发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)最新文献

筛选
英文 中文
Relaxation with model switching and its application to shape matching 模型切换松弛及其在形状匹配中的应用
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007750
K. Kameyama, K. Toraichi
{"title":"Relaxation with model switching and its application to shape matching","authors":"K. Kameyama, K. Toraichi","doi":"10.1109/IJCNN.2002.1007750","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007750","url":null,"abstract":"This paper introduces a novel approach for contour-based shape matching named as constructive relaxation matching (CRM). In image matching relying on a particular modeling method, apparently similar images can be judged as being quite distant, according to the nature of the modeling process. In the proposed CRM, the modeling stage for a novel input image contour, commonly done in the same procedure used for modeling the templates, will be included in the procedure of iterative relaxation matching. Upon dynamically constructing the model during relaxation, pairs of contour objects having similar template label assignment probabilities will be unified to make one object. After describing the CRM procedures, the method is applied to simple shape matching problems demonstrating the ability to adaptively model the input image during relaxation. It is shown that the proposed CRM improves the object-label correspondence for evaluation of the image similarities in the following stages of shape matching applications.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116656226","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
Technique for application of hi-bright LED in automobile industry through intelligent systems 基于智能系统的高亮度LED在汽车工业中的应用技术
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007569
A. V. Ortega, I. D. da Silva
{"title":"Technique for application of hi-bright LED in automobile industry through intelligent systems","authors":"A. V. Ortega, I. D. da Silva","doi":"10.1109/IJCNN.2002.1007569","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007569","url":null,"abstract":"The advantages offered by the electronic component LED (light emitting diode) have caused a quick and wide application of this device in replacement of incandescent lights. However, in its combined application, the relationship between the design variables and the desired effect or result is very complex and it becomes difficult to model by conventional techniques. This work consists of the development of a technique, through artificial neural networks, to make possible to obtain the luminous intensity values of brake lights using LEDs from design data.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124943481","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
Natural gradient learning for second-order nonstationary source separation 二阶非平稳源分离的自然梯度学习
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1005550
Seungjin Choi, A. Cichocki, S. Amari
{"title":"Natural gradient learning for second-order nonstationary source separation","authors":"Seungjin Choi, A. Cichocki, S. Amari","doi":"10.1109/IJCNN.2002.1005550","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1005550","url":null,"abstract":"In this paper we consider a problem of source separation when sources are second-order nonstationary stochastic processes. We employ the natural gradient method and develop learning algorithms for both linear feedback and feedforward neural networks. Thus our algorithms possess equivariant property. The local stability analysis shows that separating solutions are always locally stable stationary points of the proposed algorithms, regardless of probability distributions of sources.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116769535","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
Multi-aspect pattern classification using predictive networks and error mapping 基于预测网络和错误映射的多方面模式分类
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007799
J. Salazar, M. Robinson, M. Azimi-Sadjadi
{"title":"Multi-aspect pattern classification using predictive networks and error mapping","authors":"J. Salazar, M. Robinson, M. Azimi-Sadjadi","doi":"10.1109/IJCNN.2002.1007799","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007799","url":null,"abstract":"A classification scheme is developed for classifying underwater mine-like and non-mine-like objects from acoustic backscattered signals. This scheme uses a predictive network along with a neural network classifier. The results of this scheme on an acoustic backscattered data set are given.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122788674","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
Driving environmental change detection subsystem in a vision-based driver assistance system 基于视觉的驾驶辅助系统中的驾驶环境变化检测子系统
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1005544
C. Fang, C. Fuh, Sei-Wang Chen
{"title":"Driving environmental change detection subsystem in a vision-based driver assistance system","authors":"C. Fang, C. Fuh, Sei-Wang Chen","doi":"10.1109/IJCNN.2002.1005544","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1005544","url":null,"abstract":"We propose a computational model motivated by human cognitive processes for detecting changes of driving environments. The model consists of three major components: sensory, perceptual, and conceptual components. The proposed computational model is used as the underlying framework in which a system for detecting changes of driving environments is developed.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122843215","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
