Gradient Information Research Articles

MDD-DETR: Lightweight Detection Algorithm for Printed Circuit Board Minor Defects

PCBs (printed circuit boards) are the core components of modern electronic devices, and inspecting them for defects will have a direct impact on the performance, reliability and cost of the product. However, the performance of current detection algorithms in identifying minor PCB defects (e.g., mouse bite and spur) still requires improvement. This paper presents the MDD-DETR algorithm for detecting minor defects in PCBs. The backbone network, MDDNet, is used to efficiently extract features while significantly reducing the number of parameters. Simultaneously, the HiLo attention mechanism captures both high- and low-frequency features, transmitting a broader range of gradient information to the neck. Additionally, the proposed SOEP neck network effectively fuses scale features, particularly those rich in small targets, while INM-IoU loss function optimization enables more effective distinction between defects and background, further improving detection accuracy. Experimental results on the PCB_DATASET show that MDD-DETR achieves a 99.3% mAP, outperforming RT-DETR by 2.0% and reducing parameters by 32.3%, thus effectively addressing the challenges of detecting minor PCB defects.

Group Forward–Backward Orthogonal Matching Pursuit for General Convex Smooth Functions

This paper introduces the Group Forward–Backward Orthogonal Matching Pursuit (Group-FoBa-OMP) algorithm, a novel approach for sparse feature selection. The core innovations of this algorithm include (1) an integrated backward elimination process to correct earlier misidentified groups; (2) a versatile convex smooth model that generalizes previous research; (3) the strategic use of gradient information to expedite the group selection phase; and (4) a theoretical validation of its performance in terms of support set recovery, variable estimation accuracy, and objective function optimization. These advancements are supported by experimental evidence from both synthetic and real-world data, demonstrating the algorithm’s effectiveness.

A lightweight deep-learning model for parasite egg detection in microscopy images.

Intestinal parasitic infections are still a serious public health problem in developing countries, and the diagnosis of parasitic infections requires the first step of parasite/egg detection of samples. Automated detection can eliminate the dependence on professionals, but the current detection algorithms require large computational resources, which increases the lower limit of automated detection. Therefore, we have designed a lightweight deep-learning model, YAC-Net, to achieve rapid and accurate detection of parasitic eggs and reduce the cost of automation. This paper uses the ICIP 2022 Challenge dataset for experiments, and the experiments are conducted using fivefold cross-validation. The YOLOv5n model is used as the baseline model, and then two improvements are made to the baseline model based on the specificity of the egg data. First, the neck of the YOLOv5n is modified to from a feature pyramid network (FPN) to an asymptotic feature pyramid network (AFPN) structure. Different from the FPN structure, which mainly integrates semantic feature information at adjacent levels, the hierarchical and asymptotic aggregation structure of AFPN can fully fuse the spatial contextual information of egg images, and its adaptive spatial feature fusion mode can help the model select beneficial feature and ignore redundant information, thereby reducing computational complexity and improving detection performance. Second, the C3 module of the backbone of the YOLOv5n is modified to a C2f module, which can enrich gradient information, improving the feature extraction capability of the backbone. Moreover, ablation studies are designed by us to verify the effectiveness of the AFPN and C2f modules in the process of model lightweighting. The experimental results show that compared with YOLOv5n, YAC-Net improves precision by 1.1%, recall by 2.8%, the F1 score by 0.0195, and mAP_0.5 by 0.0271 and reduces the parameters by one-fifth. Compared with some state-of-the-art detection methods, YAC-Net achieves the best performance in precision, F1 score, mAP_0.5, and parameters. The precision, recall, F1 score, mAP_0.5, and parameters of our method on the test set are 97.8%, 97.7%, 0.9773, 0.9913, and 1,924,302, respectively. Compared with the baseline model, YAC-Net optimizes the model structure and simplifies the parameters while ensuring the detection performance. It helps to reduce the equipment requirements for performing automated detection and can be used to realize the automatic detection of parasite eggs under microscope images.

