Pub Date : 1991-09-30DOI: 10.1109/DMESP.1991.171737
G. D. Bailey, S. Raghavan, N. Gupta, B. Lambird, D. Lavine
A discussion is presented of an architecture called InFuse (Intelligent Fusion) for the multiple sensor fusion problem. InFuse exploits the notion of combining expert systems and neural networks to capture the advantages of both technologies. The application involves the extraction of natural terrain features from imagery provided by multiple sensors. In addition to the imagery, terrain knowledge in geographical databases needs to be integrated. The uniqueness of the approach lies in its ability to combine symbolic data of spatial databases and domain-specific knowledge about sensor behavior in expert systems with example-induced learning from neural networks to achieve a high classification rate. Results are presented to demonstrate the power of the approach.<>
{"title":"InFuse-an integrated expert neural network for intelligent sensor fusion","authors":"G. D. Bailey, S. Raghavan, N. Gupta, B. Lambird, D. Lavine","doi":"10.1109/DMESP.1991.171737","DOIUrl":"https://doi.org/10.1109/DMESP.1991.171737","url":null,"abstract":"A discussion is presented of an architecture called InFuse (Intelligent Fusion) for the multiple sensor fusion problem. InFuse exploits the notion of combining expert systems and neural networks to capture the advantages of both technologies. The application involves the extraction of natural terrain features from imagery provided by multiple sensors. In addition to the imagery, terrain knowledge in geographical databases needs to be integrated. The uniqueness of the approach lies in its ability to combine symbolic data of spatial databases and domain-specific knowledge about sensor behavior in expert systems with example-induced learning from neural networks to achieve a high classification rate. Results are presented to demonstrate the power of the approach.<<ETX>>","PeriodicalId":117336,"journal":{"name":"[1991] Proceedings of the IEEE/ACM International Conference on Developing and Managing Expert System Programs","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122724101","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}
Pub Date : 1991-09-30DOI: 10.1109/DMESP.1991.171714
M. Fathi, A. Hoffmann
A knowledge-based application system for composite material design is presented. The system supports the engineer in designing optimized composite materials for highly stressed structural components of technical systems, e.g., a piston ring for an engine. Such components often require material properties which cannot be found within one specific material. Furthermore, in designing and producing composite materials, several other objectives. e.g. economical or ecological ones. can be achieved more adequately. To integrate the diverse, heterogeneous sources of knowledge and to build a modular. easily extensible system. a blackboard architecture has been chosen. The architecture is presented, and the usefulness of the system is illustrated by means of an example.<>
{"title":"A blackboard system for the construction of composite materials","authors":"M. Fathi, A. Hoffmann","doi":"10.1109/DMESP.1991.171714","DOIUrl":"https://doi.org/10.1109/DMESP.1991.171714","url":null,"abstract":"A knowledge-based application system for composite material design is presented. The system supports the engineer in designing optimized composite materials for highly stressed structural components of technical systems, e.g., a piston ring for an engine. Such components often require material properties which cannot be found within one specific material. Furthermore, in designing and producing composite materials, several other objectives. e.g. economical or ecological ones. can be achieved more adequately. To integrate the diverse, heterogeneous sources of knowledge and to build a modular. easily extensible system. a blackboard architecture has been chosen. The architecture is presented, and the usefulness of the system is illustrated by means of an example.<<ETX>>","PeriodicalId":117336,"journal":{"name":"[1991] Proceedings of the IEEE/ACM International Conference on Developing and Managing Expert System Programs","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129163992","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}
Pub Date : 1991-09-30DOI: 10.1109/DMESP.1991.171705
Clayton M. Johnson, Stefan Feyock
The genetic algorithm (GA) is a powerful search paradigm which combines elements from evolutionary biology with concepts from population genetics. Because they operate in a domain-independent fashion, GAs have been successfully applied to a wide variety of optimization and learning problems. A technique is presented by which genetic algorithms can be adapted to operate upon the LISP-like production rules typically used in expert systems. A brief overview is presented of genetic algorithms and genetics-based learning.<>
