Low-rank Constraint Research Articles

Tensorized and Compressed Multi-View Subspace Clustering via Structured Constraint.

Multi-view learning has raised more and more attention in recent years. However, traditional approaches only focus on the difference while ignoring the consistency among views. It may make some views, with the situation of data abnormality or noise, ineffective in the progress of view learning. Besides, the current datasets have become high-dimensional and large-scale gradually. Therefore, this paper proposes a novel multi-view compressed subspace learning method via low-rank tensor constraint, which incorporates the clustering progress and multi-view learning into a unified framework. First, for each view, we take the partial samples to build a small-size dictionary, which can reduce the effect of both redundancy information and computation cost greatly. Then, to find the consistency and difference among views, we impose a low-rank tensor constraint on these representations and further design an auto-weighted mechanism to learn the optimal representation. Last, due to the non-square of the learned representation, the bipartite graph has been introduced, and under the structured constraint, the clustering results can be obtained directly from this graph without any post-processing. Extensive experiments on synthetic and real-world benchmark datasets demonstrate the efficacy and efficiency of our method, especially for the views with noise or outliers.

A novel bearing weak fault diagnosis method based on rank constrained low-rank and sparse decomposition

Abstract Addressing the challenge of diagnosing incipient bearing faults amidst significant noise, a novel diagnostic approach is introduced, leveraging a Rank Constrained Low-Rank and Sparse Decomposition (RCLRSD) model tailored for weak fault detection in bearings. Initially, we raised the Autocorrelation Function of the Square Envelope in Frequency Domain (AFSEFD) as an innovative method for the estimation of fault frequencies. Subsequently, we constructed a two-dimensional observation matrix, which is formulated independently of predefined assumptions. Then, we examine the configuration and distribution patterns of bearing fault signals, uncovering the low-rank nature of fault characteristics within a designated two-dimensional transform domain. Moreover, we found the noise signal to exhibit sparsity and an approximate Gaussian distribution. Based on this, a rank-constrained low-rank sparse decomposition model is established, and rank-constrained low-rank regular constraints for feature information and sparse regular constraints and Gaussian constraints for interference signals are constructed respectively. Ultimately, we employed the Gray Wolf Optimization (GWO) algorithm to refine the model parameters, and we deduced the model's solver via the Alternating Direction Method of Multipliers (ADMM). The proposed RCLRSD model decomposes bearing fault data into three constituents: low-rank, sparse, and Gaussian components, effectively addressing the challenge of extracting weak fault signatures from bearings. The weak feature extraction capability of the RCLRSD model is verified using a multi-interference simulation model and experimental data of bearing failures under strong noise conditions; the generalization of the model is verified by the classification effect of the Support Vector Machine (SVM) under two bearing failure datasets. Comparison with various algorithms confirms the superiority of the proposed algorithm.

Low-rank iterative infilling for zero echo-time (ZTE) imaging.

A new referenceless low-rank reconstruction technique has been introduced to address the issue of missing samples within the Zero Echo Time (ZTE) dead-time gap. The proposed method reformulates the in-filling of the missing samples as an inverse problem subject to low-rank constraints. Its performance and robustness are evaluated through a comparative analysis that combines Monte Carlo computational simulations and data obtained from in vivo experiments. The proposed method is tested for dead-time gaps ranging up to 4.5 Nyquist dwells, across signal-to-noise ratio levels of 5, 10, 15, and 20 dB. Consistently superior performance is observed across all cases compared to algebraic and parallel imaging methods. The speed for convergence decreases exponentially as the dead-time gap expands. The proposed method enables artifact-free reconstruction up to dead-time gap of 4 Nyquist dwells and thereby supports ZTE imaging up to an imaging bandwidth of kHz (assuming transmit and receive switching less than 30 s). It demonstrates superior performance compared to algebraic and parallel imaging methods.

