Iterative Block Research Articles

A cascaded FAS-UNet+ framework with iterative optimization strategy for segmentation of organs at risk.

Segmentation of organs at risks (OARs) in the thorax plays a critical role in radiation therapy for lung and esophageal cancer. Although automatic segmentation of OARs has been extensively studied, it remains challenging due to the varying sizes and shapes of organs, as well as the low contrast between the target and background. This paper proposes a cascaded FAS-UNet+ framework, which integrates convolutional neural networks and nonlinear multi-grid theory to solve a modified Mumford-shah model for segmenting OARs. This framework is equipped with an enhanced iteration block, a coarse-to-fine multiscale architecture, an iterative optimization strategy, and a model ensemble technique. The enhanced iteration block aims to extract multiscale features, while the cascade module is used to refine coarse segmentation predictions. The iterative optimization strategy improves the network parameters to avoid unfavorable local minima. An efficient data augmentation method is also developed to train the network, which significantly improves its performance. During the prediction stage, a weighted ensemble technique combines predictions from multiple models to refine the final segmentation. The proposed cascaded FAS-UNet+ framework was evaluated on the SegTHOR dataset, and the results demonstrate significant improvements in Dice score and Hausdorff Distance (HD). The Dice scores were 95.22%, 95.68%, and HD values were 0.1024, and 0.1194 for the segmentations of the aorta and heart in the official unlabeled dataset, respectively. Our code and trained models are available at https://github.com/zhuhui100/C-FASUNet-plus .

Gradient Coding With Iterative Block Leverage Score Sampling

Gradient Coding With Iterative Block Leverage Score Sampling

MsDC-DEQ-Net: Deep Equilibrium Model (DEQ) with Multiscale Dilated Convolution for Image Compressive Sensing (CS)

Compressive sensing (CS) is a technique that enables the recovery of sparse signals using fewer measurements than traditional sampling methods. To address the computational challenges of CS reconstruction, our objective is to develop an interpretable and concise neural network model for reconstructing natural images using CS. We achieve this by mapping one step of the iterative shrinkage thresholding algorithm (ISTA) to a deep network block, representing one iteration of ISTA. To enhance learning ability and incorporate structural diversity, we integrate aggregated residual transformations (ResNeXt) and squeeze-and-excitation mechanisms into the ISTA block. This block serves as a deep equilibrium layer connected to a semi-tensor product network for convenient sampling and providing an initial reconstruction. The resulting model, called MsDC-DEQ-Net, exhibits competitive performance compared to state-of-the-art network-based methods. It significantly reduces storage requirements compared to deep unrolling methods, using only one iteration block instead of multiple iterations. Unlike deep unrolling models, MsDC-DEQ-Net can be iteratively used, gradually improving reconstruction accuracy while considering computation tradeoffs. Additionally, the model benefits from multiscale dilated convolutions, further enhancing performance.

Corrections to “Underground Defects Detection Based on GPR by Fusing Simple Linear Iterative Clustering Phash (SLIC-Phash) and Convolutional Block Attention Module (CBAM)-YOLOv8”

Corrections to “Underground Defects Detection Based on GPR by Fusing Simple Linear Iterative Clustering Phash (SLIC-Phash) and Convolutional Block Attention Module (CBAM)-YOLOv8”

Enhancing Organizing Pneumonia Diagnosis: A Novel Super-token Transformer Approach for Masson Body Segmentation.

