Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2最新文献

{"title":"Improving planning efficient by conceptual clustering","authors":"Hua Yang, D. Fisher, H. Franke","doi":"10.1145/98894.99104","DOIUrl":"https://doi.org/10.1145/98894.99104","url":null,"abstract":"Automated acquisition and organization of plan knowledge has been investigated by many researchers. Vere's THOTH (1980) induces a minimal set of relational operators that cover a training set of state to state transitions. For example, having observed the many individual transitions required to build a block tower, THOTH might formulate abstract operator descriptions that correspond to the 'classic' operators of Stack, Pick-up, etc. However, THOTH does not have a strong notion of 'good' operator organization, other than to discover a minimal set of abstractions that cover the training examples. Nonetheless, THOTH's ability to autonomously discover operator 'classes' makes it an early conceptual ancestor of the clustering approach that we propose. Unlike THOTH, STRIPS (Fikes, Hart & Nilsson, 1972) begins with a set of abstract operator descriptions and conjoins them using means-ends analysis to form plans. Moreover, STRIPS generalizes the applicability of these plans (using analytic methods in contrast to THOTH's empirical approach) and stores them for reuse. However, recent work in learning to plan indicates that a STRIPS approach to saving plans in an unconstrained manner may actually have detrimental effects on planning time: the time to search for applicable past experience may eventually surpass the cost of planning from scratch (Minton, 1988). Anderson and Farley (1988) suggests a possible way to mitigate the cost of finding applicable past knowledge. Their system, PLANERUS, generates a hierarchy based on common ADD conditions of STRIPS-like operators. ADD condition indices allow PLANERUS to find operators that reduce differences in a means-ends planner. In principle a discrimination net over ADD conditions can be very efficient, but like THOTH, PLANERUS appears to lack a strong prescription of operator class quality: its indexing method appears to require an exponential number of indices in the worst case because it groups operators based on combinations of one or more shared conditions. In this regard Minton (1988) points out that even with indexing schemes, systems must also be willing to dispose of past experiences (e.g., abstractions, ADD-condition combinations) that prove to be of low utility (e.g., infrequent). THOTH, STRIPS, and PLANERUS are important precursors to our work, but we hope to extend the ideas illustrated by these systems in several directions. First, a system like PLANERUS is designed primarily to facilitate goal-driven behavior, as its exclusive reliance on ADD-condition indexing indicates. However, work in reactive or situated planning (Schoppers, 1989) suggests that the current situation should also influence the selection of applicable operators: an ideal operator is one that achieves desirable goals and requires minimal alterations to the current situation to do so. Thus, we propose that when using STRIPS-like operators, PRE conditions, as well as ADD conditions should be used to retrieve operators that make progre","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126614928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using artificial intelligence techniques for intelligent simulation in memory re-education","authors":"C. Bonnet, Helene Taterode, J. Kouloumdjian, Mohand-Said Hacid","doi":"10.1145/98894.98941","DOIUrl":"https://doi.org/10.1145/98894.98941","url":null,"abstract":"The increasing complexity of new applications has made it necessary to have tools offering a large spectrum of functionalities and several paradigms. This is especially true for intelligent tutoring systems which need (meta)rule based inference for adaptive teaching strategies, object oriented paradigm for learner modeling, graphic simulation tools and large data management facilities for storing lessons and results. The carrying out of such tools, where several software cooperate, should take into account the development of user-friendly environments. This paper describes an intelligent rehabilitation system used for people suffering from memory troubles. It is aimed at simulating everyday “ecological” situations by means of graphical scenes: patients are then asked to realize specific actions on the displayed objects such as preparing breakfast according to dynamically predefined scenarii. The construction of such a system needs to use intelligent tools, which are able to substitute neuropsychologists in the re-education phase. Our solution consists of combining Artificial Intelligence tools and Simulation ones. The system articulates around an expert system generator and an interactive graphical simulation package. The detailed architecture and the working of the system are described here.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134287900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hybrid expert system-neural networks methodology for anticipatory control in a process environment","authors":"L. Tsoukalas, J. Reyes-Jimenez","doi":"10.1145/98894.99121","DOIUrl":"https://doi.org/10.1145/98894.99121","url":null,"abstract":"A methodology is presented that couples expert systems to neural networks for the purpose of monitoring and control in a process environment. This is achieved within the framework of the anticipatory paradigm. The basic assumption of the anticipatory paradigm is that a complex system can modify its behavior on the basis of present as well as anticipated future states. The complex systems contemplated in this research use measures of performance to represent current as well as anticipated states in such a manner that decisions about change of state are related to a search for maximizing the performance associated with a state variable. Current performance is computed on the basis of a comparison between measured(sensor) and calculated(model) data. Anticipated performance is computed on the basis of predictions made by pre-trained neural networks. A fuzzified Bayes formula is used as the computational link between present and future states. The implementation of such a system calls for a coupling between expert systems(ESs) and artificial neural networks(ANNs). This coupling allows a knowledge-based system to make control decisions through an assessment of the current performance of the process and an estimate of its anticipated performance a &Dgr;t time latter; pre-trained neural networks provide fast estimates of future states.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129495626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Knowledge-based assistant for colonscopy","authors":"L. Sucar, D. Gillies","doi":"10.1145/98894.98914","DOIUrl":"https://doi.org/10.1145/98894.98914","url":null,"abstract":"Endoscopy is a complex task in which an expert physician is required to guide the endoscope inside the human colon. The objective of this system is to develop a computer assistant that could help the doctor with the navigation of the endoscope inside the colon, serving as an advisory system for learning endoscopists. A knowledge-base (KB) in colon endoscopy has been compiled from the knowledge extracted from an expert colonoscopist. It includes knowledge for colon image interpretation and for control of the endoscope. Using features from intermediate vision we are using the expert rules to recognize the important objects in the images, in the first stage, and later for advise and control. In particular, we are interested in detecting “special” situations in the colon for which the expert heuristics are useful. An initial prototype has been implemented using a parallel architecture with transputers and a PC. The expert system is implemented in Prolog and it communicates with the feature extraction programs running in a “transputer pyramid” by transforming the vision features into symbolic predicates for logical inference. We have tested the system with real colon images from a videotape to identify the lumen. Work is in progress to extend the feature extraction process so more objects could be recognized by the system.