Search Results (13)

The current development of machine learning has advanced many fields in applied sciences and industry, including remote sensing. In this area, deep neural networks are used to solve routine object detection problems, satisfying the required rules and conditions. However, the growing number and difficulty of such problems cause the developers to construct machine learning models with higher computational complexities, such as an increased number of hidden layers, epochs, learning rate, and rate decay. In this paper, we propose the Yolov8 architecture with decomposed layers via canonical polyadic and Tucker methods for accelerating the solving of the object detection problem in satellite images. Our positive–negative momentum approaches enabled a reduction in the loss in precision and recall assessments for the proposed neural network. The convolutional layer factorization reduces the shapes and accelerates the computations at kernel nodes in the proposed deep learning models. The advanced optimization algorithms achieve the global minimum of loss functions, which makes the precision and recall metrics superior to the ones for their known counterparts. We examined the proposed Yolov8 with decomposed layers, comparing it with the conventional Yolov8 on the DIOR and VisDrone 2020 datasets containing the UAV images. We verified the performance of the proposed and known neural networks on different optimizers. It is shown that the proposed neural network accelerates the solving object detection problem by 44–52%. The proposed Yolov8 with Tucker and canonical polyadic decompositions has greater precision and recall metrics than the usual Yolov8 with known analogs by 0.84–0.94 and 0.228–1.107 percentage points, respectively. Full article

Since multi-view learning leverages complementary information from multiple feature sets to improve model performance, a tensor-based data fusion layer for neural networks, called Multi-View Data Tensor Fusion (MV-DTF), is used. It fuses M feature spaces ${\mathcal{X}}_1,\cdots ,{\mathcal{X}}_M$, referred to as views, in a new latent tensor space, $\mathcal{S}$, of order P and dimension $J_1\times \cdots \times J_P$, defined in the space of affine mappings composed of a multilinear map $\mathcal{T}:{\mathcal{X}}_1\times \cdots \times {\mathcal{X}}_M\to \mathcal{S}$—represented as the Einstein product between a $(P+M)$-order tensor $\mathcal{A}$ anda rank-one tensor, $\mathcal{X}={\mathbf{x}}^{(1)}\otimes \cdots \otimes {\mathbf{x}}^{(M)}$, where ${\mathbf{x}}^{(m)}\in {\mathcal{X}}_m$ is the m-th view—and a translation. Unfortunately, as the number of views increases, the number of parameters that determine the MV-DTF layer grows exponentially, and consequently, so does its computational complexity. To address this issue, we enforce low-rank constraints on certain subtensors of tensor $\mathcal{A}$ using canonical polyadic decomposition, from which M other tensors ${\mathcal{U}}^{(1)},\cdots ,{\mathcal{U}}^{(M)}$, called here Hadamard factor tensors, are obtained. We found that the Einstein product $\mathcal{A}{⊛}_M\mathcal{X}$ can be approximated using a sum of R Hadamard products of M Einstein products encoded as ${\mathcal{U}}^{(m)}{⊛}_1{\mathbf{x}}^{(m)}$, where R is related to the decomposition rank of subtensors of $\mathcal{A}$. For this relationship, the lower the rank values, the more computationally efficient the approximation. To the best of our knowledge, this relationship has not previously been reported in the literature. As a case study, we present a multitask model of vehicle traffic surveillance for occlusion detection and vehicle-size classification tasks, with a low-rank MV-DTF layer, achieving up to $92.81\%$ and $95.10\%$ in the normalized weighted Matthews correlation coefficient metric in individual tasks, representing a significant $6\%$ and $7\%$ improvement compared to the single-task single-view models. Full article

The Boltzmann equation with multiple-relaxation-time (MRT) collision operators has been widely employed in kinetic theory to describe the behavior of gases and liquids at the macro-level. Given the successful development of deep learning and the availability of data analytic tools, it is a feasible idea to try to solve the Boltzmann-MRT equation using a neural network-based method. Based on the canonical polyadic decomposition, a new physics-informed neural network describing the Boltzmann-MRT equation, named the network for MRT collision (NMRT), is proposed in this paper for solving the Boltzmann-MRT equation. The method of tensor decomposition in the Boltzmann-MRT equation is utilized to combine the collision matrix with discrete distribution functions within the moment space. Multiscale modeling is adopted to accelerate the convergence of high frequencies for the equations. The micro–macro decomposition method is applied to improve learning efficiency. The problem-dependent loss function is proposed to balance the weight of the function for different conditions at different velocities. These strategies will greatly improve the accuracy of the network. The numerical experiments are tested, including the advection–diffusion problem and the wave propagation problem. The results of the numerical simulation show that the network-based method can obtain a measure of accuracy at $O\left({10}^{-3}\right)$. Full article

