Pub Date : 1993-11-01DOI: 10.1109/ACSSC.1993.342396
D. Carhoun
Reduced-rank subspace projection methods are used indirectly in frequency and angle-of-arrival estimation algorithms such as MUSIC and its relatives, but they are not commonly used directly in least-squares detection applications. The author has been exploring their use for the processing of underwater acoustic receiver array data for detection and matched-field localization. He describes and illustrates several techniques that have been developed and applied to signals recorded from different types of arrays.<>
{"title":"Signal subspace projection methods of adaptive sensor array processing","authors":"D. Carhoun","doi":"10.1109/ACSSC.1993.342396","DOIUrl":"https://doi.org/10.1109/ACSSC.1993.342396","url":null,"abstract":"Reduced-rank subspace projection methods are used indirectly in frequency and angle-of-arrival estimation algorithms such as MUSIC and its relatives, but they are not commonly used directly in least-squares detection applications. The author has been exploring their use for the processing of underwater acoustic receiver array data for detection and matched-field localization. He describes and illustrates several techniques that have been developed and applied to signals recorded from different types of arrays.<<ETX>>","PeriodicalId":266447,"journal":{"name":"Proceedings of 27th Asilomar Conference on Signals, Systems and Computers","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134623891","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}
Pub Date : 1993-11-01DOI: 10.1109/ACSSC.1993.342500
T. A. Barton, D. Fuhrmann
Under a complex-Gaussian data model, a maximum likelihood method based on the iterative expectation-maximization algorithm is given to estimate structured covariance matrices for multidimensional data organized into column-vector form. The covariance structures of interest involve a hierarchy of subblocks within the covariance matrix, and include block-circulant and block Toeplitz matrices and their generalizations. These covariance matrices are elements of certain covariance constraint sets such that each element may be described as a matrix multiplication of a known matrix of Kronecker products and a nonnegative-definite, block-diagonal matrix. Several convergence properties of the estimation procedure are discussed, and an example of algorithm behavior is provided.<>
{"title":"Covariance estimation for multidimensional data using the EM algorithm","authors":"T. A. Barton, D. Fuhrmann","doi":"10.1109/ACSSC.1993.342500","DOIUrl":"https://doi.org/10.1109/ACSSC.1993.342500","url":null,"abstract":"Under a complex-Gaussian data model, a maximum likelihood method based on the iterative expectation-maximization algorithm is given to estimate structured covariance matrices for multidimensional data organized into column-vector form. The covariance structures of interest involve a hierarchy of subblocks within the covariance matrix, and include block-circulant and block Toeplitz matrices and their generalizations. These covariance matrices are elements of certain covariance constraint sets such that each element may be described as a matrix multiplication of a known matrix of Kronecker products and a nonnegative-definite, block-diagonal matrix. Several convergence properties of the estimation procedure are discussed, and an example of algorithm behavior is provided.<<ETX>>","PeriodicalId":266447,"journal":{"name":"Proceedings of 27th Asilomar Conference on Signals, Systems and Computers","volume":"241 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133879025","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}
Pub Date : 1993-11-01DOI: 10.1109/ACSSC.1993.342604
S. R. Pillai
A new higher order generalization of magnitude and power complementary filters is proposed. The proposed scheme is shown to have superior frequency characteristics compared to the ordinary complementary filters. Applications of these generalized complementary filters include subband coding for audio and video, and sharpening of amplitude characteristics of digital filters. Interestingly, as shown in the present paper, this new design procedure can be used to generate ordinary multichannel magnitude and power complementary filters with sharper band responses.<>
{"title":"Design of generalized higher order complementary filters","authors":"S. R. Pillai","doi":"10.1109/ACSSC.1993.342604","DOIUrl":"https://doi.org/10.1109/ACSSC.1993.342604","url":null,"abstract":"A new higher order generalization of magnitude and power complementary filters is proposed. The proposed scheme is shown to have superior frequency characteristics compared to the ordinary complementary filters. Applications of these generalized complementary filters include subband coding for audio and video, and sharpening of amplitude characteristics of digital filters. Interestingly, as shown in the present paper, this new design procedure can be used to generate ordinary multichannel magnitude and power complementary filters with sharper band responses.<<ETX>>","PeriodicalId":266447,"journal":{"name":"Proceedings of 27th Asilomar Conference on Signals, Systems and Computers","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117286371","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}
Pub Date : 1993-11-01DOI: 10.1109/ACSSC.1993.342513
W. Blair, D. Kazakos
In many multisensor systems, the number of sensors and the type of sensors supporting a particular target track can vary with time due to the mobility, type, and resource limitations of the individual sensors. This variability in the configuration of the sensor system poses a significant problem when tracking maneuvering targets because of the uncertainty in the target motion model. When the sensor system is fixed, the uncertainty in the motion model is addressed in the design of the tracking algorithm by considering individual target trajectories. However, considering individual target trajectories in conjunction with every possible multisensor configuration is not practical. In the paper, the problem of tracking maneuvering targets with multiple intermittent sensors is illustrated through an example involving a single motion model example. The interacting multiple model (IMM) algorithm is applied to this problem and simulation results are given.<>
