()
|
![]() |
![]() |
![]() |
Instruction. A shell was developed for building intelligent tutoring systems to train medical students in diagnosing patient cases (Reinhardt and Schewe, 1995). The system uses case data and problem-solving knowledge to handle classification problems. The main method of the system is to present case data and to control the student's actions by comparing them to the underlying expert system. The shell was developed at Wurzburg University, Germany. Interpretation. SSI is a shell for the development of signal interpretation expert systems (Arai et al., 1992). The shell is a product of the design of two expert systems for speech signal processing, where the analysis of the two systems revealed common functions and modules applicable to a wide range of signal interpretation problems. SSI was developed at Osaka University, Osaka, Japan. Monitoring. PREMON, the Predictive Monitoring system, uses the explicit model of a device to perform real-time monitoring (Doyle et al., 1987). The system has been tested on the partial model of the mirror cooling circuit of the Jet Propulsion Laboratory space simulator. PREMON has three interacting capabilities: (1) causal simulation to generate predictions about the behavior of a physical system; (2) sensor planning to assess the importance of a device's behavior and allocate sensor resources appropriately; and (3) sensor interpretation to verify expected sensor values against actual sensor readings and raise alarms when necessary. The system was developed at NASA Ames Research Center. RTie is designed specifically for developing real-time expert system applications. It can process several thousand rules per second, thus permitting it to analyze huge amounts of data from different sources. It has particular value in process monitoring applications. A form knowledge entry approach is used for creating rules, classes, and objects. It includes a temporal reasoning ability, where rules can be built to compare past data with current data, enabling trend and statistical processing. RTie is commercially available from Talarian, Mountain View, CA. Planning. GHOST is a general-purpose planning system in the area of construction (Navinchandra et al., 1988). It reasons about an object's attributes and relationships between objects to define project activities. GHOST starts with a high-level set of tasks and refines them into subnetworks of more detailed tasks. The system combines object-oriented programming with rule-sets, and employs a blackboard structure. KBLPS, Knowledge-Based Logistics Planning Shell, assists in the design of an expert system for planning allocation and transportation resource applications. It includes planning algorithms for over-constrained distribution problems, and a decision-centered graphical user interface. In use, KBLPS provides planners with a "what-if" ability to see the impact on changed information on the expected results. Planners are able to cycle through scenarios, breaking resource allocations until the most feasible recommendation is developed. It is commercially available from Carnegie Group, Pittsburgh, PA. OARPLAN is a general-purpose planning system. It generates project plans using facility object descriptions extracted from the CADD system AutoCad (Darwiche et al., 1989). The system uses an object-oriented product model that employs abstraction hierarchies to produce a plan for structuring the facility. It works within a BB1 blackboard environment. PIPPA is a general-purpose planning system that has been used to develop plans for manufacturing flight simulators, for construction foundations, and for submitting tenders for furnace installations (Marshall et al., 1987). The system uses a hierarchy of objects and actions, and a set of demons to formulate plans at any level of detail. The system is implemented in RBFS. SIPEC is a general-purpose planning shell for multiagent planning problems in the area of construction (Kartman and Levitt, 1990). The system uses knowledge based in first principles to derive relationships among activities to order them in the construction plan. SIPEC is integrated with a CADD system to obtain component descriptions.
|
![]() |
|
Use of this site is subject certain Terms & Conditions. Copyright (c) 1996-1999 EarthWeb, Inc.. All rights reserved. Reproduction in whole or in part in any form or medium without express written permission of EarthWeb is prohibited. Please read our privacy policy for details. |