{"title":"Identification of kronecker-structured dictionaries: An asymptotic analysis","authors":"Z. Shakeri, A. Sarwate, W. Bajwa","doi":"10.1109/CAMSAP.2017.8313163","DOIUrl":"https://doi.org/10.1109/CAMSAP.2017.8313163","url":null,"abstract":"The focus of this work is on derivation of conditions for asymptotic recovery of Kronecker-structured dictionaries underlying second-order tensor data. Given second-order tensor observations (equivalently, matrix-valued data samples) that are generated using a Kronecker-structured dictionary and sparse coefficient tensors, conditions on the dictionary and coefficient distribution are derived that enable asymptotic recovery of the individual coordinate dictionaries comprising the Kronecker dictionary within a local neighborhood of the true model. These conditions constitute the first step towards understanding the sample complexity of Kronecker-structured dictionary learning for second- and higher-order tensor data.","PeriodicalId":315977,"journal":{"name":"2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131085768","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":"Boolean approximation of a phase-coded aperture diffraction pattern system for X-ray crystallography","authors":"Samuel Pinilla, Tatiana Gelvez, H. Arguello","doi":"10.1109/CAMSAP.2017.8313144","DOIUrl":"https://doi.org/10.1109/CAMSAP.2017.8313144","url":null,"abstract":"The phase retrieval problem involves recovering the phase of a signal from the amplitude of its Fourier transform. Recently, a phase recovery approach for a coded aperture-based acquisition system was proposed. The modulation is realized before the signal being diffracted, such that the underlying signal is recovered from coded diffraction patterns. Moreover, the modulation effect before diffraction can be obtained by using a phase coded aperture located after the sample under study. However, the practical implementation of a phase coded aperture in an X-ray application is not feasible, since it results in a matrix with complex entries and it requires changing the phase of the diffracted beams. Hence, this paper describes a coded X-ray diffraction pattern system based on block-unblock (Boolean) coded apertures that, unlike the phase coded apertures are easily implementable. The proposed system approximates the phase coded aperture by a block-unblock coded aperture by using the detour-phase method. This work used the SAXS/WAXS X-ray crystallography software to simulate the diffraction patterns of a real crystal structure called Rhombic Dodecahedron. Several simulations were realized to obtain the performance of some Boolean approximations in recovering the phase using the simulated diffraction pattern images. The quality of the reconstructions attain up to 22dB in terms of the Peak-Signal-to-Noise-Ratio.","PeriodicalId":315977,"journal":{"name":"2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123425352","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":"Unsupervised restoration of subsampled images constructed from geometric and binomial data","authors":"Y. Altmann, S. Mclaughlin, M. Padgett","doi":"10.1109/CAMSAP.2017.8313187","DOIUrl":"https://doi.org/10.1109/CAMSAP.2017.8313187","url":null,"abstract":"In this paper, we investigate a new imaging denoising algorithm for single-photon applications where the classical Poisson noise assumption does not hold. Precisely, we consider two different acquisition scenarios where the unknown intensity profile is to be recovered from subsampled measurements following binomial or geometric distributions, whose parameters are nonlinearly related to the intensities of interest. Adopting a Bayesian approach, a flexible prior model is assigned to the unknown intensity field and an adaptive Markov chain Monte Carlo methods is used to perform Bayesian inference. In particular, it allows us to automatically adjust the amount of regularisation required for satisfactory image inpainting/restoration. The performance of the proposed model/method is assessed quantitatively through a series of experiments conducted with controlled data and the results obtained are very promising for future analysis of multidimensional single-photon images.","PeriodicalId":315977,"journal":{"name":"2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122941578","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 classify-while-track approach using dynamical tensors","authors":"F. Govaers","doi":"10.1109/CAMSAP.2017.8313221","DOIUrl":"https://doi.org/10.1109/CAMSAP.2017.8313221","url":null,"abstract":"Since a lot of nuclear material (e.g. from hospitals or power plants) is out of the control of the authorities, chances