{"title":"Regularized successive interference cancellation (SIC) under mismatched modeling","authors":"Jun Tong, Li Li, Qinghua Guo, P. Schreier, J. Xi","doi":"10.1109/SSP.2014.6884642","DOIUrl":"https://doi.org/10.1109/SSP.2014.6884642","url":null,"abstract":"Successive interference cancellation (SIC) has been extensively applied to estimate transmit signals in communication systems. When the channel state information (CSI) and noise statistics are imperfectly estimated, the standard SIC estimators that ignore the model mismatch may perform poorly. This paper introduces regularized SIC estimation to provide robustness against the model mismatch. Suboptimal, low-complexity implementations using (sorted) QR decomposition and approximate choice of regularization parameters are also introduced. Simulation examples demonstrate that the regularized SIC estimators can significantly outperform the standard version.","PeriodicalId":188962,"journal":{"name":"2014 IEEE Workshop on Statistical Signal Processing (SSP)","volume":"289 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123171038","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":"Robust bootstrap based observation classification for Kalman Filtering in harsh LOS/NLOS environments","authors":"Stefan Vlaski, A. Zoubir","doi":"10.1109/SSP.2014.6884643","DOIUrl":"https://doi.org/10.1109/SSP.2014.6884643","url":null,"abstract":"The bootstrap allows for the estimation of the distribution of an estimate without requiring assumptions on the distribution of the underlying data, relying on asymptotic results or theoretical derivations. In contrast to a point estimate, the distribution estimate captures the uncertainty about the statistic of interest. We introduce a novel robust bootstrap method and demonstrate how this additional information is utilized to improve the performance of robust tracking methods. A robust bootstrap method is crucial, because the classical bootstrap is highly sensitive to outliers, irrespective of the robustness of the underlying estimator. Using the robust distribution estimate of the state prediction as a measure of confidence, the bootstrap allows to incorporate an observation weighting scheme into the tracking algorithm, which enhances performance.","PeriodicalId":188962,"journal":{"name":"2014 IEEE Workshop on Statistical Signal Processing (SSP)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124207805","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 Normalised Bayesian smoothers for signals modelled by non-causal compositions of reciprocal chains","authors":"L. White, F. Carravetta","doi":"10.1109/SSP.2014.6884611","DOIUrl":"https://doi.org/10.1109/SSP.2014.6884611","url":null,"abstract":"The present work is a sequel of our paper [1] where a Bayesian unnormalised smoother was proposed for the so-called class of partially observed reciprocal chains (RC). Within this Bayesian setting, an issue remained unsolved concerning practical implementation due to the unnormalised feature of the smoother. Here a normalised Bayesian smoother is developed for a class of signals even more general than RCs, termed Generalised Reciprocal Chains (GRC) which are relevant from an application point of view. A simple numerical example involving target tracking in one dimension is presented which illustrates that a potential benefit of the new models and associated optimal smoothers can be obtained, albeit with increased computational cost. More work is needed to ascertain classes of problems where the new models yield significant benefit.","PeriodicalId":188962,"journal":{"name":"2014 IEEE Workshop on Statistical Signal Processing (SSP)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114624353","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":"EM algorithm for estimating poisson measurement noise","authors":"G. Einicke","doi":"10.1109/SSP.2014.6884572","DOIUrl":"https://doi.org/10.1109/SSP.2014.6884572","url":null,"abstract":"In the standard minimum-variance filter recursions it is routinely assumed that the noises are zero-mean and white. In image restoration applications, the data can be contaminated with (nonzero-mean) Poisson noise. This paper introduces the minimum-variance filter for the case where the measurement noise includes a Poisson-distributed component. An EM algorithm for estimating the Poisson noise intensity is described. Conditions for the convergence of the algorithms are also investigated. An image restoration example is presented which demonstrates the efficacy of the described method.","PeriodicalId":188962,"journal":{"name":"2014 IEEE Workshop on Statistical Signal Processing (SSP)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121713679","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. Davey, H. Vu, S. Arulampalam, F. Fletcher, C. Lim
{"title":"Clutter mapping for Histogram PMHT","authors":"S. Davey, H. Vu, S. Arulampalam, F. Fletcher, C. Lim","doi":"10.1109/SSP.2014.6884598","DOIUrl":"https://doi.org/10.1109/SSP.2014.6884598","url":null,"abstract":"The Histogram PMHT is a parametric track-before-detect method that has good detection performance and low computation complexity. However, the method assumes a known clutter distribution. This paper introduces a method for learning a non-uniform clutter map where the map is represented as a mixture of parameterised components. The modified Histogram PMHT is compared with the uniform clutter model using airborne imagery.","PeriodicalId":188962,"journal":{"name":"2014 IEEE Workshop on Statistical Signal Processing (SSP)","volume":"772 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125747980","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":"Sampling from a multivariate Gaussian distribution truncated on a simplex: A