{"title":"Tracking maneuvering targets with multiple, intermittent sensors","authors":"W. Blair, D. Kazakos","doi":"10.1109/ACSSC.1993.342513","DOIUrl":"https://doi.org/10.1109/ACSSC.1993.342513","url":null,"abstract":"In many multisensor systems, the number of sensors and the type of sensors supporting a particular target track can vary with time due to the mobility, type, and resource limitations of the individual sensors. This variability in the configuration of the sensor system poses a significant problem when tracking maneuvering targets because of the uncertainty in the target motion model. When the sensor system is fixed, the uncertainty in the motion model is addressed in the design of the tracking algorithm by considering individual target trajectories. However, considering individual target trajectories in conjunction with every possible multisensor configuration is not practical. In the paper, the problem of tracking maneuvering targets with multiple intermittent sensors is illustrated through an example involving a single motion model example. The interacting multiple model (IMM) algorithm is applied to this problem and simulation results are given.<<ETX>>","PeriodicalId":266447,"journal":{"name":"Proceedings of 27th Asilomar Conference on Signals, Systems and Computers","volume":"282 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116079627","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}
Pub Date : 1993-11-01DOI: 10.1109/ACSSC.1993.342319
Wenyuan Xu, M. Kaveh
Angle-dependent weighted MUSIC or weighted norm MUSIC is a broad class of MUSIC-like parameter estimators which includes as special case the standard "spectral" MUSIC. Based on a general approach for deriving the point statistics of the signal-subspace estimators, the relation between the large-sample moments of MUSIC and angle-dependent weighted MUSIC is presented in this paper. The optimum weight function resulting in the estimator with zero bias of order N/sup -1/ is derived. The approximate realizations of this optimum estimator in a parametric subclass of angle-dependent weighted MUSIC for arrays measuring closely spaced sources are discussed. Simulation examples verify the theoretical analysis and demonstrate the proposed estimators have small estimation biases over a wide range of signal-to-noise ratio.<>
{"title":"The optimum weight of angle-dependent weighted MUSIC and its approximations","authors":"Wenyuan Xu, M. Kaveh","doi":"10.1109/ACSSC.1993.342319","DOIUrl":"https://doi.org/10.1109/ACSSC.1993.342319","url":null,"abstract":"Angle-dependent weighted MUSIC or weighted norm MUSIC is a broad class of MUSIC-like parameter estimators which includes as special case the standard \"spectral\" MUSIC. Based on a general approach for deriving the point statistics of the signal-subspace estimators, the relation between the large-sample moments of MUSIC and angle-dependent weighted MUSIC is presented in this paper. The optimum weight function resulting in the estimator with zero bias of order N/sup -1/ is derived. The approximate realizations of this optimum estimator in a parametric subclass of angle-dependent weighted MUSIC for arrays measuring closely spaced sources are discussed. Simulation examples verify the theoretical analysis and demonstrate the proposed estimators have small estimation biases over a wide range of signal-to-noise ratio.<<ETX>>","PeriodicalId":266447,"journal":{"name":"Proceedings of 27th Asilomar Conference on Signals, Systems and Computers","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115488442","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}
Pub Date : 1993-11-01DOI: 10.1109/ACSSC.1993.342606
R. Elliott, L. Aggoun
Using a change of measure a filtering problem is discussed where both the signal and observation processes are diffusions with jumps.<>
利用测度变化讨论了信号过程和观测过程都是具有跳变的扩散的滤波问题。
{"title":"A jump process filter","authors":"R. Elliott, L. Aggoun","doi":"10.1109/ACSSC.1993.342606","DOIUrl":"https://doi.org/10.1109/ACSSC.1993.342606","url":null,"abstract":"Using a change of measure a filtering problem is discussed where both the signal and observation processes are diffusions with jumps.<<ETX>>","PeriodicalId":266447,"journal":{"name":"Proceedings of 27th Asilomar Conference on Signals, Systems and Computers","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123249365","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}
Pub Date : 1993-11-01DOI: 10.1109/ACSSC.1993.342540
A. Gopalakrishnan, Xiangping Jiang, Mu-Song Chen, M. Manry
We show that the pattern storage capability of the Gabor polynomial is much higher than the commonly used lower bound on multi-layer perceptron (MLP) pattern storage. We also show that multi-layer perceptron networks having second and third degree polynomial activations can be constructed which efficiently implement Gabor polynomials and therefore have the same high pattern storage capability. The polynomial networks can be mapped to conventional sigmoidal MLPs having the same efficiency. It is shown that training techniques like output weight optimization and conjugate gradient attain only the lower bound of pattern storage. Certainly they are not the final solutions to the MLP training problem.<>
