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
Face detector combining eigenfaces, neural network and bootstrap 结合特征脸、神经网络和自举的人脸检测器
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889762
G. Mota, R. Feitosa, S. Paciornik
{"title":"Face detector combining eigenfaces, neural network and bootstrap","authors":"G. Mota, R. Feitosa, S. Paciornik","doi":"10.1109/SBRN.2000.889762","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889762","url":null,"abstract":"A critical issue in an automatic face recognition system is the determination of the region containing a face in an image with a cluttered background. The paper presents a method that optimizes the detection task through the use of eigenfaces, neural networks and a bootstrap algorithm. The main component of the proposed method is a nonlinear operator that detects the presence of a well-framed face image in 20x20 pixel windows. To detect faces larger than the window size the input image is successively reduced by a factor of 1.2 and the procedure is applied at each scale. To obtain a compact representation of the face images, the method applies principal component analysis directly to the pixel intensities of face images. Each image window analyzed by the detection algorithm is then projected upon the n principal components, the so-called eigenfaces. The dimensionality reduction thus achieved implies in a reconstruction error, the DFFS-distance from features space. The patterns representing an image window are formed by the n projections plus the DFFS.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"12 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":"115448279","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
Hierarchical neuro-fuzzy BSP model-HNFB 层次神经模糊BSP模型- hnfb
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889758
F. J. Souza, M. Vellasco, M. Pacheco
{"title":"Hierarchical neuro-fuzzy BSP model-HNFB","authors":"F. J. Souza, M. Vellasco, M. Pacheco","doi":"10.1109/SBRN.2000.889758","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889758","url":null,"abstract":"Summary form only given. This paper presents a new hybrid neuro-fuzzy model which is capable of learning structure and parameters by means of recursive binary space partitioning (BSP), and hence performing pattern classification.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"37 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":"124141646","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
Fetal left atrium segmentation using Kohonen maps to measure the septum primum redundancy index 利用Kohonen图对胎儿左心房分割测量鼻中隔原始冗余指数
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889759
M. L. Siqueira, G. Drehmer, P. Navaux
{"title":"Fetal left atrium segmentation using Kohonen maps to measure the septum primum redundancy index","authors":"M. L. Siqueira, G. Drehmer, P. Navaux","doi":"10.1109/SBRN.2000.889759","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889759","url":null,"abstract":"Summary form only given. Echocardiographic images are used by physicians in early detection of congenital heart diseases. Ultrasonic imaging has been the basis of noninvasive methods for early detection of fetal heart diseases. However, echocardiographic images are contaminated by speckle noise, and other imaging disturbances, making it difficult to visualize important heart structures. Usually the diagnosis is obtained by measurements on the echocardiographic images. One important measure is the redundancy index of the septum primum that is associated with premature atrial contractions and the thickness of septum interventricular that can indicate the presence of myocardial hypertrophy in the fetus. The redundancy index of septum primum was obtained by ratio ledger between the maximum excursion of the septum primum (SP) to inside of left atrium and the maximum diameter of left atrium, both during diastole. For images of fetal echocardiography exams, we use Kohonen self-organizing maps (SOM) to segment and afterwards obtain measures that can help the physicians in the analysis of several congenital cardiopathies. The SOM organizes unknown data into groups of similar patterns, according to a similarity criterion. An important feature of this neural network is its ability to process noisy data. For this reason, the SOM approach has been recommended to process echocardiographic images. In this work, random samples of gray tones means of the images were used to train the map.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"60 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":"116258392","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
Simulated annealing for robust VQ: improving image transmission through a fading channel 鲁棒VQ的模拟退火:通过衰落信道改善图像传输
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889746
W. Lopes, F. Madeiro, M. Alencar, B. Neto
{"title":"Simulated annealing for robust VQ: improving image transmission through a fading channel","authors":"W. Lopes, F. Madeiro, M. Alencar, B. Neto","doi":"10.1109/SBRN.2000.889746","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889746","url":null,"abstract":"Vector quantization (VQ) has been extensively used in image coding systems. However, when the communications system involves a noise channel, it is well known that VQ is highly sensitive to channel errors. As a consequence, a considerable degradation may be introduced in the reconstructed images. In the present paper, simulated annealing (SA) is applied to robust VQ, that is, it is used for assigning binary indexes to the VQ code vectors, as an attempt to circumvent the effect of channel errors. Simulations involving image transmission through a Rayleigh fading channel clearly indicate the suitability of SA. The authors also show that an additional improvement can be obtained by using an alternative initialization of the SA algorithm.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"33 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":"116533989","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
Neural computation: From neuroscience to technology and back again 神经计算:从神经科学到技术再回来
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889707
J. Mira, A. E. Delgado
{"title":"Neural computation: From neuroscience to technology and back again","authors":"J. Mira, A. E. Delgado","doi":"10.1109/SBRN.2000.889707","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889707","url":null,"abstract":"The purpose of the paper is to reassume some of the motivations of the groundwork stages of biocybernetics and the later bionic formulations and try to reconsider two basic questions: (1) What can neuroscience bring into computation? (the new bionics). (2) What can return computation to neuroscience? (the new biocybernetics).","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"14 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":"122777098","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