are high that terrorist groups will be able to own such material and mix it with explosives in a “dirty bomb” to intensify the scaring effect of an attack. In this paper, a fusion framework based on a tensor with dynamic changing dimensions is presented to solve the association problem of a nuclear source in an open space scenario. Since the decay process of a nuclear source is a random process itself, a likelihood is derived to integrate the distances of all persons to the sensors, the Poisson nature of such a decay, and additive white white noise in the sensing process. As a closed form solution is intractable in general, a Poisson approximation and the saddle point method is proposed. The approach is evaluated in an experimental setup using different scenarios which are motivated from typical situations in a railway station.","PeriodicalId":315977,"journal":{"name":"2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124681587","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 sensor selection with application to time varying graphs","authors":"Buddhika L. Samarakoon, M. Murthi, K. Premaratne","doi":"10.1109/CAMSAP.2017.8313073","DOIUrl":"https://doi.org/10.1109/CAMSAP.2017.8313073","url":null,"abstract":"This paper addresses the problem of efficiently selecting sensors such that the mean squared estimation error is minimized under jointly Gaussian assumptions. First, we propose an O(n3) algorithm that yields the same set of sensors as a previously published near mean squared error (MSE) optimal method that runs in O(n4). Then we show that this approach can be extended to efficient sensor selection in a time varying graph. We consider a rank one modification to the graph Laplacian, which captures the cases where a new edge is added or deleted, or an edge weight is changed, for a fixed set of vertices. We show that we can efficiently update the new set of sensors in O(n2) time for the best case by saving computations that were done for the original graph. Experiments demonstrate advantages in computational time and MSE accuracy in the proposed methods compared to recently developed graph sampling methods.","PeriodicalId":315977,"journal":{"name":"2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126289676","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":"Coded aperture design for super-resolution compressive X-ray tomography","authors":"Edson Mojica, Said Pertuz, H. Arguello","doi":"10.1109/CAMSAP.2017.8313126","DOIUrl":"https://doi.org/10.1109/CAMSAP.2017.8313126","url":null,"abstract":"Computed tomography obtains the inner structure of an object. However, obtaining an accurate image reconstruction while keeping a low radiation dose is a challenging problem. For this purpose, compressed sensing has been studied to reduce the number of measurements required. In this work, we present an algorithm for the design of high-resolution coded apertures for compressed sensing computed tomography. The aim is to combine high-resolution apertures with low-resolution detectors in order to achieve super-resolution. To design the coded apertures, the proposed method iteratively improves random coded apertures using a gradient descending algorithm subject to constraints on the homogeneity induced by the coded aperture of the compressive sensing process. Computational experiments using synthetic data show a significant improvement in the quality of CT image reconstructions achieved with the designed coded apertures over the random coded apertures up to 3dB in terms of PSNR. Further simulations are performed with different transmittances and shots to assess the robustness of the proposed approach.","PeriodicalId":315977,"journal":{"name":"2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114545596","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}
Khaled Ardah, Y. Silva, W. Freitas, F. Cavalcanti, Gábor Fodor
{"title":"An ADMM approach to distributed coordinated beamforming in dynamic TDD networks","authors":"Khaled Ardah, Y. Silva, W. Freitas, F. Cavalcanti, Gábor Fodor","doi":"10.1109/CAMSAP.2017.8313195","DOIUrl":"https://doi.org/10.1109/CAMSAP.2017.8313195","url":null,"abstract":"We consider a dynamic time division duplexing wireless network and propose a distributed coordinated beamforming algorithm based on Alternating Direction Method of Multipliers (ADMM) technique assuming the availability of perfect channel state information. Our design objective is to minimize the sum transmit power at the base stations subject to minimum signal-to-interference-plus-noise ratio (SINR) constraints for downlink mobile stations and a maximum interference power threshold for uplink mobile stations. First, we propose a