In this study, we introduce an innovative deep-learning model architecture aimed at enhancing the accuracy of detecting and classifying organizing pneumonia (OP), a condition characterized by the presence of Masson bodies within the alveolar spaces due to lung injury. The variable morphology of Masson bodies and their resemblance to adjacent pulmonary structures pose significant diagnostic challenges, necessitating a model capable of discerning subtle textural and structural differences. Our model incorporates a novel architecture that integrates advancements in three key areas: Semantic segmentation, texture analysis, and structural feature recognition. We employed a dataset of whole slide imaging from 20 patients, totaling 100 slides of OP, segmented into training, validation, and testing sets to reflect real-world application scenarios. Our approach utilizes a modified multi-head self-attention mechanism combined with ResUNet for semantic segmentation, enhanced by superpixel concepts. This method facilitates the generation of representative token features through iterative super-token blocks, creating high-resolution token maps that leverage local and high-level feature information for improved accuracy. Benefiting from token features and distribution for enhanced texture alignment with fewer false-positives, the super-token transformer (STT) model achieved a mean intersection over union (mIOU) of 72.42%, with a sensitivity of 47.81%, specificity of 99.83%, positive predictive value of 64.03%, and negative predictive value of 99.94%, highlighting superior efficacy in Masson body segmentation in complex cross-tissue analyses. Our team developed an iterative learning model based on the STT approach, emphasizing token features of super token, including texture and distribution, that enable enhanced alignment with the unique textures of Masson bodies to improve sensitivity and mIOU, The development of this STT model presents a significant advancement in the field of medical image analysis for OP that offers a promising avenue for improving diagnostic precision and patient outcomes in pulmonary pathology.

Enhanced synthesis of multiblock copolymers via acid-triggered RAFT polymerization.

The synthesis of multiblock copolymers has emerged as an efficient tool to not only reveal the optimal way to access complex structures and investigate polymer properties but also to ascertain the end-group fidelity of a given polymerization methodology. Although reversible addition-fragmentation chain-transfer (RAFT) polymerization is arguably the most dominant strategy employed, its success is often hampered by the unavoidable and excessive use of radical initiators which results in increased termination and loss of end-group fidelity. In this work, we employ acid in RAFT polymerization to enhance the synthesis of multiblock copolymers. By the addition of a small amount of acid, a 4-fold decrease in the overall required radical initiator concentration was achieved, enabling the synthesis of a range of well-defined multiblock copolymers with various degrees of polymerization (DP) per block. The acid enhances the propagation rate, minimizing the initiator concentration. In all cases, near-quantitative monomer conversion was obtained (>97%) for every iterative block formation step. Notably, and in contrast to conventional RAFT approaches, the tailing to low molecular weight was significantly suppressed and the dispersity was maintained nearly constant (i.e. in most cases Đ = 1.1-1.2), thus indicating minor termination events and side reactions during acid-enhanced synthesis. The possibility to synthesize multiblocks consisting of methacrylates, acrylates, and acrylamides was also demonstrated. This work presents an advancement in the synthesis of well-defined multiblock copolymers and more broadly, RAFT polymers with high end-group fidelity.

Iterative Block Decision Feedback Equalization for the Hybrid Carrier System

Iterative Block Decision Feedback Equalization for the Hybrid Carrier System

Exploiting NOMA and RIS in Integrated Sensing and Communication

A novel integrated sensing and communication (ISAC) system is proposed, where a dual-functional base station is utilized to transmit the superimposed non-orthogonal multiple access (NOMA) communication signal for serving communication users and sensing targets simultaneously. Furthermore, a new reconfigurable intelligent surface (RIS)-aided-sensing structure, where a dedicated RIS is deployed to provide virtual line-of-sight (LoS) links for radar targets, is also proposed to address the significant path loss or blockage of LoS links for the sensing task. Based on this setup, the beampattern gain at the RIS for the radar target is derived and adopted as a sensing metric. The objective of this paper is to maximize the minimum beampattern gain by jointly optimizing active beamforming at the base station (BS), power allocation coefficients among NOMA users and passive beamforming at the RIS. To tackle the non-convexity of the formulated optimization problem, the beampattern gain and constraints are first transformed into more tractable forms. Then, an iterative block coordinate descent (IBCD) algorithm is proposed by employing successive convex approximation (SCA), Schur complement, semidefinite relaxation (SDR) and sequential rank-one constraint relaxation (SRCR) methods. To reduce the complexity of the proposed IBCD algorithm, a low-complexity iterative alternating optimization (IAO) algorithm is proposed. Particularly, the active beamforming is optimized by solving a semidefinite programming (SDP) problem and the closed-form solutions of the power allocation coefficients are derived. Numerical results show that: i) the proposed RIS-NOMA-ISAC system always outperforms the RIS-ISAC system without NOMA in beampattern gain and illumination power; ii) the low-complexity IAO algorithm achieves a comparable performance to that achieved by the IBCD algorithm. iii) high beampattern gain can be achieved by the proposed joint optimization algorithms in underloaded and overloaded communication scenarios.

