发布求助
文献互助 智能选刊 最新文献

International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003最新文献

筛选
英文 中文
Significant coefficient decomposition based stack X-tree multiple description coding 基于显著系数分解的堆栈x树多重描述编码
International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003 Pub Date : 1900-01-01 DOI: 10.1109/ICNNSP.2003.1281080
C. Cai, Jing Chen, R. Ding
{"title":"Significant coefficient decomposition based stack X-tree multiple description coding","authors":"C. Cai, Jing Chen, R. Ding","doi":"10.1109/ICNNSP.2003.1281080","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1281080","url":null,"abstract":"A new multiple description coding approach is presented in this paper. In this approach, first each significant wavelet coefficient is decomposed into two coefficients. One is made from the bits in the odd positions, whereas, the other is made from the bits in the even positions. These two types of coefficients are then grouped into two sub-signals. Two descriptions of coded data are formed from these sub-signals and transmitted over different channels. To realize a balance multiple description coding, data from different sub-signals are knitted to produce two descriptions. Experimental results have shown that the performances of the proposed scheme are better than those of the polyphase transform and selective quantization one.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"50 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":"127096357","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
Alternate feature optimization for 3-class underwater target recognition based on SVM classifiers 基于SVM分类器的3类水下目标识别交替特征优化
International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003 Pub Date : 1900-01-01 DOI: 10.1109/ICNNSP.2003.1279232
W. Haiyan, Tian Na, Z. Xiaomin, Feng Xi-an, Zhao Ni
{"title":"Alternate feature optimization for 3-class underwater target recognition based on SVM classifiers","authors":"W. Haiyan, Tian Na, Z. Xiaomin, Feng Xi-an, Zhao Ni","doi":"10.1109/ICNNSP.2003.1279232","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1279232","url":null,"abstract":"A novel signal processing method based on alternate feature optimization is introduced and analyzed in this paper. And a new underwater target recognition system using the optimized feature and SVM (support vector machine) is presented here. The system utilizes the alternate feature extraction method to optimize the feature selection process. The optimized feature set feeds a 3-class classification module, which is based on the traditional binary SVM classifier. The optimized feature set reduces the burden of the SVM classifier and improves its learning speed and classification accuracy. The paper includes, the algorithm of alternate feature optimization, the classification mechanism of SVM and the simulation studies. The result indicates that the proposed system has excellent performance.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"22 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":"130164997","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
Improved Bayesian approach to robust speech segmentation 改进的贝叶斯鲁棒语音分割方法
International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003 Pub Date : 1900-01-01 DOI: 10.1109/ICNNSP.2003.1280740
Z. Wenjun, Xie Jianying
{"title":"Improved Bayesian approach to robust speech segmentation","authors":"Z. Wenjun, Xie Jianying","doi":"10.1109/ICNNSP.2003.1280740","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1280740","url":null,"abstract":"To enhance the robustness of speech segmentation, this paper presents the improved segmentation model based on Bayesian method which combined with a prior probability which is independent to noise feature as the compensation for the mismatch of acoustic model. We evaluated and compared the performance of different methods in speech segmentation experiment.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"26 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":"122345251","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
Phoneme sequence pattern recognition using fuzzy neural network 基于模糊神经网络的音素序列模式识别
International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003 Pub Date : 1900-01-01 DOI: 10.1109/ICNNSP.2003.1279329
H. Kwan, X. Dong
{"title":"Phoneme sequence pattern recognition using fuzzy neural network","authors":"H. Kwan, X. Dong","doi":"10.1109/ICNNSP.2003.1279329","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1279329","url":null,"abstract":"In this paper, a 2-D phoneme sequence pattern recognition using the fuzzy neural network is presented. The self-organizing map and the learning vector quantization are used to organize the phoneme feature vectors of short and long phonemes segmented from speech samples to obtain the phoneme maps. The 2-D phoneme response sequences of the speech samples are formed on the phoneme maps by the Viterbi search algorithm. These 2-D phoneme response sequence curves are used as inputs to the fuzzy neural network for training and recognition of 0-9 digit-voice utterances. Simulation results are given.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"6 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":"132466090","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
Infimum of features in number and feature selection of target recognition 目标识别中特征数量和特征选择的最小值
International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003 Pub Date : 1900-01-01 DOI: 10.1109/ICNNSP.2003.1279345
Li Xihai, L. Dai-zhi, Zhao Ke, L. Zhigang
{"title":"Infimum of features in number and feature selection of target recognition","authors":"Li Xihai, L. Dai-zhi, Zhao Ke, L. Zhigang","doi":"10.1109/ICNNSP.2003.1279345","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1279345","url":null,"abstract":"Based on the attractor analysis approach in phase space, 7 kinds of general features are extracted from the Lorenz model system to compute the infimum of uncorrelated features in number by numerical experiments. This infimum indicates that the least number of features is feasible to classify samples of special target recognition completely. After the infimum is chosen, a new feature selection method - ordinal optimization is introduced and applied to the selection of the least and optimum feature group. Blind picking rule of ordinal optimization is tested in the experiments and the experimental results indicate that ordinal optimization can reduce the size of feature space quickly and efficiently, and is a feasible approach to search the satisfactory subset from huge feature combination space.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"174 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":"132029002","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
