Search Results (86)

This paper introduces efficient randomized fixed-precision and single-pass algorithms for low-tubal-rank approximation of third-order tensors. The proposed fixed-precision algorithms are faster and more efficient than the existing algorithms for approximating the truncated tensor SVD (T-SVD). Furthermore, unlike existing single-pass methods, which directly extend early, unstable matrix algorithms, the proposed approach adapts enhanced and stabilized matrix techniques to the tensor setting. Through extensive numerical experiments, we identify a critical flaw in current single-pass algorithms: using sketching parameters of equal size often produces ill-conditioned tensor least-squares problems, leading to inaccurate approximations. The proposed algorithms are demonstrably robust to this issue, achieving superior performance under identical conditions. We also evaluate the robustness of existing single-pass methods on real-world data tensors, including images and videos, a topic that has not been thoroughly examined before. Numerical results confirm the effectiveness of the proposed methods. Three applications are presented: image compression, video super-resolution, and deep learning. Full article

Background/Objectives: Mandibular kinematics are increasingly central to the construction of the digital dental avatar, and can be recorded with two categories of devices: dedicated jaw motion analysers and intraoral scanners with motion-tracking modules. Few studies have compared these categories on the same patients. This pilot study compared the Zebris JMA and Medit i700 in a paired-cohort design, using an open-source Blender-based framework developed for the uniform analysis of their XML exports. Methods: A prospective, observational, paired-cohort study was conducted on 17 adults recorded with both systems by a single operator. A custom Python 3.11 add-on for Blender 4.5 LTS and Blender4Dental 1.1.99, developed within the study, supported the analytical workflow. A common anatomical origin between the two systems was first validated by comparing the occlusal contact area at MIP. At each threshold, the two systems were then compared on the directional decomposition (X, Y, Z components) of the mandibular displacement along the anatomical axes. Agreement was evaluated using paired t-tests or Wilcoxon signed-rank tests, Bland–Altman analysis, Pearson or Spearman correlation coefficients, and the intraclass correlation coefficient. Results: Validation at maximum intercuspation showed near-perfect agreement between the two workflows (Pearson r = 0.997; ICC(2,1) = 0.997). During protrusion, the dominant displacement component shifted to the anteroposterior axis. SVD residuals were smaller for Medit (~0.003–0.004 mm) than for Zebris (~0.024–0.046 mm; p < 0.001), but were interpreted only as internal rigid-body fitting residuals rather than accuracy metrics. Conclusions: Zebris JMA and Medit i700 yielded similar scalar displacement values under the threshold-based frame-selection procedure, but showed systematic differences in directional decomposition. Full article

Background: Retail product recognition is difficult in practice because products often look similar, class distributions are unbalanced, and annotations usually contain only one observed product label, even though products belong to broader category structures. This study addresses this setting as classification under incomplete supervision rather than as a fully annotated multi-label problem. Methods: We evaluate a lightweight hierarchy-aware recognition framework on a laboratory-based retail dataset containing real supermarket products. Visual features are extracted with a pretrained ResNet-50, reduced by truncated singular value decomposition (TSVD), and classified using class-conditional kernel density estimation (KDE). A coarse-to-fine refinement step first assigns each sample to one of seven product groups and then applies a group-specific classifier. Results: The hierarchical TSVD-KDE model achieved 83.7% Top-1 accuracy, 95.8% Top-5 accuracy, and 71.8% macro-averaged F1-score, improving over the flat TSVD-KDE variant and the convolutional neural network (CNN) linear baseline. For rare classes, the model reached 62.4% Top-1 accuracy while maintaining an average inference time of 6.1 ms per sample. Conclusions: The results suggest that combining compact visual representations with probabilistic classification and a simple product hierarchy can improve balanced recognition performance without relying on a large end-to-end architecture. Full article

