{"title":"Neural network approaches to nonlinear blind source separation","authors":"Pei Gao, W. L. Woo, S. Dlay","doi":"10.1109/ISSPA.2005.1580200","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1580200","url":null,"abstract":"In this paper, several recently proposed neural network approaches to nonlinear blind signal separation (BSS) are reviewed. Of great interest, popular multilayer perceptron (MLP), radial basis function (RBF) and polynomial neural networks are the focus of the paper. In order to uniquely extract the original source signals from only nonlinearly mixed observations, some forms of constrains are always imposed on the neural networks. Three structurally constrained nonlinear independent component analysis mixing models are presented, followed by the discussion on additional signal constraints to the original cost function stemmed from the Kullback-Leibler Divergence.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114068426","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":"Characterization of phonocardiogram signals using bispectral estimation","authors":"B. Ergen, Y. Tatar","doi":"10.1109/ISSPA.2005.1580231","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1580231","url":null,"abstract":"The application of the bispectrum as a high-order spectrum (HOS) method in analyzing normal and pathological heart sound signal is investigated in this paper. The bispectrum of phonocardiogram (PCG) signals is used to characterize the abnormalities while detecting non-linearity or non-Gaussianity in order to improve the diagnostic performance. In the comparison of the diagonal slice of the bispectrum and the power spectrum of PCG signal, the results have shown that the HOS reveal the differences in heart sound analysis indicating non-Gaussianity or non-linearity. It is concluded that the diagonal slice and the peaks of bispectrum are efficiently determine the cardiac dysfunctions effecting on heart sounds.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116347104","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":"De-ringing using morphological filters for waveletbased compressed image","authors":"W. Yen, Yen-Yu Chen","doi":"10.1109/ISSPA.2005.1580264","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1580264","url":null,"abstract":"JPEG2000 Standard is a new generation image compression technique, enabling encoding images at low bit-rates with acceptable quality. Since JPEG2000 is based on wavelet transforms, the reconstructed image will contain perceivable ringing artifacts in medium and low bit-rate regimes of lossy compression. This work utilizes a quad-tree partitioning scheme for post-processing the reconstructed image in a spatially varying manner and presents a voting strategy to determine a set of morphological filters to be used for reducing the ringing artifacts. Simulation results demonstrate that the proposed technique enhances reconstructed image quality compared to unprocessed JPEG2000 output at an equivalent bit-rate accounting for the side-information overhead, in terms of both PSNR and Visible Ringing Measure (VRM).","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132115202","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":"Fast convergence polynomial based separation algorithm","authors":"L. Khor, W. L. Woo, S. Dlay","doi":"10.1109/ISSPA.2005.1580983","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1580983","url":null,"abstract":"Nonlinear Blind Source Separation which is an extension of its more popular linear counterpart has gained increasing attention over recent years. Its development presents a more realistic approach due to the nonlinear mixing introduced by transmitter and receiver elements such as loudspeaker, amplifier and microphones. Though more accurate than linear models, it is also more complex and suffers from convergence issues. This paper proposes a polynomial neural network for blind nonlinear signal separation and also addresses the fundamental difficulty of non-unique solutions and slow convergence. Efficiency of the objective function is enhanced by a polynomial based model which is a flexible and more accurate fit. Coupled with reduced indeterminacy using additional constraints and improved convergence speed via adaptive learning rates, the proposed algorithm produces very promising results. Issues of convergence speed, accuracy and robustness against noise are investigated and results demonstrate the efficacy of the algorithm with adaptive learning rates.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133072369","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 separation principle for optimum biorthogonal dmt without a high bit rate assumption","authors":"Xuejie Song, S. Dasgupta","doi":"10.1109/ISSPA.2005.1580186","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1580186","url":null,"abstract":"We consider the design of optimum biorthogonal, as opposed to orthonormal, discrete multitone (DMT) systems supporting a service whose quality of service (QoS) requirements are quantified by bit rate and symbol error rate specifications. Our goal is to minimize the transmitted power given the QoS specifications subject to the knowledge of the channel and colored interference at the receiver input of the DMT system. We find an optimum bit loading scheme that distributes the bit rate transmitted across the various subchannels, and an optimum transceiver. Earlier papers, [2] and [4] showed the following: (i) Relaxing the orthonormality constraint yields no performance improvement. (ii) The optimum transceiver is unaffected by changing service characteristics, and depends only on the channel and interference conditions. (iii) The QoS requirements, only affect bitloading. These conclusions form a separation principle that has important implications to wireline applications like DSL. These papers, [2] and [4], however worked with an approximation that only works if each subchannel supports a very high data rate. In this paper we show that even if one relaxes this high bit rate assumption, (i-iii) still hold.