Adaptive Sparse Research Articles

Rational Polynomial Coefficient Estimation via Adaptive Sparse PCA-Based Method

The Rational Function Model (RFM) is composed of numerous highly correlated Rational Polynomial Coefficients (RPCs), establishing a mathematical relationship between two-dimensional images and three-dimensional spatial coordinates. Due to the existence of ill-posedness and overparameterization, the estimated RPCs are sensitive to any slight perturbations in the observation data, particularly when handling a limited number of Ground Control Points (GCPs). Recently, Principal Component Analysis (PCA) has demonstrated significant performance improvements in the RFM optimization problem. In the PCA-based RFM, each Principal Component (PC) is a linear combination of all variables in the design matrix. However, some original variables are noise related and have very small or almost zero contributions to the construction of PCs, which leads to the overparameterization problem and makes the RPC estimation process ill posed. To address this problem, in this paper, we propose an Adaptive Sparse Principal Component Analysis-based RFM method (ASPCA-RFM) for RPC estimation. In this method, the Elastic Net sparsity constraint is introduced to ensure that each PC contains only a small number of original variables, which automatically eliminates unnecessary variables during PC computation. Since the optimal regularization parameters of the Elastic Net vary significantly in different scenarios, an adaptive regularization parameter approach is proposed to dynamically adjust the regularization parameters according to the explained variance of PCs and degrees of freedom. By adopting the proposed method, the noise and error in the design matrix can be reduced, and the ill-posedness and overparameterization of the RPC estimation can be significantly mitigated. Additionally, we conduct extensive experiments to validate the effectiveness of our method. Compared to existing state-of-the-art methods, the proposed method yields markedly improved or competitive performance.

Adaptive Sparse Regular Split Gaussian Kernel Least Mean Square Algorithm for Super-Low-Frequency Motion-Induced Noise Cancellation

In super-low-frequency (SLF) submarine communication, the motion-induced noise of the towed antenna is the primary noise source, and below 500 Hz, it increases with increasing speed. We propose an improved quadratic Approximate Forward–Backward Split Gaussian Kernel Least Mean Square Algorithm (ASRSG–KLMS) based on the forward–backward split criterion using noise approximation of the nonlinear kernel least mean square, which introduces an L2-paradigm regularization term and has good sparsity while maintaining optimization stability. The ASRSG–KLMS algorithm could improve the narrowband signal-to-noise ratio by approximately 6.93 dB in the frequency range of 45–55 Hz, making it suitable for motion-induced noise cancellation in the SLF band.

Centralised visual processing center for remote sensing target detection

Target detection in satellite images is an essential topic in the field of remote sensing and computer vision. Despite extensive research efforts, accurate and efficient target detection in remote sensing images remains unsolved due to the large target scale span, dense distribution, and overhead imaging and complex backgrounds, which result in high target feature similarity and serious occlusion. In order to address the above issues in a comprehensive manner, within this paper, we first propose a Centralised Visual Processing Center (CVPC), this structure is a parallel visual processing center for Transformer encoder and CNN, employing a lightweight encoder to capture broad, long-range interdependencies. Pixel-level Learning Center (PLC) module is used to establish pixel-level correlations and improve the depiction of detailed features. CVPC effectively improves the detection efficiency of remote sensing targets with high feature similarity and severe occlusion. Secondly, we propose a centralised feature cross-layer fusion pyramid structure to fuse the results with the CVPC in a top-down manner to enhance the detailed feature representation capability at each layer. Ultimately, we present a Context Enhanced Adaptive Sparse Convolutional Network (CEASC), which improves the accuracy while ensuring the detection efficiency. Based on the above modules, we designed and conducted a series of experiments. These experiments are conducted on three challenging public datasets, DOTA-v1.0, DIOR, and RSDO, showing that our proposed 3CNet achieves a more advanced detection accuracy while balancing the detection speed (78.62% mAP for DOTA-v1.0, 79.12% mAP for DIOR, and 95.50% mAP for RSOD).