In this research, surface Au concentration measurements are considered as a spatially correlated geochemical field associated with deep occurrences of disturbing masses using real geological exploration data from the Novo-Khairuzovsky gold deposit in East Kazakhstan. The approach is based on the relationship between potential-field continuation problems and reconstruction of subsurface geological anomalies from surface observations. The considered approaches include Tikhonov and Lavrentiev regularization, SVD, and TSVD. Special attention is given to regularization parameter selection using the L-curve method, Morozov discrepancy principle, and GCV. Comparative computational analysis is performed to evaluate the accuracy, stability, and efficiency of these methods in solving first-kind Fredholm integral equations. Results are assessed using error metrics and spatial visualization of reconstructed fields within a Geographic Information System (ArcGIS), enabling consistent geospatial interpretation. Results show that Lavrentiev regularization with L-curve criterion provides the most stable and reliable reconstruction across all depths, achieving high correlations ($R=0.8876$ at 100 m and $R=0.8049$ at 200 m) with low reconstruction errors. Tikhonov regularization performs acceptably at 100 m but becomes less stable at greater depths. Among spectral methods, TSVD improves stability compared with classical SVD, while standard SVD shows weak correlations and larger reconstruction errors due to high noise sensitivity. Full article

This paper develops a robust numerical scheme based on a frame collocation method for solving multi-term fractional ordinary differential equations (FODEs) whose solutions exhibit multiple singularities at the origin. To adaptively capture the singular behavior, we construct a hybrid basis-function frame by combining shifted fractional Legendre polynomials. An efficient computational formula for the Caputo fractional derivative is derived, which transforms the original problem into a nonlinear algebraic system at the collocation points. Due to the over-completeness of the fractional polynomial frame, the resulting linear system becomes rank-deficient, with only a small subset of singular components carrying meaningful solution information. To eliminate the adverse effects of numerical null-space components, we employ truncated singular value decomposition (TSVD) regularization, thereby enabling stable and high-precision solutions. Extensive numerical experiments on several benchmark problems, including the fractional Bagley–Torvik equation, linear multi-term FODEs, and nonlinear cases, demonstrate that the proposed method achieves exponential convergence rates. Notably, when the singular exponent of the solution matches a tunable parameter ($\delta$) in the basis functions, superconvergence is observed, significantly outperforming standard spectral methods. Compared with traditional spectral approaches, the proposed frame collocation framework retains spectral accuracy while exhibiting superior capability in handling complex singular structures, providing a powerful and reliable tool for high-precision simulations of multi-term fractional differential equations. Full article

In this review, we examine the occurrence of two independent, single recombination events which occurred between human enteroviruses (Picornaviridae, Enterovirus, Enterovirus betacoxsackie). These recombination events contributed to the emergence of two viruses which adapted to pigs. These viruses have caused epizootics of swine vesicular disease (SVD) for many years. As was shown previously, the classical SVD virus (SVDV-1) originated from human coxsackievirus B5. The strain T75 (SVDV-2) emerged from human coxsackievirus B4 in the Tambov region of Russia, where it circulated from 1975 to 1977. A high percentage of similarity between both types of the SVD virus was found in the 3D protein coding region (88%). In our previous work, analysis of the VP1 gene dates the appearance of the SVDV-2 precursor to between 1954 and 1975. In this work, the origin of the genome region encoding non-structural proteins was analyzed and is believed to be a result of multiple recombination events between human enteroviruses (hypothetically, E1, E9, E11 and coxsackievirus A9). The recombination breakpoint between the region of structural CVB4 proteins and non-structural T75 proteins is located in region 2A. This mini-review also represents the historical research of SVDV-1 and SVDV-2 strains (O72(USS/6/72) and T75, respectively) isolated in the former Soviet Union. Full article