Tensorial multiview low-rank high-order graph learning for context-enhanced domain adaptation

Unsupervised Domain Adaptation (UDA) is a machine learning technique that facilitates knowledge transfer from a labeled source domain to an unlabeled target domain, addressing distributional discrepancies between these domains. Existing UDA methods often fail to effectively capture and utilize contextual relationships within the target domain. This research introduces a novel framework called Tensorial Multiview Low-Rank High-Order Graph Learning (MLRGL), which addresses these challenges by learning high-order graphs constrained by low-rank tensors to uncover contextual relations. The proposed framework ensures prediction consistency between randomly masked target images and their pseudo-labels by leveraging spatial context to generate multiview domain-invariant features through various augmented masking techniques. A high-order graph is constructed by combining Laplacian graphs to propagate these multiview features. Low-rank constraints are applied along both horizontal and vertical dimensions to better uncover inter-view and inter-class correlations among multiview features. This high-order graph is used to create an affinity matrix, mapping multiview features into a unified subspace. Prototype vectors and unsupervised clustering are then employed to calculate conditional probabilities for UDA tasks. We evaluated our approach using three different backbones across three benchmark datasets. The results demonstrate that the MLRGL framework outperforms current state-of-the-art methods in various UDA tasks. Additionally, our framework exhibits robustness to hyperparameter variations and demonstrates that multiview approaches outperform single-view solutions.

Simultaneous Multislice Cardiac Multimapping based on Locally Low-Rank and Sparsity Constraints.

Although quantitative myocardial T1 and T2 mappings are clinically used to evaluate myocardial diseases, their application needs a minimum of 6 breath-holds to cover 3 short-axis slices. The purpose of this work is to simultaneously quantify multi-slice myocardial T1 and T2 across 3 short-axis slices in one breath-hold by combining simultaneous multi-slice (SMS) with Multimapping. An SMS-Multimapping sequence with multi-band RF excitations and Cartesian FLASH readouts was developed for data acquisition. When 3 slices are simultaneously acquired, the acceleration rate is around 12-fold, causing a highly ill-conditioned reconstruction problem. To mitigate image artifacts and noise caused by the ill-conditioning, a reconstruction algorithm based on Locally Low-Rank and Sparsity (LLRS) was developed. Validation was performed in phantoms and in vivo imaging, with 20 healthy subjects and 4 patients, regarding regional mean, precision, and scan-rescan reproducibility. The phantom imaging shows that SMS-Multimapping with LLRS accurately reconstructed multi-slice T1 and T2 maps despite a 6-fold acceleration of scan time. Healthy subject imaging shows that the proposed LLRS algorithm substantially improved image quality relative to split slice-GRAPPA. Compared with MOLLI, SMS-Multimapping exhibited higher T1 mean (1118±43ms vs 1190±49ms, P<0.01), lower precision (67±17ms vs 90±17ms, P<0.01), and acceptable scan-rescan reproducibility measured by two scans 10-minute apart (bias=1.4ms for MOLLI and 9.0ms for SMS-Multimapping). Compared with bSSFP T2 mapping, SMS-Multimapping exhibited similar T2 mean (43.5±3.3ms vs 43.0±3.5ms, P=0.64), similar precision (4.9±2.1ms vs 5.1±1.0ms, P=0.93), and acceptable scan-rescan reproducibility (bias=0.13ms for bSSFP T2 mapping and 0.55ms for SMS-Multimapping). In patients, SMS-Multimapping clearly showed the abnormality in a similar fashion as the reference methods despite using only one breath-hold. SMS-Multimapping with the proposed LLRS reconstruction can measure multi-slice T1 and T2 maps in one breath-hold with good accuracy, reasonable precision, and acceptable reproducibility, achieving a 6-fold reduction of scan time and an improvement of patient comfort.