A machine-learning architecture with two strategies for low-speed impact localization of composite laminates

In this paper, a machine-learning architecture with the integration of two strategies including data enhancement and adaptive generation scheme for Impact Localization (IL) are developed to address the aforementioned issues for location identification of impacts on composite laminates. Two main contributions are included in this research: First, response signals collected from low-speed impact experiments under various working conditions are denoised using Adaptive Sparse Noise Reduction Algorithm (ASNRA), which aims at maximizing the preservation of the original signal amplitude, thereby avoiding the underestimation of pulse features during denoising. Then a RIME-optimized Dual-layer Support Vector Regression (RDSVR) method for the real-time update of hyperparameters is implemented in the machine-learning architecture to realize IL. The superior performances of the IL architecture over different IL models are validated throughout the numerical examples in terms of stability and efficiency. Results demonstrate that proposed architecture has the ability to realize the accurate and robust IL of composite laminates.

Incorporating Adaptive Sparse Graph Convolutional Neural Networks for Segmentation of Organs at Risk in Radiotherapy

Precisely segmenting the organs at risk (OARs) in computed tomography (CT) plays an important role in radiotherapy’s treatment planning, aiding in the protection of critical tissues during irradiation. Renowned deep convolutional neural networks (DCNNs) and prevailing transformer-based architectures are widely utilized to accomplish the segmentation task, showcasing advantages in capturing local and contextual characteristics. Graph convolutional networks (GCNs) are another specialized model designed for processing the nongrid dataset, e.g., citation relationship. The DCNNs and GCNs are considered as two distinct models applicable to the grid and nongrid datasets, respectively. Motivated by the recently developed dynamic-channel GCN (DCGCN) that attempts to leverage the graph structure to enhance the feature extracted by the DCNNs, this paper proposes a novel architecture termed adaptive sparse GCN (ASGCN) to mitigate the inherent limitations in DCGCN from the aspect of node’s representation and adjacency matrix’s construction. For the node’s representation, the global average pooling used in the DCGCN is replaced by the learning mechanism to accommodate the segmentation task. For the adjacency matrix, an adaptive regularization strategy is leveraged to penalize the coefficient in the adjacency matrix, resulting in a sparse one that can better exploit the relationships between nodes. Rigorous experiments on multiple OARs’ segmentation tasks of the head and neck demonstrate that the proposed ASGCN can effectively improve the segmentation accuracy. Comparison between the proposed method and other prevalent architectures further confirms the superiority of the ASGCN.

Compression of Convolutional Neural Networks With Divergent Representation of Filters.

Convolutional neural networks (CNNs) have made remarkable achievements in many tasks. However, most of them are hardly applied to embedded systems directly because of the requirement of huge memory space and computing power. In this article, we propose a pruning framework, namely, FiltDivNet, to accelerate and compress CNN models for their applicability to small or portable devices. The correlations among filters are taken into account and measured by the goodness of fit. On this basis, a hybrid-cluster pruning strategy is designed with dynamic pruning ratios for different clusters in CNN models. It aims at representing its filters in their diversity by removing redundant ones cluster by cluster. In addition, a new loss function with adaptive sparsity constraints is introduced for the retraining and fine-tuning in the FiltDivNet. Finally, some comparative experiments based on classical CNN models are carried out to demonstrate its effectiveness in compression performance and its adaptability with different CNN architectures.

Error-Triggered Adaptive Sparse Identification for Predictive Control and Its Application to Multiple Operating Conditions Processes.

With the digital transformation of process manufacturing, identifying the system model from process data and then applying to predictive control has become the most dominant approach in process control. However, the controlled plant often operates under changing operating conditions. What is more, there are often unknown operating conditions such as first appearance operating conditions, which make traditional predictive control methods based on identified model difficult to adapt to changing operating conditions. Moreover, the control accuracy is low during operating condition switching. To solve these problems, this article proposes an error-triggered adaptive sparse identification for predictive control (ETASI4PC) method. Specifically, an initial model is established based on sparse identification. Then, a prediction error-triggered mechanism is proposed to monitor operating condition changes in real time. Next, the previously identified model is updated with the fewest modifications by identifying parameter change, structural change, and combination of changes in the dynamical equations, thus achieving precise control to multiple operating conditions. Considering the problem of low control accuracy during the operating condition switching, a novel elastic feedback correction strategy is proposed to significantly improve the control accuracy in the transition period and ensure accurate control under full operating conditions. To verify the superiority of the proposed method, a numerical simulation case and a continuous stirred tank reactor (CSTR) case are designed. Compared with some state-of-the-art methods, the proposed method can rapidly adapt to frequent changes in operating conditions, and it can achieve real-time control effects even for unknown operating conditions such as first appearance operating conditions.