Single image deraining using scale constraint iterative update network

Rain streaks, which can be viewed as a type of noise, have the potential to destroy the structural integrity of objects within an image, leading to a dramatic degradation in the performance of advanced vision algorithms. Therefore, it is important to develop an effective deraining algorithm. There are three challenges in the current deraining task: First, it is difficult to separate rain streaks from the image background because of the complexity of rain types. Second, most of the existing methods use encoder–decoder-based structures, but the models are designed to be too bulky and inflexible to accommodate complex rain streaks. Third, many models perform the same operation for all rain types, which can reduce the generalizability of the model. To address these challenges, we propose a scale constraint iterative update network which divides the network structure into feature extraction block, multi-scale constraint block, and iterative update block. In the feature extraction block, the deep mixed attention is used to extract complex rain streak features, and the mixed convolution block is used to extract the background details. The multi-scale constraint block aggregates contextual features across different scales, while the Global GateUnit captures long-range dependencies. We followed a coarse-to-fine pipeline. In the iterative update block, the feature maps are updated based on features from different scales, gradually refining the image. The final optimized result is obtained by performing learnable up-sampling. During the whole iteration process, the parameters are shared to reduce the complexity of the model while maintaining the performance. Additionally, We also designed a dynamic inference mechanism, which dynamically selects the number of iterations for different types of rain streaks, effectively enhancing the generalization of the model. We conducted extensive experiments on synthetic and real-world rain datasets, as well as a raindrop dataset. The results of our experiments demonstrate that our method outperforms existing deraining methods in terms of effectiveness and generalization ability.

Secure transmission for IoT wireless energy-carrying communication systems.

The wireless energy-carrying communication method for the Internet of Things (IoT) presents several difficulties for information security such as eavesdropping or data loss. To solve these issues, this paper presents a new secure transmission method for IoT wireless energy-carrying communication systems. In this method, first the secret message is turned into a word, delivered to the intended recipient and unlawful listener, respectively, and the received message is characterized as an entropy function. The message is iteratively solved using the block coordinate descent technique, and for each iteration, a digital baseband signal containing the receiver's secret message symbol and the matching beamforming vector is delivered. By concurrently optimizing the transmit beamforming vector, the noise covariance matrix, and the receiver power allocation factor based on a design that complies with the security rate and energy acquisition limitations for each receiver, the overall system transmit power is reduced. The Lagrangian method is used to solve the secure transmission problem of the communication system based on an iterative block coordinate descent algorithm, as well as to change the nonconvex problem into a convex problem and precisely derive the upper and lower bounds of the original transmission problem. In comparison to the conventional policy transmission scheme, the experimental results demonstrate that the DIPS (Digital Image Processing System) scheme can increase the STP (Signaling Transfer Point) by approximately 34.16 percent in the eavesdropper independent eavesdropping and joint eavesdropping scenarios. The usefulness of the secure transmission strategy for wireless energy-carrying communication systems is confirmed by this investigation.