INCOMPLETE multi-view clustering based on low-rank adaptive graph learning

The challenge of acquiring complete data has led to substantial progress in incomplete multi-view clustering (IMVC) methods. Because graph structures can be excellent representations of data structure relationships, exceptional performance in handling incomplete data is demonstrated by graph-based methods at present. However, these methods still have their limitations. Most incomplete multi-view algorithms primarily focus on local information, neglecting global information. Therefore, these methods cannot dynamically recover the structural relationships in incomplete data by harnessing potential information from multiple perspectives and overall structural information. In response to the aforementioned concerns, we introduced an IMVC based on low-rank adaptive graph learning (IMVC-LAGL). This method initially constructs an affinity matrix based on the inter-view adjacency relationships. It also utilizes tensor low-rank constraints and consensus representation learning to explore higher-order correlations among different views. Subsequently, it adaptively reconstructs the incomplete graph structure to ultimately obtain a complete affinity relationship. It leads to excellent clustering results by integrating relevant information within views, overall structural information and potential information from multiple perspectives. We conducted experiments comparing our algorithm with eight incomplete multi-view algorithms using five different evaluation metrics. The results show that our algorithm achieves the best clustering results across eight datasets with varying missing rates. Particularly in the BBCSport dataset and YaleB dataset, the clustering accuracy of our algorithm is improved by 19.83 % and 16.41 %, respectively, compared with the second-best algorithm, under a 50 % missing rate.

Multi-kernel clustering with tensor fusion on Grassmann manifold for high-dimensional genomic data

The high dimensionality and noise challenges in genomic data make it difficult for traditional clustering methods. Existing multi-kernel clustering methods aim to improve the quality of the affinity matrix by learning a set of base kernels, thereby enhancing clustering performance. However, directly learning from the original base kernels presents challenges in handling errors and redundancies when dealing with high-dimensional data, and there is still a lack of feasible multi-kernel fusion strategies. To address these issues, we propose a Multi-Kernel Clustering method with Tensor fusion on Grassmann manifolds, called MKCTM. Specifically, we maximize the clustering consensus among base kernels by imposing tensor low-rank constraints to eliminate noise and redundancy. Unlike traditional kernel fusion approaches, our method fuses learned base kernels on the Grassmann manifold, resulting in a final consensus matrix for clustering. We integrate tensor learning and fusion processes into a unified optimization model and propose an effective iterative optimization algorithm for solving it. Experimental results on ten datasets, comparing against 12 popular baseline clustering methods, confirm the superiority of our approach. Our code is available at https://github.com/foureverfei/MKCTM.git.

Spectral weighted sparse unmixing based on adaptive total variation and low-rank constraints

Hyperspectral sparse unmixing, an image processing technique, leverages a spectral library enriched with endmember spectral information as a prerequisite. It decomposes the hyperspectral data to ascertain the abundance corresponding to each endmember in the spectral library. Currently, the majority of sparse unmixing methods are inadequate in high-noise environments due to their failure to comprehensively account for hyperspectral characteristics. Addressing this challenge, this paper introduces an innovative sparse unmixing approach for hyperspectral images named spectral weighted sparse unmixing based on adaptive total variation and low-rank constraints (SWSU-ATVLR). Initially, the sparse unmixing algorithm is introduced in detail. Subsequently, we present the our method. This method seamlessly integrates the low-rank, adaptive TV and spectral weighting characteristics of hyperspectral data. While preserving the low-rank attributes and sparsity of abundance, the adaptively adjusted abundance matrix exhibits a regularized horizontal and vertical difference ratio across various structures and fully utilizes spectral information, enhancing denoising efficiency. Subsequently, the ADMM algorithm is employed to solve the new model. To validate our proposed algorithm, SWSU-ATVLR method is compared and analysed in detailed experiments with several current state-of-the-art methods through simulated and real data experiments. Experimental results prove that our proposed method is superior to these state-of-the-art methods.

Accelerated Cartesian cardiac T2 mapping based on a calibrationless locally low-rank tensor constraint.

