{"title":"Neural model of visual selective attention for automatic translation invariant object recognition in cluttered images","authors":"E. Chong, C. Lim, P. Lozo","doi":"10.1109/KES.1999.820201","DOIUrl":"https://doi.org/10.1109/KES.1999.820201","url":null,"abstract":"This paper presents a biologically inspired neural model for detecting, locating and recognising all known objects in the visual scene automatically. In particular, this model employs bottom-up segmentation to achieve shifts in spatial attention, for selecting potential regions of interest across the visual scene.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"578 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132623206","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":"Evaluation of an idea generation method and its supporting groupware","authors":"J. Munemori, K. Yagishita, M. Sudo","doi":"10.1109/KES.1999.820118","DOIUrl":"https://doi.org/10.1109/KES.1999.820118","url":null,"abstract":"KJ method is a well-known idea generation method in Japan. We propose an evaluation method for compositions of B type KJ method (i.e. conclusive compositions of the KJ method). The method consists of \"a pair comparison\" for evaluations of contents and Petri net graph for evaluations of structures. We applied the method to evaluation experiments of compositions, and compared the results, and then we discussed the evaluation capability of the method and some structural features of compositions of B type KJ method. The results of evaluation experiments represented that contents of compositions of B type KJ method were superior to those made without the KJ method significantly and that structures of them were also significantly different and the performance of GUNGEN was almost equal to that of a conventional method on paper.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128928309","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 integrated object representation for recognition and grasping","authors":"E. Kefalea, E. Maël, R. Würtz","doi":"10.1109/KES.1999.820213","DOIUrl":"https://doi.org/10.1109/KES.1999.820213","url":null,"abstract":"As a step towards systems that can acquire knowledge automatically, we have designed a system that can learn new objects with a minimum of user interaction and implemented it on our robot platform GripSee (M. Becker et al., 1999). A novel object is placed into the robot's gripper in order to define a default orientation and a default grip. The robot then places the object on a turning table and builds up a visual representation that consists of a collection of graphs, labeled with multiscale edges. A user interface that can correct errors in the representation is also part of the system. The visual representation is complemented by a grip library, which contains possible ways of grasping and manipulating the object in a robust manner. We regard this procedure as an example of human assisted learning.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133406920","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}
M. Ostrognay, L. Jain, A. Cropley, V. Puri, D. Filippidis
{"title":"Intelligent data processing in training evaluation practices","authors":"M. Ostrognay, L. Jain, A. Cropley, V. Puri, D. Filippidis","doi":"10.1109/KES.1999.820110","DOIUrl":"https://doi.org/10.1109/KES.1999.820110","url":null,"abstract":"Data mining and knowledge representation processes are explored for use in pre-processing data for an evaluation system. The RAN (Royal Australian Navy) Bridge Simulator provides the evaluation environment. Both performance grading and biological measures are analysed and processed to provide a basic level of knowledge representation. These knowledge fragments can then be passed to an evaluation system.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132653541","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":"Neuromorphic VLSI systems for visual information processing: drawbacks","authors":"A. Moini","doi":"10.1109/KES.1999.820200","DOIUrl":"https://doi.org/10.1109/KES.1999.820200","url":null,"abstract":"In this paper, the neuromorphic VLSI approach for visual processing and detection is presented. A brief history of neuromorphic vision systems is presented. The advantages and disadvantages of neuromorphic systems are highlighted and some of the major barriers towards realizing these systems are discussed. In particular, the implementation of early visual processing models using analogue VLSI is described and some of the general misconceptions are addressed.