We advanced the practical development of compressive hyperspectral cameras for remote sensing scenarios with a design that simultaneously compresses and captures high-quality spectral information of a scene via configurable measurements. We built a prototype imaging system that is compatible with light-modulation devices that encode the incoming spectrum. The sensing approach enables a substantial reduction in the volume of data collected and transmitted, facilitating large-scale remote hyperspectral imaging. A main advantage of our sensing design is that it allows for adaptive sampling. When prior information of a survey region is available or gained, the modulation patterns can be re-programmed to efficiently sample and detect desired endmembers. Given target spectral signatures, we propose an optimization scheme that guides the encoding process. The approach severely reduces the number of required sampling patterns, with the ability to achieve image segmentation and correct distortions. Additionally, to decode the modulated data, we considered a novel reconstruction algorithm suited for large-scale images. The computational methodology leverages the multidimensional structure and redundant representation of hyperspectral images via the canonical polyadic decomposition of multiway arrays. Under realistic remote sensing scenarios, we demonstrated the efficiency of our approach with several data sets collected by our prototype camera and reconstructed by our low-rank tensor decoder. Full article

Spectral computed tomography (CT)-reconstructed images often exhibit severe noise and artifacts, which compromise the practical application of spectral CT imaging technology. Methods that use tensor dictionary learning (TDL) have shown superior performance, but it is difficult to obtain a high-quality pre-trained global tensor dictionary in practice. In order to resolve this problem, this paper develops an algorithm called tensor decomposition with total generalized variation (TGV) for sparse-view spectral CT reconstruction. In the process of constructing tensor volumes, the proposed algorithm utilizes the non-local similarity feature of images to construct fourth-order tensor volumes and uses Canonical Polyadic (CP) tensor decomposition instead of pre-trained tensor dictionaries to further explore the inter-channel correlation of images. Simultaneously, introducing the TGV regularization term to characterize spatial sparsity features, the use of higher-order derivatives can better adapt to different image structures and noise levels. The proposed objective minimization model has been addressed using the split-Bregman algorithm. To assess the performance of the proposed algorithm, several numerical simulations and actual preclinical mice are studied. The final results demonstrate that the proposed algorithm has an enormous improvement in the quality of spectral CT images when compared to several existing competing algorithms. Full article

Modern convolutional neural networks (CNNs) play a crucial role in computer vision applications. The intricacy of the application scenarios and the growing dataset both significantly raise the complexity of CNNs. As a result, they are often overparameterized and have significant computational costs. One potential solution for optimizing and compressing the CNNs is to replace convolutional layers with low-rank tensor decomposition. The most suitable technique for this is Canonical Polyadic (CP) decomposition. However, there are two primary issues with CP decomposition that lead to a significant loss in accuracy. Firstly, the selection of tensor ranks for CP decomposition is an unsolved issue. Secondly, degeneracy and instability are common problems in the CP decomposition of contractional tensors, which makes fine-tuning the compressed model difficult. In this study, a novel approach was proposed for compressing CNNs by using CP decomposition. The first step involves using the sensitivity of convolutional layers to determine the tensor ranks for CP decomposition effectively. Subsequently, to address the degeneracy issue and enhance the stability of the CP decomposition, two novel techniques were incorporated: optimization with sensitivity constraints and iterative fine-tuning based on sensitivity order. Finally, the proposed method was examined on common CNN structures for image classification tasks and demonstrated that it provides stable performance and significantly fewer reductions in classification accuracy. Full article