Fully 3D implementation of the end-to-end deep image prior-based PET image reconstruction using block iterative algorithm

Objective. Deep image prior (DIP) has recently attracted attention owing to its unsupervised positron emission tomography (PET) image reconstruction method, which does not require any prior training dataset. In this paper, we present the first attempt to implement an end-to-end DIP-based fully 3D PET image reconstruction method that incorporates a forward-projection model into a loss function. Approach. A practical implementation of a fully 3D PET image reconstruction could not be performed at present because of a graphics processing unit memory limitation. Consequently, we modify the DIP optimization to a block iteration and sequential learning of an ordered sequence of block sinograms. Furthermore, the relative difference penalty (RDP) term is added to the loss function to enhance the quantitative accuracy of the PET image. Main results. We evaluated our proposed method using Monte Carlo simulation with [18F]FDG PET data of a human brain and a preclinical study on monkey-brain [18F]FDG PET data. The proposed method was compared with the maximum-likelihood expectation maximization (EM), maximum a posteriori EM with RDP, and hybrid DIP-based PET reconstruction methods. The simulation results showed that, compared with other algorithms, the proposed method improved the PET image quality by reducing statistical noise and better preserved the contrast of brain structures and inserted tumors. In the preclinical experiment, finer structures and better contrast recovery were obtained with the proposed method. Significance. The results indicated that the proposed method could produce high-quality images without a prior training dataset. Thus, the proposed method could be a key enabling technology for the straightforward and practical implementation of end-to-end DIP-based fully 3D PET image reconstruction.

Iterative descent group hard thresholding algorithms for block sparsity

In this paper we consider the problem of recovering block-sparse structures in a linear regression context. Penalized mean squared criteria are generally considered in such contexts where ℓ2,1 mixed norm penalty terms is often used as a convex alternative to the ℓ2,0 penalty. Here, we propose an iterative block cyclic descent algorithm approach to address the case of an ℓ2,0 penalty. We prove its convergence and illustrate its potential benefit compared to ℓ2,1 or ℓ2,q (0<q≤1) penalization. We also propose a momentum approach for accelerated convergence and an application to sensor positioning for array processing.

Numerical analysis of the stressed-deformed state of a tubular element under thermal loading

In articles [2-5] solving relations and the block iteration method algorithm for solving linear and nonlinear equations by the semi-analytical finite element method for curvilinear heterogeneous prismatic bodies are implemented. In article [1], a numerical study of the convergence of the solution was performed, a wide range of test problems for bodies with smoothly and abruptly changing physical and geometric characteristics in elastic and elastic-plastic settings were considered. In [6], to confirm the reliability of the results obtained on the basis of the semi-analytical method of finite elements, the effectiveness of the application of this approach for the calculation of curvilinear inhomogeneous prismatic objects is shown. Solving control problems of the theory of elasticity, thermoelasticity, and thermoplasticity, as well as shape change problems, makes it possible to draw a conclusion about the reliability of the results of the research of a selected class of objects based on the developed methodology and implements its application program package.&#x0D; In this paper, using the methodology outlined in the above works, the results of the numerical solution of the problem, which have an applied value, were presented. The stress-strain state of a tubular element with a rectangular cutout under conditions of thermoforce loading was studied. As a rule, solving similar problems is carried out in a flat setting without taking into account the bending load. This approach greatly simplifies the formulation of the problem, but leads to very significant errors in the results. At zero value of the bending load, a good agreement of the planar and spatial solutions is observed. The presence of a bending load leads to deviation of the curves from their initial position. The maximum discrepancy of the results is almost 50%.&#x0D; The analysis of this structure from the standpoint of the spatial problem of thermoplasticity, which ensures taking into account the dependence of the physical and mechanical characteristics of the material on temperature and taking into account the bending load on the section of the cut, allowed us to reveal the real features of its deformation.

