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
Multi-module network associating patterns and symbols with attention mechanism 多模块网络关联模式和符号与注意机制
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616878
Y. Hattori, T. Furuhashi, Y. Uchikawa
{"title":"Multi-module network associating patterns and symbols with attention mechanism","authors":"Y. Hattori, T. Furuhashi, Y. Uchikawa","doi":"10.1109/KES.1997.616878","DOIUrl":"https://doi.org/10.1109/KES.1997.616878","url":null,"abstract":"The authors present a new network which consists of symbol layers and a pattern layer for acquiring concepts and inferring meanings of patterns and symbols. Nonlinear dynamics which can cause chaotic vibration in the internal state of the network is used for the recollection of various related patterns and symbols. The authors also propose a multi-module network with the multiple symbol-pattern networks for association and inference from vague patterns with multiple meanings. This paper presents an attention mechanism for this model. This new mechanism works to control the search area for related patterns and symbols. Simulation using face patterns consisting of eyebrow, eye and mouth patterns are done to show that the attention mechanism works well to recall related facial expressions successively.","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":"133458758","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
Learning algorithm for RBF networks as features extractors RBF网络作为特征提取器的学习算法
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616905
H. Teodorescu, C. Bonciu
{"title":"Learning algorithm for RBF networks as features extractors","authors":"H. Teodorescu, C. Bonciu","doi":"10.1109/KES.1997.616905","DOIUrl":"https://doi.org/10.1109/KES.1997.616905","url":null,"abstract":"A specific learning algorithm, developed in the context of the hybrid linear-nonlinear features space filtering (FSF) system architecture, is proposed. The neural FSF system presented is based on a radial-basis functions (RBF) decomposition of the input data space. An adaptive linear combiner (ALC) is used as transversal filter. The features space is generated by the parameters of the local nonlinear function decomposition. ALC coefficients are adapted with this algorithm to minimize the distance, in the features space, between the reference features vector and the actual features vector obtained from the noisy data. The fuzzy estimation of features matching in the frame of this algorithm is also briefly discussed. Simulation results of spectrography/electrophoresis (EPK)-type data filtering are presented.","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":"115617223","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
Robot arm controller using fuzzy speech recognition 机器人手臂控制器采用模糊语音识别
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616857
T. Hung, Hung-Ching Lu
{"title":"Robot arm controller using fuzzy speech recognition","authors":"T. Hung, Hung-Ching Lu","doi":"10.1109/KES.1997.616857","DOIUrl":"https://doi.org/10.1109/KES.1997.616857","url":null,"abstract":"Fuzzy set theory techniques are employed to develop a speech recognition system. The idea is to generate a control signal for driving a robot arm system using fuzzy speech recognition. First, the authors design an independent microprocessor system combined with the control circuit of the robot arm. The speech signal is then analyzed in accordance with fuzzy set logic. The speech signal is divided into several units which produces the feature parameters in accordance with the locations of the frequency spectrum peak. By using training, it will generate the speech reference pattern and can be transformed into a membership function. After calculating pattern similarity, the recognition results and the output control signal are produced.","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":"115731960","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
Classification of symbolic data using fuzzy set theory 符号数据的模糊集分类
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619413
M. Dinesh, K. Gowda, T. V. Ravi
{"title":"Classification of symbolic data using fuzzy set theory","authors":"M. Dinesh, K. Gowda, T. V. Ravi","doi":"10.1109/KES.1997.619413","DOIUrl":"https://doi.org/10.1109/KES.1997.619413","url":null,"abstract":"Proposes a new algorithm to carry out classification of symbolic data using fuzzy set theory without any a priori assumption. The aim is to show how to apply fuzzy concepts to symbolic data. The new algorithm involves two stages. In the first stage, the number of classes present in the data is found using a cluster indicator, and in the second stage, fuzzy descriptions on symbolic data have been developed. The proposed work is new in the sense that no research work has previously been reported on the application of fuzzy concepts to symbolic data classification. The results of the proposed algorithm are compared with other symbolic clustering techniques.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"19 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":"114709223","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
Estimation of class regions in feature space using rough set theory 基于粗糙集理论的特征空间类区域估计
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619411
F. Taniguchi, Mineichi Kudo, M. Shimbo
{"title":"Estimation of class regions in feature space using rough set theory","authors":"F. Taniguchi, Mineichi Kudo, M. Shimbo","doi":"10.1109/KES.1997.619411","DOIUrl":"https://doi.org/10.1109/KES.1997.619411","url":null,"abstract":"A technique to find sure and ambiguous regions in a class is proposed. These regions are defined by lower approximations in rough set theory. Outputs of many classifiers are combined in order to make such lower approximations and to give class labels to them. As an application of this technique, a classifier with a few misclassifications is proposed.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"40 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":"126169225","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