Microwave imaging is a promising non-ionizing technique for bedside follow-up of intracranial hemorrhage, but dynamic monitoring remains challenging under limited multistatic sampling because weak inter-frame changes can be obscured by measurement variability, model mismatch, and the high cost of frame-by-frame nonlinear inversion. To address this problem, this paper proposes a state-referenced truncated singular-value decomposition (SR-TSVD) framework for dynamic microwave monitoring of hemorrhagic evolution. The method maintains an internal gate state and reconstructs only the state-referenced increment at each monitoring instant. A row-whitened TSVD inversion is introduced to reduce channel dominance effects and improve robustness to route-dependent imbalance, while a residual-driven gate-refresh mechanism updates the internal state only when the current linearization background becomes insufficiently accurate. The proposed method was validated through two-dimensional numerical experiments and hardware phantom measurements. The numerical study examined different lesion evolution scenarios and analyzed the effects of antenna count, frequency diversity, and measurement noise. The hardware study showed that the method preserves the main dynamic evolution in a real measurement system and remains more stable than baseline linear methods under sparse array conditions. These results indicate that SR-TSVD provides an effective and computationally practical framework for repeated bedside microwave monitoring of intracranial hemorrhage. Full article

In microwave imaging with finite antenna arrays, the limited number of array elements constrains spatial sampling and degrades reconstruction quality. To enlarge the aperture effectively, virtual antennas are usually adopted. However, it may lead virtual data to dominate the reconstruction process, thereby amplifying artifacts. This work proposes an interpolation-weighted truncated singular value decomposition (IW-TSVD) framework that expands multistatic scattering matrix by using an integer interpolation factor. The proposed method preserves all physically measured antenna data and applies explicit weighting to virtual channels to suppress their influence. Simulations and hardware experiments show that IW-TSVD improves structural similarity index (SSIM), reduces the mean squared error (MSE), and suppresses artifacts compared with conventional TSVD and zero-padding-based interpolated TSVD, without increasing hardware complexity. Full article

Insect bites are a common cause of skin irritation and can contribute to disease transmission through vector-borne pathogens. Early identification of the likely biting organism can assist preliminary guidance (e.g., monitoring for warning signs, considering exposure history) and may reduce complications through timely follow-up. This paper studies a compact attention-guided learning framework for multiclass insect-bite image classification under strict storage constraints. A teacher network (BiteAI-T) based on MobileNetV3-Small is trained with spatial attention pooling to emphasize lesion-relevant regions while maintaining an efficient backbone. A lightweight depthwise-separable student (BiteAI-S) is trained using multi-level knowledge distillation that combines softened-logit matching with intermediate supervision through attention-map alignment and pooled-feature matching. Model storage is further reduced through weight-only quantization-aware training using an LSQ-inspired learnable scaling factor; BatchNorm running statistics are frozen during quantization fine-tuning to improve stability. Experiments on an eight-class dataset (ants, bed bugs, chiggers, fleas, mosquitos, no bites, spiders, ticks) show that BiteAI-T reaches 93.75% test accuracy. For deployment, we export (i) a TorchScript Lite teacher artifact (BiteAI-T_Lite, 2.35 MB) and (ii) a weight-only int8 student artifact (BiteAI-S_int8, 0.992 MB). Comparative results are also reported for an SVD-compressed + fine-tuned FP16 variant (92.66% test accuracy, 2.84 MB), illustrating accuracy–size trade-offs across compression strategies. Full article

Graph-based multi-view clustering has gained significant attention in recent years due to its superior ability to reveal clustering structures. However, existing methods often incur high computational costs when capturing local information and overlook the higher-order correlations between multiple views. To address these issues, we propose Tensorized Consensus Graph Learning for Incomplete Multi-View Clustering with Confidence Integration (TCGL). This approach constructs adjacency and local heat kernel graphs by filtering missing samples to better capture local structures while leveraging a t-SVD-based weighted tensor nuclear norm sparsification method to reduce noise. Additionally, we introduce a matrix energy-based adjacency graph normalization strategy that utilizes common nearest neighbors to generate probability matrices, enhancing noise resistance and improving structural exploration. Experimental results demonstrate that TCGL effectively handles incomplete data and significantly outperforms state-of-the-art approaches across multiple datasets. Full article