{"title":"A genetics-based technique for the automated acquisition of expert system rule bases","authors":"Clayton M. Johnson, Stefan Feyock","doi":"10.1109/DMESP.1991.171705","DOIUrl":"https://doi.org/10.1109/DMESP.1991.171705","url":null,"abstract":"The genetic algorithm (GA) is a powerful search paradigm which combines elements from evolutionary biology with concepts from population genetics. Because they operate in a domain-independent fashion, GAs have been successfully applied to a wide variety of optimization and learning problems. A technique is presented by which genetic algorithms can be adapted to operate upon the LISP-like production rules typically used in expert systems. A brief overview is presented of genetic algorithms and genetics-based learning.<<ETX>>","PeriodicalId":117336,"journal":{"name":"[1991] Proceedings of the IEEE/ACM International Conference on Developing and Managing Expert System Programs","volume":"186 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114174072","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}
Pub Date : 1991-09-30DOI: 10.1109/DMESP.1991.171712
T. Usuki, T. Tatsumi, Naoki Kigawa, H. Ueno, Y. Kagawa, E. Kanayama
XAS is an expert system that contains knowledge for designing and simulating CCD chips. It synthesizes correct simulation programs automatically given the same process and mask data used by chip designers and selecting parameters according to the purpose of the simulation. XAS has the following characteristics. The XAS editors have expert knowledge of CCD chips and use it to display appropriate figures and menus. Because the user interface is mouse based, inputting data is both interactive and easy. In addition, XAS gives the same environment on every workstation connected within a local area network, so that many designers can access the system simultaneously.<>
{"title":"An expert system to aid in CCD design: XAS","authors":"T. Usuki, T. Tatsumi, Naoki Kigawa, H. Ueno, Y. Kagawa, E. Kanayama","doi":"10.1109/DMESP.1991.171712","DOIUrl":"https://doi.org/10.1109/DMESP.1991.171712","url":null,"abstract":"XAS is an expert system that contains knowledge for designing and simulating CCD chips. It synthesizes correct simulation programs automatically given the same process and mask data used by chip designers and selecting parameters according to the purpose of the simulation. XAS has the following characteristics. The XAS editors have expert knowledge of CCD chips and use it to display appropriate figures and menus. Because the user interface is mouse based, inputting data is both interactive and easy. In addition, XAS gives the same environment on every workstation connected within a local area network, so that many designers can access the system simultaneously.<<ETX>>","PeriodicalId":117336,"journal":{"name":"[1991] Proceedings of the IEEE/ACM International Conference on Developing and Managing Expert System Programs","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121977969","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}
Pub Date : 1991-09-30DOI: 10.1109/DMESP.1991.171703
V. Arora, J. E. Cooke
Based on the development of PRXDM, an expert system for the fault diagnosis of the PRX/A electronic telephone exchange, a development life-cycle for expert system development is proposed. Seven phases are identified: domain definition, general design, detailed design, prototype development, integration, field testing, and operation. Provision is made for the extensive iteration and incrementation that is an essential part of all expert system development. A framework for testing. verifying, and validating expert systems is presented, and relevant metrics that could be collected in each phase of development are suggested.<>
{"title":"Towards effective management of expert system projects","authors":"V. Arora, J. E. Cooke","doi":"10.1109/DMESP.1991.171703","DOIUrl":"https://doi.org/10.1109/DMESP.1991.171703","url":null,"abstract":"Based on the development of PRXDM, an expert system for the fault diagnosis of the PRX/A electronic telephone exchange, a development life-cycle for expert system development is proposed. Seven phases are identified: domain definition, general design, detailed design, prototype development, integration, field testing, and operation. Provision is made for the extensive iteration and incrementation that is an essential part of all expert system development. A framework for testing. verifying, and validating expert systems is presented, and relevant metrics that could be collected in each phase of development are suggested.<<ETX>>","PeriodicalId":117336,"journal":{"name":"[1991] Proceedings of the IEEE/ACM International Conference on Developing and Managing Expert System Programs","volume":"259 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115876970","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}