Spectrum Reconstruction of Multispectral Light Field Imager Based on Adaptive Sparse Representation

Spectrum Reconstruction of Multispectral Light Field Imager Based on Adaptive Sparse Representation

Multichannel Image Completion With Mixture Noise: Adaptive Sparse Low-Rank Tensor Subspace Meets Nonlocal Self-Similarity.

Multichannel image completion with mixture noise is a common but complex problem in the fields of machine learning, image processing, and computer vision. Most existing algorithms devote to explore global low-rank information and fail to optimize local and joint-mode structures, which may lead to oversmooth restoration results or lower quality restoration details. In this study, we propose a novel model to deal with multichannel image completion with mixture noise based on adaptive sparse low-rank tensor subspace and nonlocal self-similarity (ASLTS-NS). In the proposed model, a nonlocal similar patch matching framework cooperating with Tucker decomposition is used to explore information of global and joint modes and optimize the local structure for improving restoration quality. In order to enhance the robustness of low-rank decomposition to data missing and mixture noise, we present an adaptive sparse low-rank regularization to construct robust tensor subspace for self-weighing importance of different modes and capturing a stable inherent structure. In addition, joint tensor Frobenius and l1 regularizations are exploited to control two different types of noise. Based on alternating directions method of multipliers (ADMM), a convergent learning algorithm is designed to solve this model. Experimental results on three different types of multichannel image sets demonstrate the advantages of ASLTS-NS under five complex scenarios.

Self-organizing Competitive Neural Network Based Adaptive Sparse Representation for Magnetotelluric Data Denoising

The existing sparse decomposition denoising methods for magnetotelluric (MT) data need to set the iterative stop condition manually, which not only has a large workload and high difficulty, but also easily causes subjective bias. To this end, we propose a new adaptive sparse representation method for MT data denoising. First, the data to be processed is divided into high-quality segments and noisy segments by machine learning algorithm. Then, the characteristic parameters of high-quality segments are calculated, and the boundary value of the characteristic parameters is taken as the threshold. The threshold has two functions, one is as a criterion for signal-to-noise identification, and the other is as an iterative stop condition for subsequent sparse decomposition. Finally, the optimized orthogonal matching pursuit algorithm is used to separate the signal and noise of the noisy segments, and the denoised segments and high-quality segments are combined to obtain the complete denoised MT data. The field data processing results show that this method is a fully automatic and intelligent MT data denoising method. It greatly improves the signal-to-noise ratio and the apparent resistivity-phase curves.

QoS based Optimal Path Selection Using Adaptive Sparse Bayesian Find-FixFinish-Exploit-Analyze Based Extreme Learning Machine for SDN based IoT Networks

QoS based Optimal Path Selection Using Adaptive Sparse Bayesian Find-FixFinish-Exploit-Analyze Based Extreme Learning Machine for SDN based IoT Networks

A Constellation Diagram Learning-Based Adaptive Sparse Nonorthogonal Wavelet Division Multiplexing for Sonar Image Underwater Acoustic Transmission

In underwater Internet of Things (IoT) applications, efficient and reliable transmission is demanding. Recently, the non-orthogonal multicarrier (MC) modulation is utilized as a promising spectrum-efficient solution in the UWA channel, where generally, the constellation mapping (CM) methods (such as 8-PSK and 16-QAM) are utilized to further increase the transmission rate. In this paper, we focus on the transmission of sonar images among IoT nodes and a constellation diagram learning-based adaptive sparse non-orthogonal wavelet division multiplexing (CDLA-SNOWDM) system is proposed to combat complex channel states between IoT nodes. We found that different CM methods contribute to unique time-frequency characteristics in constellation diagrams. We first utilize the time-frequency characteristics in designing the non-orthogonal subcarriers. The complex-valued CM signals are regarded as a new type of image. We introduce dictionary learning (DL) to non-orthogonal subcarrier designing, with the idea that designing CM signal adaptive non-orthogonal subcarriers can be regarded as designing an adaptive subcarrier dictionary. The CDLA-SNOWDM modulation is performed as a projection of the CM image to the subcarriers with an adaptive dictionary. The learned adaptive subcarriers can represent constellation diagrams more efficiently and improve transmission reliability. Both simulations and experiments show that the proposed scheme improved the reliability in transmitting sonar images over other orthogonal and non-orthogonal modulation schemes in UWA scenarios.

