发布求助
文献互助 智能选刊 最新文献

Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks最新文献

筛选
英文 中文
A novel approach for solving constrained nonlinear optimization problems using neurofuzzy systems 用神经模糊系统求解约束非线性优化问题的新方法
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889741
I. Silva, A. Souza, M. E. Bordon
{"title":"A novel approach for solving constrained nonlinear optimization problems using neurofuzzy systems","authors":"I. Silva, A. Souza, M. E. Bordon","doi":"10.1109/SBRN.2000.889741","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889741","url":null,"abstract":"A neural network model for solving constrained nonlinear optimization problems with bounded variables is presented. More specifically, a modified Hopfield network is developed and its internal parameters are computed using the valid-subspace technique. These parameters guarantee the convergence of the network to the equilibrium points. The network is shown to be completely stable and globally convergent to the solutions of constrained nonlinear optimization problems. A fuzzy logic controller is incorporated in the network to minimize convergence time. Simulation results are presented to validate the proposed approach.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126570115","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
Real estate value at Porto Alegre city using artificial neural networks 利用人工神经网络分析阿雷格里港市的房地产价值
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889745
A. Cechin, Antonio Souto, M. González
{"title":"Real estate value at Porto Alegre city using artificial neural networks","authors":"A. Cechin, Antonio Souto, M. González","doi":"10.1109/SBRN.2000.889745","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889745","url":null,"abstract":"Focuses on the MLP neural network in order to solve the problem of an apartment's monetary worth appraisal in the Porto Alegre city (South Brazil). Many factors are involved in this calculation, like the size of the apartment, the environment conditions of the site, the actual conservation state of the apartment, the neighborhood, its geographical location in the city etc. Two databases were investigated: the first one is a list of apartments for sale and the second one is a list of apartments for rent. The analysis was performed with the use of both linear regression and neural network methods, with the purpose of comparison. The last one was used mainly to model the strong nonlinearities due to the geographical position of the apartments, since there is not a linear monotonic relation between position and value.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131125245","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: 27
Scalars, a way to improve the multi-objective prediction of the GAdC-method 标量，一种改进gadc方法多目标预测的方法
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889713
D. Devogelaere, M. Rijckaert
{"title":"Scalars, a way to improve the multi-objective prediction of the GAdC-method","authors":"D. Devogelaere, M. Rijckaert","doi":"10.1109/SBRN.2000.889713","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889713","url":null,"abstract":"This paper describes a hybrid method for supervised training of multivariate regression systems. The proposed methodology relies on supervised clustering with genetic algorithms and local learning. Genetic algorithm driven clustering (GAdC) offers certain advantages related to robustness, generalization performance, feature selection, explanatory behavior and the additional flexibility of defining the error function and the regularization constraints. In this contribution we present the use of GAdC for prediction of algae distributions. We highlight one of the advantages of this method namely, the use of scalars to obtain the sequence in which the prediction of algae distributions should be calculated. Using this sequence leads to an improvement of the prediction.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132118066","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
Neural networks vs. PARMA modelling: case studies of river flow prediction 神经网络与PARMA模型:河流流量预测的案例研究
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889723
M. Valença, Teresa B Ludermir
{"title":"Neural networks vs. PARMA modelling: case studies of river flow prediction","authors":"M. Valença, Teresa B Ludermir","doi":"10.1109/SBRN.2000.889723","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889723","url":null,"abstract":"This paper presents an constructive neural network model for seasonal stream flow forecasting. This surface water hydrology is basic to the design and operation of the reservoir. If information on the nature of the inflow is determinable in advance, then the reservoir can be operated by some decision rule to minimize downstream flood damage. For this reasons, several companies in the Brazilian Electrical Sector use the linear time-series models such as PARMA (periodic autoregressive moving average) models developed by Box-Jenkins. This paper provides for river flow prediction a numerical comparison between neural networks, called nonlinear sigmoidal regression blocks networks (NSRBN) and PARMA models. The model was implemented to forecast weekly average inflow on an step-ahead basis. It was tested on four hydroelectric plants located in different river basins in Brazil. The results obtained using the NSRBN were better than the results obtained with PARMA models.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125015327","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
An improved genetic algorithm performance with benchmark functions 一种改进的带有基准函数的遗传算法
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889764
A. L. Araújo, F. M. Assis