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125689554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Specification of an object to object protocol in Abstract Syntax Notation One (ASN.1)","authors":"J. Toth","doi":"10.1145/98894.99142","DOIUrl":"https://doi.org/10.1145/98894.99142","url":null,"abstract":"Object-oriented languages and environments have opened up a new way to develop software. Unfortunately, object-to-object transmittal of control and data has been highly indigenous to its particular domain; whether it be a compiler, interpreter or database. The DARPA Initiative for Concurrent Engineering (DICE) has specified a DICE Communications Channel (DCC) in which a heterogeneous environment, including object-oriented databases and subsystems, has driven the requirement for an integration scheme between disjunct entities. Another DICE formalism, known as the Part, Process and Organization (PPO) database, has served as the locus of integration between the various environments that require access to it. This paper will address an application-specific problem encountered in the first two phases of the DICE program, regarding the integration of heterogeneous object-oriented environments. Using the PPO database as a case study, a basic application and presentation layer specification of an object-to-object protocol (OOP) will be formalized using the ISO Abstract Syntax Notation One (ASN.1) protocol definition.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124424377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Knowledge-based learning integrating acquisition and learning","authors":"B. L. Whitehall, R. Stepp, S. Lu","doi":"10.1145/98894.99102","DOIUrl":"https://doi.org/10.1145/98894.99102","url":null,"abstract":"Empirical learning algorithms are hampered by their inability to use domain knowledge to guide the induction of new rules. This paper describes knowledge-based learning, an approach to learning that selects the examples and relevant attributes for an empirical algorithm. Knowledge-based learning can be used for developing rules for engineering expert systems. Engineers often have some rules for problem solving, but also many experiences (examples) that facilitate solving problems. Knowledge-based learning systems are able to use both forms of knowledge.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"156 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123471122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DEIMOS: a functional paradigm for mechanical design","authors":"Daniel Ligman","doi":"10.1145/98894.98930","DOIUrl":"https://doi.org/10.1145/98894.98930","url":null,"abstract":"This paper presents an expert system paradigm for mechanical design that allows control within the system to be guided by the function of the final design. A concept of functional attributes, which incorporates ideas from both functional reasoning (Freeman & Newell '71) and planning, is used to characterize an object's function. These attributes are used to guide design through a top down design paradigm. Functional attributes will produce more novel designs than a system doing routine design and are useful for constructing general purpose design systems because they are not domain dependent. DEIMOS, a small general purpose design system, was built to study the use of functional attributes.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124835684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Equation generation for clustering","authors":"B. L. Whitehall, R. Stepp, S. Lu","doi":"10.1145/98894.98929","DOIUrl":"https://doi.org/10.1145/98894.98929","url":null,"abstract":"Clustering events into useful classifications is an important part of problem solving in engineering. This paper discusses the role of clustering in engineering and why numerical and conceptual clustering techniques are not always adequate. The knowledge based equation generator system was constructed to overcome one of these shortfalls. This system partitions events based upon mathematical formulas used to describe the events.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126393161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A management system for a PACS network in a hospital environment","authors":"V. Jonckers, B. Criel","doi":"10.1145/98894.98915","DOIUrl":"https://doi.org/10.1145/98894.98915","url":null,"abstract":"The paper reports on a network management system for a Picture Archiving and Communication System (PACS) in a hospital environment. The size of a typical data transfer in this environment is several orders of magnitude larger than a typical data transfer in a local area computer network. To ensure reasonable response times to the system's users, it is necessary to sequentialise the image traffic on the PACS network. Knowledge about patient flow, radiologist flow, and image flow which is available in the hospital environment, can be exploited for careful planning and scheduling of network traffic. We designed and implemented a prototype of a network management system in which both the network configuration and the traffic management strategy are modeled explicitly. In combination with a discrete-event simulator a platform is realised which allows for experimentation with different hypothetical network configurations and/or different traffic management strategies. The current prototype is developed on a HP 9000 workstation using the knowledge representation system KEE.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117103175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An augmented Prolog programming environment for tutoring applications","authors":"Moon-Chuen Lee","doi":"10.1145/98894.98884","DOIUrl":"https://doi.org/10.1145/98894.98884","url":null,"abstract":"This paper focuses on the design of an Augmented Prolog Programming Environment (APPE) for learning Prolog. It stresses the importance of being able to detect and classify errors present in the student program. In general, language compilers and interpreters can only detect syntax errors and can hardly diagnose semantic errors. It is conceived that a Prolog system can be enhanced considerably with the inclusion of an intelligent diagnoser and facilities for doing problem acquisition from the teacher and administering problems to the student. Unlike traditional CAI programs which support mainly teacher-centered tutorials, APPE facilitates the discovery mode of learning since it can cope with individual student programs. The design enables the diagnoser to classify Prolog program bugs into five categories: incorrect solutions, uncovered solutions, redundant solutions, nontermination, and invalid parameters. Further, the proposed diagnoser can identify various causes of nontermination bugs. Besides identifying the errors in a program, it can also provide remedial advice to the student programmer.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126785274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}