New compensation algorithm for color backlight images 彩色背光图像补偿新算法
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007720
M. Su, Jiaxuan Guo, Daw-Tung Lin, Guo Chung Wang
{"title":"New compensation algorithm for color backlight images","authors":"M. Su, Jiaxuan Guo, Daw-Tung Lin, Guo Chung Wang","doi":"10.1109/IJCNN.2002.1007720","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007720","url":null,"abstract":"This paper presents a new algorithm for compensating exposure in the case of backlighting, regardless of the position of objects. To achieve this compensation, the fuzzy c-means algorithm is first used to extract features from a backlight image. Then these extracted features are input into an SOM-based fuzzy system to determine the amount of compensation. A set of 26 images was tested to illustrate the performance of the algorithm.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131165497","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
HMMs and Coupled HMMs for multi-channel EEG classification hmm和耦合hmm用于多通道脑电分类
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007657
Shi Zhong, Joydeep Ghosh
{"title":"HMMs and Coupled HMMs for multi-channel EEG classification","authors":"Shi Zhong, Joydeep Ghosh","doi":"10.1109/IJCNN.2002.1007657","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007657","url":null,"abstract":"A variety of Coupled HMMs (CHMMs) have recently been proposed as extensions of HMM to better characterize multiple interdependent sequences. This paper introduces a novel distance coupled HMM. It then compares the performance of several HMM and CHMM models for a multi-channel EEG classification problem. The results show that, of all approaches examined, the multivariate HMM that has low computational complexity surprisingly outperforms all other models.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"11 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131225415","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: 149
How reliable is the connectivity in cortical neural networks? 皮质神经网络的连通性有多可靠?
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007767
A. Faisal, S. Laughlin, J. White
{"title":"How reliable is the connectivity in cortical neural networks?","authors":"A. Faisal, S. Laughlin, J. White","doi":"10.1109/IJCNN.2002.1007767","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007767","url":null,"abstract":"Neurons use stochastic components, including ion channels, to process and transmit information. In small structures these can cause significant signal fluctuations. We developed a stochastic simulator to investigate the reliability of cortical axons. Ion channel stochasticity makes these thin axons highly susceptible to spontaneous action potentials and information rates decrease linearly with distance.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131557345","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: 15
An efficient defect compensation scheme for multi-layer neural networks on WSI devices 一种有效的WSI器件上多层神经网络缺陷补偿方案
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1005622
K. Yamamori, T. Abe, S. Horiguchi, I. Yoshihara
{"title":"An efficient defect compensation scheme for multi-layer neural networks on WSI devices","authors":"K. Yamamori, T. Abe, S. Horiguchi, I. Yoshihara","doi":"10.1109/IJCNN.2002.1005622","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1005622","url":null,"abstract":"Discusses a high speed off-line defect compensation scheme for trained multi-layer neural networks implemented in WSI devices. Since the partial retraining scheme utilizes the redundancy of neural networks, no additional circuits are needed. The performance of the partial retraining scheme is compared with that of a back-propagation algorithm on a face image recognition problem.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127642618","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
A multilayer feedforward network for model estimation from range data 基于距离数据的多层前馈网络模型估计
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Pub Date : 2002-08-07 DOI: 10.1109/IJCNN.2002.1007692
A. Chella, R. Pirrone
{"title":"A multilayer feedforward network for model estimation from range data","authors":"A. Chella, R. Pirrone","doi":"10.1109/IJCNN.2002.1007692","DOIUrl":"https://doi.org/10.1109/IJCNN.2002.1007692","url":null,"abstract":"A novel neural architecture aimed to estimate superquadrics parameters form range data is presented. The network topology is designed to model and compute the inside-outside function of an undeformed superquadric in whatever attitude, starting from the (x,y,z) data triples. The network has been trained using backpropagation, and the weights arrangement, after training, represents a robust estimate of the superquadric parameters. The architectural approach is general, it can be extended to other geometric primitives for part-based object recognition, and performs faster than classical model fitting techniques. Detailed explanation of the theoretical approach, along with some experiments with real data, are reported.","PeriodicalId":382771,"journal":{"name":"Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127664056","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
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