发布求助
文献互助 智能选刊 最新文献

Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97最新文献

筛选
英文 中文
A multimedia interactive environment: a front-end module for modeling and simulation 多媒体交互环境:前端建模与仿真模块
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616919
J. Y. Ang, Hee King Jim
{"title":"A multimedia interactive environment: a front-end module for modeling and simulation","authors":"J. Y. Ang, Hee King Jim","doi":"10.1109/KES.1997.616919","DOIUrl":"https://doi.org/10.1109/KES.1997.616919","url":null,"abstract":"In this paper, the \"Multimedia Interactive Environment (MIE)\" under development at Gintic is described. This environment introduces the user to simulation concepts, provides guidance during problem formulation, helps in model building and finally assists in analysing the results.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124899742","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}
引用次数: 0
CT image reconstruction by the Boltzmann machine 用玻尔兹曼机重建CT图像
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619405
Z. Nakao, M. Noborikawa, Yenwei Chen, Yasuyuki Kina
{"title":"CT image reconstruction by the Boltzmann machine","authors":"Z. Nakao, M. Noborikawa, Yenwei Chen, Yasuyuki Kina","doi":"10.1109/KES.1997.619405","DOIUrl":"https://doi.org/10.1109/KES.1997.619405","url":null,"abstract":"The Boltzmann machine model is used in CT image reconstruction from four projections. The system is based on Boltzmann simulated annealing for adaptation of pixel values. As the temperature is decreased, the gray level of images is increased exponentially to 256. Satisfactory agreement between the original and reconstructed images was obtained in simulation, and the results obtained are compared to those obtained by the well-known algebraic reconstruction technique (ART), and it was found that the neural network method is more effective than ART when the number of projection directions is very limited.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124039590","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}
引用次数: 0
A multi-agent architecture for situation awareness 用于态势感知的多智能体体系结构
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619429
T. Nguyen
{"title":"A multi-agent architecture for situation awareness","authors":"T. Nguyen","doi":"10.1109/KES.1997.619429","DOIUrl":"https://doi.org/10.1109/KES.1997.619429","url":null,"abstract":"The paper describes an architecture of a system for assisting an aircraft crew in enhancing its situation awareness by creating a complete surveillance picture of the environment in real time. The architecture is based on the framework of the multi agent technology where tasks are solved cooperatively among heterogeneous intelligent agents; each performs one defined function. This architecture offers a number of advantages such as synergy, scalability, reusability, reliability.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130710015","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}
引用次数: 4
Handwriting recognition for a postal check reading system 用于邮政支票阅读系统的手写识别
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616852
T. M. Ha, Guido Kaufmann, Matthias Zimmermann, H. Bunke
{"title":"Handwriting recognition for a postal check reading system","authors":"T. M. Ha, Guido Kaufmann, Matthias Zimmermann, H. Bunke","doi":"10.1109/KES.1997.616852","DOIUrl":"https://doi.org/10.1109/KES.1997.616852","url":null,"abstract":"This paper discusses several aspects of automatic handwriting recognition designed for a postal check reading system. We first present the general methodology, including a new approach called perturbation method. Then we explain how the general methodology is applied to three subproblems in handwriting recognition, namely, the recognition of isolated numerals: that of numeral strings, and the recognition of cursively handwritten words drawn from a small lexicon. Experimental results performed on worldwide standard databases show that our systems are either equivalent to or better than state-of-the-art systems. A preliminary experiment of reading real Swiss checks shows that the system rejects about 50% and correctly recognises the remaining checks.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122142100","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}
引用次数: 1
Efficient fuzzy modeling and evaluation criteria 高效的模糊建模和评价标准
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616921
S. Matsushita, T. Furuhashi, H. Tsutsui, Y. Uchikawa
{"title":"Efficient fuzzy modeling and evaluation criteria","authors":"S. Matsushita, T. Furuhashi, H. Tsutsui, Y. Uchikawa","doi":"10.1109/KES.1997.616921","DOIUrl":"https://doi.org/10.1109/KES.1997.616921","url":null,"abstract":"Hierarchical fuzzy modeling using fuzzy neural networks (FNN) is one of the effective approaches for modeling of nonlinear systems. Decision of antecedent structures of fuzzy models of nonlinear systems is made possible by a combination of FNN and genetic algorithm (GA). The disadvantage of this fuzzy modeling method is that the learning of FNN is time consuming. This paper presents an efficient fuzzy modeling method using simple fuzzy inference. The results of fuzzy modeling are heavily dependent on evaluation criteria. This paper also studies effects of evaluation criteria for the decision of the antecedent structure. Numerical experiments are done.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115493784","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}
引用次数: 3
Rule extraction from trained artificial neural network with functional dependency preprocessing 基于函数依赖预处理的人工神经网络规则提取
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619437
S. Geva, M. T. Wong, M. Orlowski