Cardiac T2 mapping is a valuable tool for diagnosing myocardial edema, inflammation, and infiltration, yet its spatial resolution is limited by the single-shot balanced steady-state free precession acquisition and duration of the cardiac quiescent period, which may reduce sensitivity in detecting focal lesions in the myocardium. To improve spatial resolution without extending the acquisition window, this study examined a novel accelerated Cartesian cardiac T2 mapping technique. We introduce a novel improved-resolution cardiac T2 mapping approach leveraging a calibrationless space-contrast-coil locally low-rank tensor (SCC-LLRT)-constrained reconstruction algorithm in conjunction with Cartesian undersampling trajectory. The method was validated with phantom imaging and in vivo imaging that involved 13 healthy participants and 20 patients. The SCC-LLRT algorithm was compared with a conventional locally low-rank (LLR)-constrained algorithm and a nonlinear inversion (NLINV) reconstruction algorithm. The improved-resolution T2 mapping (1.4 mm × 1.4 mm) was compared globally and regionally with the regular-resolution T2 mapping (2.3 mm × 1.9 mm) according to the 16-segment model of the American Heart Association. The agreement between the improved-resolution and regular-resolution T2 mappings was evaluated by linear regression and Bland-Altman analyses. Image quality was scored by two experienced reviewers on a five-point scale (1, worst; 5, best). In healthy participants, SCC-LLRT significantly reduced artifacts (4.50±0.39) compared with LLR (2.31±0.60; P<0.001) and NLINV (3.65±0.56; P<0.01), suppressed noise (4.12±0.35) compared with NLINV (2.65±0.50; P<0.001), and improved the overall image quality (4.38±0.40) compared with LLR (2.54±0.41; P<0.001) and NLINV (3.04±0.50; P<0.001). Compared with the regular-resolution T2 mapping, the proposed method significantly improved the sharpness of myocardial boundaries (4.46±0.60 vs. 3.04±0.50; P<0.001) and the conspicuity of papillary muscles and fine structures (4.46±0.63 vs. 2.65±0.30; P<0.001). Myocardial T2 values obtained with the proposed method correlated significantly with those from regular-resolution T2 mapping in both healthy participants (r=0.79; P<0.01) and patients (r=0.94; P<0.001). The proposed SCC-LLRT-constrained reconstruction algorithm in conjunction with Cartesian undersampling pattern achieved improved-resolution cardiac T2 mapping of comparable accuracy, precision, and scan-rescan reproducibility compared with the regular-resolution T2 mapping. The higher resolution improved the sharpness of myocardial borders and the conspicuity of image fine details, which may increase diagnostic confidence in cardiac T2 mapping for detecting small lesions.

Ship Wake Detection in a Single SAR Image via a Modified Low-Rank Constraint

Ship Wake Detection in a Single SAR Image via a Modified Low-Rank Constraint

Retrospective motion correction for cardiac multi-parametric mapping with dictionary matching-based image synthesis and a low-rank constraint.

To develop a model-based motion correction (MoCo) method that does not need an analytical signal model to improve the quality of cardiac multi-parametric mapping. The proposed method constructs a hybrid loss that includes a dictionary-matching loss and a signal low-rankness loss, where the former registers the multi-contrast original images to a set of motion-free synthetic images and the latter forces the deformed images to be spatiotemporally coherent. We compared the proposed method with non-MoCo, a pairwise registration method (Pairwise-MI), and a groupwise registration method (pTVreg) via a free-breathing Multimapping dataset of 15 healthy subjects, both quantitatively and qualitatively. The proposed method achieved the lowest contour tracking errors (epicardium: 2.00 ± 0.39 mm vs 4.93 ± 2.29 mm, 3.50 ± 1.26 mm, and 2.61 ± 1.00 mm, and endocardium: 1.84 ± 0.34 mm vs 4.93 ± 2.40 mm, 3.43 ± 1.27 mm, and 2.55 ± 1.09 mm for the proposed method, non-MoCo, Pairwise-MI, and pTVreg, respectively; all p < 0.01) and the lowest dictionary matching errors among all methods. The proposed method also achieved the highest scores on the visual quality of mapping (T1: 4.74 ± 0.33 vs 2.91 ± 0.82, 3.58 ± 0.87, and 3.97 ± 1.05, and T2: 4.48 ± 0.56 vs 2.59 ± 0.81, 3.56 ± 0.93, and 4.14 ± 0.80 for the proposed method, non-MoCo, Pairwise-MI, and pTVreg, respectively; all p < 0.01). Finally, the proposed method had similar T1 and T2 mean values and SDs relative to the breath-hold reference in nearly all myocardial segments, whereas all other methods led to significantly different T1 and T2 measures and increases of SDs in multiple segments. The proposed method significantly improves the motion correction accuracy and mapping quality compared with non-MoCo and alternative image-based methods.