Pub Date : 1991-09-30DOI: 10.1109/DMESP.1991.171700
A.K. Wadaa, S. Shen
The authors propose LASSP, an apprentice system for learning problem-solving rules in domains where solving a problem entails multiple, possibly dependent, queries performed on an underlying database. Contrary to other learning apprentice systems, LASSP has a domain theory that is initially empty, yet ever improves in terms of its strength and correctness as successive problem-solving episodes are experienced. LASSP has the desirable property of being able to learn and exploit its domain theory concurrently. Foremost, LASSP can asynchronously integrate expertise of multiple experts into a common domain theory, in a seamless manner. This parallel assimilation of knowledge potentially enables the apprentice to develop its domain theory in a fraction of the time normally needed in serial assimilation approaches.<>
{"title":"Apprenticeship learning of query based problem solving rules","authors":"A.K. Wadaa, S. Shen","doi":"10.1109/DMESP.1991.171700","DOIUrl":"https://doi.org/10.1109/DMESP.1991.171700","url":null,"abstract":"The authors propose LASSP, an apprentice system for learning problem-solving rules in domains where solving a problem entails multiple, possibly dependent, queries performed on an underlying database. Contrary to other learning apprentice systems, LASSP has a domain theory that is initially empty, yet ever improves in terms of its strength and correctness as successive problem-solving episodes are experienced. LASSP has the desirable property of being able to learn and exploit its domain theory concurrently. Foremost, LASSP can asynchronously integrate expertise of multiple experts into a common domain theory, in a seamless manner. This parallel assimilation of knowledge potentially enables the apprentice to develop its domain theory in a fraction of the time normally needed in serial assimilation approaches.<<ETX>>","PeriodicalId":117336,"journal":{"name":"[1991] Proceedings of the IEEE/ACM International Conference on Developing and Managing Expert System Programs","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122151187","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}
Pub Date : 1991-09-30DOI: 10.1109/DMESP.1991.171774
M. Sierhuis
It is shown how the object-oriented (OO) paradigm and the KADS methodology's four-layer knowledge paradigm can be used to develop a design method for knowledge-based systems (KBSs). An example is used to illustrate how this method helps the knowledge engineer not only in the design of the system, but also in the implementation of this design into a workable prototype of the system. The method can be implemented in an OO expert system shell that has extended OO programming features. Limitations in the use of state-of-the-art OO languages for knowledge representation are discussed.<>
{"title":"An object-oriented design method for knowledge based systems","authors":"M. Sierhuis","doi":"10.1109/DMESP.1991.171774","DOIUrl":"https://doi.org/10.1109/DMESP.1991.171774","url":null,"abstract":"It is shown how the object-oriented (OO) paradigm and the KADS methodology's four-layer knowledge paradigm can be used to develop a design method for knowledge-based systems (KBSs). An example is used to illustrate how this method helps the knowledge engineer not only in the design of the system, but also in the implementation of this design into a workable prototype of the system. The method can be implemented in an OO expert system shell that has extended OO programming features. Limitations in the use of state-of-the-art OO languages for knowledge representation are discussed.<<ETX>>","PeriodicalId":117336,"journal":{"name":"[1991] Proceedings of the IEEE/ACM International Conference on Developing and Managing Expert System Programs","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125994134","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}
Pub Date : 1991-09-30DOI: 10.1109/DMESP.1991.171738
Tai-Hoon Cho, R. Conners, P. Araman
As classifiers for use in automated industrial inspection, the rule-based, k-nearest-neighbor, and neural-network approaches are discussed. These approaches were implemented and tested for label verification in a machine vision system for hardwood lumber inspection. The test results, together with other considerations, have led to the selection of neural networks as the preferred method for doing the label verification in this machine vision system.<>
