{"title":"Agents and classifiers a transaction logic approach","authors":"Manuel Santos, José Neves, O. Belo","doi":"10.1109/KES.1998.725997","DOIUrl":"https://doi.org/10.1109/KES.1998.725997","url":null,"abstract":"Presents a transaction logic (I/sub R/) formal specification of a distributed architecture for learning classifier systems (LCS) based on a blackboard as a shared database and a set of agents, an architecture that brings parallelism to the LCS functionalities and caters for the distribution of classifiers and associate processes-the DICE system. /spl Ifr//sub R/ captures the behaviour of the system in terms of state changes due to elementary updates embedded in the agent's transactions. The blackboard is viewed as an active database system and the agents as a transaction bases; that is, sets of active rules and transactions.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129745836","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":"Living with ZK-an approach towards communication with analogue messages","authors":"Toshiro Minami, H. Sazuka, S. Hirokawa, T. Ohtani","doi":"10.1109/KES.1998.725872","DOIUrl":"https://doi.org/10.1109/KES.1998.725872","url":null,"abstract":"It is well known that we communicate more with non-verbal means than verbal ones. It is also true that, when we communicate using paper and pencil, we use not only words and text but also use marks, symbols, and other non-verbal information such as arrangement and color. The paper proposes an approach to electronic communication which allows verbal and non-verbal (or analogue) messages. ZK (Zeichenblock) allows us to exchange analogue messages in a network-transparent fashion. Its potential importance is demonstrated with applications such as an analogue questionnaire and concept representation. These analogue data, represented as ZK-scripts, are effectively distributed by a \"word-of-mouth\" mechanism.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130348175","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":"Degree of familiarity ART2 in fuzzy fusion landmine detection","authors":"A. Filippidis, P. Lozo, L. Jain","doi":"10.1109/KES.1998.725934","DOIUrl":"https://doi.org/10.1109/KES.1998.725934","url":null,"abstract":"The self organising network ART2 has been modified to provide a fuzzy output value, which indicated the degree of familiarity of a new analogue input pattern to previous patterns stored in the long term memory weights of the network. The outputs of the multilayer perceptron and this modification output of ART2 allows it to now provide an analogue value to a fuzzy rule-based fusion technique which also uses a processed polarisation resolved image as its third input. In real-time these two classifier outputs indicate the likelihood of a surface landmine target when presented with a number of multispectral and textural bands. Due to the modifications in ART2 this updated alternative architecture has improved real-time landmine detection capabilities although the registration of all bands is more critical to the accuracy of results in this case. The real-time fuzzy rule based system has detected two of the 3 landmines and the landmine surrogate with 2 false alarms.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123487274","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}
Y. Okabe, T. Kouhara, H. Hayashi, Atsushi Narusawa, M. Kitagawa, M. Miyao
{"title":"Moderatism: new concept for self-organization of neural networks","authors":"Y. Okabe, T. Kouhara, H. Hayashi, Atsushi Narusawa, M. Kitagawa, M. Miyao","doi":"10.1109/KES.1998.725979","DOIUrl":"https://doi.org/10.1109/KES.1998.725979","url":null,"abstract":"A self-organization mechanism, \"moderatism\" is proposed, by which the input-to-output relationship of neural networks is automatically formed so as to adapt to the environment, even if there are feedback loops inside and/or outside. By applying this organization mechanism, it is shown that the networks acquire the reflex to avoid the dangerous stimulus. Also the networks start self-oscillation by themselves to get some amount of stimulus when there is no external signal.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121176559","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 analog VLSI which emulates biological vision","authors":"T. Yagi, Y. Hayashida, S. Kameda","doi":"10.1109/KES.1998.726008","DOIUrl":"https://doi.org/10.1109/KES.1998.726008","url":null,"abstract":"A linear analog network model is proposed to describe the neural circuit of the outer retina. Using the model, we characterized the spatial filtering properties of the circuit in terms of the standard regularization theory in which the early vision problems are attributed to minimization of a cost function. Inspired by the algorithm/architecture of the circuit, a vision chip was designed using analog CMOS VLSI circuit technology. The chip fabricated is an one-dimensional 100 pixel line sensor. In the chip, sample/hold amplifier circuits are incorporated to compensate for the fixed pattern noise of photosensors as well as statistic transistor mismatch. The chip effectively extracts contour of given images by controlling the receptive field size, simulating a light-adaptive mechanism suggested in the vertebrate retinal circuit.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113938267","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}