Tensor-based unsupervised feature selection for error-robust handling of unbalanced incomplete multi-view data

Recent advancements in multi-view unsupervised feature selection (MUFS) have been notable, yet two primary challenges persist. First, real-world datasets frequently consist of unbalanced incomplete multi-view data, a scenario not adequately addressed by current MUFS methodologies. Second, the inherent complexity and heterogeneity of multi-view data often introduce significant noise, an aspect largely neglected by existing approaches, compromising their noise robustness. To tackle these issues, this paper introduces a Tensor-Based Error Robust Unbalanced Incomplete Multi-view Unsupervised Feature Selection (TERUIMUFS) strategy. The proposed MUFS framework specifically caters to unbalanced incomplete multi-view data, incorporating self-representation learning with a tensor low-rank constraint and sample diversity learning. This approach not only mitigates errors in the self-representation process but also corrects errors in the self-representation tensor, significantly enhancing the model’s resilience to noise. Furthermore, graph learning serves as a pivotal link between MUFS and self-representation learning. An innovative iterative optimization algorithm is developed for TERUIMUFS, complete with a thorough analysis of its convergence and computational complexity. Experimental results demonstrate TERUIMUFS’s effectiveness and competitiveness in addressing unbalanced incomplete multi-view unsupervised feature selection (UIMUFS), marking a significant advancement in the field.

Low-rank sparse fully-connected tensor network for tensor completion

Fully-connected tensor network (FCTN) has recently drawn lots of attention in tensor completion due to its full description of all correlations between any two modes. However, the FCTN model has multiple ranks, and existing methods often ignore the difficulty brought about by rank selection, especially when the model is rank-sensitive. To overcome this drawback, this paper proposed a low-rank sparse FCTN for tensor completion. Specifically, we theoretically show that, for a tensor with FCTN structure, its subtensor can be represented as a coefficient sum of basic tensors, where the coefficients are remained in the FCTN’s factors. This means that factors’ sparsity can improve the robustness of FCTN to larger rank selection. Moreover, according to the relation between the target tensor and its FCTN’s factors, low-rank constrain is used to enhance rank robustness. Lastly, we optimize the proposed model by the alternating direction method of multipliers (ADMM) algorithm. Experimental results show that the low-rank sparse constraint effectively improves the rank robustness of the FCTN model, and achieves excellent results compared with other state-of-the-art completion methods.

Joint local smoothness and low-rank tensor representation for robust multi-view clustering

Low-rank tensor representation (LRTR) has become a significant method for achieving improved multi-view clustering (MVC) performance. Generally, most LRTR methods impose a tensor low-rank constraint (TLRC) on a tensor, which is spliced by the representation matrix of each view, to explore the low-rank prior hidden in these representation matrices. However, two problems remain unsolved. On the one hand, these representation matrices still contain noise since the raw data usually possess noise; on the other hand, and more importantly, is there any other prior information that can be explored among these representation matrices? Since samples located in the same cluster are similar, the coefficients of their representation matrices should exhibit similar. That is, these representation matrices should be local smoothness (LS), which is also verified by our numerical tests. In addition, the use of the LS prior helps to denoise the noise contain in the data. Then, in this paper, we propose a joint LS and LRTR for robust MVC method (LS-LRTR), which can simultaneously exploit the low-rank and LS priors. Specifically, we utilize a TLRC to explore the low-rank prior in the representation matrices. Subsequently, to mine the LS prior and further reduce the influence of noise, we introduce the Total Variation (TV) norm to the constraint representation matrices. Then, we fuse the TLRC and TV norm into a unified framework. Additionally, we apply an Augmented Lagrange Multiplier to solve the optimization problem of LS-LRTR. Experiments conducted on several datasets indicate that LS-LRTR outperforms the state-of-the-art clustering methods.