MIMO DFRC Signal Design in Signal-Dependent Clutter

This paper deals with the Dual-Function Radar and Communication (DFRC) signal design for a Multiple-Input–Multiple-Output (MIMO) system, considering the presence of signal-dependent clutter. A modulation methodology called Spectral Position Index and Amplitude (SPIA) modulation is proposed, which involves selecting passband and stopband positions and applying amplitude modulation. Signal to Interference plus Noise Ratio (SINR) is maximized to enhance radar detectability. Meanwhile, variable modulus and communication modulation constraints are enforced to ensure compatibility with the current hardware techniques and communication demand, respectively. In addition, the mainlobe width and sidelobe level constraints used to concentrate energy in a specific area of space are enforced. To tackle the resulting nonconvex and NP-hard optimization problem, an Iterative Block Enhancement (IBE) framework that alternately updates each signal in each emitting antenna is exploited to monotonically increase SINR. Each block involves the Dinkelbach’s Iterative Procedure (DIP), Sequential Convex Approximation (SCA) and Alternating Direction Method of Multipliers (ADMM) to obtain a single signal. The computational complexity and convergence of the algorithm are analyzed. Finally, the numerical results highlight the effectiveness of the proposed dual-function scheme in sidelobe signal-dependent clutter.

Low complexity nonlinear detection for multiuser hybrid MIMO systems and performance analysis

This paper proposes an analytical framework and a system of distortion-aware receiver structures for single-carrier uplink hybrid beamforming-based multiple-input-multiple-output (MIMO) channels. Proposed single-user processing units cooperate at the base station (BS) in an iterative manner for multi-user symbol detection under hardware impairments. Firstly, in the proposed system, an iterative nonlinear interference cancellation (nIC) based on feedforward neural network (NN) modeling is developed to eliminate the nonlinear distortion effects of power amplifiers (PAs). Furthermore, depending on the fading pattern of the instantaneous channel, it is analytically shown that a large gain may be applied to the distortion signal during the equalization stage, which yields distortion amplification causing a significant decrease in the signal-to-distortion-plus-noise ratio (SDNR). A reduced complexity distortion aware detector, based on a bank of fractionally delayed iterative block decision feedback equalization (IB-DFE) receivers, is introduced to adjust the combiner weights for fractionally delayed IB-DFE outputs so that distortion power is minimized before detection. Consequently, multi-user detection capability is enhanced considerably. Secondly, an asymptotic SDNR analysis is performed. The theoretical analysis, verified via numerical evaluations, clearly shows that distortion amplification limits the achievable SDNR at the BS, and the proposed reduced complexity multi-user receiver architecture improves the BER performance by effectively mitigating this effect.

IRS Backscatter Enhancing Against Jamming and Eavesdropping Attacks

This paper proposes a novel intelligent reflecting surface (IRS) backscatter enhancing strategy to secure multi-input multi-output (MIMO) transmission in the presence of an eavesdropper and a malicious jammer. To be specific, the IRS is employed to backscatter the jamming signal into the desired signal to enhance the reception of the user. Utilizing this strategy, we maximize the system secrecy rate by jointly designing the reflection coefficients of IRS and active beamforming at the base station (BS). To efficiently handle this non-convex optimization problem, we adopt an iterative block coordinate descent (BCD)-based algorithm, where the active beamforming is optimized through the Lagrange multiplier method and the backscatter coefficient matrix of IRS is optimized via the majorization-minimization (MM) method. Then, we examine the robustness of the proposed scheme when considering channel estimation errors. Extensive simulations confirm the secrecy performance gains achieved by our proposed strategy and verify its superiority compared to conventional IRS-based physical layer security (PLS) strategy, IRS backscatter-aided anti-eavesdropping strategy and other baselines.

