{"title":"The application of binary image in digital audio watermarking","authors":"Lili Cui, Shu-Xun Wang, Tanfeng Sun","doi":"10.1109/ICNNSP.2003.1281159","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1281159","url":null,"abstract":"In this paper, we propose apply a visually recognizable binary image as watermarking embedding audio signals cepstrum domain. Cepstrum representation of audio can be shown to be very robust to a wide range of attacks including most challenging time-scaling and pitch-shifting warping. An intuitive psychoacoustic model is employed to control the audibility of introduced distortion. The results have shown the watermark imperceptible and robust against some signal processing, and our method succeeded in detection the embedded binary image. Extensive experimental results prove that the proposed method robustness to against the data compression and some kinds of synchronization attacks such as MP3, Gaussian white noise, filter and so on.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"529 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":"129700150","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}
{"title":"The extraction of MMN modulated by attention","authors":"Ding Hy, Yew Dt","doi":"10.1109/ICNNSP.2003.1279227","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1279227","url":null,"abstract":"The mismatch negativity (MMN) component of the auditory event-related brain potential can be measured in the absence of attention and without any task requirements, which makes it the objective measure of the central auditory function. While in the collection of evoked potentials, selective attention may affect the appearance of the evoked MMN. In some cases, MMN may be followed or even substituted by P300. We investigated the role of attention on the MMN extraction. Based on the discussion of such phenomenon, an ensemble average method modulated by attention is proposed in the present study. This method may restrain the affection of distraction and increase the amplitude of MMN to a great extent. Furthermore, such method may shorten the time cost of MMN extraction experiment, which will be helpful for the research of complex function nature of neural discrimination mechanism.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"37 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":"126885803","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}
{"title":"Radial basis function neural network-based nonparametric estimation approach for missing data reconstruction of non-stationary series","authors":"Baoming Hong, C.H. Chen","doi":"10.1109/ICNNSP.2003.1279216","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1279216","url":null,"abstract":"In real world, due to various reasons, the data we can acquire is usually incomplete, i.e., a significant number of data can be often missing in a non-stationary time series. Traditional interpolation or estimation methods (e.g., cubic spline) are becoming invalid when the observation interval of the missing data is not small. In this paper we introduced a novel method where a radial basis function (RBF) neural network was particularly designed as an optimal estimator for reconstruction of the missing data, in which several important features of the raw data were chosen as input pattern, and one primary feature was used as the desired output response of the RBF network so as to make it learn enough of the data distribution structure. The experimental simulations on Zooplankton data showed that this method had better performance than other methods such as backpropagation (BP)-based neural network and cubic spline interpolation in the meaning of mean square error and confidence intervals.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"44 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":"123833839","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}
{"title":"High speed frequency response masking filter design using genetic algorithm","authors":"Ling Cen, Y. Lian","doi":"10.1109/ICNNSP.2003.1279380","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1279380","url":null,"abstract":"This paper presents the design of high-speed, multiplier free, arbitrary bandwidth shape FIR filters based on frequency response masking technique (FRM). The FRM filter structure has been modified to improve the throughput by replacing long bandedge shaping filter with several cascaded short filters [Yong Lian, 2000]. Genetic algorithm (GA) is introduced to simultaneously optimize all subfilters in a cascaded connection. The coefficients of all subfilters are quantized to signed power-of-two (SPoT) values to eliminate multipliers in the filter implementation. It is shown by example that the coefficient word length for each cascaded short filter has been reduced significantly.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"12 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":"123942721","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}
{"title":"New data-aided frequency estimation algorithm based on discriminator for GMSK signals","authors":"Tuanfeng Wu","doi":"10.1109/ICNNSP.2003.1281213","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1281213","url":null,"abstract":"Data-aided frequency estimation algorithm has good performance of mean square error (MSE) than non-data-aided frequency estimation algorithm while its estimation range is smaller than the latter. This paper presents a new data-aided frequency estimation algorithm based on discriminator for GMSK signals, which treats GMSK signal as digital FM signal. Simulations are carried out and results show that this scheme can reach large estimation range about /spl plusmn/0.5 * (1/T) while the frequency MSE is close to MCRB.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"19 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":"124189065","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}
