J. Nishino, M. Yamamoto, H. Shirai, Tomohiro Odaka, H. Ogura
{"title":"Fuzzy linguistic facial caricature drawing system","authors":"J. Nishino, M. Yamamoto, H. Shirai, Tomohiro Odaka, H. Ogura","doi":"10.1109/KES.1998.725887","DOIUrl":"https://doi.org/10.1109/KES.1998.725887","url":null,"abstract":"Considers a realization of a process drawing facial caricatures and exaggerating them using the concept of fuzzy information granulation. Face space is introduced, for the facial caricature drawn in computer graphics. The linguistic terms which indicate features of one's face are given as a fuzzy set by means of the concept of computing with words. Exaggerated knowledge is realized as rules on linguistic labels. Also simulation examples of facial caricature drawing and exaggerating are shown.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"14 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":"127665614","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":"Hyperbox model for fuzzy rule evaluation in neural networks","authors":"D. Durmaz, F. Alpaslan","doi":"10.1109/KES.1998.725929","DOIUrl":"https://doi.org/10.1109/KES.1998.725929","url":null,"abstract":"A model that is suggested for pattern classification by using fuzzy sets in a neural network is modified to include fuzzy rule evaluation. The proposed model is aimed to be used for medical diagnosis applications. In this paper, two variations of the original model are described. The drawbacks and advantages of both models are discussed along with the implementation results. We used the maximum hyperbox size parameter (/spl theta/) in the first model but not in the second one. The effects of /spl theta/ and the defuzzification methods are also examined only for the first model. The related learning algorithms, which adjust the minimum and the maximum points for hyperboxes that represent the fuzzy ranges, are given with the necessary changes.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"71 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":"129356133","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 more efficient man/machine interface: fusion of the interacting telethesis and smart wheelchair projects","authors":"P. Pino, P. Arnoud, E. Brangier","doi":"10.1109/KES.1998.725951","DOIUrl":"https://doi.org/10.1109/KES.1998.725951","url":null,"abstract":"Presents a new and more efficient man/machine interface resulting from the fusion of two projects: the smart wheelchair project and the interacting telethesis project. This new interface allows a more natural control of the automatic motion capabilities of the smart wheelchair VAHM (autonomous vehicle for motor impaired people). Indeed, the pilot needs only to make his request (switch on the TV for example) without giving details about its location. The VAHM project aims to bring piloting assistance for motor impaired people to powered wheelchairs using techniques coming from mobile robotics. It is possible to call upon local primitives like \"wall following\" or \"automatic forward motion\", or to plan an automatic trajectory. The second project aims to realize a man/machine communication interface for people with motor impairments; interface defined as an \"interacting telethesis\", i.e. as a cognitive and/or valid motion resource(s) extension of the user. Therefore, the interacting telethesis allows disabled persons to be able to communicate (read, write, speak, listen, warn) with other people and to act on their environment (TV, music, etc.).","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"76 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":"115335456","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":"Neural associative memory for intelligent information processing","authors":"M. Hattori, M. Hagiwara","doi":"10.1109/KES.1998.725937","DOIUrl":"https://doi.org/10.1109/KES.1998.725937","url":null,"abstract":"In this paper, first we derive a novel relaxation method for the system of linear inequalities and apply it to the learning for associative memories. Since the proposed intersection learning can guarantee the recall of all training data, it can greatly enlarge the storage capacity of associative memories. In addition, it requires much less weights renewal times than the conventional methods. We also propose a multimodule associative memory which can be learned by the intersection learning algorithm. The proposed associative memory can deal with many-to-many associations and it is applied to a knowledge processing task. Computer simulation results show the effectiveness of the proposed learning algorithm and associative memory.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"30 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":"127193935","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":"Specialised neural network for learning synonyms and related concepts in large document collections","authors":"P. Baranyi, P. Aradi, L. Kóczy, Tom Gedeon","doi":"10.1109/KES.1998.725848","DOIUrl":"https://doi.org/10.1109/KES.1998.725848","url":null,"abstract":"For very large document collections or high volume streams of documents, finding relevant documents is a major information filtering problem. One of the main types of information retrieval systems produces a word frequency measure estimated by some important parts of the document using neural network approaches. This paper reports a new network structure for this task. It is specialised considering the main difficulties of these kinds of applications, namely, the calculation time complexity. It will be pointed out that the calculation, hence, the learning time is much reduced applying the new algorithm, however, the result is significantly improved compared to the former approaches, which offer a possibility to increase the number of considered words, hence, improve the effectiveness of information filtering systems.