Semantic-agnostic progressive subtractive network for image manipulation detection and localization

In this paper, we propose a new detection and localization framework capable of detecting suspicious forgeries using the Semantic-Agnostic Progressive Subtractive Network (SAPS-Net). Our approach is based on the key observation that fluctuations in image content severely interfere with the capture of general manipulations by existing convolutional architecture. Distinct from the aggregation attention employed by traditional methods, we design the Semantic-Agnostic Manipulation Attention (SAMA) based on subtractive operation for mitigating the effect of rich image semantics on manipulation extraction. Initially, the Multi-Scale feature Iterative Fusion Block (MSIFB) and Multi-Kernel feature Fusion Residual Block (MKFRB) are designed to iteratively crawl potential semantic associations of different hierarchical feature mappings. Then, we further devise the subtractive operation to effectively remove the semantic associations as distractors and promote the network to adaptively learn general forgery. Notably, these semantic associations based on image content may be fundamentally different from the manipulation traces that alter the internal patterns of images. By progressively utilizing SAMAs, the network remains robust to image content manipulation with rich semantics. Extensive experiments on six challenge datasets show that our approach has more than 3.03% pixel-level AUC gains and 3.70% image-level AUC gains in cross-dataset scenarios compared to state-of-the-art methods, especially on the IMD20 dataset (pixel-level AUC: 0.859) and Wild dataset (pixel-level AUC: 0.821) with realistic scenarios.

Improved local truncation schemes for the higher-order tensor renormalization group method

The higher-order tensor renormalization group is a tensor-network method providing estimates for the partition function and thermodynamical observables of classical and quantum systems in thermal equilibrium. At every step of the iterative blocking procedure, the coarse-grid tensor is truncated to keep the tensor dimension under control. For a consistent tensor blocking procedure, it is crucial that the forward and backward tensor modes are projected on the same lower-dimensional subspaces. In this paper we present two methods, the SuperQ and the iterative SuperQ method, to construct tensor truncations that reduce or even minimize the local approximation errors, while satisfying this constraint.

DRFENet: An Improved Deep Learning Neural Network via Dilated Skip Convolution for Image Denoising Application

Deep learning technology dominates current research in image denoising. However, denoising performance is limited by target noise feature loss from information propagation in association with the depth of the network. This paper proposes a Dense Residual Feature Extraction Network (DRFENet) combined with a Dense Enhancement Block (DEB), a Residual Dilated Block (RDB), a Feature Enhancement Block (FEB), and a Simultaneous Iterative Reconstruction Block (SIRB). The DEB uses our proposed interval transmission strategy to enhance the extraction of noise features in the initial stage of the network. The RDB module uses a combination strategy of concatenated dilated convolution and a skip connection, and the local features are amplified through different perceptual dimensions. The FEB enhances local feature information. The SIRB uses an attention block to learn the noise distribution while using residual learning (RL) technology to reconstruct a denoised image. The combination strategy in DRFENet makes the neural network deeper to obtain higher fine-grained image information. We respectively examined the performance of DRFENet in gray image denoising on datasets BSD68 and SET12 and color image denoising on datasets McMaster, Kodak24, and CBSD68. The experimental results showed that the denoising accuracy of DRFENet is better than most existing image-denoising methods under PSNR and SSIM evaluation indicators.

Cache-oblivious Hilbert Curve-based Blocking Scheme for Matrix Transposition

This article presents a fast SIMD Hilbert space-filling curve generator, which supports a new cache-oblivious blocking-scheme technique applied to the out-of-place transposition of general matrices. Matrix operations found in high performance computing libraries are usually parameterized based on host microprocessor specifications to minimize data movement within the different levels of memory hierarchy. The performance of cache-oblivious algorithms does not rely on such parameterizations. This type of algorithm provides an elegant and portable solution to address the lack of standardization in modern-day processors. Our solution consists in an iterative blocking scheme that takes advantage of the locality-preserving properties of Hilbert space-filling curves to minimize data movement in any memory hierarchy. This scheme traverses the input matrix, in O(nm) time and space, improving the behavior of matrix algorithms that inherently present poor memory locality. The application of this technique to the problem of out-of-place matrix transposition achieved competitive results when compared to state-of-the-art approaches. The performance of our solution surpassed Intel MKL version after employing standard software prefetching techniques.