Sparse graph-regularized dictionary learning for full waveform inversion

Full waveform inversion is a nonlinear fitting technique that requires regularization methods to alleviate ill-posedness. Based on the newly introduced Graph-Laplacian regularization, which offers outstanding manifold learning, we propose a novel regularization method for FWI that can combine the graph Laplacian matrix with a sparse representation in a learning-based dictionaries. Besides employing an adaptive sparsity prior, the graph Laplacian matrix incorporates the nonlocal self-similarity prior into the FWI process, and consequently improve the stability of the inversion process and produce more accurate inversion results. The Alternating Direction Method of Multipliers (ADMM) is applied to solve the problem numerically. A series of experiments are performed on the Marmousi model and the BG Compass model. The experimental results verify the effectiveness of the proposed FWI method in both quantitative analysis and visual perception.

ASB-CS: Adaptive sparse basis compressive sensing model and its application to medical image encryption

Recent advances in intelligent wearable devices have brought tremendous chances for the development of healthcare monitoring system. However, the data collected by various sensors in it are user-privacy-related information. Once the individuals’ privacy is subjected to attacks, it can potentially cause serious hazards. For this reason, a feasible solution built upon the compression-encryption architecture is proposed. In this scheme, we design an Adaptive Sparse Basis Compressive Sensing (ASB-CS) model by leveraging Singular Value Decomposition (SVD) manipulation, while performing a rigorous proof of its effectiveness. Additionally, incorporating the Parametric Deformed Exponential Rectified Linear Unit (PDE-ReLU) memristor, a new fractional-order Hopfield neural network model is introduced as a pseudo-random number generator for the proposed cryptosystem, which has demonstrated superior properties in many aspects, such as hyperchaotic dynamics and multistability. To be specific, a plain medical image is subjected to the ASB-CS model and bidirectional diffusion manipulation under the guidance of the key-controlled cipher flows to yield the corresponding cipher image without visual semantic features. Ultimately, the simulation results and analysis demonstrate that the proposed scheme is capable of withstanding multiple security attacks and possesses balanced performance in terms of compressibility and robustness.

An Adaptive Sparse Channel Estimation Algorithm for OFDM Systems Based on Distributed Compressive Sensing

The current greedy iterative pursuit algorithms for sparse channel estimation in an orthogonal frequency division multiplexing (OFDM) system based on compressive sensing (CS) or distributed CS (DCS) have the disadvantages of relying on channel priori information as halting condition and having a low support searching efficiency. Under DCS framework, this letter proposes a unique halting condition for greedy algorithms by exploiting the delay correlation between adjacent symbol channels. Additionally, we present a segmented pruning strategy that supports to select multiple atoms in a single iteration to improve the support searching efficiency. Simulation results show that our algorithm can achieve more robust sparsity-adaptive channel estimation with reduced computational complexity compared to the traditional methods.

An enhanced K-SVD denoising algorithm based on adaptive soft-threshold shrinkage for fault detection of wind turbine rolling bearing

Due to nonstationary operating conditions of wind turbines and surrounding harsh working environments, the impulse features induced by bearing faults are always overwhelmed by heavy noise, which brings challenges to accurately detect rolling bearing faults. Sparse representation exhibits excellent performance in nonstationary signal analysis, but it is closely bound up with the degree of similarity between the atoms in a dictionary and signals. Therefore, this paper investigates an enhanced K-SVD denoising method based on adaptive soft-threshold shrinkage to achieve high-precision extraction of impulse signals, and applies it to fault detection of generator bearing of wind turbines. An adaptive sparse coding shrinkage soft-threshold denoising is first proposed to remove noise and harmonic interference in the residual term of dictionary updating, so that the updated atoms show obvious impact characteristics. Furthermore, a soft-threshold shrinkage function with adaptive threshold is designed to further suppress clutter in atoms of the learned dictionary, so as to obtain an optimized dictionary for recovering impulse signals. Two actual engineering cases are selected for analysis, and the envelope spectrum correlation kurtosis corresponding to the results obtained by the proposed method is significantly higher than that of other comparison methods, thus verifying its superiority in detecting rolling bearing faults.

Adaptive Sparsity Orthogonal Least Square with Neighbor Strategy for Fluorescence Molecular Tomography.