{"title":"Constructive proof of efficient pattern storage in the multi-layer perceptron","authors":"A. Gopalakrishnan, Xiangping Jiang, Mu-Song Chen, M. Manry","doi":"10.1109/ACSSC.1993.342540","DOIUrl":"https://doi.org/10.1109/ACSSC.1993.342540","url":null,"abstract":"We show that the pattern storage capability of the Gabor polynomial is much higher than the commonly used lower bound on multi-layer perceptron (MLP) pattern storage. We also show that multi-layer perceptron networks having second and third degree polynomial activations can be constructed which efficiently implement Gabor polynomials and therefore have the same high pattern storage capability. The polynomial networks can be mapped to conventional sigmoidal MLPs having the same efficiency. It is shown that training techniques like output weight optimization and conjugate gradient attain only the lower bound of pattern storage. Certainly they are not the final solutions to the MLP training problem.<<ETX>>","PeriodicalId":266447,"journal":{"name":"Proceedings of 27th Asilomar Conference on Signals, Systems and Computers","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124786043","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}
Pub Date : 1993-11-01DOI: 10.1109/ACSSC.1993.342558
Jitendra Tugnait
A general (possibly asymmetric noncausal and/or nonminimum phase) two-dimensional autoregressive moving average random field model driven by an i.i.d. two-dimensional (2D) non-Gaussian sequence is considered. We address the problem of parameter identifiability of the model parameters given the higher-order (third- or fourth-order, for example) cumulants of the 2D signal on a finite set of lags. The signal observations may be noisy. A key result is the parameter identifiability of 2D MA models. Using the MA parameter identifiability results, the parameter identifiability of AR and ARMA models follows immediately via a novel approach.<>
{"title":"On parameter identifiability of multidimensional non-Gaussian ARMA models using cumulant matching","authors":"Jitendra Tugnait","doi":"10.1109/ACSSC.1993.342558","DOIUrl":"https://doi.org/10.1109/ACSSC.1993.342558","url":null,"abstract":"A general (possibly asymmetric noncausal and/or nonminimum phase) two-dimensional autoregressive moving average random field model driven by an i.i.d. two-dimensional (2D) non-Gaussian sequence is considered. We address the problem of parameter identifiability of the model parameters given the higher-order (third- or fourth-order, for example) cumulants of the 2D signal on a finite set of lags. The signal observations may be noisy. A key result is the parameter identifiability of 2D MA models. Using the MA parameter identifiability results, the parameter identifiability of AR and ARMA models follows immediately via a novel approach.<<ETX>>","PeriodicalId":266447,"journal":{"name":"Proceedings of 27th Asilomar Conference on Signals, Systems and Computers","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125237913","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}
Pub Date : 1993-11-01DOI: 10.1109/ACSSC.1993.342465
Y. C. Pati, R. Rezaiifar, P. Krishnaprasad
We describe a recursive algorithm to compute representations of functions with respect to nonorthogonal and possibly overcomplete dictionaries of elementary building blocks e.g. affine (wavelet) frames. We propose a modification to the matching pursuit algorithm of Mallat and Zhang (1992) that maintains full backward orthogonality of the residual (error) at every step and thereby leads to improved convergence. We refer to this modified algorithm as orthogonal matching pursuit (OMP). It is shown that all additional computation required for the OMP algorithm may be performed recursively.<>
{"title":"Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition","authors":"Y. C. Pati, R. Rezaiifar, P. Krishnaprasad","doi":"10.1109/ACSSC.1993.342465","DOIUrl":"https://doi.org/10.1109/ACSSC.1993.342465","url":null,"abstract":"We describe a recursive algorithm to compute representations of functions with respect to nonorthogonal and possibly overcomplete dictionaries of elementary building blocks e.g. affine (wavelet) frames. We propose a modification to the matching pursuit algorithm of Mallat and Zhang (1992) that maintains full backward orthogonality of the residual (error) at every step and thereby leads to improved convergence. We refer to this modified algorithm as orthogonal matching pursuit (OMP). It is shown that all additional computation required for the OMP algorithm may be performed recursively.<<ETX>>","PeriodicalId":266447,"journal":{"name":"Proceedings of 27th Asilomar Conference on Signals, Systems and Computers","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129274006","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}
Pub Date : 1993-11-01DOI: 10.1109/ACSSC.1993.342589
F. Busaba, P. Lala
This paper introduces new technique for designing self-checking interacting machines for on-line detection of multiple stuck-at faults. The only assumption is that each constituent submachine of a composite submachine can have only one single stuck-at fault. The proposed technique adds checkers at the embedded interfaces between the submachines.<>
{"title":"Design of self-checking interacting FSMs for multiple faults","authors":"F. Busaba, P. Lala","doi":"10.1109/ACSSC.1993.342589","DOIUrl":"https://doi.org/10.1109/ACSSC.1993.342589","url":null,"abstract":"This paper introduces new technique for designing self-checking interacting machines for on-line detection of multiple stuck-at faults. The only assumption is that each constituent submachine of a composite submachine can have only one single stuck-at fault. The proposed technique adds checkers at the embedded interfaces between the submachines.<<ETX>>","PeriodicalId":266447,"journal":{"name":"Proceedings of 27th Asilomar Conference on Signals, Systems and Computers","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130945994","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：