发布求助
文献互助 智能选刊 最新文献

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.最新文献

筛选
英文 中文
Analysis of phase transitions in KIV with amygdala during simulated navigation control 具有杏仁核的KIV在模拟导航控制中的相变分析
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1555817
R. Kozma, M. Myers
{"title":"Analysis of phase transitions in KIV with amygdala during simulated navigation control","authors":"R. Kozma, M. Myers","doi":"10.1109/IJCNN.2005.1555817","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1555817","url":null,"abstract":"A biologically inspired dynamical neural network model called KIV is used in this work to design autonomous agents. The KIV set models the vertebrate limbic system. Previous studies indicated that KIV is able to provide a control algorithm for navigation and decision-making for autonomous mobile agents. In this work we use Hilbert transform to capture global synchronized spatio-temporal patterns of amplitude modulation in KIV. We identify phase transition in the simulated amygdala and show that it shares several important features of EEC signals.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126802312","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
Recurrent neural equalization for communication channels in impulsive noise environments 脉冲噪声环境下通信信道的递归神经均衡
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556445
Jongsoo Choi, Martin Bouchard, T. Yeap
{"title":"Recurrent neural equalization for communication channels in impulsive noise environments","authors":"Jongsoo Choi, Martin Bouchard, T. Yeap","doi":"10.1109/IJCNN.2005.1556445","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556445","url":null,"abstract":"In some communication systems, the transmitted signal is contaminated by impulsive noise with a non-Gaussian distribution. Non-Gaussian noise causes significant performance degradation to communication receivers. In this paper, we apply a recurrent neural equalizer to impulsive noise channels, for which the performance of neural network equalizers has never been evaluated. This new application is motivated from the fact that the unscented Kalman filter (UKF), which is suited for training of the recurrent neural equalizer, provides a higher accuracy than the extended Kalman filter (EKF) in capturing the statistical characteristics for non-Gaussian random variables. The performance of the recurrent neural equalizer is evaluated for impulsive noise channels through Monte Carlo simulations. The results support the superiority of the UKF to the EKF in compensating the effect of non-Gaussian impulsive noise.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126915494","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
Generalized 2D principal component analysis 广义二维主成分分析
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1555814
Hui Kong, Xuchun Li, Lei Wang, E. K. Teoh, Jian-gang Wang, R. Venkateswarlu
{"title":"Generalized 2D principal component analysis","authors":"Hui Kong, Xuchun Li, Lei Wang, E. K. Teoh, Jian-gang Wang, R. Venkateswarlu","doi":"10.1109/IJCNN.2005.1555814","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1555814","url":null,"abstract":"A two-dimensional principal component analysis (2DPCA) by J. Yang et al. (2004) was proposed and the authors have demonstrated its superiority over the conventional principal component analysis (PCA) in face recognition. But the theoretical proof why 2DPCA is better than PCA has not been given until now. In this paper, the essence of 2DPCA is analyzed and a framework of generalized 2D principal component analysis (G2DPCA) is proposed to extend the original 2DPCA in two perspectives: a bilateral-projection-based 2DPCA (B2DPCA) and a kernel-based 2DPCA (K2DPCA) schemes are introduced. Experimental results in face recognition show its excellent performance.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130585869","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: 90
Maximum margin classifiers with noisy data: a robust optimization approach 带噪声数据的最大边际分类器:一种鲁棒优化方法
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556373
T. Trafalis, R. Gilbert
{"title":"Maximum margin classifiers with noisy data: a robust optimization approach","authors":"T. Trafalis, R. Gilbert","doi":"10.1109/IJCNN.2005.1556373","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556373","url":null,"abstract":"In this paper, we investigate the theoretical aspects of robust classification using support vector machines. Given training data (x/sub 1/,y/sub 1/),..., (x/sub l/y/sub l/), where l represents the number of samples, x/sub i/ /spl isin/ /spl Ropf//sup n/ and y/sub i/ /spl isin/ {-1,1}, we investigate the training of a support vector machine in the case where bounded perturbation is added to the value of the input x/sub i/ /spl isin/ /spl Ropf//sup n/. We consider both cases where our training data are either linearly separable or nonlinearly separable respectively. We show that we can perform robust classification by using linear or second order cone programming.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123895355","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
Performance of neural classifiers for fabric faults classification 神经分类器在织物故障分类中的性能
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556186
M. Abdulhady, H. M. Abbas, Y.H. Dakrowry, S. Nassar
{"title":"Performance of neural classifiers for fabric faults classification","authors":"M. Abdulhady, H. M. Abbas, Y.H. Dakrowry, S. Nassar","doi":"10.1109/IJCNN.2005.1556186","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556186","url":null,"abstract":"In this paper, fabric faults classification using CNeT (Behnke and Karayiannis, 1998) is studied. The basic objectives are to improve the features selection used in CNeT (Behnke and Karayiannis, 1998) classifier and compare the results with other neural network classifiers. The algorithm adopted here is composed of three stages. The first stage is a preprocessing phase where defects are detected and localized. Since every detected defect has its different shape and size, all defects are normalized to a predetermined size. In the second stage a set of features are calculated for each defect using the Haralick (1973, 1979) spatial features. The improved classification performance is achieved by employing a statistical method to select the most important features that can be used in classification. This is done by calculating a classification factor (Milligan and Cooper, 1985) for each feature vector to determine its effect in the classification process. During the third and last stage, those features are then used to train a competitive neural tree (CNeT) (Behnke and Karayiannis, 1998) designed to learn in a supervised manner the class associated with each set of features. The network can be then used to test and classify new defects. The approach is experimented with a set of images of fault free and faulty textiles and output results are compared with radial basis function classifiers.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"7 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121747053","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