{"title":"A simple blind equalization approach based on multi-mode error switch","authors":"Lingyun Dai, Ju Liu","doi":"10.1109/ICNNSP.2003.1281137","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1281137","url":null,"abstract":"Blind signal processing has been one of the key technology in communication and signal processing area. In wireless communication systems there always exists severely inter-symbol interference (ISI) and multiple access interference (MAI). In this paper, a new blind equalization algorithm for MQAM digital communication system based on the multi-mode error switch is proposed. The algorithm is based on the constant modulus characteristic of the transmitted signal and the multi-mode error switch is used during the training. Analysis and computer simulations show that the new algorithm can reduce the remainder error and the computational complexity , ensure the convergence rates, and the convergence performance is much better than that of algorithm in literature.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"30 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120860449","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}
{"title":"A new method to construct the fuzzy controller using neural networks","authors":"Yu Yongquan, H. Ying, Zeng Bi","doi":"10.1109/ICNNSP.2003.1279326","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1279326","url":null,"abstract":"The new method to construct fuzzy controller based on perceptron neurons and aggregation logic neurons is presented in this paper. The analysis result shows the neuro-fuzzy controller proposed in this paper is effective and simple for using.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"203 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":"121513743","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}
{"title":"Generalized additive-multiplicative fuzzy neural network optimal parameters identification based on genetic algorithm","authors":"Dong-hai Zhai, Li Li, F. Jin","doi":"10.1109/ICNNSP.2003.1279328","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1279328","url":null,"abstract":"In additive-multiplicative fuzzy neural networks (AMFNN), its membership functions have no adaptability and the number of fuzzy rules is determined subjectively. In this paper, a generalized additive-multiplicative fuzzy neural network (generalized AMFNN) is presented, and the parameters of membership functions can be adjusted. Therefore, there are many parameters to be determined. The matrix coding in genetic algorithm (GA), which combines binary coding with real number coding, is adopted to search the optimal parameters of the generalized AMFNN and determine the number of fuzzy rules. The generalized AMFNN has lower complexity and can approximate to a nonlinear system at high accuracy degree. A numerical simulation has demonstrated the validity of this approach.","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":"124031127","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}
{"title":"Codebook design by a hybridization of ant colony with improved LBG algorithm","authors":"Li Xia, Luo Xuehui, Zhang Jihong","doi":"10.1109/ICNNSP.2003.1279310","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1279310","url":null,"abstract":"Ant colony algorithm is a newly emerged stochastic searching optimization algorithm in recent years. In this paper, an appropriately adapted ant colony system embedded with a simple improved LBG algorithm is proposed for vector quantization codebook design. The emphasis is put on the design of the probability transfer function and the tabu list in the ant colony algorithm, the utilization of the next nearest neighborhood in the LBG algorithm, as well as the update of the pheromone in both local and global sense. Experimental results show that the new algorithm outperforms other well-known codebook design algorithms, and particularly, the improvement of PSNR exceeds 2 dB compared with the conventional LBG algorithm.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"30 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":"124125374","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}
{"title":"Complex exponential expansion based blind channel amplitude frequency response estimation for OFDM systems","authors":"Xiaodong Xie, X. Dai","doi":"10.1109/ICNNSP.2003.1281136","DOIUrl":"https://doi.org/10.1109/ICNNSP.2003.1281136","url":null,"abstract":"In this paper, we present a new blind channel amplitude frequency response (APR) estimation method for orthogonal frequency division multiplexing (OFDM). After exploiting the second order instantaneous moment of the received signals in frequency domain, the proposed complex exponential expansion algorithm is introduced to identify the channel amplitude with few parameters. Through the whole algorithm, only a small amount of computation is involved. Therefore, the algorithms can track the channel APR continuously and are amenable to real applications. The algorithm is tested with simulations and also compared with, other method.","PeriodicalId":336216,"journal":{"name":"International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003","volume":"14 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":"127734772","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}