Fluorescence molecular tomography (FMT) is a highly sensitive and noninvasive optical imaging technique which has been widely applied to disease diagnosis and drug discovery. However, FMT reconstruction is a highly ill-posed problem. In this work, L0-norm regularization is employed to construct the mathematical model of the inverse problem of FMT. And an adaptive sparsity orthogonal least square with a neighbor strategy (ASOLS-NS) is proposed to solve this model. This algorithm can provide an adaptive sparsity and can establish the candidate sets by a novel neighbor expansion strategy for the orthogonal least square (OLS) algorithm. Numerical simulation experiments have shown that the ASOLS-NS improves the reconstruction of images, especially for the double targets reconstruction.Clinical relevance- The purpose of this work is to improve the reconstruction results of FMT. Current experiments are focused on simulation experiments, and the proposed algorithm will be applied to the clinical tumor detection in the future.

Multi objective task resource allocation method based on hierarchical Bayesian adaptive sparsity for edge computing in low voltage stations

AbstractIn order to achieve more efficient and optimised resource scheduling, this research carried out a multi‐objective task resource allocation method for low‐voltage station edge computing based on hierarchical Bayesian adaptive sparsity. Based on hierarchical Bayesian adaptive sparsity, the multi‐objective task resource allocation technical framework for edge computing in low‐voltage stations is established, which is composed of end pipe edge cloud; After collecting real‐time operation data of power distribution equipment, substation terminals, transmission terminals, etc. in the architecture end, it is transmitted to the data middle platform and service middle platform of the Internet of Things management platform in the cloud through the edge Internet of Things agent; Set and solve the constraint conditions, and build a multi type flexible load hierarchical optimal allocation model; The abnormal area topology identification sub module of multi‐objective task resource of low‐voltage station area edge computing is used to identify the abnormal area topology of the current low‐voltage station area; Taking it as input, the multi‐objective task resources of edge computing are allocated, and the multi‐objective task resources allocation method of edge computing in low pressure platform area is realized under the differential evolution algorithm. The experimental results show that the proposed method has good convergence effect, strong distribution ability, relatively gentle increase in energy consumption, and the calculated results are basically consistent with the actual values, with good effectiveness.

Neighbor-based adaptive sparsity orthogonal least square for fluorescence molecular tomography.

Fluorescence molecular tomography (FMT) is a promising imaging modality, which has played a key role in disease progression and treatment response. However, the quality of FMT reconstruction is limited by the strong scattering and inadequate surface measurements, which makes it a highly ill-posed problem. Improving the quality of FMT reconstruction is crucial to meet the actual clinical application requirements. We propose an algorithm, neighbor-based adaptive sparsity orthogonal least square (NASOLS), to improve the quality of FMT reconstruction. The proposed NASOLS does not require sparsity prior information and is designed to efficiently establish a support set using a neighbor expansion strategy based on the orthogonal least squares algorithm. The performance of the algorithm was tested through numerical simulations, physical phantom experiments, and small animal experiments. The results of the experiments demonstrated that the NASOLS significantly improves the reconstruction of images according to indicators, especially for double-target reconstruction. NASOLS can recover the fluorescence target with a good location error according to simulation experiments, phantom experiments and small mice experiments. This method is suitable for sparsity target reconstruction, and it would be applied to early detection of tumors.

Lightweight-YOLOv5s for the camouflaged personnel detection in the woodland

Unmanned aerial vehicles(UAVs) technology and target detection technology are increasingly integrated. However, the target detection networks are cumbersome and complex, and it is hard to directly deploy these networks on the UAVs. To address this problem, a Lightweight-YOLOv5s which can be applied to the UAVs is proposed to detect the camouflaged personnel in the woodland. Depthwise separable convolutions are added to the YOLOv5s for reducing the parameters and computational effort. Then a new channel pruning method based on Batch Normalization(BN) layer scaling factor with adaptive sparsity training is proposed for network compression, which can balance the compression ratio and accuracy of the detection. The pruned network is then fine-tuned to detect the camouflaged personnel. In addition, a special dataset is built for the camouflaged personnel detection in the woodland. The quantitative results on this dataset prove that the proposed Lightweight-YOLOv5s greatly improve the YOLOv5s. Parameters from 7.06M to 1.86M, floating point operations from 16.4G to 9.9G and inference time from 8.16ms to 7.06ms. Besides, mAP of the Lightweight-YOLOv5s is 0.83, which shows the excellent detection performance of the proposed method.