{"title":"Adaptive vision system for high velocity tooling machines","authors":"D. Merad, S. Lelandais, M. Mallem, J. Triboulet","doi":"10.1109/ISSPA.2003.1224761","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224761","url":null,"abstract":"The work we present here is a diagnostic task, which must be solved for high velocity industrial tooling machines URANE-20. Due to environment degraded conditions, direct measurements are not possible, also for rapidity of the machine, human intervention is not possible in case of position fault. Therefore, an oriented vision solution is proposed. Degraded conditions are vibrations, dazzling, water and chips of metal projections. In this case, the once method cannot achieve a diagnostic problem: is it the right piece at the right place? That is why complementary methods presented in this paper are proposed in an adaptive way to solve this diagnostic problem. Image processing methods allow us to find image parameters. After a data analysis, image parameters are reduced. Then, using Bayesian approach and neural approach, it is possible to ensure the diagnostic result. With these two methods, we obtain encouraging results and we show that it is possible to improve the results by combining different classifiers approaches.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123567323","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 keyword spotting approach based on reward function","authors":"Y. B. Ayed, D. Fohr, J. Haton, G. Chollet","doi":"10.1109/ISSPA.2003.1224726","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224726","url":null,"abstract":"In this paper, we compare the performance achieved by different word-spotting techniques based on hidden Markov models. We propose two methods to detect keywords, the first one uses a GMM (Gaussian mixture model) as a filler model to absorb the out-of-vocabulary words. The second is an alternative approach which does not attempt to model out-of-vocabulary words, instead, it uses a loop phonemes based grammar. Furthermore, it uses different reward functions to favour the recognition of the keywords phonemes.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116051574","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":"Approximate diagonalization approach to blind source separation with a subset of matrices","authors":"A. Tomé, E. Lang","doi":"10.1109/ISSPA.2003.1224826","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224826","url":null,"abstract":"In blind source separation problems it is assumed that the approximate diagonalization of a matrix set achieves more robust solutions than the simultaneous diagonalization of a matrix pencil. In this work we will analyse approximate diagonalization methods using a generalized eigendecomposition (GED) of any pair of a given matrix set. The constraints of GHD solutions provide a criterion to choose a matrix subset even when none of the matrices follows an ideal model. We also present some numerical simulations comparing the performance of the solutions achieved by the referred approaches.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"280 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122298281","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":"Blind adaptation of a matched filter using the constant modulus algorithm coupled with an optional correction method","authors":"I. Ozcelik, B. Baykal, I. Kale","doi":"10.1109/ISSPA.2003.1224871","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224871","url":null,"abstract":"The matched filter (MF) with the whitening filter (WF) is the optimum receiver front end for the maximum likelihood sequence detection (MLSD). The MF+WF followed by the decision feedback equalizer (DFE) is an approximation for the maximum likelihood (ML) receiver. The estimation of the MF is of utmost importance in a receiver. The WF and the MF are treated separately and the MF is estimated blindly using the constant modulus algorithm (CMA) in this work. In this way, a very simple and blind adaptive way of the MF estimate is obtained instead of the methods like the singular value decomposition (SVD), which is complex and computationally expensive. Moreover, a correction method on the MF is introduced to obtain faster convergence and better performance. Simulations prove that the method is very effective and successful.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122552035","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":"Multiresolution adaptive structure for acquisition and detection in DS-SS digital receiver in a multiuser environment","authors":"R. A. Pages, J. Moran, J. Socoró","doi":"10.1109/ISSPA.2003.1224878","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224878","url":null,"abstract":"In this paper a new combined acquisition and detection scheme for a multiuser communications system is presented. The goal of this scheme is not only the minimization of multiuser interference in the detection, but also to minimize multiuser effect in the acquisition stage. The acquisition and tracking problems are both solved with the multiresolutive adaptive structure. Once the receiver is synchronized, a detector scheme estimates the interfering subspace to minimize its influence. This information is fedback and helps the acquisition scheme to minimize the effect of multiuser interference.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"190 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122630109","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}
M. Feki, G. Gelle, M. Colas, B. Robert, G. Delaunay
{"title":"Secure digital communication using chaotic modulation with feedback","authors":"M. Feki, G. Gelle, M. Colas, B. Robert, G. Delaunay","doi":"10.1109/ISSPA.2003.1224891","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224891","url":null,"abstract":"In this note we propose a new chaotic modulation schema with output feedback. It is shown that the receiver can synchronize with the transmitter with any desired rate. Moreover, this approach can be applied to a large class of chaotic systems and provides higher security against an intruder. The robustness of our scheme with respect to noise is illustrated and compared, to the symmetric chaos shift keying method.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"1083 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122901466","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":"Fractionally spaced bussgang equalization for GMSK modulated signals","authors":"S. Colonnese, G. Panci, P. Campisi, G. Scarano","doi":"10.1109/ISSPA.2003.1224790","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224790","url":null,"abstract":"The problem of blind equalization of GMSK modulated signals is here addressed. In particular, resorting to a linearized model of the GMSK signal we design a Bussgang blind equalization algorithm that allows a simple incorporation of the correlation between adjacent symbols. Simulation results show that this equalization scheme achieves good performance in term of MSE on the equalized symbols, and hence, in probability of bit error.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121988988","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}
S. Affes, K. Lajnef, K. Cheikhrouhou, P. Mermelstein
{"title":"Adaptive MIMO-diversity selection with closed-loop power control over wireless CDMA rayleigh-fading channels","authors":"S. Affes, K. Lajnef, K. Cheikhrouhou, P. Mermelstein","doi":"10.1109/ISSPA.2003.1224635","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224635","url":null,"abstract":"This contribution considers adaptive (multiple input multiple output) MIMO-diversity selection at the receiver jointly with closed-loop power control (PC) to efficiently combat fading with only few transmit (Tx) and receive (Rx) antennas. Hence we avoid resorting to antenna selection among large MIMO-arrays without PC which would be otherwise required to keep complexity low. With low Doppler closed-loop PC significantly increases the transmission capacity and reduces the MIMO-array size.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122019441","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":"Support vector machine for HRRP classification","authors":"Wan Xiao-dan, Wang Ji-qin","doi":"10.1109/ISSPA.2003.1224709","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224709","url":null,"abstract":"Radar target identification schemes by using high resolution range profile(HRRP) as features have been studied extensively. In practical systems we usually have only a very limited amount of training data. Therefore how to train a classifier with good generalization performance based on the training set is obviously a challenging task. This paper introduce the newest branch of statistic learning theory, support vector machine(SVM) to range profile classification. The range profiles of two targets were classified by SVM and LVQ (Learning Vector Quantization). Experiment results show that applying SVM to range profiles classification can get higher correct classification rate and better generalization performance.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116676170","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":"Phenotyping neurons with pattern recognition of molecular mixtures","authors":"R. Mare","doi":"10.1109/ISSPA.2003.1224797","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224797","url":null,"abstract":"Phenotyping cells and tracking their functional states are key tasks in cell biology and molecular medicine. Current cell classification methods are idiosyncratic to specific fields and based on ad hoc discovery of presumed univariate markers. We propose a general theory of phenotyping based on broadly distributed multivariate markers as the metrics of classification and standard pattern recognition algorithms as the method of class discovery. We present a real-world test case based on the vertebrate retina and demonstrate that pattern recognition methods can extract singular populations of neurons from complex heterocellular arrays: populations visualized solely as elements in a micromolecular N-space. The applications of this computational approach to cell phenotyping range from phylogenetics to drug discovery to environmental monitoring.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129849385","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}