Label-guided low-rank Approximation for functional brain network learning in identifying subcortical vascular cognitive impairment

Background and ObjectiveFunctional brain network (FBN) has played a pivotal role in unraveling the inherent mechanism of cognition/behavior and investigating neuropsychological disorders. Particularly, growing evidence suggests that FBNs have shown great potential in classifying brain disorders such as subcortical vascular cognitive impairment (SVCI). However, learning a high-quality FBN is still challenging since there is no ground truth. Most traditional methods tend to focus on learning FBNs independently of the downstream task. This practice neglects the valuable label information crucial for accurate classification. Besides, the methodology of constructing brain networks in an isolated, individualistic manner sidesteps the common information among individuals. MethodsTo address these issues, we developed a new FBN joint learning strategy named Label-Guided Low-rank Approximation (LGLA). LGLA integrates label information from training subjects and uses unlabeled testing subjects for auxiliary training, enhancing the discriminative power of FBN features tailored to testing subjects. By enforcing class-specific similarities and differences, and applying a low-rank constraint to capture shared information, LGLA presents an optimization framework that can be effectively solved. ResultsExperimental results demonstrate the effectiveness of our proposed FBN learning method for identifying SVCI. The proposed method achieved an accuracy of 75.70% and an area under the receiver operating characteristic curve (AUC) of 0.8233 in the task of identifying patients with amnestic mild cognitive impairment (aMCI). For identifying patients with non-amnestic mild cognitive impairment (naMCI), it achieved an accuracy of 63.64% and an AUC of 0.7857, while the task of identifying patients with no cognitive impairment (NCI), it achieved an accuracy of 63.64% and an AUC of 0.7917. Additionally, we further explored the brain network features and discovered potential biomarkers for personalized diagnosis. ConclusionThe LGLA method enhances FBN construction and classification accuracy for SVCI diagnosis by effectively integrating the label information and shared structure among subjects.

Consistent and specific multi-view multi-label learning with correlation information

In multi-view multi-label (MVML) learning, each sample is represented by several heterogeneous distinct feature representations while associated with a set of class labels simultaneously. To achieve MVML learning, most of the existing methods contribute to the recovery of a consistent subspace, i.e., a shared feature representation, among multiple views. Nevertheless, each view has its inherent specific properties used in the discrimination process of labels. These methods lose sight in the specific information exploitation, and therefore are easily trapped in a sub-optimal result. In this study, we present an optimization framework CSVL to solve the learning problem. The main technical contribution in CSVL is a formulation for MVML learning while consistent subspace across views, specific subspace for each view, and the correlations among labels are taken into account. Specifically, consistent subspace is recovered by imposing a low-rank constraint among multiple views, and specific subspace of each view is extra generated with Frobenius norm. To further improve model generalization capability, we preserve both feature manifolds from multiple views and label correlations from multiple labels. Extensive experiments on 7 benchmark datasets show that our proposal CSVL has the advantages in MVML learning.

Data Completion-Guided Unified Graph Learning for Incomplete Multi-View Clustering

Due to its heterogeneous property, multi-view data has been widely concerned over single-view data for performance improvement. Unfortunately, some instances may be with partially available information because of some uncontrollable factors, for which the incomplete multi-view clustering (IMVC) problem is raised. IMVC aims to partition unlabeled incomplete multi-view data into their clusters by exploiting the heterogeneity of multi-view data and overcoming the difficulty of data loss. However, most existing IMVC methods like BSV, MIC, OMVC, and IVC tend to conduct basic completion processing on the input data, without taking advantage of the correlation between samples and information redundancy. To overcome the above issue, we propose one novel IMVC method named data completion-guided unified graph learning (DCUGL), which could complete the data of missing views and fuse multiple learned view-specific similarity matrices into one unified graph. Specifically, we first reduce the dimension of the input data to learn multiple view-specific similarity matrices. By stacking all view-specific similarity matrices, DCUGL constructs a third-order tensor with the low-rank constraint, such that sample correlation within and between views can be well explored. Finally, by dividing the original data into observed data and unobserved data, DCUGL can infer and complete the missing data according to the view-specific similarity matrices, and obtain a unified graph, which can be directly used for clustering. To solve the proposed model, we design an iterative algorithm, which is based on the alternating direction method of multipliers framework. The proposed model proves to be superior by benchmarking on six challenging datasets compared with state-of-the-art IMVC methods.