The adverse propagation environment in underground coal mine tunnels caused by enclosed spaces, rough surfaces, and dense scatterers severely degrades reliable wireless signal transmission, which further impedes the deployment of IoT applications such as gas monitors and personnel positioning terminals. However, the conventional power enhancement solutions are infeasible for the underground coal mine scenario due to strict explosion-proof safety regulations and battery-powered IoT devices. To address this challenge, we propose singular value decomposition-based Lagrangian optimization (SVD-LOP) to minimize transmit power at the mining base station (MBS) for IRS-assisted coal mine wireless communication systems. In particular, we first establish a three-dimensional twin cluster geometry-based stochastic model (3D-TCGBSM) to accurately characterize the underground coal mine channel. On this basis, we formulate the MBS transmit power minimization problem constrained by user signal-to-noise ratio (SNR) target and IRS phase shifts. To solve this non-convex problem, we propose the SVD-LOP algorithm that performs SVD on the channel matrix to decouple the complex channel coupling and introduces the Lagrange multipliers. Furthermore, we develop a low-complexity successive convex approximation (LC-SCA) algorithm to reduce computational complexity, which constructs a convex approximation of the objective function based on a first-order Taylor expansion and enables suboptimal solutions. Simulation results demonstrate that the proposed SVD-LOP and LC-SCA algorithms achieve transmit power peaks of $20.8\mathrm{dBm}$ and $21.4\mathrm{dBm}$, respectively, which are slightly lower than the $21.8\mathrm{dBm}$ observed for the SDR algorithm. It is evident that these algorithms remain well below the explosion-proof safety threshold, which achieves significant power reduction. However, computational complexity analysis reveals that the proposed SVD-LOP and LC-SCA algorithms achieve $\mathcal{O}\left(N^3\right)$ and $\mathcal{O}\left(N^2\right)$ respectively, which offers substantial reductions compared to the SDR algorithm’s $\mathcal{O}\left(N^7\right)$. Moreover, both proposed algorithms exhibit robust convergence across varying user SNR targets while maintaining stable performance gains under different tunnel roughness scenarios. Full article

Recently, a growing number of researchers have focused on multi-view subspace clustering (MSC) due to its potential for integrating heterogeneous data. However, current MSC methods remain challenged by limited robustness and insufficient exploitation of cross-view high-order latent information for clustering advancement. To address these challenges, we develop a novel MSC framework termed TMSC-TNNBDR, a tensorized MSC framework that leverages t-SVD based tensor nuclear norm (TNN) regularization and block diagonal representation (BDR) learning to unify view consistency and structural sparsity. Specifically, each subspace representation matrix is constrained by a block diagonal regularizer to enforce cluster structure, while all matrices are aggregated into a tensor to capture high-order interactions. To efficiently optimize the model, we developed an optimization algorithm based on the inexact augmented Lagrange multiplier (ALM). The TMSC-TNNBDR exhibits both optimized block-diagonal structure and low-rank properties, thereby enabling enhanced mining of latent higher-order inter-view correlations while demonstrating greater resilience to noise. To investigate the capability of TMSC-TNNBDR, we conducted several experiments on certain datasets. Benchmarking on circumscribed datasets demonstrates our method’s superior clustering performance over comparative algorithms while maintaining competitive computational overhead. Full article