{"title":"A comparison of rule-based, k-nearest neighbor, and neural net classifiers for automated industrial inspection","authors":"Tai-Hoon Cho, R. Conners, P. Araman","doi":"10.1109/DMESP.1991.171738","DOIUrl":"https://doi.org/10.1109/DMESP.1991.171738","url":null,"abstract":"As classifiers for use in automated industrial inspection, the rule-based, k-nearest-neighbor, and neural-network approaches are discussed. These approaches were implemented and tested for label verification in a machine vision system for hardwood lumber inspection. The test results, together with other considerations, have led to the selection of neural networks as the preferred method for doing the label verification in this machine vision system.<<ETX>>","PeriodicalId":117336,"journal":{"name":"[1991] Proceedings of the IEEE/ACM International Conference on Developing and Managing Expert System Programs","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130820821","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}
Pub Date : 1991-09-30DOI: 10.1109/DMESP.1991.171727
J. Fenn, L.C. Veren
Results are presented of a survey of how commercial and government organizations are currently tackling key issues in expert system development. Recommendations made by methodology researchers are compared with the findings from a survey of over 30 organizations. The survey findings cover areas such as features of a successful application, project initiation activities, the overall life cycle, and the roles of prototyping, documentation, and the hardware and software environment. Lessons learned by survey respondents about methods and techniques which have proven particularly effective are included. A discussion of the differences between theory and practice centers around the role of prototyping in the life cycle, the documentation that is produced, and the amount of user interaction required.<>
{"title":"Expert system development methodologies in theory and practice","authors":"J. Fenn, L.C. Veren","doi":"10.1109/DMESP.1991.171727","DOIUrl":"https://doi.org/10.1109/DMESP.1991.171727","url":null,"abstract":"Results are presented of a survey of how commercial and government organizations are currently tackling key issues in expert system development. Recommendations made by methodology researchers are compared with the findings from a survey of over 30 organizations. The survey findings cover areas such as features of a successful application, project initiation activities, the overall life cycle, and the roles of prototyping, documentation, and the hardware and software environment. Lessons learned by survey respondents about methods and techniques which have proven particularly effective are included. A discussion of the differences between theory and practice centers around the role of prototyping in the life cycle, the documentation that is produced, and the amount of user interaction required.<<ETX>>","PeriodicalId":117336,"journal":{"name":"[1991] Proceedings of the IEEE/ACM International Conference on Developing and Managing Expert System Programs","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126264955","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}
Pub Date : 1991-09-30DOI: 10.1109/DMESP.1991.171716
M. Gray
The author points out an opportunity for using first-generation expert system programs to construct systems that can solve large-scale problems in a cooperative manner. He describes the requirements for expert system programs to support integration into such systems and proposes the application of the communication-free cooperating agents theory (M.R. Genesereth et al., 1986) as a model for these systems. A minimal modification approach that uses an integration agent is discussed, and the feasibility of the proposal is assessed. An illustrative example from the design domain is included.<>
作者指出了利用第一代专家系统程序构建能够以协作方式解决大规模问题的系统的机会。他描述了支持集成到这些系统中的专家系统程序的要求，并提出应用无通信合作代理理论(M.R. Genesereth et al.， 1986)作为这些系统的模型。讨论了一种使用集成代理的最小修改方法，并评估了该建议的可行性。包括来自设计领域的说明性示例。
{"title":"On integrating expert system programs into cooperative systems","authors":"M. Gray","doi":"10.1109/DMESP.1991.171716","DOIUrl":"https://doi.org/10.1109/DMESP.1991.171716","url":null,"abstract":"The author points out an opportunity for using first-generation expert system programs to construct systems that can solve large-scale problems in a cooperative manner. He describes the requirements for expert system programs to support integration into such systems and proposes the application of the communication-free cooperating agents theory (M.R. Genesereth et al., 1986) as a model for these systems. A minimal modification approach that uses an integration agent is discussed, and the feasibility of the proposal is assessed. An illustrative example from the design domain is included.<<ETX>>","PeriodicalId":117336,"journal":{"name":"[1991] Proceedings of the IEEE/ACM International Conference on Developing and Managing Expert System Programs","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131381460","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：