centralized algorithm based on the relaxed Semidefinite Programming (SDP) technique. To obtain the beamforming solution in a distributed way, we further propose a distributed coordinated beamforming algorithm using the ADMM technique. Detailed simulation results are presented to examine the effectiveness of the proposed algorithms. It is shown that the proposed algorithm achieves better performance in terms of the design objective and converges faster than the reference algorithm based on primal decomposition.","PeriodicalId":315977,"journal":{"name":"2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129078554","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":"Structure-Exploiting variational inference for recurrent switching linear dynamical systems","authors":"Scott W. Linderman, Matthew J. Johnson","doi":"10.1109/CAMSAP.2017.8313132","DOIUrl":"https://doi.org/10.1109/CAMSAP.2017.8313132","url":null,"abstract":"Many natural systems, such as neurons firing in the brain or basketball teams traversing a court, give rise to time series data with complex, nonlinear dynamics. We can gain insight into these systems by decomposing the data into segments that are each explained by simpler dynamic units. This is the motivation underlying the class of recurrent switching linear dynamical systems (rSLDS) [1], which build on the standard SLDS by introducing a model of how discrete transition probabilities depend on observations or continuous latent states. Previous work relied on Markov chain Monte Carlo algorithms and augmentation schemes for inference, but these methods only applied to a limited class of recurrent dependencies. Here we relax these constraints and consider recurrent dependencies specified by arbitrary parametric, nonlinear functions. We derive two structure-exploiting variational inference algorithms for these challenging models. Both leverage the conditionally linear Gaussian and Markovian nature of the models to perform efficient posterior inference.","PeriodicalId":315977,"journal":{"name":"2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125653868","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}
A. R. Braga, C. Fritsche, F. Gustafsson, Marcelo G. S. Bruno
{"title":"Rapid system identification for jump Markov non-linear systems","authors":"A. R. Braga, C. Fritsche, F. Gustafsson, Marcelo G. S. Bruno","doi":"10.1109/CAMSAP.2017.8313089","DOIUrl":"https://doi.org/10.1109/CAMSAP.2017.8313089","url":null,"abstract":"This work evaluates a previously introduced algorithm called Particle-Based Rapid Incremental Smoother within the framework of state inference and parameter identification in Jump Markov Non-Linear System. It is applied to the recursive form of two well-known Maximum Likelihood based algorithms who face the common challenge of online computation of smoothed additive functionals in order to accomplish the task of model parameter estimation. This work extends our previous contributions on identification of Markovian switching systems with the goal to reduce the computational complexity. A benchmark problem is used to illustrate the results.","PeriodicalId":315977,"journal":{"name":"2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117352724","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":"Performance analysis of ESPRIT-Type algorithms for co-array structures","authors":"Jens Steinwandt, F. Roemer, M. Haardt","doi":"10.1109/CAMSAP.2017.8313207","DOIUrl":"https://doi.org/10.1109/CAMSAP.2017.8313207","url":null,"abstract":"In the recent field of co-array signal processing, sparse linear arrays are processed to form a virtual uniform linear array (ULA), termed co-array, that allows to resolve more sources than physical sensors. The extra degrees of freedom (DOFs) are leveraged by the assumption that the signals are uncorrelated, which requires a large sample size. In this paper, we first review the Standard ESPRIT and Unitary ESPRIT algorithms for co-array processing. Secondly, we propose a performance analysis for both methods, which is asymptotic in the effective signal-to-noise ratio (SNR), i.e., the results become exact for either high SNRs or a large sample size. Based on the derived analytical expressions, we study the effects of a small sample size such as the residual sample signal correlation and the sample noise contribution on the estimation accuracy of the proposed algorithms. Simulation results verify the derived analytical expressions.","PeriodicalId":315977,"journal":{"name":"2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","volume":"7 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127988538","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}