Modern mobile networks exhibit a complex heterogeneous structure. To enhance the Quality of Service (QoS) in these networks, intelligent control mechanisms should be implemented. These functions are based on the processing of large amounts of data and feature extraction. One such feature is information about user mobility. However, directly determining user mobility remains challenging. To address this issue, this study proposes an approach based on multi-linear data processing. The user mobility is proposed to determine, using the multi-linear data, about the changing of the Signal-to-Interference-plus-Noise-Ratio (SINR). SINR varies individually for each user over time, relative to the network’s base stations. It is natural to represent these data as a tensor. A tensor-based preprocessing step employing Canonical Polyadic Decomposition (CPD) is proposed to extract user mobility information and reduce the data volume. In the next step, using the DBSCAN algorithm, users are clustered according to their mobility patterns. Subsequently, users are clustered based on their mobility patterns using the DBSCAN algorithm. The proposed approach is evaluated utilizing data from Network Simulator 3 (NS-3), which simulates a portion of the mobile network. The results of processing these data using the proposed method demonstrate superior performance in determining user mobility. Full article

Multispectral and hyperspectral image fusion (MHF) aims to reconstruct high-resolution hyperspectral images by fusing spatial and spectral information. Unlike the traditional canonical polyadic decomposition and Tucker decomposition models, the block-term tensor decomposition model is able to improve the quality of fused images using known endmember and abundance information. This paper presents an improved hyperspectral image fusion algorithm. Firstly, the two abundance matrices are combined into a single bulk matrix to promote structural sparsity by introducing the $L_{2,1}$-norm to eliminate the scaling effects present in the model. Secondly, the counter-scaling effect is eliminated by adding the $L_2$-norm to the endmember matrix. Finally, the chunk matrix and the endmember matrix are coupled together, and the matrix is reorganized by adding the $L_{2,1}$-norm to the matrix to facilitate chunk elimination and solved using an extended iterative reweighted least squares (IRLS) method, focusing on the problem of the inability to accurately estimate the tensor rank in the chunk-term tensor decomposition model and the noise/artifact problem arising from overestimation of rank. Experiments are conducted on standard and local datasets, and the fusion results are compared and analyzed in four ways: visual result analysis, metric evaluation, time of the algorithm, and classification results, and the experimental results show that the performance of the proposed method is better than the existing methods. An extensive performance evaluation of the algorithms is performed by conducting experiments on different datasets. The experimental results show that the proposed algorithm achieves significant improvements in terms of reconstruction error, signal-to-noise ratio, and image quality compared with the existing methods. Especially in the case of a low signal-to-noise ratio, the proposed algorithm shows stronger robustness and accuracy. These results show that the proposed algorithm has significant advantages in dealing with multispectral high-resolution hyperspectral data. Full article

The problem of multispectral and hyperspectral image fusion (MHF) is to reconstruct images by fusing the spatial information of multispectral images and the spectral information of hyperspectral images. Focusing on the problem that the hyperspectral canonical polyadic decomposition model and the Tucker model cannot introduce the physical interpretation of the latent factors into the framework, it is difficult to use the known properties and abundance of endmembers to generate high-quality fusion images. This paper proposes a new fusion algorithm. In this paper, a coupled non-negative block-term tensor model is used to estimate the ideal high spatial resolution hyperspectral images, its sparsity is characterized by adding 1-norm, and total variation (TV) is introduced to describe piecewise smoothness. Secondly, the different operators in two directions are defined and introduced to characterize their piecewise smoothness. Finally, the proximal alternating optimization (PAO) algorithm and the alternating multiplier method (ADMM) are used to iteratively solve the model. Experiments on two standard datasets and two local datasets show that the performance of this method is better than the state-of-the-art methods. Full article

In this study, we propose a tensor-based learning model to efficiently detect abnormalities on digital mammograms. Due to the fact that the availability of medical data is limited and often restricted by GDPR (general data protection regulation) compliance, the need for more sophisticated and less data-hungry approaches is urgent. Accordingly, our proposed artificial intelligence framework utilizes the canonical polyadic decomposition to decrease the trainable parameters of the wrapped Rank-R FNN model, leading to efficient learning using small amounts of data. Our model was evaluated on the open source digital mammographic database INBreast and compared with state-of-the-art models in this domain. The experimental results show that the proposed solution performs well in comparison with the other deep learning models, such as AlexNet and SqueezeNet, achieving 90% ± 4% accuracy and an F1 score of 84% ± 5%. Additionally, our framework tends to attain more robust performance with small numbers of data and is computationally lighter for inference purposes, due to the small number of trainable parameters. Full article

