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

{"title":"Modelling signal behaviour in DAME","authors":"N. Dimopoulos, B. Huber, K. F. Li, D. Caughey, M. Escalante, Dongni Li, R. Burnett, E. Manning","doi":"10.1145/98894.98921","DOIUrl":"https://doi.org/10.1145/98894.98921","url":null,"abstract":"DAME (Design Automation of Microprocessor-based systems, using an Expert system approach) is an expert system that will be capable of configuring and designing a customized microprocessor system from original specifications. We have postulated that such an expert system, can be easily constructed, since most of the interfaces used by the various microprocessors and related peripherals are standardized. Thus, once the gross structure of the design and the modules comprising it have been chosen, their interconnection is fairly straight-forward. Our investigation into the modelling of signal behavior confirmed this premise. In this work, we present the notation used to model signals in DAME. A notation is developed to allow complete specification of the static and temporal behavior of signals and their relation to other signals. Knowledge representation using frames is presented, together with some typical rules used for the design process. Actual examples of frame representation, rules to design interfaces between microprocessor and memory components are illustrated.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"61 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":"133177730","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":"Learning apprentice system for turbine modelling","authors":"M. J. Sawar, Richard C. Thomas","doi":"10.1145/98894.99106","DOIUrl":"https://doi.org/10.1145/98894.99106","url":null,"abstract":"A learning apprentice system is presented, which learns from examples extracted from user dialogues. The system provides an interface between the user and the turbine modeller. While a dialogue is carried out between the user and the turbine modelling software, the system observes the dialogues and whenever a new example is observed which performs a task completely, the system tries to learn it. The learning methodology used by the system is described and various drawbacks are pointed out. A new learning methodology is proposed which easily overcomes the problems faced by the earlier methodology.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"175 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":"133750171","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":"Adaptive multiagent planning in a distributed environment","authors":"Kai-Hsiung Chang, W. Day","doi":"10.1145/98894.98936","DOIUrl":"https://doi.org/10.1145/98894.98936","url":null,"abstract":"Currently there are several paradigms for distributed problem solving. First, the Contract Nets [ 19, 51 approach emphasizes the task-sharing and result-sharing phases of distributed problem solving through formal contracting procedures, including task announcement, bidding, and contract award. Second, the Actors style of concurrent programming [ 15, 1] provides the ability to model shared objects which have changing local states, to reconfigure dynamically the network, and to promote inherent parallelism in an application. Third, the functionally accurate, cooperative (FA/C) distributed system [16, 7, 81 is characterized by its handling of distribution-caused uncertainty and errors. In a FA/C system partial tentative results are exchanged among nodes, within the context of common goals. Fourth, when applied to multiagent planning, nodes channel their results to coordinating nodes that generate and distribute multiagent plans; see [ 11, 12, 131. We have constructed a new model for distributed problem solving based on parallel logic programming; see IZ 3, 6 71.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"250 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":"124215303","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":"Transforming rule-based programs: from the sequential to the parallel","authors":"R. Gamble","doi":"10.1145/98894.98939","DOIUrl":"https://doi.org/10.1145/98894.98939","url":null,"abstract":"Conflict resolution is a form of global control used in production systems to achieve an efficient sequential execution of a rule-based program. This type of control is not used in parallel production system models[6, 13]. Instead, only those programs are executed which make no assumptions regarding conflict resolution. Therefore, the initial sequential rule-based programs are either executed in parallel without their conflict resolution strategy, which normally results in incorrect behavior, or the programs are transformed in an ad hoc manner to execute on a particular parallel production system model. As a result, these programs do not exhibit the parallelism hoped for [10, 13]. We believe that a second reason behind the lack of parallelism is that no formal methods of verifying the correctness of rule-based programs are utilized. Correctness is especially important when conflict resolution is no longer utilized, because it necessary to transform sequential rule-based programs into equivalent programs without conflict resolution. Also, the parallel execution of a rule-based program is more complex and demands these formal methods even more than its sequential counterpart. We are concerned with designing and developing correct rule-based programs for parallel execution. In this paper, we show the difficulty in transforming a simple sequential rule-based program to a new version of the program with no conflict resolution. Also, we show that the use of a new programming paradigm and language may result in more efficient programs which are provably correct, and can be executed in parallel.","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":"114797721","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":"Supporting choice and evaluation in preliminary design","authors":"K. Ryan, N. Harty","doi":"10.1145/98894.98934","DOIUrl":"https://doi.org/10.1145/98894.98934","url":null,"abstract":"This paper describes the theory, methodology and implementation of a knowledge based system for the preliminary design of multi-story buildings. The system is intended to act as an intelligent assistant and embodies some of the design expertise and working principles of experienced civil engineering designers. As an aid to exploratory design, the system proposes only a user-specified number of alternatives at any one time and uses a system of hard and soft constraints to evaluate alternative possibilities. An illustrative example is given and the system is evaluated with respect to its potential use by practicing designers and is compared to some previous design systems in related domains.