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
Schematic interpretation and the CLARET consolidated learning algorithm 原理图解释和CLARET合并学习算法
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616853
A. Pearce, T. Caelli
{"title":"Schematic interpretation and the CLARET consolidated learning algorithm","authors":"A. Pearce, T. Caelli","doi":"10.1109/KES.1997.616853","DOIUrl":"https://doi.org/10.1109/KES.1997.616853","url":null,"abstract":"A new learning algorithm, the Consolidated Learning Algorithm based on Relational Evidence Theory (CLARET) is presented, which relies on inductive logic programming and graph matching techniques. In relational evidence theory, two different approaches to evidential learning are consolidated in how they apply to generalising within relational data structures. Attribute-based discrimination (decision trees) is integrated with part-based interpretation (graph matching) for evaluating and updating representations in spatial domains. This allows an interpretation stage to be incorporated into the generalization process. A systematic approach to finding interpretations is demonstrated for an online, hand drawn, schematic diagram and symbols recognition system. The approach uses an adaptive representational bias and search strategy during learning by efficiently grounding the learning procedures in the relational spatial constraints of their application.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"85 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":"116720468","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
Document segmentation and classification with top-down approach 采用自顶向下的方法进行文档分割和分类
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616915
Han Wang, S. Li, S. Ragupathi
{"title":"Document segmentation and classification with top-down approach","authors":"Han Wang, S. Li, S. Ragupathi","doi":"10.1109/KES.1997.616915","DOIUrl":"https://doi.org/10.1109/KES.1997.616915","url":null,"abstract":"A robust algorithm for document segmentation and classification has been implemented. In this algorithm, a top-down approach is adopted due to its fast processing speed and reliability. The approach accounts for every portion of the processed page. It is also capable of image display at different scales and allows editing of classified blocks such as the changing, merging and splitting of blocks. The segmentation and classification processes are explained using examples. A large number of sample document images have been tested with satisfactory results.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"1 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":"122414309","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: 5
FuGeNeSys: Sw and Hw implementation FuGeNeSys:软件和硬件实现
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616908
M. Russo
{"title":"FuGeNeSys: Sw and Hw implementation","authors":"M. Russo","doi":"10.1109/KES.1997.616908","DOIUrl":"https://doi.org/10.1109/KES.1997.616908","url":null,"abstract":"The author shows the main characteristics of the tool called FuGeNeSys. Using the basic techniques of soft computing, FuGeNeSys allows supervised approximation and classification of multi-input/multi-output systems. It is also shown that by using recent results obtained in the field of fuzzy processors it is possible to design a multiprocessor card which will significantly accelerate the learning process.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"54 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":"131795565","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: 5
Hidden node activation differential-a new neural network relevancy criteria 隐节点激活差——一种新的神经网络关联准则
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616920
Patrick Chan Khue Hiang
{"title":"Hidden node activation differential-a new neural network relevancy criteria","authors":"Patrick Chan Khue Hiang","doi":"10.1109/KES.1997.616920","DOIUrl":"https://doi.org/10.1109/KES.1997.616920","url":null,"abstract":"Neural networks have been used in many problems such as character recognition, time series forecasting and image coding. The generalisation of the network depends on its internal structure. Network parameters should be set correctly so that data outside the class will not be overfitted. One mechanism to achieve an optimal neural network structure is to identify the essential components (hidden nodes) and to prune off the irrelevant ones. Most of the proposed criteria used for pruning are expensive to compute and impractical to use for large networks and large training samples. In this paper, a new relevancy criteria is proposed and three existing criteria are investigated. The properties of the proposed criteria are covered in detail and their similarities to existing criteria are illustrated.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"2 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":"133887098","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
Applying fuzzy techniques to particle detectors 模糊技术在粒子探测器中的应用
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616912
G. V. Russo, D. L. Presti, S. Panebanco, C. Petta, N. Randazzo, S. Reito, C. Caligiore, M. Russo, M. Masetti, E. Gandolfi, A. Gabrielli
{"title":"Applying fuzzy techniques to particle detectors","authors":"G. V. Russo, D. L. Presti, S. Panebanco, C. Petta, N. Randazzo, S. Reito, C. Caligiore, M. Russo, M. Masetti, E. Gandolfi, A. Gabrielli","doi":"10.1109/KES.1997.616912","DOIUrl":"https://doi.org/10.1109/KES.1997.616912","url":null,"abstract":"A smart solution concerning the front end and the readout of a Silicon Drift Chamber is proposed. Online data processing will produce a significant decrease in the amount of transmitted data without also losing essential information. A processor that exploits fuzzy logic plays a central role. It is capable of computing, with reasonable precision, the position of the tracks and the total charge released inside the detector.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"61 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":"124698725","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
Distinguishing chaos from random fractal sequences by the comparison of forward and backward predictions: utilization of the difference in time reversal symmetry of time series 通过前后向预测的比较来区分混沌与随机分形序列:利用时间序列时间反转对称性的差异
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616863
M. Naito, N. Tanaka, H. Okamoto