Lossless high dynamic range image coding based on lifting scheme using nonlinear interpolative effect of discrete-time cellular neural networks 基于提升方案的高动态范围图像无损编码，利用离散时间细胞神经网络的非线性插值效应
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556132
H. Aomori, K. Kawakami, T. Otake, N. Takahashi, M. Yamauchi, M. Tanaka
{"title":"Lossless high dynamic range image coding based on lifting scheme using nonlinear interpolative effect of discrete-time cellular neural networks","authors":"H. Aomori, K. Kawakami, T. Otake, N. Takahashi, M. Yamauchi, M. Tanaka","doi":"10.1109/IJCNN.2005.1556132","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556132","url":null,"abstract":"The lifting scheme is a flexible method for the construction of linear and nonlinear wavelet transforms. In this paper, we propose a novel lossless high dynamic range (HDR) image coding method based on the lifting scheme using discrete-time cellular neural networks (DT-CNNs). In our proposed method, the image is interpolated by using the nonlinear interpolative dynamics of DT-CNN. Because the output function of DT-CNN works as a multi-level quantization function, our method adapts for the prediction of HDR image, and composes the integer lifting scheme for lossless coding. Moreover, our method makes good use of the nonlinear interpolative dynamics by A-template compared with conventional CNN image coding methods using only B-template. The experimental results show a better coding performance compared with the conventional lifting method using linear filters.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"16 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124532869","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
Evaluation of cluster combination functions for mixture of experts 混合专家聚类组合函数的评价
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556016
R. Redhead, M. Heywood
{"title":"Evaluation of cluster combination functions for mixture of experts","authors":"R. Redhead, M. Heywood","doi":"10.1109/IJCNN.2005.1556016","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556016","url":null,"abstract":"The mixtures of experts (MoE) model provides the basis for building modular neural network solutions. In this work we are interested in methods for decomposing the input before forwarding to the MoE architecture. By doing so we are able to define the number of experts from the data itself. Specific schemes are shown to be appropriate for regression and classification problems, where each appear to have different preferences.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127594106","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
Application of neural networks to 3G power amplifier modeling 神经网络在3G功率放大器建模中的应用
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556274
Taijun Liu, S. Boumaiza, F. Ghannouchi
{"title":"Application of neural networks to 3G power amplifier modeling","authors":"Taijun Liu, S. Boumaiza, F. Ghannouchi","doi":"10.1109/IJCNN.2005.1556274","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556274","url":null,"abstract":"In this paper a real-valued time-delayed neural network (RVTDNN) is utilized to build a baseband behavioral model of a 3G power amplifier. Based on the inphase and quadratic components of the input and output signals of a high power amplifier, a three-layer RVTDNN is firstly trained in Matlab and then implemented in Agilent design system software. In order to speed up the training process, a second-order learning algorithm namely scaled conjugate gradient method (SCGM) is employed to extract the RVTDNN model parameters (weights and biases). The comparison of the simulation based results to the measured ones reveals the strong ability of the identified RVTDNN to accurately predict the dynamic nonlinear behavior of a 90-Watt LDMOS power amplifier under a two-carrier 3GPP-FDD excitation signal.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"224 1-2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131990973","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
Model of neuron-like systems: examples of dynamic processes 类神经元系统的模型:动态过程的例子
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556160
V. Yakhno, I. Nuidel, A. Ivanov
{"title":"Model of neuron-like systems: examples of dynamic processes","authors":"V. Yakhno, I. Nuidel, A. Ivanov","doi":"10.1109/IJCNN.2005.1556160","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556160","url":null,"abstract":"A model system \"cortex-thalamus-reticular thalamic neurons\", which uses three distributed layers of similar neuron-like elements and describes processing of sensor signals by animals is considered. It is shown that the regime of pulsations and fragmentary perception of stabilized images, stationarily fixed on the eye retina of a human being corresponds to some dynamic regimes of the considered model system.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132415777","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
Embedded fastICA algorithm applied to the sensor noise extraction problem of foundation fieldbus network 嵌入式fastICA算法应用于基金会现场总线网络传感器噪声提取问题
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556245
I.M. Costa, A. Neto, J.D. de Melo, Jose A. N. de Oliveira
{"title":"Embedded fastICA algorithm applied to the sensor noise extraction problem of foundation fieldbus network","authors":"I.M. Costa, A. Neto, J.D. de Melo, Jose A. N. de Oliveira","doi":"10.1109/IJCNN.2005.1556245","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556245","url":null,"abstract":"This paper presents the description and the operation of a system composed of an intelligent algorithm, that separates information and noise coming from different sources, implemented with embedded technology in a DSP (digital signal processor), that interacts with field bus devices connected through a foundation field bus network. The technique used in this blind source separation (BSS) process was the independent component analysis (ICA), that explores the possibility of separating mixed signals based on the fact that they are statistically independent. The algorithm and its implementation are presented, as well as the test results.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132419997","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：481959085
Book学术官方微信