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"82 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":"126062244","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":"Attractor systems and analog computation","authors":"H. Siegelmann, S. Fishman","doi":"10.1109/KES.1998.725853","DOIUrl":"https://doi.org/10.1109/KES.1998.725853","url":null,"abstract":"Attractor systems are useful in neurodynamics, mainly in the modeling of associative memory. This paper presents a complexity theory for continuous phase space dynamical systems with discrete or continuous time update, which evolve to attractors. In our framework we associate complexity classes with different types of attractors. Fixed points belong to the class BPP/sub d/, while chaotic attractors are in NP/sub d/. The BPP=NP question of classical complexity theory is translated into a question in the realm of chaotic dynamical systems. This theory enables an algorithmic analysis of attractor networks and flows for the solution of various problem such as linear programming. We exemplify our approach with an analysis of the Hopfield network.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"79 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":"124105704","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":"Intelligent decision support systems utilizing neural networks and temporal difference learning","authors":"N. Baba","doi":"10.1109/KES.1998.725822","DOIUrl":"https://doi.org/10.1109/KES.1998.725822","url":null,"abstract":"The use of intelligent techniques in various decision support systems has recently become one of the most exciting and promising application areas. In this paper, we try to utilize neural networks and temporal difference learning method to construct an intelligent decision support system for dealing stocks. We also briefly touch upon an intelligent sales prediction system which has been developed in our group.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"68 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":"125111485","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":"New Kansei machine vision application. A prospect for human sensory factors in machine vision","authors":"H. Koshimizu, N. Nagata","doi":"10.1109/KES.1998.725909","DOIUrl":"https://doi.org/10.1109/KES.1998.725909","url":null,"abstract":"Describes the trends of the Kansei machine vision technology. This technology is expected to be a breakthrough, answering new machine vision needs such as simulating human vision, monitoring human beings and human-machine interfaces. The paper presents its application fields, technical topics and various approaches including a facial caricaturing system and a pearl-quality evaluation system.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"21 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":"122325858","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":"Right brain computing hardware: a psychological brain model on silicon","authors":"T. Shibata","doi":"10.1109/KES.1998.726004","DOIUrl":"https://doi.org/10.1109/KES.1998.726004","url":null,"abstract":"Despite the enormous power of present-day computers, digital systems cannot respond to real-world events in real time. Biological systems built with very slow chemical transistors, however, are very fast in such tasks as seeing, recognizing, and taking actions. The paper will discuss what we can learn from biological computing systems and how we can implement the principle using the state-of-the-art silicon technology. Intelligent LSI systems based on the psychological model of a brain are proposed. The system stores the past experience in nonvolatile vast analog memories and recalls the most similar event to a current input using the association processor working in the analog/digital-merged decision-making principle.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"42 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":"116460982","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":"Neighborhood structures for genetic local search algorithms","authors":"T. Murata, H. Ishibuchi, M. Gen","doi":"10.1109/KES.1998.725920","DOIUrl":"https://doi.org/10.1109/KES.1998.725920","url":null,"abstract":"We examine the performance of a genetic local search (GLS) algorithm for flowshop scheduling problems. The GLS is a hybrid algorithm of a local search and a genetic algorithm. We have already modified the local search procedure in order to improve the performance of the GLS. In the modified local search procedure, all the neighborhood solutions are not examined. The performance of the GLS is not sensitive to the choice of parameter values such as the crossover probability and the mutation probability. That is the main advantage of the GLS. In this paper, we examine the relation between a mutation operator and a local search procedure. By computer simulations on flowshop scheduling problems, we find that a shift change is appropriate for the local search procedure in the GLS.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"50 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":"134006438","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}