发布求助
文献互助 智能选刊 最新文献

VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.最新文献

筛选
英文 中文
Internet economic news gathering and classification: a neural network software agent based approach 互联网经济新闻采集与分类:一种基于神经网络软件代理的方法
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181446
E. M. Duarte, A. Braga, J. L. Braga
{"title":"Internet economic news gathering and classification: a neural network software agent based approach","authors":"E. M. Duarte, A. Braga, J. L. Braga","doi":"10.1109/SBRN.2002.1181446","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181446","url":null,"abstract":"The explosive growth on the amount of information available on the Internet makes it a hard task to select what is worth reading in our scarce available time. The project described in this paper tackles this problem using techniques taken from the areas of autonomous agents and artificial neural networks. An agent for economic news gathering and classification was designed implemented and successfully tested over sites about economy available on the Internet. Inputs to the system are news text picked up by software agents from selected Internet economic sites, and the outputs are those same news classified by topics of interest in at most six classes. The classification is based on an artificial neural network that runs inside the classification agent, especially trained with patterns that allow carrying out the desired news analysis and classifications.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133356306","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
Segmentation of digitized mammograms using self-organizing maps in a breast cancer computer aided diagnosis system 在乳腺癌计算机辅助诊断系统中使用自组织图分割数字化乳房x线照片
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181458
T. André, Antônio Carlos Roque da Silva Filho
{"title":"Segmentation of digitized mammograms using self-organizing maps in a breast cancer computer aided diagnosis system","authors":"T. André, Antônio Carlos Roque da Silva Filho","doi":"10.1109/SBRN.2002.1181458","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181458","url":null,"abstract":"The objective of this work is to develop a digitized mammogram feature extraction approach using Kohonen's self-organizing maps (SOM). Once developed, the SOM network can be used as the first processing stage in a breast cancer computer aided diagnosis system. Its role is to offer segmented data as input to a second stage dedicated to the diagnosis task, which is implemented via a multilayer perceptron trained by the backpropagation algorithm.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132739017","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: 8
Pattern recognition of gases of petroleum based on RBF model 基于RBF模型的石油气体模式识别
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181445
Maria Silva Santos Barbosa, Teresa B Ludermir, Marizete Silva Santos, F. L. D. Santos, José Edison Gomes de Souza, C. P. D. Melo
{"title":"Pattern recognition of gases of petroleum based on RBF model","authors":"Maria Silva Santos Barbosa, Teresa B Ludermir, Marizete Silva Santos, F. L. D. Santos, José Edison Gomes de Souza, C. P. D. Melo","doi":"10.1109/SBRN.2002.1181445","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181445","url":null,"abstract":"In the case of aerial accident spreading out dangerous gases into the atmosphere, an instrument called electronic nose can warn about the beginning of petroleum derived leaks. In this paper we present the architecture of the neural network for pattern recognition of gases of petroleum based on an RBF model. With this model we analyzed the pattern recognition of five gases: ethane, methane, propane, butane and carbon monoxide, separated in three classes of problems.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122513193","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
Spatially adaptive image restoration by neural network filtering 基于神经网络滤波的空间自适应图像恢复
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181467
A. S. Palmer, M. Razaz, D. Mandic
{"title":"Spatially adaptive image restoration by neural network filtering","authors":"A. S. Palmer, M. Razaz, D. Mandic","doi":"10.1109/SBRN.2002.1181467","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181467","url":null,"abstract":"When using a regularized approach for image restoration there is always a compromise between image sharpness and noise suppression. Therefore, the main problem is to remove as much noise as possible while preserving sharpness in the restoration. To this cause we introduce a spatially regularized neural approach that makes use of local image statistics to apply varying regularization to different areas of the image. This is achieved with an efficient parallel implementation of the Hopfield neural network. The proposed approach exhibits an improvement in restoration quality and execution time over the existing approaches. This is illustrated on simulations on benchmark images.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123319443","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
A heuristic method based on unsupervised learning and fuzzy inference for the vehicle routing problem 基于无监督学习和模糊推理的车辆路径问题的启发式方法
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181454
L. D. C. Gomes, F. V. Zuben
{"title":"A heuristic method based on unsupervised learning and fuzzy inference for the vehicle routing problem","authors":"L. D. C. Gomes, F. V. Zuben","doi":"10.1109/SBRN.2002.1181454","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181454","url":null,"abstract":"This paper deals with a fuzzy-based system to solve the capacitated vehicle routing problem. The proposed method makes use of a neural network with unsupervised learning guided by a fuzzy rule base. The algorithm implements a policy of penalties and rewards, a strategy of neuron inhibition, insertion and pruning, and also takes into account certain statistical characteristics of the input space. The fuzzy theory is considered to minimize drawbacks related to uncertainty and availability of partial information, leading to an adaptive process of constraint relaxation. The effectiveness of the proposed method is attested by means of a series of computational simulations. As the proposed approach has no adaptation to any particular instance, it represents a good candidate to provide the initial condition for more dedicated approaches, like tabu search.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130606798","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
Identification of a multivariate fermentation process using constructive learning 利用建设性学习识别多元发酵过程
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181429
L. Meleiro, R.J.G.B. Campello, R. M. Filho, F. V. Zuben