T. Ohtani, H. Ichihashi, T. Miyoshi, K. Nagasaka, Y. Kanaumi
{"title":"Structural learning of neurofuzzy GMDH with Minkowski norm","authors":"T. Ohtani, H. Ichihashi, T. Miyoshi, K. Nagasaka, Y. Kanaumi","doi":"10.1109/KES.1998.725899","DOIUrl":"https://doi.org/10.1109/KES.1998.725899","url":null,"abstract":"There have been many studies of mathematical models of neural networks. However, there always arises a problem of determining their optimal structures due to the lack of prior information. We propose a procedure for the structure clarification of neurofuzzy GMDH model whose building blocks are represented by the radial basis functions network. The proposed method prunes the unnecessary links and units from the larger network to identify, as well as to clarify the network structure by minimizing the Minkowski norm of the derivatives of the building blocks.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"193 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134193194","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":"Modelling communication systems in a resource allocation process using coloured Petri nets","authors":"C. Janczura, I. Coat","doi":"10.1109/KES.1998.725947","DOIUrl":"https://doi.org/10.1109/KES.1998.725947","url":null,"abstract":"The paper presents a coloured Petri net model of a communication network which captures certain social and temporal characteristics of the network. The coloured Petri net is simulated over a period of time and the observed characteristics of the network are recorded. Based on these observations, the new model is constructed to represent the accumulated (partial) knowledge. Some initial basic analysis of the derived model is conducted.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130698822","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 overview and new methods in fuzzy clustering","authors":"S. Miyamoto","doi":"10.1109/KES.1998.725825","DOIUrl":"https://doi.org/10.1109/KES.1998.725825","url":null,"abstract":"Principal methods in nonhierarchical and hierarchical fuzzy clustering are overviewed. In particular, the method of fuzzy c-means is focused upon and recent algorithms in fuzzy c-means are described. It is shown that the concept of regularization plays an important role in the fuzzy c-means. Classification functions induced from fuzzy clustering are discussed and variations of the standard fuzzy c-means are introduced. The hierarchical classification based on the transitive closure is equivalent to the single link method of agglomerative clustering. The roles of the concept of fuzziness in nonhierarchical and hierarchical methods are thus contrasted.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133593174","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":"On the treatment of imperfect information in intelligent databases","authors":"M. Nakata, G. Resconi, T. Murai","doi":"10.1109/KES.1998.725968","DOIUrl":"https://doi.org/10.1109/KES.1998.725968","url":null,"abstract":"A relational data model is extended under a modal logic approach so that it can deal with different kinds of imperfect information. In the extended model the imperfect information is uniformly represented in a set of possible worlds and an accessibility relation. This leads to the extended data model having the same operations to different kinds of imperfect information. Moreover, the model can support flexible queries. The approach gives fundamentals to integrate different kinds of databases handling different types of imperfect information.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"172 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133272347","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":"Hardware of structured brain computer","authors":"T. Ae, K. Sakai, Hiroyuki Araki, N. Honda","doi":"10.1109/KES.1998.726019","DOIUrl":"https://doi.org/10.1109/KES.1998.726019","url":null,"abstract":"We have proposed a two-level architecture for brain computing, where two levels are introduced for processing of meta-symbol. At Level 1 a conventional pattern recognition is performed, where neural computation is included, and its output gives the meta-symbol which is a symbol enlarged from a symbol to a kind of pattern. At Level 2 an algorithm acquisition is made by using a state machine for abstract states (which is a meta-symbol expression). We are also developing the VLSI chips at each level for the structured brain computer (SBC) version 1.0. To explain SEC we introduce the brain computing and the artificial memory system as well as the hardware of SBC.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"469 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115869797","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}