Background: Vascular risk factors (VRFs) are known to influence cerebral small vessel disease (cSVD) burden and progression. However, their specific impact on the presence and distribution of each cSVD imaging marker (white matter hyperintensity [WMH], perivascular spaces [PVSs], lacunes, and cerebral microbleeds [CMBs]) and their spatial distribution remains unclear. Methods: We conducted a retrospective analysis of 93 patients with lacunar stroke with a standardized investigational magnetic resonance imaging protocol using a 3T scanner. WMH and PVSs were segmented semi-automatically, and lacunes and CMBs were manually segmented. We assessed the univariable associations of four common VRFs (hypertension, hyperlipidemia, diabetes, and smoking) with the load of each cSVD marker. Then, we assessed the independent associations of these VRFs in multivariable regression models adjusted for age and sex. Spatial lesion patterns were explored with regional volumetric comparisons using Pearson’s coefficient analysis, which was adjusted for multiple comparisons, and by visually examining heatmap lesion distributions. Results: Hypertension was the VRF that exhibited stronger associations with the cSVD markers in the univariable analysis. In the multivariable analysis, only lacunes (p = 0.009) and PVSs in the basal ganglia (p = 0.014) and white matter (p = 0.016) were still associated with hypertension. In the regional analysis, hypertension showed a higher WMH load in deep structures and white matter, particularly in the posterior periventricular regions. In patients with hyperlipidemia, WMH was preferentially found in hippocampal regions. Conclusions: Hypertension was confirmed to be the VRF with the most impact on cSVD load, especially for lacunes and PVSs, while the lesion topography was variable for each VRF. These findings shed light on the complexity of cSVD expression in relation to factors detrimental to vascular health. Full article

Microwave imaging systems show potential as replacements for commonly used stroke diagnostic systems. We developed and tested a 10-port microwave system on a liquid head phantom with ischemic and hemorrhagic strokes of varying sizes and positions. This system allows for visualization of changes in dielectric parameters using the TSVD Born approximation, enabling recognition of stroke position and size from the resulting images. The SVM algorithm effectively distinguishes between ischemic and hemorrhagic strokes, achieving 98% accuracy on experimental data, with 99% accuracy in ischemic scenarios and 97% in hemorrhagic scenarios. Using the TSVD Born algorithm, it was possible to precisely image changes in the absolute permittivity of different stroke locations; however, changes in stroke size were more apparent in the variations of absolute permittivity than in the reconstructed stroke size within the antenna plane. Outside this plane, changes in the S-parameters decreased depending on the distance and size of the stroke, making detection and classification more difficult. One ring of antennas around the head proved insufficient, prompting us to focus on developing a system with antennas positioned around the entire head. Full article

Real-time monitoring of soil health parameters is crucial for efficient use of resources, improving agricultural productivity, and sustainability. Traditional soil analysis methods, although accurate, are time-consuming and lack the spatial and temporal resolution necessary for dynamic agricultural environments. Recent advancements in sensor technology offer promising alternatives, enabling real-time, in situ monitoring of key soil health indicators. This study details the deployment and validation of novel Sensor-in-Field probes at the Donald Danforth Plant Science Center Farm in Missouri, U.S., in a winter wheat plot. Three Sensor-in-Field probes were evaluated for their ability to measure nitrate (NO₃), ammonium (NH₄), soil organic matter (SOM), carbonaceous soil minerals (CSMs), soil volumetric density (SVD), soil hydration state (SHS), and total soil carbon (TSC) over a 28-day period. The probes’ coefficients of variation were well within acceptable limits (<20%) for all parameters. The measured metrics averaged 0.05% ± 0.001 and 1.92% ± 0.02 for CSMs and SOM, respectively, while TSC was 1.18% ± 0.15. For the nutrients, the measured NO₃ and NH₄ values were 4.44 ppm ± 0.37 and 2.78 ppm ± 0.22, respectively. The accuracy of the soil probes was validated at a certified traditional soil analysis laboratory. Three samples were collected at three different time points and analyzed. Bland–Altman analysis showed <$\pm$ 10% difference between the soil probes and traditional lab analysis for CSMs, SOM, and TSC, while t-test analysis reported p-values > 0.005 for NO₃, NH₄, and SHS/SVD, indicating non-significant differences between the probes and traditional soil analysis methods. Full article