{"title":"Identification of a multivariate fermentation process using constructive learning","authors":"L. Meleiro, R.J.G.B. Campello, R. M. Filho, F. V. Zuben","doi":"10.1109/SBRN.2002.1181429","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181429","url":null,"abstract":"In the present work, a constructive learning algorithm is employed to design an optimal one-hidden neural network structure that best approximates a given mapping. The method determines not only the optimal number of hidden neurons but also the best activation function for each node. Here, the projection pursuit technique is applied in association with the optimization of the solvability condition, giving rise to a more efficient and accurate computational learning algorithm. As each activation function of a hidden neuron is optimally defined for every approximation problem, better rates of convergence are achieved. Since the training process operates the hidden neurons individually, a pertinent activation function employing Hermite polynomials can be iteratively developed for each neuron as a function of the learning set. The proposed constructive learning algorithm was successfully applied to identify a large-scale multivariate process, providing a multivariable model that was able to describe the complex process dynamics, even in long-range horizon predictions.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126722804","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
Character recognition in car license plates based on principal components and neural processing 基于主成分和神经处理的车牌字符识别
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 1900-01-01 DOI: 10.1109/SBRN.2002.1181475
A. da Rocha Gesualdi, J. Manoel de Seixas
{"title":"Character recognition in car license plates based on principal components and neural processing","authors":"A. da Rocha Gesualdi, J. Manoel de Seixas","doi":"10.1109/SBRN.2002.1181475","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181475","url":null,"abstract":"We present, in details, the principal component analysis (PCA) applied to a neural based recognition system. The technique is valuated on the extraction of principal components in character images of Brazilians' car license plates. This paper focus on the usage of the PCA in the recognition of character images. Comparisons with different neural classifiers are made.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"2018 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121667819","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
Neural coding by redundancy reduction and correlation 基于冗余缩减和相关性的神经编码
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 1900-01-01 DOI: 10.1109/SBRN.2002.1181478
A. Kardec Barros, A. Chichocki
{"title":"Neural coding by redundancy reduction and correlation","authors":"A. Kardec Barros, A. Chichocki","doi":"10.1109/SBRN.2002.1181478","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181478","url":null,"abstract":"Redundancy reduction as a form of neural coding has been a topic of large research interest. A number of strategies has been proposed, but the one which is attracting the most attention assumes that this coding is carried out so that the output signals are mutually independent. In this work we go one step further and suggest an algorithm that separates also non-orthogonal signals (i.e. dependent signals). The resulting algorithm is very simple, as it is computationally economical and based on second order statistics that, as it is well know, is more robust to errors than higher order statistics. Moreover, the permutation/scaling problem is also avoided. The framework is given with a biological background, and we point out that the algorithm can also be used in other applications such as biomedical engineering and telecommunications.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129846297","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
Comparing immune and neural networks 比较免疫网络和神经网络
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 1900-01-01 DOI: 10.1109/SBRN.2002.1181486
L. de Castro
{"title":"Comparing immune and neural networks","authors":"L. de Castro","doi":"10.1109/SBRN.2002.1181486","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181486","url":null,"abstract":"The complexity of the immune system is sometimes compared to that of the brain. Both systems can be viewed as composed of networks of elements, which endow them with interesting features for the development of computational tools with potentialities for problem solving. This paper has two main goals: 1) to introduce the general features of immune networks to the artificial neural network (ANN) community; and 2) to present a theoretical comparison between an ANN and a standard immune network. The comparison is highly simplified and general, taking into account how each network is structured, their basic components and mechanisms of adaptation, and information processing capabilities.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115684574","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
Multicast routing with quality of service and traffic engineering requirements in the Internet, based on genetic algorithm 基于遗传算法的多播路由是Internet中满足业务质量和流量工程要求的一种路由算法
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 1900-01-01 DOI: 10.1109/SBRN.2002.1181470
P.T. de Araujo, G.M.B. de Oliveira
{"title":"Multicast routing with quality of service and traffic engineering requirements in the Internet, based on genetic algorithm","authors":"P.T. de Araujo, G.M.B. de Oliveira","doi":"10.1109/SBRN.2002.1181470","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181470","url":null,"abstract":"In order to deal with the high computational power required by the QoS routing, the use of genetic algorithm (GA) as a method to obtain the appropriate routes has been presented in various works. The GA discussed in this work was adapted from the model presented by Erdun et al. (2001), that uses bandwidth, delay and cost as metrics to evaluate the routes. Two innovations were incorporated in the GA in order to attend traffic engineering requirements: inclusion of the metric number of steps (or hops) in the route evaluation, and a mechanism to avoid the generation of repeated individuals producing several optimal and sub-optimal routes. In order to test the proposed genetic algorithm, two examples of network topology were used. The results indicate that the GA discussed in this work converges to the global optimal solution, while the implementations discussed in Ravikumar et al. (1998) and Erdun et al. did not reach it. Besides, even in the runs that the GA did not converge to the global optimum, sub-optimal solutions that attend to the constraint delay were obtained with a small increment in the cost.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124452963","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: 10
首页 上一页
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