A study of possible improvements to the Alopex training algorithm 对Alopex训练算法可能改进的研究
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889726
A. Bia
{"title":"A study of possible improvements to the Alopex training algorithm","authors":"A. Bia","doi":"10.1109/SBRN.2000.889726","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889726","url":null,"abstract":"We studied the performance of the Alopex algorithm, and proposed modifications that improve the training time, and simplified the algorithm. We tested different variations of the algorithm. We describe the best cases and summarize the conclusions we arrived at. One of the proposed variations (99/B) performs slightly faster than the Alopex algorithm described by Unnikrishnan et al. (1994), showing less unsuccessful training attempts, while being simpler to implement. Like Alopex, our versions are based on local correlations between changes in individual weights and changes in the global error measure. Our algorithm is also stochastic, but it differs from Alopex in the fact that no annealing scheme is applied during the training process and hence it uses less parameters.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"217 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":"123503255","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
A comparative study of LBG and SOA codebooks concerning the computational complexity of the minimum distortion encoding for VQ LBG和SOA码本对VQ最小失真编码计算复杂度的比较研究
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889754
F. Madeiro, M. S. Vajapeyam, B. Neto
{"title":"A comparative study of LBG and SOA codebooks concerning the computational complexity of the minimum distortion encoding for VQ","authors":"F. Madeiro, M. S. Vajapeyam, B. Neto","doi":"10.1109/SBRN.2000.889754","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889754","url":null,"abstract":"Summary form only given. Vector quantization (VQ),is a well-known compression technique which has been widely used in many speech and image coding systems. Techniques for codebook design attempt to produce a codebook that is optimum for a given source. To date, the most widely used technique for VQ codebook design is the LBG (Linde-Buzo-Gray) algorithm. Madeim et al. (1999) show that an unsupervised neural network algorithm, referred to as SOA (self-organizing algorithm), provides good VQ codebooks, leading to reconstructed signals with better quality when compared to the ones obtained by using LBG codebooks. In this paper, an investigation is carried out to evaluate the \"inherent\" quality of SOA and LBG codebooks regarding the computational complexity of medium distortion encoding. The present work shows that the SOA codebooks overperforms the LBG codebooks in the sense that they yield a smaller average number of multiplications per sample for image VQ.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"4 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":"122077974","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
Application of neural networks: a molecular geometry optimization study 神经网络的应用:分子几何优化研究
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889760
M. R. Lemes, C. R. Zacharias, Arnaldo Dal Pino Júnior
{"title":"Application of neural networks: a molecular geometry optimization study","authors":"M. R. Lemes, C. R. Zacharias, Arnaldo Dal Pino Júnior","doi":"10.1109/SBRN.2000.889760","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889760","url":null,"abstract":"Summary form only given. Optimization algorithms are iterative procedures that evolve from guessed starting points (SP) to the desired global minimum. Their performance can be greatly improved, if a neural network (NN) is created to select suitable SP. In this paper we consider the use of trained NN to select possible ground-state geometries for silicon clusters. A genetic algorithm is initial population energy optimization. For convenience, a cluster's geometry is described as a piling up of plane layers of atoms.","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":"125940486","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
A model for the simulation of a cold rolling mill, using neural networks and sensitivity factors 利用神经网络和敏感因子建立了冷轧机的仿真模型
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889736
Luis E. Zárate
{"title":"A model for the simulation of a cold rolling mill, using neural networks and sensitivity factors","authors":"Luis E. Zárate","doi":"10.1109/SBRN.2000.889736","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889736","url":null,"abstract":"Rolling process mathematical modeling involves nonlinear parameters and relationships that usually lead to nonlinear equations of difficult numerical solution. Such is the case of Alexandre's model (1972), considered one of the most complete regarding rolling theory. For simulation purposes, Alexandre's model requires too much computational time, which prevents its use in online control and supervision systems. In order to obtain a model for the simulation of a cold rolling mill, it is necessary to obtain an expression to calculate the outgoing thickness and the rolling load. This function can be written in terms of the sensitivity factors and these can be obtained by differentiating an artificial neural network (ANN) previously trained, reducing the computational time necessary. In this paper, a model for the simulation of a cold rolling process based in ANN is presented. Simulation results and conclusions to show the application of the model are also presented.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"36 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120839723","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
A hybrid genetic algorithm for finding stable conformations of small molecules 用于寻找小分子稳定构象的混合遗传算法
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889719
H. Barbosa, F. Raupp, C. Lavor, H. Lima, N. Maculan
{"title":"A hybrid genetic algorithm for finding stable conformations of small molecules","authors":"H. Barbosa, F. Raupp, C. Lavor, H. Lima, N. Maculan","doi":"10.1109/SBRN.2000.889719","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889719","url":null,"abstract":"In this work we use a hybrid genetic algorithm for finding the global minimum energy conformation of small molecules based on the Lennard-Jones potential function. Finding the global minimum of this function is very difficult because it has a large number of local minima, which may grow exponentially with molecule size. Experimental evidences show that the global minimum potential energy of a given molecule usually corresponds to its most stable conformation, which dictates the majority of its properties.","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":"123741344","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
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