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116177761","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 and analysis of fuzzy schedulers using fuzzy Lyapunov synthesis","authors":"M. Margaliot, G. Langholz","doi":"10.1109/KES.1999.820156","DOIUrl":"https://doi.org/10.1109/KES.1999.820156","url":null,"abstract":"The authors recently suggested a new approach to the design of fuzzy control rules. The method, referred to as fuzzy Lyapunov synthesis, extends classical Lyapunov synthesis to the domain of \"computing with words\", and allows the systematic, instead of heuristic, design and analysis of fuzzy controllers given linguistic information about the plant. In this paper we use the fuzzy Lyapunov synthesis method to design and analyze the rule-base of a fuzzy scheduler. We show that fuzzy rules, previously suggested based on heuristics, can be derived systematically and, therefore, that the entire process can be automated. This may lead to a novel \"computing with words\" algorithm: the input is linguistic information concerning the \"plant\" and the \"control\" objective, and the output is a suitable fuzzy rule-base.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122020802","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":"Mathematical modeling into performance evaluation using simulator training and correlation with live training practices","authors":"V. Ivancevic, L. Jain, V. Puri, D. Filippidis","doi":"10.1109/KES.1999.820234","DOIUrl":"https://doi.org/10.1109/KES.1999.820234","url":null,"abstract":"In this paper, the problem of the objective evaluation of trainee performance from simulators, and the subsequent prediction of the trainee's competency, is solved in two ways: (i) using a linear factor structure and linear factor dynamics, in the case of large samples of trainees and simulator tests, and (ii) using a nonlinear Hopfield overlap-based structure and nonlinear overlap dynamics, in the case of small samples of trainees and simulator tests.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125775211","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}
Kozo Sugiyama, Kazuo Misue, I. Watanabe, Kiyoshi Nitta
{"title":"Development and evaluation of human thinking support tools","authors":"Kozo Sugiyama, Kazuo Misue, I. Watanabe, Kiyoshi Nitta","doi":"10.1109/KES.1999.820117","DOIUrl":"https://doi.org/10.1109/KES.1999.820117","url":null,"abstract":"Our efforts for developing and evaluating human thinking support tools are summarized. First, the organization and functions of the tools are described briefly, then three levels for evaluation are identified, and several methods in each level are explained. Results for applying the evaluation methods to the tools show the effectiveness of them.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126031323","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}
J. Konishi, S. Shimba, J. Toyama, Mineichi Kudo, M. Shimbo
{"title":"Tabu search for solving optimization problems on Hopfield neural networks","authors":"J. Konishi, S. Shimba, J. Toyama, Mineichi Kudo, M. Shimbo","doi":"10.1109/KES.1999.820237","DOIUrl":"https://doi.org/10.1109/KES.1999.820237","url":null,"abstract":"Over the past few decades, numerous attempts have been made to solve combinatorial optimization problems that are NP-complete or NP-hard in a heuristic approach. A Hopfield-type neural network is a method that is often used to solve problems such as the traveling salesman problem. However, it is difficult to find an optimal solution because it is based on gradient descent and its energy function has many local minima. Therefore, many attempts have been made to find ways of escaping from local minima and to find better solutions. T. Tanaka et al. (1996) succeeded in improving the solutions by controlling the coefficient of the energy function. However, their results were not completely satisfying in terms of the quality of the solutions and the computation time. In order to find better solutions in a short time, we introduced a method called tabu search into a Hopfield-type neural network. Tabu search is a simple and flexible method for obtaining good solutions quickly and has been applied to NP-complete problems. Through computer simulations, better solutions were obtained than those obtained by using an ordinary model. Moreover, the computation time was reduced.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131375865","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":"Developing a fuzzy controller for a helicon plasma source","authors":"T. Lund, A. Cheetham, J. Rayner, S. Zhang","doi":"10.1109/KES.1999.820187","DOIUrl":"https://doi.org/10.1109/KES.1999.820187","url":null,"abstract":"A distributed data acquisition and control system for a helicon plasma source is being developed, making use of microcontrollers linked by the IEEE-488 bus (GPIB) to a central supervisory computer. These microcontrollers enable us to construct intelligent instruments and actuators, one of which is described in this paper. This device makes use of fuzzy logic to control the tuning capacitors in an RF power matching circuit, and will soon control the whole process of coupling RF power into the circuit.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134187325","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}