An Objective Evaluation Method for Image Sharpness Under Different Illumination Imaging Conditions

Blurriness is troublesome in digital images when captured under different illumination imaging conditions. To obtain an accurate blurred image quality assessment (IQA), a machine learning-based objective evaluation method for image sharpness under different illumination imaging conditions is proposed. In this method, the visual saliency, color difference, and gradient information are selected as the image features, and the relevant feature information of these three aspects is extracted from the image as the feature value for the blurred image evaluation under different illumination imaging conditions. Then, a particle swarm optimization-based general regression neural network (PSO-GRNN) is established to train the above extracted feature values, and the final blurred image evaluation result is determined. The proposed method was validated based on three databases, i.e., BID, CID2013, and CLIVE, which contain real blurred images under different illumination imaging conditions. The experimental results showed that the proposed method has good performance in evaluating the quality of images under different imaging conditions.

Probabilistic geophysical inversion of complex resistivity measurements using the Hamiltonian Monte Carlo method

Summary In this work, we introduce the probabilistic inversion of tomographic complex resistivity (CR) measurements using the Hamiltonian Monte Carlo (HMC) method. The posterior model distribution on which our approach operates accounts for the underlying complex-valued nature of the CR imaging problem accurately by including the individual errors of the measured impedance magnitude and phase, allowing for the application of independent regularization on the inferred subsurface conductivity magnitude and phase, and incorporating the effects of cross-sensitivities. As the tomographic CR inverse problem is non-linear, of high dimension and features strong correlations between model parameters, efficiently sampling from the posterior model distribution is challenging. To meet this challenge we use HMC, a Markov-chain Monte Carlo method that incorporates gradient information to achieve efficient model updates. To maximize the benefit of a given number of forward calculations, we use the No-U-Turn sampler (NUTS) as a variant of HMC. We demonstrate the probabilistic inversion approach on a synthetic CR tomography measurement. The NUTS succeeds in creating a sample of the posterior model distribution that provides us with the ability to analyze correlations between model parameters and to calculate statistical estimators of interest, such as the mean model and the covariance matrix. Our results provide a strong basis for the characterization of the posterior model distribution and uncertainty quantification in the context of the tomographic CR inverse problem.

Hierarchical Fusion of Infrared and Visible Images Based on Channel Attention Mechanism and Generative Adversarial Networks.

In order to solve the problem that existing visible and infrared image fusion methods rely only on the original local or global information representation, which has the problem of edge blurring and non-protrusion of salient targets, this paper proposes a layered fusion method based on channel attention mechanism and improved Generative Adversarial Network (HFCA_GAN). Firstly, the infrared image and visible image are decomposed into a base layer and fine layer, respectively, by a guiding filter. Secondly, the visible light base layer is fused with the infrared image base layer by histogram mapping enhancement to improve the contour effect. Thirdly, the improved GAN algorithm is used to fuse the infrared and visible image refinement layer, and the depth transferable module and guided fusion network are added to enrich the detailed information of the fused image. Finally, the multilayer convolutional fusion network with channel attention mechanism is used to correlate the local information of the layered fusion image, and the final fusion image containing contour gradient information and useful details is obtained. TNO and RoadSence datasets are selected for training and testing. The results show that the proposed algorithm retains the global structure features of multilayer images and has obvious advantages in fusion performance, model generalization and computational efficiency.

Distributed Optimization on Matrix‐Weighted Networks

ABSTRACTThis article is intended to tackle the optimization problems for continuous‐time first‐order and second‐order multi‐agent systems (MASs) operating over matrix‐weighted networks. A matrix‐weighted network serves as a powerful framework to model the interdependence among agents' multidimensional states, providing an effective approach to analyze smart grids, intelligent transportation systems, and so forth. Our optimization objective is to facilitate the convergence of all agents toward the optimal value of a global cost function, which is formed by a sum of local cost functions. To achieve this goal, distributed optimization algorithms based on Hessian matrix and gradient information are constructed. Additionally, an edge‐based event‐triggered mechanism is utilized to avoid communicating with all neighbors at the time of event triggering. It is proved that this mechanism theoretically excludes Zeno behavior. The results show that the proposed algorithms ensure that the agents can achieve the optimization goal while reducing energy consumption. Finally, an application is presented to substantiate the theoretical results.

