{"title":"Model selection using cross validation Bayesian predictive densities","authors":"M. Bekara, G. Fleury","doi":"10.1109/ISSPA.2003.1224925","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224925","url":null,"abstract":"In this paper, a new model selection criterion for linear Gaussian models is proposed. The criterion is based on choosing the model that achieves the highest prediction ability. A natural way to measure the prediction ability of a given model is to use the principle of cross validation (CV) that partitions the data into estimation set and validation set. However, instead of using CV to obtain a point estimate of the prediction error, the predictive density is used to obtain a measure of the marginal likelihood of the validation data set, conditioned on the event that the estimation data set is observed and that the candidate model is true. The performance of the new criterion is compared with AIC and MDL through Monte Carlo simulations. The cross validation Bayesian predictive density selection rule is shown to outperform the well known consistent criterion MDL. as well as having a good small sample performance.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"152 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":"115187264","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":"Preliminary investigation into the use of the cross Wigner-Ville distribution to detect high impedance earth faults in power systems","authors":"E. Palmer, G. Ledwich, Mohamed Deriche","doi":"10.1109/ISSPA.2003.1224774","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224774","url":null,"abstract":"This paper presents the results of a preliminary investigation into the viability of using the cross Wigner-Ville distribution (XWVD) in the detection of high impedance earth faults in power systems. High impedance earth faults are characterised an extremely low current with a time varying spectral characteristic superimposed on the mains current. It is shown that the XWVD provides a good identification of the extremely small high impedance arc fault current with signal to noise ratios as low as -10dB.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"20 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":"115681357","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":"Structured interference cancellation at a WCDMA terminal","authors":"A. Bastug, D. Slock","doi":"10.1109/ISSPA.2003.1224750","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224750","url":null,"abstract":"In third generation CDMA-based cellular mobile systems, loading fraction is going to be less than one due to interference limitations. In other words, to achieve an acceptable BER, the number of served users and hence used codes will be less than the spreading factor. Accordingly, the existence of unused codes implies the existence of a noise subspace, which can be exploited to partially cancel the intracell and intercell interference. When aperiodic scrambling is used, as in the FDD mode of UMTS, the noise subspace varies with symbol period. In this case, multiuser interference cancelling receivers should contain time varying parts. We discuss two-stage structured receivers for mobile terminals that contain (de)scrambling, (de)spreading, projection/hard-limiting/tangent-hyperbolic decision operations and linear filters the time-varying parts of which are limited to de-scrambling and scrambling. The first stages estimate and delete the intracell and/or intercell interference whereas the second stages operate on the resultant improved SINR signal to detect the user symbols. Performances of various different schemes are compared via simulations.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"62 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":"114767882","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 FPGA implementation of discrete Hartley transforms","authors":"A. Amira, A. Bouridane","doi":"10.1109/ISSPA.2003.1224781","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224781","url":null,"abstract":"Discrete Hartley transforms (DHTs) are very important in many types of applications including image and signal processing. Two novel architectures for computing DHTs using both systolic architecture and distributed arithmetic design methodologies are presented in this paper. The first approach uses the modified Booth-encoder-Wallace trees multiplication (MBWM) algorithm for a systolic architecture implementation. The second approach is based on distributed arithmetic ROM and accumulator structure. Implementations of the algorithms on a Xilinx FPGA board are described. Distributed arithmetic approach exhibits better performances when compared with the systolic architecture approach.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"20 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":"116993949","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 genetic matching pursuit algorithm","authors":"D. Stefanoiu, F. Ionescu","doi":"10.1109/ISSPA.2003.1224769","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224769","url":null,"abstract":"Advanced signal processing (SP) methods often lead to greedy algorithms that are time consuming, so useless in real time applications. However, nowadays, efficient implementations of such algorithms become more and more feasible, eventually with the help of concepts withdrawn from fields outside SP. This paper introduces an implementation for one of the most appealing signal analysis procedures based on a method devised about 10 years ago: the matching pursuit algorithm (MPA).","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"41 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":"115172547","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":"Parametric estimation of space-time channels with spatially correlated noise by JADE-ESPRIT","authors":"J. Picheral, U. Spagnolini","doi":"10.1109/ISSPA.2003.1224902","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224902","url":null,"abstract":"In mobile communications the antenna array makes it possible to estimate the path delay, angle of arrival (or angle) and amplitude for the multipath propagation channel. This paper considers the problem of parametric channel estimation by the joint angle and delay estimation (JADE) in a time division system. By exploiting the angle/delay invariance of the channel regardless of the fast faded amplitude variation (i.e., angle/delay is assumed quasi-static). The shift invariance method (JADE-ESPRIT) is chosen for its capacity to pair delay and angle for each path. In this paper, it is shown that the consistency of JADE-ESPRIT for a large enough number of slots guarantees the feasibility of the method for spatially correlated noise. Bounds of the channel MSE are derived when JADE is used.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"22 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":"115476413","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}