Evaluating the performance of Bayesian classification in a high-dimensional random tensor is a fundamental problem, usually difficult and under-studied. In this work, we consider two Signal to Noise Ratio (SNR)-based binary classification problems of interest. Under the alternative hypothesis, i.e., for a non-zero SNR, the observed signals are either a noisy rank-R tensor admitting a Q-order Canonical Polyadic Decomposition (CPD) with large factors of size $N_q\times R$ , i.e., for $1\le q\le Q$ , where $R,N_q\to \infty$ with $R^{1/q}/N_q$ converge towards a finite constant or a noisy tensor admitting TucKer Decomposition (TKD) of multilinear $(M_1,\dots ,M_Q)$ -rank with large factors of size $N_q\times M_q$ , i.e., for $1\le q\le Q$ , where $N_q,M_q\to \infty$ with $M_q/N_q$ converge towards a finite constant. The classification of the random entries (coefficients) of the core tensor in the CPD/TKD is hard to study since the exact derivation of the minimal Bayes’ error probability is mathematically intractable. To circumvent this difficulty, the Chernoff Upper Bound (CUB) for larger SNR and the Fisher information at low SNR are derived and studied, based on information geometry theory. The tightest CUB is reached for the value minimizing the error exponent, denoted by $s^{\star }$ . In general, due to the asymmetry of the s-divergence, the Bhattacharyya Upper Bound (BUB) (that is, the Chernoff Information calculated at $s^{\star }=1/2$ ) cannot solve this problem effectively. As a consequence, we rely on a costly numerical optimization strategy to find $s^{\star }$ . However, thanks to powerful random matrix theory tools, a simple analytical expression of $s^{\star }$ is provided with respect to the Signal to Noise Ratio (SNR) in the two schemes considered. This work shows that the BUB is the tightest bound at low SNRs. However, for higher SNRs, the latest property is no longer true. Full article

Gears are key components in rotation machinery and its fault vibration signals usually show strong nonlinear and non-stationary characteristics. It is not easy for classical time–frequency domain analysis methods to recognize different gear working conditions. Therefore, this paper presents a joint fault diagnosis scheme for gear fault classification via tensor nuclear norm canonical polyadic decomposition (TNNCPD) and multi-scale permutation entropy (MSPE). Firstly, the one-dimensional vibration data of different gear fault conditions is converted into a three-dimensional tensor data, and a new tensor canonical polyadic decomposition method based on nuclear norm and convex optimization called TNNCPD is proposed to extract the low rank component of the data, which represents the feature information of the measured signal. Then, the MSPE of the extracted feature information about different gear faults can be calculated as the feature vector in order to recognize fault conditions. Finally, this researched scheme is validated by practical gear vibration data of different fault conditions. The result demonstrates that the proposed scheme can effectively recognize different gear fault conditions. Full article

This paper investigates a two-dimensional angle of arrival (2D AOA) estimation algorithm for the electromagnetic vector sensor (EMVS) array based on Type-2 block component decomposition (BCD) tensor modeling. Such a tensor decomposition method can take full advantage of the multidimensional structural information of electromagnetic signals to accomplish blind estimation for array parameters with higher resolution. However, existing tensor decomposition methods encounter many restrictions in applications of the EMVS array, such as the strict requirement for uniqueness conditions of decomposition, the inability to handle partially-polarized signals, etc. To solve these problems, this paper investigates tensor modeling for partially-polarized signals of an L-shaped EMVS array. The 2D AOA estimation algorithm based on rank- $(L_1,L_2,·)$ BCD is developed, and the uniqueness condition of decomposition is analyzed. By means of the estimated steering matrix, the proposed algorithm can automatically achieve angle pair-matching. Numerical experiments demonstrate that the present algorithm has the advantages of both accuracy and robustness of parameter estimation. Even under the conditions of lower SNR, small angular separation and limited snapshots, the proposed algorithm still possesses better performance than subspace methods and the canonical polyadic decomposition (CPD) method. Full article