Showing papers on "Multidimensional signal processing published in 2021"

Recognition of motion patterns using accelerometers for ataxic gait assessment

Abstract: The recognition of motion patterns belongs to very important research areas related to neurology, rehabilitation, and robotics It is based on modern sensor technologies and general mathematical methods, multidimensional signal processing, and machine learning The present paper is devoted to the detection of features associated with accelerometric data acquired by 31 time-synchronized sensors located at different parts of the body Experimental data sets were acquired from 25 individuals diagnosed as healthy controls and ataxic patients The proposed method includes the application of the discrete Fourier transform for the estimation of the mean power in selected frequency bands and the use of these features for data segments classification The study includes a comparison of results obtained from signals recorded at different positions Evaluations are based on classification accuracy and cross-validation errors estimated by support vector machine, Bayesian, nearest neighbours (k-NN], and neural network (NN) methods Results show that highest accuracies of 771%, 789%, 899%, 980%, and 985% were achieved by NN method for signals acquired from the sensors on the feet, legs, uplegs, shoulders, and head/spine, respectively, recorded in 201 signal segments The entire study is based on observations in the clinical environment and suggests the importance of augmented reality to decisions and diagnosis in neurology

Truncated tensor-based Bayesian recovery for multidimensional compressive sensing

Abstract: Bayesian methods are widely used to recover sparse signals from their incomplete measurements with Gaussian white noise. However, while recovering multidimensional signals, these methods are limited by their considerable computational complexities. To address this problem, we develop the truncated Bayesian recovery algorithm for compressive sensing (CS) of multidimensional signals, such as hyperspectral remote sensing images. For each dimension of multidimensional sparse signal, the entries are modeled by the type-II Laplacian prior, such that the support is indicated by the largest variance hyperparameters. The entries of noise tensor are assumed to be independent and Gaussian with zero mean. We approximately estimate the hyperparameters using the maximum a posteriori (MAP) process to determine the supports for each dimension. Based on the supports, the recovered sparse signal is obtained through the tensor-based least square strategy. The required number of iterative cycles can be significantly reduced, compared with conventional method that iterates the MAP process until convergence. Experimental results on synthetic data, hyperspectral images, and hyperspectral remote sensing images demonstrate that the proposed algorithm can obviously speed up multidimensional Bayesian CS recovery.

Dictionary-Based Tensor-Train Sparse Coding

Abstract: Multidimensional signal processing is receiving a lot of interest recently due to the wide spread appearance of multidimensional signals in different applications of data science. Many of these fields rely on prior knowledge of particular properties, such as sparsity for instance, in order to enhance the performance and the efficiency of the estimation algorithms. However, these multidimensional signals are, often, structured into high-order tensors, where the computational complexity and storage requirements become an issue for growing tensor orders. In this paper, we present a sparse-based Joint dImensionality Reduction And Factors rEtrieval (JIRAFE). More specifically, we assume that an arbitrary factor admits a decomposition into a redundant dictionary coded as a sparse matrix, called the sparse coding matrix. The goal is to estimate the sparse coding matrix in the Tensor-Train model framework.

GPU Accelerated SL0 for Multidimensional Signals

Abstract: In this paper, we propose a novel GPU-based method for highly parallel compressed sensing of n-dimensional (nD) signals based on the smoothed (SL0) algorithm. We demonstrate the efficiency of our approach by showing several examples of nD tensor reconstructions. Moreover, we also consider the traditional 1D compressed sensing, and compare the results. We show that the multidimensional SL0 algorithm is computationally superior compared to the 1D variant due to the small dictionary sizes per dimension. This allows us to fully utilize the GPU and perform massive batch-wise computations, which is not possible for the 1D compressed sensing using SL0. For our evaluations, we use light field and light field video data sets. We show that we gain more than an order of magnitude speedup for both one-dimensional as well as multidimensional data points compared to a parallel CPU implementation. Finally, we present a theoretical analysis of the SL0 algorithm for nD signals, which generalizes previous work for 1D signals.

A New Passage to the Reciprocity Attributes of Multidimensional IFT Through Those of the Multidimensional IHT

Abstract: This paper nonce a volitional path to the Reciprocity Attributes of the Multidimensional Complex Fourier Transform (IFT) or the Infiite Fourier Transform (IFT) finis the Multidimensional Infinite Hartley Transform (IHT). The provenances for the reciprocity attributes of multidimensional IFT are conferred out of the reciprocity attributes of the multidimensional IHT, and this is doable mainly due to the mathematical liaison betwixt the IFT and the IHT. Apres the IHT is a real transform, it is viable to deduce the reciprocity attributes for IFT throughout the whilom in multidimensions. It is quotidian run-through in signal processing and communication engineering to chance upon signals having the same fettle in the temporal- and frequency-bailiwicks, such as the Gaussian function. In such paradigms, the reciprocity attributes can be blisteringly wont for working out the onward and rearward transforms of the signals under query. In multidimensional signal processing where the outgo of perpertration is of superemeinent momentousness and the IFT is the exemplar, and where the reciprocity attributes of the IFT are to be wont, it is propounded to execute these reciprocity attributes of the IFT by using the reciprocity attributes of the IHT which have been philosophized in this paper. This props up in the penny-pinching of the utraexpensive reckoning time and disbursement by moiety of one-c as it is a well-established fact that real transforms take less time for execution than those the complex transforms. Thus, the reciprocity attributes unfolded in this paper can be used in digital video processing and in the solutions of differential equations and integral equations.