D. R. Iskander, Siegfried Mioschek, Martin Trunk, W. Werth
{"title":"Detecting eyes in digital images","authors":"D. R. Iskander, Siegfried Mioschek, Martin Trunk, W. Werth","doi":"10.1109/ISSPA.2003.1224805","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224805","url":null,"abstract":"Detecting eyes in digital images taken in a variety of natural lighting conditions is not a straightforward task. Great difficulties are experienced when one attempts to employ traditional methods such as the Radon or Hough transforms. They appear to be not robust enough to perform the detection task in images that include blur, speckles, or a reflection in the pupil or iris areas. Also, in some practical applications these techniques are not computationally efficient. We propose a simple quadruple axis spatial-domain-based symmetry indicator for detecting circularly symmetric objects in digital images. The proposed detector is an inherent part of a larger system for estimating 2D characteristics of the human eye. The efficacy of the proposed technique versus a frequency domain energy detector has been evaluated using artificial images. It has been shown that the proposed method outperforms the energy-based detector for moderate levels of noise. Also, the method appears to be more robust than its frequency domain counterpart and correctly detects the eye in a wide variety of images. An application of the detector to clinical assessment and patient diagnosis in optometry is provided.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"362 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":"122811069","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":"Efficient classification of noisy speech using neural networks","authors":"Cathy Shao, M. Bouchard","doi":"10.1109/ISSPA.2003.1224714","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224714","url":null,"abstract":"The classification of active speech vs. inactive speech in noisy speech is an important part of speech applications, typically in order to achieve a lower bit-rate. In this work, the error rates for raw classification (i.e. with no hangover mechanism) of noisy speech obtained with traditional classification algorithms are compared to the rates obtained with neural network classifiers, trained with different learning algorithms. The traditional classification algorithms used are the linear classifier, some nearest neighbor classifiers and the quadratic Gaussian classifier. The training algorithms used for the neural networks classifiers are the extended Kalman filter and the Levenberg-Marquadt algorithm. An evaluation of the computational complexity for the different classification algorithms is presented. Our noisy speech classification experiments show that using neural network classifiers typically produces a more accurate and more robust classification than other traditional algorithms, while having a significantly lower computational complexity. Neural network classifiers may therefore be a good choice for the core component of a noisy speech classifier, which would typically also include a hangover mechanism and possibly a speech enhancement algorithm.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"40 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":"123904630","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 strain gauges platform for vertical jumping study","authors":"S. Boukhenous, M. Attari, N. Ababou","doi":"10.1109/ISSPA.2003.1224803","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224803","url":null,"abstract":"The aim of this work is the realization of a strain gauge platform for studying the human body gesture. This mechanical system is fed by a special instrumentation for measuring the ground reaction force during a vertical jumping phase. Four composites sensors that support the whole rigid plate were realized with metallic strain gauges. The low level signal at the output was carefully amplified and earned out to a PC computer via a special data acquisition card for subsequent signal analysis. In this paper, special features were dedicated to study the whole phase during successive jumps conducted by an athlete and experimental tests have been carried out for this purpose. The output signals were reported and a particularity was given to the power spectrum when the athlete takes off. The analysis puts into evidence the vertical jumping behavior and anomalies is especially studied in the falling down moment.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"8 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":"126192121","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":"Latency time optimization for FIR and block transmit filters","authors":"M. Joham, W. Utschick, J. Nossek","doi":"10.1109/ISSPA.2003.1224693","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224693","url":null,"abstract":"We address the problem of optimizing the latency time for transmit filters which can have FIR or block structure. When we allow the transmission system to have latency time, we gain an additional degree of freedom which can be exploited to improve the performance substantially. Contrary to the latency time optimization for FIR filters, the optimization for block transmit filters is very complex. We present a sub-optimum approach for block transmit filters which leads to results close to optimum but with low complexity.","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":"125803833","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}