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"515 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116215942","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":"Advanced ECG interpretation routines as world-distributed web services","authors":"P. Augustyniak, R. Tadeusiewicz","doi":"10.1109/ISSPA.2005.1580225","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1580225","url":null,"abstract":"The manufacturers of ECG equipment usually face the advanced interpretation routines implementation problem. The development of these routines entails great financial expenditures, however for their specificity, the customers rarely demand them. This paper proposes a distributed computing approach to the advanced interpretation routines. Our proposal assumes each cardiologic issue to be interpreted by an unique specialized center automatically or with a human expert assistance if necessary. The interpretation service is accessible through the web for distant clients meeting the selection criteria. These may include customers of a particular enterprise, members of a given society or subscribed individual cardiologists. Among numerous advantages of this proposal, the most important is world wide unification of methods since most complicated software have to be developed only once and remain undisclosed to the others.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125793770","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":"Design of Al/ZnO/Si one-port SAW resonator filter","authors":"E. Ntagwirumugara, T. Gryba, J. Lefebvre","doi":"10.1109/ISSPA.2005.1580222","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1580222","url":null,"abstract":"In this paper, we present an analysis and real isation of a ladder-type SAW filter composed of six resonators on the same port. The filter will be developed on a structure with three layers of a ZnO film and aluminium (AI) electrodes on a silicon (Si) substrate with TilAu for metallization in the 925-960MHz frequency band range. Up to now, RF front-end and interstage SAW filters for mobile communication are mainly fabricated on LiNb03 and LiTa03 substrates. A monolithic integration of these filters on semiconductor substrates is highly desirable to miniaturize the outer dimensions of the cellular phones. For analysis, we used the coupling-of-mode (COM) theory for analysing SAW periodic structures such as reflectors and interdigital transducers which has been used by the SAW industry as the standard modelling tool and we found the corresponding insertion loss for our resonator is very small, which will be very helpful in manufacturing corresponding SAW resonator filters.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123599064","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":"2D dimension, location and speed descriptors from surveillance video","authors":"A. Sugama, S. Emmanuel, A. Vinod","doi":"10.1109/ISSPA.2005.1581013","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1581013","url":null,"abstract":"Use of video surveillance systems are on the rise for various applications such as protecting the personnel property, law enforcement and traffic management. In surveillance applications; it is necessary to automatically extract actual 2D dimension, location and speed descriptors of moving objects from the surveillance video for annotation and indexing purposes. In this paper we propose a method of estimating the actual 2D dimension, location and speed descriptors of moving objects especially from surveillance video of indoor environments such as indoor car parks, corridors of buildings, shopping malls etc. Experiments are conducted to find the accuracy of the estimated 2D dimension, location and speed of the moving object and the accuracy is found to be high.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125090679","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":"Varational method using the Kuan filtering approach for the restoration of blurred images with multiplicative noise","authors":"Luc Klaine, B. Vozel, K. Chehdi","doi":"10.1109/ISSPA.2005.1580266","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1580266","url":null,"abstract":"The main idea of the proposed restoration approach is the joint use of the Kuan filtering approach and a variational method of restoration. Three alternative formulations of the total mean quadratic error criterion are considered (stochastic, integral and differential). We show that the resulting integral and differential potential energies are well adapted for the purpose of image restoration as they correspond to regularization energies. The differential potential energy coincides with the regularization energy of Geman-McClure. A fidelity term to the data is introduced in the two integral and differential energies. The two methods are evaluated on different images blurred with different PSFs and degraded with multiplicative noise. The results are overall promising like those for most notconvex regularization energies.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125929060","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":"An improved dynamic model for optical feedback self-mixing interferometry-based measurement and instrumentation","authors":"J. Xi, Yanguang Yu, E. Li, J. Chicharo","doi":"10.1109/ISSPA.2005.1581077","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1581077","url":null,"abstract":"Abstract This paper presents a new model that describes the behaviour of optical feedback self-mixing interferometry(OFSMI). Compared to the existing model, the proposed one does not suffer from the multiple valueambiguity problems. The proposed model is a dynamic one that gives a unique relationship between theexternal target moving law and the self-mixing signal (SMS) waveform (SMS) when other parameters aregiven. A computer simulation tool for OFSMI has been implemented to generate SMS waveforms and itseffectiveness has been verified by experimental data. Publication Details This paper originally appeared as: Xi, J, Yu, Y, Li, E & Chicharo, J, An improved dynamic model for opticalfeedback self-mixing interferometry-based measurement and instrumentation, Proceedings of the EighthInternational Symposium on Signal Processing and Its Applications, 28-31 August 2005, vol 2, 871-874.Copyright IEEE 2005. This conference paper is available at Research Online: http://ro.uow.edu.au/infopapers/263","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130224418","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}