{"title":"Learning textural concepts through multilevel symbolic transformations","authors":"J. Bala, R. Michalski","doi":"10.1109/TAI.1991.167081","DOIUrl":"https://doi.org/10.1109/TAI.1991.167081","url":null,"abstract":"The TEXTRAL system, used for determining structural visual properties of textures through symbolic transformations, is presented. The method consists of two phases: one that extracts information from raw textural images by applying convolutional operators and learns an initial set of rules; and a second that iteratively extracts symbolic information from the transformed representation of initial image and learns another set of rules. The transformed symbolic representation is obtained by applying previously learned rules to a new image location and generating symbolic images based on rule assertions.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121746790","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":"Reducing the search time of a steady state genetic algorithm using the immigration operator","authors":"M. C. Moed, Charles V. Stewart, R. Kelley","doi":"10.1109/TAI.1991.167032","DOIUrl":"https://doi.org/10.1109/TAI.1991.167032","url":null,"abstract":"An examination is made of the fundamental trade-off between exploration and exploitation in a genetic algorithm (GA). An immigration operator is introduced that infuses random members into successive GA populations. It is theorized that immigration maintains much of the exploitation of the GA while increasing exploration. To test this theory, a set of functions that often require the GA to perform an excessive number of evaluations to find the global optimum of the function is designed. For These functions, it is shown experimentally that a GA enhanced with immigration (1) reduces the number of trials that require an excessive number of evaluations and (2) decreases the average number of evaluations needed to find the optimum function.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121944598","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 genetic algorithm programming environment: Splicer","authors":"Steven E. Bayer, Lui Wang","doi":"10.1109/TAI.1991.167088","DOIUrl":"https://doi.org/10.1109/TAI.1991.167088","url":null,"abstract":"Genetic algorithms have been used to solve parameter optimization problems and for machine learning. Basic genetic algorithm concepts are introduced. The authors discuss genetic algorithm applications, and present results of a project to develop a software tool-a genetic algorithm programming environment-called Splicer.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122089024","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 maxima-tracking method for skeletonization from Euclidean distance function","authors":"F. Shih, C. C. Pu","doi":"10.1109/TAI.1991.167101","DOIUrl":"https://doi.org/10.1109/TAI.1991.167101","url":null,"abstract":"A skeletonization algorithm based on the Euclidean distance function using the sequential maxima-tracking method is described which, when applied to a connected image, generates a connected skeleton composed of simple digital arcs. With a slight modification, the algorithm can preserve the more important features in the skeletal branches which touch the object boundary at corners. Therefore its application to shape recognition can be easily achieved.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127952820","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":"Components of expertise for knowledge level modeling","authors":"R. Chang, G. S. Novak","doi":"10.1109/TAI.1991.167039","DOIUrl":"https://doi.org/10.1109/TAI.1991.167039","url":null,"abstract":"A new dimension of object-oriented components is presented to describe knowledge-level models of an application. From the knowledge-level perspective, components are needed for modeling the problems, solution methods, and their relationships in a problem-solving process. A problem can often be decomposed recursively by various methods into subproblems until reaching primitive ones. Each primitive problem is confined to a simple computational task, which can be solved by one problem-solving method. The process of problem solving is viewed as a modeling activity through explicitly represented knowledge-level models that are, then, operationalized. Design issues that are encountered when developing such a component-based framework for knowledge-level modeling are described.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133760788","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":"Abstraction of formal specifications from program code","authors":"B. Cheng, G. Gannod","doi":"10.1109/TAI.1991.167086","DOIUrl":"https://doi.org/10.1109/TAI.1991.167086","url":null,"abstract":"A description is presented of the development of the tool AUTOSPEC (automated specification), which abstracts formal specifications from program code. The abstraction process can incorporate domain-specific information supplied interactively by the user, as necessary. The abstraction algorithms and a discussion of the use of formal methods and object-oriented techniques for the development of AUTOSPEC are given. Implementation-specific information is given and related work is described.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130572271","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}
L. Marinos, R. A. Smit, S. Oei, Jan Sirks, M. D. Jong, J. V. D. Meersch
{"title":"An intelligent mediator for database application development","authors":"L. Marinos, R. A. Smit, S. Oei, Jan Sirks, M. D. Jong, J. V. D. Meersch","doi":"10.1109/TAI.1991.167124","DOIUrl":"https://doi.org/10.1109/TAI.1991.167124","url":null,"abstract":"The authors elaborate on the structure and functionality of a front-end to a relational database. By using object-oriented features they overcome problems emanating from the monolithic nature of the relational model. At the same time, by maintaining knowledge about the database schema at the level of the front-end, they guarantee consistent manipulation of the database information, while on the other hand providing a transparent access to the underlying database.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131164802","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":"Iterative development life cycle (IDLC): a management process for large scale intelligent system development","authors":"F. Miller, Rosemarie J. Paradis, Kevin Whalen","doi":"10.1109/TAI.1991.167042","DOIUrl":"https://doi.org/10.1109/TAI.1991.167042","url":null,"abstract":"The iterative development life cycle (IDLC) provides a management process for the successful development of large-scale intelligent system applications. The iterative process minimizes both risks and costs by combining both the well structured management techniques of the waterfall process and the early validation techniques of the evolutionary model. This process is more adaptable to the full range of software project situations and provides the flexibility necessary to accommodate a high dynamic range of technical alternatives.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126631889","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":"Preventing infinite looping in Prolog","authors":"J. Han","doi":"10.1109/TAI.1991.167044","DOIUrl":"https://doi.org/10.1109/TAI.1991.167044","url":null,"abstract":"A method is proposed to modify Prolog compilers so that infinite looping can often be avoided in recursive Prolog programs. The study is carried out in the context of deductive databases. Termination of recursive query processing here is related to boundedness: uniform boundedness and extensional boundedness. Limitations of this method are briefly discussed.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127080128","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 event-based real-time logic to specify the behavior and timing properties of real-time systems","authors":"Horng-Yuan Chen, J. Tsai, Yao-Dong Bi","doi":"10.1109/TAI.1991.167097","DOIUrl":"https://doi.org/10.1109/TAI.1991.167097","url":null,"abstract":"A modification is presented of temporal logic-event-based real-time logic (ERL), based on an event-based conceptual model. The ERL provides a high-level framework for specifying timing properties of real-time software systems. The ERL is used to specify both expected behavior (specification) and actual behavior (execution traces) of the target systems; it is also used to verify that the program achieves the specification. A method is also described to implement the ERL using the Prolog programming language for testing and debugging real-time software systems.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114508937","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}