{"title":"An improved genetic algorithm performance with benchmark functions","authors":"A. L. Araújo, F. M. Assis","doi":"10.1109/SBRN.2000.889764","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889764","url":null,"abstract":"In a previous paper by the authors (1998) it was shown that a new genetic algorithm (GA) performed better than a basic GA. In the present paper we focus on an improved genetic algorithm which uses the theory of cosets. The new technique was tested using some benchmark functions for which the basic GA performance was not good enough. The main purpose of this paper is to suggest how to use linear codes properties to guide the GA search.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117314757","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
Graph layout using a genetic algorithm 图形布局使用遗传算法
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889735
A. Barreto, H. Barbosa
{"title":"Graph layout using a genetic algorithm","authors":"A. Barreto, H. Barbosa","doi":"10.1109/SBRN.2000.889735","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889735","url":null,"abstract":"We report on our experiences with applying genetic algorithms to the graph drawing problem. The automatic generation of drawings of graphs has important applications in key computer technologies. We are interested here in producing aesthetically-pleasing two-dimensional pictures of undirected graphs drawn with straight edges. To do so we use a hybrid process, applying concepts inspired by the force-directed placement technique with several aesthetic criteria which are to be minimized together. The optimization algorithm used is the genetic algorithm.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123917966","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: 18
Fuzzy systems to solve inverse kinematics problem in robots control: application to an hexapod robots' leg 模糊系统求解机器人控制中的逆运动学问题:在六足机器人腿上的应用
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889730
S. Netto, M. Dutra, Alexandre Evsukoff
{"title":"Fuzzy systems to solve inverse kinematics problem in robots control: application to an hexapod robots' leg","authors":"S. Netto, M. Dutra, Alexandre Evsukoff","doi":"10.1109/SBRN.2000.889730","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889730","url":null,"abstract":"The complexity of walking robots poses a number of control problems due to the large number of degrees of freedom involved in the robot's motion. This work deals with the design of a hexapod robot, whose legs have 3 rotative joints and the same configuration. The kinematics analysis of one leg is presented and used to generate data for black box identification using fuzzy systems and neural networks: the direct kinematics is used to generate the training data and the inverse kinematics is used to generate the testing data. Two fuzzy systems and a neural network are used as general black box methods to solve the inverse kinematics problem in robots' leg control. Results have shown that reasonable precision can be achieved with low computational cost.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123342964","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: 9
Online neo-fuzzy-neuron state observer 在线新模糊神经元状态观测器
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889738
R. P. Landim, B. R. Menezes, S. Silva, W. Caminhas
{"title":"Online neo-fuzzy-neuron state observer","authors":"R. P. Landim, B. R. Menezes, S. Silva, W. Caminhas","doi":"10.1109/SBRN.2000.889738","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889738","url":null,"abstract":"An algorithm for a state observation based on a neo-fuzzy-neuron (NFN) with real time training is presented. Some useful theorems are promptly demonstrated and used to aid the design of the observer. Two applications of this state observer are shown: an induction machine rotor flux observer and an induction machine speed observer. Digital simulation and experimental results show the good performance of the observer.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126592556","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: 6
Feedback-error-learning for controlling a flexible link 柔性连杆控制的反馈误差学习
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889751
A. A. Neto, Wilson Rios Neto, L. Góes, C. Nascimento
{"title":"Feedback-error-learning for controlling a flexible link","authors":"A. A. Neto, Wilson Rios Neto, L. Góes, C. Nascimento","doi":"10.1109/SBRN.2000.889751","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889751","url":null,"abstract":"This paper discusses two approaches for neural control of a flexible link using the feedback-error-learning technique. This technique aims to acquire the inverse dynamics model of the plant and uses a neural network acting as an adaptive controller to improve the performance of a conventional non-adaptive feedback controller. The non-collocated control of a flexible link is characterized as a non-minimum phase system, which is difficult to be controlled by most control techniques. Two different neural approaches are used in this paper to overcome this difficulty. The first approach uses a virtual re-defined output as one of the impacts for the neural network and feedback controllers, while the other employs a delayed reference input signal in the feedback path and a tapped-delay line to process the reference input before presenting it to the neural network.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127075224","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
Neurosymbolic processing: non-monotonic operators and their FPGA implementation 神经符号处理:非单调算子及其FPGA实现
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889705
E. Burattini, M. D. Gregorio, G. Tamburrini
{"title":"Neurosymbolic processing: non-monotonic operators and their FPGA implementation","authors":"E. Burattini, M. D. Gregorio, G. Tamburrini","doi":"10.1109/SBRN.2000.889705","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889705","url":null,"abstract":"Recalling the insights of McCulloch and Pitts (1945), von Neumann (1956) and Minsky (1956) we introduce some non-monotonic operators implemented by means of new electronic devices (FPGA) for a neurosymbolic processor (NSP). Some nets performing logical and arithmetic functions are also presented.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131349122","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: 9
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