A frequency diversity scheme for OFDM systems based on space-time block coding 一种基于空时分组编码的OFDM系统分集方案
International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003 Pub Date : 1900-01-01 DOI: 10.1109/ICNNSP.2003.1279317
Fengye Hu, Shuxun Wang, Xiaoying Sun
{"title":"A frequency diversity scheme for OFDM systems based on space-time block coding","authors":"Fengye Hu, Shuxun Wang, Xiaoying Sun","doi":"10.1109/ICNNSP.2003.1279317","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1279317","url":null,"abstract":"In this paper, a frequency diversity scheme for space-time block coded orthogonal frequency division multiplexing (STBC-OFDM) systems is investigated. The scheme can simultaneously obtain frequency diversity and space diversity gain. Extensive simulations show that the proposed scheme with two transmit antennas and a single receive antenna almost has the same performance as STBC-OFDM systems with four transmit antennas and a single receive antenna. Under the same symbol error rate (SER) performance, the number of transmit antenna is not required to be increased because of using frequency diversity.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"1 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":"130247092","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
FPGA based Sobel algorithm as vehicle edge detector in VCAS 基于FPGA的Sobel算法在车辆边缘检测中的应用
International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003 Pub Date : 1900-01-01 DOI: 10.1109/ICNNSP.2003.1281070
Li Xue, Z. Rongchun, Wang Qing
{"title":"FPGA based Sobel algorithm as vehicle edge detector in VCAS","authors":"Li Xue, Z. Rongchun, Wang Qing","doi":"10.1109/ICNNSP.2003.1281070","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1281070","url":null,"abstract":"The technology of detecting the edge of lateral vehicle by Sobel algorithm based on FPGA in vehicle collision avoidance system (VCAS) is proposed in this paper. In general, Sobel operator is an image edge detector, which is realized by programming and implemented on the microprocessor. To simplify the complex structure of the VCAS and decrease the computation burden of main processor, FPGA is introduced to realize the Sobel algorithm instead of the program. Processed results of acquired vehicle images are presented to illustrate the performance capabilities of this technology.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","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":"127957702","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: 13
Edge and motion detection using a bio-inspired CMOS vision chip robust to device mismatches 边缘和运动检测使用生物启发CMOS视觉芯片鲁棒器件不匹配
International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003 Pub Date : 1900-01-01 DOI: 10.1109/ICNNSP.2003.1279279
Jong-Ho Park, Jung-Hwan Kim, Jang-Kyoo Shin, Minho Lee, P. Choi
{"title":"Edge and motion detection using a bio-inspired CMOS vision chip robust to device mismatches","authors":"Jong-Ho Park, Jung-Hwan Kim, Jang-Kyoo Shin, Minho Lee, P. Choi","doi":"10.1109/ICNNSP.2003.1279279","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1279279","url":null,"abstract":"Human retina is able to detect the edge and motion of the object by effective mechanism. We designed and fabricated a CMOS vision chip by modeling retinal cells involved in edge and motion detection. There are several fluctuation factors which affect characteristics of MOSFETs during CMOS fabrication process and this effect appears as output offset of the vision chip. The output offset affects the efficiency of entire vision system. In order to eliminate the output offset, we designed a vision chip for edge and motion detection utilizing CDS (correlated double sampling) technique. The designed vision chip was fabricated using 0.6 um CMOS process and the characteristics were measured.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"1 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":"128788174","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
A new robust direct method for measurement error covariance estimation 一种新的测量误差协方差估计方法
International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003 Pub Date : 1900-01-01 DOI: 10.1109/ICNNSP.2003.1279355
Zhao Yu-hong
{"title":"A new robust direct method for measurement error covariance estimation","authors":"Zhao Yu-hong","doi":"10.1109/ICNNSP.2003.1279355","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1279355","url":null,"abstract":"Estimation of the measurement error covariance matrix is an essential requirement in data reconciliation methods. It is common practice to assume that the measurement errors are normal and have a known covariance matrix. A new robust direct algorithm for measurement error covariance estimation is proposed in this paper. Hampel's three-part redescending M-estimators are used to nullifies the effect of large outliers. A direct scheme treating the measured process variables is adopted to make it be used in the cases of nonlinear constraints. Implementation results show that credible results can be achieved either with or without the presence of external causes.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"63 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":"126834279","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
Algebraic DOA estimation and tracking using ULV decomposition 基于ULV分解的代数DOA估计与跟踪
International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003 Pub Date : 1900-01-01 DOI: 10.1109/ICNNSP.2003.1281112
C. Coviello, L. Sibul, P. Yoon
{"title":"Algebraic DOA estimation and tracking using ULV decomposition","authors":"C. Coviello, L. Sibul, P. Yoon","doi":"10.1109/ICNNSP.2003.1281112","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1281112","url":null,"abstract":"Blind beamforming is an important technique that is used to determine signal sources from the original signals mixed with additive noise and to estimate their direction of arrival (DOA). Before recovering the DOA information, it is necessary to preprocess the data matrix to decorrelate and normalize the mixed sources before applying nonlinear algorithms for the signal separation. A popular choice for the preprocessor has been based on the singular value decomposition (SVD). In this paper we propose an alternative preprocessor based on the ULV decomposition (ULVD). We compare both in an algebraic beamformer in terms of performance and accuracy.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"8 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":"126369987","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
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