Research and Application of Destriping Algorithm based on Weighted Block Sparse Representation to FengYun Satellite Imager Data

Abstract In remote sensing imaging systems, stripe noise is a pervasive issue primarily caused by the inconsistent response of multiple detectors. Stripe noise not only affects image quality but also severely hinders subsequent quantitative derived products and applications. Therefore, it is crucial to eliminate stripe noise while preserving detailed structure information in order to enhance image quality. Although existing destriping methods have achieved certain effects to some extent, they still face problems such as loss of image details, image blur, and ringing artifacts. To address these issues, this study proposes an image stripe correction algorithm based on weighted block sparse representation. This research applies techniques such as differential low-rank constraint and edge weight factor to remove stripe noise while retaining image detail information. The algorithm also uses the alternating direction method of multipliers (ADMM) to solve the MCP regularized least squares optimization problem model, improving the processing efficiency of the model. The results of this study have been applied and validated in imager data from the Medium Resolution Spectral Imager (MERSI-II) onboard FengYun-3D satellite, the Multi-channel Scanning Radiometer (AGRI) onboard FengYun-4A satellite and Precipitation Microwave Radiometer (MWRI–RM) onboard FengYun-3G. Compared to typical stripe correction methods, the proposed method achieves better stripe removal while preserving image detail information. The destriped image data can be used to generate high-quality quantitative products for various applications. Overall, by combining insights from prior research and innovative techniques, this study provides a more effective and robust solution to the stripe noise problem in remote sensing and weather forecast.

An unrolled neural network for accelerated dynamic MRI based on second-order half-quadratic splitting model

The reconstruction of dynamic magnetic resonance images from incomplete k-space data has sparked significant research interest due to its potential to reduce scan time. However, traditional iterative optimization algorithms fail to faithfully reconstruct images at higher acceleration factors and incur long reconstruction time. Furthermore, end-to-end deep learning-based reconstruction algorithms suffer from large model parameters and lack robustness in the reconstruction results. Recently, unrolled deep learning models, have shown immense potential in algorithm stability and applicability flexibility. In this paper, we propose an unrolled deep learning network based on a second-order Half-Quadratic Splitting(HQS) algorithm, where the forward propagation process of this framework strictly follows the computational flow of the HQS algorithm. In particular, we propose a degradation-sense module by associating random sampling patterns with intermediate variables to guide the iterative process. We introduce the Information Fusion Transformer(IFT) to extract both local and non-local prior information from image sequences, thereby removing aliasing artifacts resulting from random undersampling. Finally, we impose low-rank constraints within the HQS algorithm to further enhance the reconstruction results. The experiments demonstrate that each component module of our proposed model contributes to the improvement of the reconstruction task. Our proposed method achieves comparably satisfying performance to the state-of-the-art methods and it exhibits excellent generalization capabilities across different sampling masks. At the low acceleration factor, there is a 0.7% enhancement in the PSNR. Furthermore, when the acceleration factor reached 8 and 12, the PSNR achieves an improvement of 3.4% and 5.8% respectively.

Vortex rope identification in Francis turbine based on cyclostationary extended dictionary learning

Francis turbine is one of the most commonly used hydraulic machinery for hydroelectric power generation, but its stability is frequently jeopardized by vortex rope. It is crucial to promptly and accurately detect vortex rope for the reliable operation of turbine unit. To address this challenge, the Cyclostationary Extended Dictionary Learning (CEDL) approach is proposed to identify vortex rope in Francis turbine. CEDL utilizes the Fisher discrimination criterion and low-rank constraints through the preprocessing and extending strategies to achieve accurate identification. Preprocessing specifically refers to the construction of filter for raw data based on cyclostationarity Then, the trained dictionary is used to extract features, and a linear classifier is developed based on these features. To evaluate the proposed method, vortex rope experiments are conducted in a Francis turbine under five conditions, and every condition includes four states: normal state, initial vortex rope, stable vortex rope and severe vortex rope. The results reveal three main findings. Firstly, the trained atoms in each sub-dictionary exhibit unique characteristics such as tonal frequency at 7 kHz and broadband frequency during 12–20 kHz, which are linked to the evolution stages of vortex rope. Secondly, the dictionary trained for a specific condition can achieve a classification accuracy of up to 90%, and even exceed 97% in some cases. Finally, the dictionary trained in a specific working condition can achieve relatively high classification accuracy in the scenarios of other working conditions.