Genetic VLSI circuit partitioning with dynamic embedding 动态嵌入的VLSI遗传电路划分
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619424
B. Moon, Chun-Kyung Kim
{"title":"Genetic VLSI circuit partitioning with dynamic embedding","authors":"B. Moon, Chun-Kyung Kim","doi":"10.1109/KES.1997.619424","DOIUrl":"https://doi.org/10.1109/KES.1997.619424","url":null,"abstract":"This paper suggests a new genetic algorithm (GA) for VLSI circuit partitioning problem. In a genetic algorithm, the encoding of a solution plays an important role. The key feature of the new genetic algorithm is a technique to provide dynamically many encodings in which encodings themselves undergo evolution. Before generating every new solution, we first generate a new encoding by combining two encodings chosen from a pool containing diverse encodings. The new solution is generated by a crossover which combines two parent solutions which are temporarily encoded by the generated encoding scheme. That is, a new solution is generated by a two-layered crossover. Depending on the new solution's quality and its improvement over the parents solutions, a fitness value is assigned to the underlying encoding. The encoding is discarded or enter the pool based on the fitness. Two populations are maintained for this purpose: one for solutions and the other for diverse encodings. On experiments with the public ACM/SIGDA benchmark circuits, the new genetic algorithm significantly outperformed recently published state-of-the-art approaches.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"99 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":"125079670","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
Intelligent electronic system on DSN basis 基于DSN的智能电子系统
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616914
A. Sachenko
{"title":"Intelligent electronic system on DSN basis","authors":"A. Sachenko","doi":"10.1109/KES.1997.616914","DOIUrl":"https://doi.org/10.1109/KES.1997.616914","url":null,"abstract":"Describes the structure and features of an intelligent electronic system (IES) with fourth (and elements of fifth) levels of intelligence. The IES includes a distributed sensor network (DSN) and contains: measurement and processing, and communication subsystems. The adaptive and iterative algorithms of the IES are based on two sensor defect compensation methods: calibration and prediction. The principles of compensation, the simulation of correction and measurement, and IES modeling are also described. The proposed approach has been implemented in industry.","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":"130573802","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
An artificial neural network approach to handwriting recognition 手写识别的人工神经网络方法
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616872
W. Goh, D. Mital, H. Babri
{"title":"An artificial neural network approach to handwriting recognition","authors":"W. Goh, D. Mital, H. Babri","doi":"10.1109/KES.1997.616872","DOIUrl":"https://doi.org/10.1109/KES.1997.616872","url":null,"abstract":"This paper explores the use of ANN (artificial neural networks) in handwriting recognition. The approach has been found to be very suitable for handwritten character recognition as it provides fast feature extraction and classification. Using the EBP (error backpropagation) algorithm, networks of relatively small sizes (ones requiring modest memory requirements) which can be trained in a reasonably short time were used. The recognition accuracy of the system has been found to be more than 97% with a response speed of about 1 character per second.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"29 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":"125404764","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: 7
A comparison between single and combined backpropagation neural networks in the prediction of turnover 单反向传播神经网络与组合反向传播神经网络在营业额预测中的比较
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619408
T. Tchaban, J. P. Griffin, M. J. Taylor
{"title":"A comparison between single and combined backpropagation neural networks in the prediction of turnover","authors":"T. Tchaban, J. P. Griffin, M. J. Taylor","doi":"10.1109/KES.1997.619408","DOIUrl":"https://doi.org/10.1109/KES.1997.619408","url":null,"abstract":"Artificial neural networks are now being extensively used in the area of marketing analysis as they are well suited to this type of non-linear problem. A retail company planned to improve its performance by using neural networks to predict turnover and data used in the experiment was provided by the company. The study compares the performance of a combination of neural networks to that of a single neural network. The results show that backpropagation neural networks are effective tools which can give good results in solving a non-linear prediction problem, even when data is poorly represented.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"IM-36 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":"126642888","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: 26
Multi-scale adaptive segmentation using edge and region based attributes 基于边缘和区域属性的多尺度自适应分割
Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616854
B. McCane, T. Caelli
{"title":"Multi-scale adaptive segmentation using edge and region based attributes","authors":"B. McCane, T. Caelli","doi":"10.1109/KES.1997.616854","DOIUrl":"https://doi.org/10.1109/KES.1997.616854","url":null,"abstract":"The authors present an adaptive multi-scale algorithm using edge and region information for segmenting intensity images into closed regions. The need for segmentation is determined by region statistics and segmentation is actually performed using edge based information. Results are shown for a number of images displaying significant improvements over mono-scale segmentation.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"29 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":"126454245","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: 14
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：481959085
Book学术官方微信