{"title":"Distinguishing chaos from random fractal sequences by the comparison of forward and backward predictions: utilization of the difference in time reversal symmetry of time series","authors":"M. Naito, N. Tanaka, H. Okamoto","doi":"10.1109/KES.1997.616863","DOIUrl":"https://doi.org/10.1109/KES.1997.616863","url":null,"abstract":"The authors propose a method for distinguishing chaos from random fractal sequences which have been difficult to discriminate from chaos. In the proposed method, the time series is predicted both in the forward direction and in the backward direction, and the accuracy of the two types of predictions is compared. They show, considering the time reversal symmetry of time series, that if the time series is chaotic and originates from a dissipative dynamical system, the accuracy is in general better for the forward prediction than for the backward prediction, whereas the accuracy is the same if the time series is a random fractal sequence. The method is also applicable to distinguishing between chaos and stationary noise. It is possible to give a quantitative evaluation of the distinction without a large amount of data or calculation.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"152 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":"134173862","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
Representations of game situations in fuzzy oriented GO system (FOG) 面向模糊的围棋系统(FOG)中博弈情境的表示
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616859
T. Yokogawa
{"title":"Representations of game situations in fuzzy oriented GO system (FOG)","authors":"T. Yokogawa","doi":"10.1109/KES.1997.616859","DOIUrl":"https://doi.org/10.1109/KES.1997.616859","url":null,"abstract":"The paper presents a fuzzy oriented GO system, FOG, and its representations of game situations of GO in the open game. FOG has two basic components; an elementary GO system and a fuzzy organized engine. They communicate and compensate for each other. Representations of situations are by concepts expressed by language (GO terms) and strategic rules are given by the represented concepts. These rules can grasp macroscopic game situations in GO and compensate for reasoning based on game tree search and pattern oriented knowledge.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"14 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":"132071901","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
Logic-enhanced memory for high performance databases 用于高性能数据库的逻辑增强内存
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619431
A. Asthana, N. Soparkar, H. Jagadish, P. Krzyzanowski
{"title":"Logic-enhanced memory for high performance databases","authors":"A. Asthana, N. Soparkar, H. Jagadish, P. Krzyzanowski","doi":"10.1109/KES.1997.619431","DOIUrl":"https://doi.org/10.1109/KES.1997.619431","url":null,"abstract":"Several emerging applications need a high performance, main memory database for which typical memory systems may be inadequate. In particular, the processor memory bandwidth proves to be a major performance limiting factor. We present the design of a back end object oriented database board and argue for its use in implementing high performance, real time applications. Our board uses programmable logic enhanced memory (i.e., data memory with select computing abilities) which is a novel way to obviate the low bandwidth problem for data intensive processing. Our efforts differ significantly from database machines by being more general purpose and targeting the bandwidth issue at a different level of the memory hierarchy. We describe the utility of logic enhanced memory in meeting the needs of high performance databases.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"21 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":"123569755","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 neural network based dynamic reconstruction filter for digital audio signals 基于神经网络的数字音频信号动态重构滤波器
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619448
H. Najafi, Donald W. Moses, Charles H. Hustig, James Kinne
{"title":"A neural network based dynamic reconstruction filter for digital audio signals","authors":"H. Najafi, Donald W. Moses, Charles H. Hustig, James Kinne","doi":"10.1109/KES.1997.619448","DOIUrl":"https://doi.org/10.1109/KES.1997.619448","url":null,"abstract":"The goal of any digital audio system is to sample and reconstruct an analog audio signal, without noticeable changes to the original signal. Currently, two major types of reconstruction filters, brickwall and monotonic filters, are used to smooth a sampled analog audio signal during its reconstruction. Brickwall filters work best on reconstruction of smooth signals and the monotonic filters are best for reconstruction of transient signals. Since audio is composed of mixed transient and smooth signals, both of these filters will introduce undesirable artifacts to the signal during its reconstruction. The paper presents a new neural network based dynamic reconstruction filter that can change its behavior to best match the type of signal that is being filtered.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"9 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":"123751937","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
Application of intelligent multimedia system in an automation-intensive production line 智能多媒体系统在某自动化密集型生产线上的应用
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616916
S. Krishnan, S. Swaminathan
{"title":"Application of intelligent multimedia system in an automation-intensive production line","authors":"S. Krishnan, S. Swaminathan","doi":"10.1109/KES.1997.616916","DOIUrl":"https://doi.org/10.1109/KES.1997.616916","url":null,"abstract":"This paper describes the development of a system involving task-dependent multimedia messages on an automation-intensive production line in a modern manufacturing plant. In order to minimize the mistakes by operators while performing a small percentage of essential (but inevitable) non-automated tasks, a PC-based Intelligent Multimedia Prompt System (IMPS) was conceived. The IMPS is designed to help the operators by reminding them of the steps involved when performing specific non-automated tasks. The three main features of the IMPS are task instructions, interrupt handling and management information. Task instructions prompt the operator about the tasks to be performed. Interrupt handling caters to operations such as abrupt termination of tasks due to unforeseen circumstances. Management information provides task-related information to the supervisors. The IMPS design includes visual displays to correspond with auditory prompt messages. The IMPS was developed for handling manual intervention tasks in the production line of a local manufacturing plant. Laboratory testing and preliminary results indicate that the system is helpful in minimizing human errors.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"21 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":"124078570","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
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