review","authors":"Y. Altmann, S. Mclaughlin, N. Dobigeon","doi":"10.1109/SSP.2014.6884588","DOIUrl":"https://doi.org/10.1109/SSP.2014.6884588","url":null,"abstract":"In many Bayesian models, the posterior distribution of interest is a multivariate Gaussian distribution restricted to a specific domain. In particular, when the unknown parameters to be estimated can be considered as proportions or probabilities, they must satisfy positivity and sum-to-one constraints. This paper reviews recent Monte Carlo methods for sampling from multivariate Gaussian distributions restricted to the standard simplex. First, a classical Gibbs sampler is presented. Then, two Hamiltonian Monte Carlo methods are described and analyzed. In a similar fashion to the Gibbs sampler, the first method has a acceptance rate equal to one whereas the second requires an accept/reject procedure. The performance of the three methods are compared through the use of a few examples.","PeriodicalId":188962,"journal":{"name":"2014 IEEE Workshop on Statistical Signal Processing (SSP)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134030645","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 greedy, adaptive approach to learning geometry of nonlinear manifolds","authors":"Talal Ahmed, W. Bajwa","doi":"10.1109/SSP.2014.6884593","DOIUrl":"https://doi.org/10.1109/SSP.2014.6884593","url":null,"abstract":"In this paper, we address the problem of learning the geometry of a non-linear manifold in the ambient Euclidean space into which the manifold is embedded. We propose a bottom-up approach to manifold approximation using tangent planes where the number of planes is adaptive to manifold curvature. Also, we exploit the local linearity of the manifold to subsample the manifold data before using it to learn the manifold geometry with negligible loss of approximation accuracy. In our experiments, our proposed Geometry Preserving Union-of-Affine Subspaces algorithm shows more than a 100-times decrease in the learning time when compared to state-of-the-art manifold learning algorithm, while achieving similar approximation accuracy.","PeriodicalId":188962,"journal":{"name":"2014 IEEE Workshop on Statistical Signal Processing (SSP)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126581354","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":"Simultaneous channel estimation and joint time-frequency domain crosstalk cancellation in multichannel personal audio systems","authors":"H. Tataria, Paul D. Teal, M. Poletti, T. Betlehem","doi":"10.1109/SSP.2014.6884682","DOIUrl":"https://doi.org/10.1109/SSP.2014.6884682","url":null,"abstract":"In this paper, we present two important contributions. The first is demonstration of the use of subliminal levels of pseudo-random noise to enhance channel estimation, and the second is a joint time and frequency domain algorithm for multichannel inversion. An adaptive system is presented where the acoustic channel is accurately estimated and utilized. In this implementation, maximum length sequences in the form of pseudo-random noise are superimposed on the source signals to aid the estimation quality of the acoustic channels. Upon estimation, crosstalk cancellation filters are designed using a time and frequency domain technique which uses a window to achieve more efficient and effective cancellation of crosstalk. For a 3×2 crosstalk system, the presented results show the improvement in channel estimation quality when low levels of maximum length sequences are superimposed on the source signals. On average -25dB of crosstalk cancellation is achieved.","PeriodicalId":188962,"journal":{"name":"2014 IEEE Workshop on Statistical Signal Processing (SSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124326188","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":"On the CRB for frequency estimation of superimposed multidimensional sinusoids","authors":"N. Letzepis","doi":"10.1109/SSP.2014.6884584","DOIUrl":"https://doi.org/10.1109/SSP.2014.6884584","url":null,"abstract":"The Cramér-Rao bound (CRB) is derived for frequency estimation of the superposition of multidimensional complex sinusoids assuming the complex gains are known. The Fisher information matrix is derived in terms of the Dirichlet kernel, a kernel well-known for its use in Fourier series. In general, it is shown that the frequency estimation error variance for a particular sinusoid can be lower bounded by its isolated (single) multidimensional sinusoid CRB times a scaling factor that is dependent on its frequency separation from each sinusoid.","PeriodicalId":188962,"journal":{"name":"2014 IEEE Workshop on Statistical Signal Processing (SSP)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124534361","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":"On the perturbation of localization networks using received signal strength","authors":"Lauren M. Huie, M. Fowler","doi":"10.1109/SSP.2014.6884581","DOIUrl":"https://doi.org/10.1109/SSP.2014.6884581","url":null,"abstract":"This paper considers the problem of source localization under received signal strength in the presence of an intelligent adversary. The adversary's goal is to redirect the location estimate to a specified location away from its true value by slightly perturbing each of the sensors' position measurements. This work takes the viewpoint of the adversary and determines the false positioning information to be injected using a semidefinite programming approach. Varying levels of control are considered where a penalty is imposed for corrupting certain sensors in the network. It is shown that the adversary can successfully achieve the desired redirection of the network's location estimate.","PeriodicalId":188962,"journal":{"name":"2014 IEEE Workshop on Statistical Signal Processing (SSP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125816158","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}