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"10 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":"123669508","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":"RASP: a resource allocator for software projects","authors":"C. Bertazzoni, F. Giannotti","doi":"10.1145/98894.98907","DOIUrl":"https://doi.org/10.1145/98894.98907","url":null,"abstract":"Rasp is a resource allocator that tries to apply artificial intelligence techniques in the project management field. Rasp expresses and manipulates all aspects concerning resource allocation exploiting a combined approach which integrates the logic programming paradigm with spreadsheet technology.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"264 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":"122085995","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 knowledge-level analysis of explanation-based learning","authors":"M. Numao, M. Shimura","doi":"10.1145/98894.99105","DOIUrl":"https://doi.org/10.1145/98894.99105","url":null,"abstract":"Although Explanation-Based Learning (EBL) has up to now been used only for deductive learning that improves execution speed, chunking in Soar, which is closely related to EBL, was demonstrated to acquire new knowledge. We first analyze such knowledge level learning in EBL, by showing that a rule set is specialized when rules in it are replaced by their composition, and is generalized when a rule is replaced by its decomposition. Counting on this discussion, we propose a method to learn generalized rules by making a decomposition of instances. Since this method acquires knowledge that is deduced from domain theory and induced from instances, it is a natural method for combining empirical and explanation-based learning. We demonstrate deductive and inductive aspects of our method by examples of logic circuit design and geometric analogy.","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":"124081045","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 VLSI asynchronous cellular architecture for neural computing: functional definition and performance evaluation","authors":"B. Faure, G. Mazaré","doi":"10.1145/98894.98937","DOIUrl":"https://doi.org/10.1145/98894.98937","url":null,"abstract":"Neural networks have two interesting features: robustness and fault tolerance on the one hand, massive parallelism on the other hand. The best way to keep those features and take into account the underlying massive parallelism is to map the neural network over a massively parallel architecture. However, a communication problem remains since the neurons are highly interconnected. A communication system, based on message transfers and without need for allocating a physical link for each connection, seems to be a solution for any parallel machine but is very hard to implement efficiently on hypercubes. We propose a dedicated VLSI architecture based on a two-dimensional array of asynchronous cells, each of which processing the simple algorithms of a neuron : both the back-propagation recall and learning schemes and being connected to its four immediate neighbors through eight unidirectional buffers, one for each way of the four directions. The main feature of this architecture is its hardware-based array-wide message transmission mechanism allowing a particular cell to communicate with potentially any other. A message is passed from a cell to one of its neighbors until it reaches its destination, its path being set dynamically in each passed-through cell. This non local communication system allows to process efficiently a class of distributed algorithms leading to a disorganized parallelism. This paper present the VLSI implementation of this architecture, shows how it can process feed-forward neural networks and discuss its performances. Our implementation of the back-propagation algorithm is at least more than 4 times faster at evaluating the NETtalk text-to-speech network than the Warp, a 20 processor systolic array, which ought to be the fastest back-propagation simulator reported in the literature. Our results indicate that two-dimensional arrays can be good candidates for neural processing, providing they can handle high communication rates.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"37 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":"125816559","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":"Design methodologies in mechanical engineering supported by artificial intelligence techniques","authors":"M. Cartmell, P. Fothergill, J. Forster","doi":"10.1145/98894.98935","DOIUrl":"https://doi.org/10.1145/98894.98935","url":null,"abstract":"The following is a description of the work at Aberdeen University concerning the application of Artificial Intelligence (AI) techniques in engineering design. This paper is based on the results of research in two fields which have traditionally been treated separately: methodologies in engineering design and artificial intelligence techniques, such as knowledge representation and inference. By attempting to integrate methodological approaches of specification expansion, solution generation and design assessment within an artificial intelligence framework, it should be possible to enhance significantly the capabilities of designers. This paper explores the current state of the art in both domains and attempts to explain how it may be possible to merge them in a new and useful manner. Also included are a description of the on-going work in Aberdeen and a brief outline of the first computerized implementation, the Design Specification Expansion 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":"14 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":"128893291","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":"Real time application of artificial neural network for incipient fault detection of induction machines","authors":"M. Chow, S. Yee","doi":"10.1145/98894.99117","DOIUrl":"https://doi.org/10.1145/98894.99117","url":null,"abstract":"This paper describes several artificial neural network architectures for real time application in incipient fault detection of induction machines. The artificial neural networks perform the fault detection in real time, based on direct measurements from the motor, and no rigorous mathematical model of the motor is needed. Different approaches used to develop a reliable fault detector are presented and compared in this paper. The designed networks vary in complexity and accuracy. A high-order fault detector neural network is discussed first. Then noise considerations are included in more complex fault detector models, since noise is an important factor in the design and analysis of real time fault detector neural networks. Simulation results show that with appropriate designs, artificial neural networks perform satisfactorily in real time incipient fault detection of induction machines.","PeriodicalId":175812,"journal":{"name":"Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2","volume":"1 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":"127918800","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}