{"title":"Rule extraction from trained artificial neural network with functional dependency preprocessing","authors":"S. Geva, M. T. Wong, M. Orlowski","doi":"10.1109/KES.1997.619437","DOIUrl":"https://doi.org/10.1109/KES.1997.619437","url":null,"abstract":"The paper describes a technique to extract symbolic rules from a trained artificial neural network with functional dependency preprocessing. RULEX (R. Andrews and S. Geva, 1994; 1995), classified as a decompositional technique of rule extraction from trained neural network in a recent survey by R. Andrews et al. (1995), is used to extract symbolic rules from data that have been preprocessed by identification of functional dependency. The identification of functional dependency offers several advantages. It can lead to significant reductions in the computational load, to reduction in the number and complexity of derived rules and to the discovery of alternative solutions that would otherwise be ignored by some methods due to implicit or explicit procedural bias. Benchmark datasets from the UCI repository of machine learning databases are used in the testing. Experimental results indicate that by including functional dependency preprocessing performance of RULEX can be improved. Good rule quality is obtained by applying RULEX with functional dependency preprocessing when compared to symbolic rule extraction technique C4.5.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124488477","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}
引用次数: 4
Generation of fuzzy k-partitions based on tolerance relations and maximal consistency 基于容差关系和最大一致性的模糊k分区的生成
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619412
T. Murai, A. Kitada, Yoshiharu Sato
{"title":"Generation of fuzzy k-partitions based on tolerance relations and maximal consistency","authors":"T. Murai, A. Kitada, Yoshiharu Sato","doi":"10.1109/KES.1997.619412","DOIUrl":"https://doi.org/10.1109/KES.1997.619412","url":null,"abstract":"A method of generating fuzzy k-partitions is proposed based on tolerance relations and maximal consistency. In particular, emphasis is put on the point that general cases of more than two clusters can be reduced to special cases of two clusters in both crisp and fuzzy partitions. Then a way of generating fuzzy subsets can be shown to be applied to the generation of fuzzy k-partitions.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124548534","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}
引用次数: 2
Extracting stochastic machines from recurrent neural networks trained on complex symbolic sequences 从复杂符号序列训练的递归神经网络中提取随机机器
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619435
P. Tiňo, V. Vojtek
{"title":"Extracting stochastic machines from recurrent neural networks trained on complex symbolic sequences","authors":"P. Tiňo, V. Vojtek","doi":"10.1109/KES.1997.619435","DOIUrl":"https://doi.org/10.1109/KES.1997.619435","url":null,"abstract":"We train a recurrent neural network on a single, long, complex symbolic sequence with positive entropy. The training process is monitored through information theory based performance measures. We show that although the sequence is unpredictable, the network is able to code the sequence's topological and statistical structure in recurrent neuron activation scenarios. Such scenarios can be compactly represented through stochastic machines extracted from the trained network. Generative models, i.e. trained recurrent networks and extracted stochastic machines, are compared using entropy spectra of generated sequences. In addition, entropy spectra computed directly from the machines capture generalization abilities of extracted machines and are related to a machines' long term behavior.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"164 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123104887","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}
引用次数: 13
A proposed model of human consciousness system with applications in pattern recognition 一种人类意识系统模型及其在模式识别中的应用
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616883
K. Le
{"title":"A proposed model of human consciousness system with applications in pattern recognition","authors":"K. Le","doi":"10.1109/KES.1997.616883","DOIUrl":"https://doi.org/10.1109/KES.1997.616883","url":null,"abstract":"Human recognition is a complex, efficient process which, for thousands of years, people have tried to analyse but have not yet fully understood. Recently, with advances in psychology, medicine and computer engineering in some research fields such as neural networks, fuzzy set theory, genetic algorithms, etc., people have tried to simulate the human brain and received significant results in the pattern recognition field. This paper proposes a model of a human consciousness system with applications in pattern recognition. The model explains how our brain saves, extracts and retrieves data. The model can recognise patterns with noise. Furthermore, when part of the model is damaged, the model can be required and re-used. An implementation of the model and some experimental results are also presented.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129879813","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}
引用次数: 0
A fuzzy controller using floating membership functions for the braking of a long haul train 基于浮动隶属函数的长途列车制动模糊控制器
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619423
G. Horwood, D. Kearney, Z. Nedic
{"title":"A fuzzy controller using floating membership functions for the braking of a long haul train","authors":"G. Horwood, D. Kearney, Z. Nedic","doi":"10.1109/KES.1997.619423","DOIUrl":"https://doi.org/10.1109/KES.1997.619423","url":null,"abstract":"Automatic train control in railway systems is gaining increasing importance with the continuous need to reduce excess fuel consumption and unnecessary time delays while still maintaining a safe and reliable rail service. The paper describes a fuzzy logic controller which forces a train to track a safe braking curve (ATP curve), thus ensuring the train avoids time consuming conservative braking, without compromising the train safety.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129130083","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}
引用次数: 1
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信