Privacy‐Preserving Optimization Algorithm for Distributed Energy Management Over Time‐Varying Graphs: A State Decomposition Method

ABSTRACTThe rapid advancements of intelligent technologies have brought about the potential vulnerability of confidential gradient information linked to cost functions when solving distributed optimization and its related problems. Within the context of distributed energy management, safeguarding such private information has risen to paramount importance. This article investigates a distributed energy management problem (DEMP) to minimize cost while simultaneously satisfying multiple local constraints and protecting the private gradient information of the cost function. To this end, a new privacy‐preserving distributed optimization algorithm under the framework of gradient tracking over time‐varying graphs is proposed for solving the DEMP. Specifically, the auxiliary variables are designed for each node in the algorithm to update the gradient while the original state variables are responsible for the interaction with original neighbors and auxiliary variables. Consequently, the devised algorithm can protect the confidentiality of private cost gradient information, even in the presence of eavesdroppers within the network. In contrast to the homomorphic encryption, signal masking method, and some other algorithms without utilizing the state decomposition, the designed algorithm does not require extra information or computing resources. Moreover, it is proven that the designed algorithm could theoretically converge to the exact optimum of the DEMP at a rate of under some mild assumptions.

Vision-based target localization and online error correction for high-precision robotic drilling

Abstract This article presents a detailed examination of circular target localization techniques for measuring robot pose and performing online pose correction. The investigated target localization methods include centroiding, ellipse fitting with point data and gradient information, and ellipse fitting methods with augmented and corrected input data. The performance of each method is evaluated in terms of accuracy and precision of measurements through experimental comparison with a laser tracker. This study provides technical and practical insights for selecting an appropriate target localization method in robotic applications. It also introduces a vision-based solution for robot relative error correction, comprising the calibration procedure and a closed-loop control with a proportional–integral-derivative controller for pose correction. Results show enhanced accuracy in robot positioning relative to workpiece, highlighting the effectiveness of the proposed solution in robotic drilling applications.

Solving higher dimensional expensive black box global optimization problems using sparse directional search on surrogates

We present a new algorithm Directional Optimization Search with Surrogate (DOSS), for optimizing problems with box constraints and a computationally expensive black-box objective function. DOSS is a radial basis function (RBF) based method that mainly focuses on higher dimensional and computationally expensive objective functions that can be multimodal. DOSS introduces three new techniques not previously used in earlier RBF algorithms, including using a combination of the coordinates knowledge level, fewer initial sampling points, and the surrogate’s gradient information. Numerical results on a test set including 14 test problems with 36, 48, and 60 dimensions show that DOSS outperforms two recently published algorithms RBFOpt and TuRBO, and earlier RBF algorithms such as DYCORS. TuRBO is a Gaussian process based optimization algorithm, which outperformed earlier state-of-the-art methods. DOSS algorithm also has a good performance on real-world optimization problems, including robot pushing and rover trajectory planning problems. Almost sure convergence for the DOSS algorithm is also proven in this paper. An implementation of DOSS is available at https://doi.org/10.5281/zenodo.13731558.

An adaptive helper and equivalent objective evolution strategy for constrained optimization

The matrix adaptation evolution strategy is a simplified covariance matrix adaptation evolution strategy with reduced computational cost. Using it as a search engine, several algorithms have been recently proposed for constrained optimization and have shown excellent performance. However, these algorithms require the simultaneous application of multiple techniques to handle constraints, and also require gradient information. This makes them inappropriate for handling non-differentiable functions. This paper proposes a new matrix adaption evolutionary strategy for constrained optimization using helper and equivalent objectives. The method optimizes two objectives but with no need for special handling of infeasible solutions and without gradient information. A new mechanism is designed to adaptively adjust the weights of the two objectives according to the convergence rate. The efficacy of the proposed algorithm is evaluated using computational experiments on the IEEE CEC 2017 Constrained Optimization Competition benchmarks. Experimental results demonstrate that it outperforms current state-of-the-art evolutionary algorithms. Furthermore, this paper provides sufficient conditions for the convergence of helper and equivalent objective evolutionary algorithms and proves that using helper objectives can reduce the likelihood of premature convergence.

Integrating Kalman filter noise residue into U-Net for robust image denoising: the KU-Net model

In low-level image processing, where the main goal is to reconstruct a clean image from a noise-corrupted version, image denoising continues to be a critical challenge. Although recent developments have led to the introduction of complex architectures to improve denoising performance, these models frequently have more parameters and higher computational demands. Here, we propose a new, simplified architecture called KU-Net, which is intended to achieve better denoising performance while requiring less complexity. KU-Net is an extension of the basic U-Net architecture that incorporates gradient information and noise residue from a Kalman filter. The network’s ability to learn is improved by this deliberate incorporation, which also helps it better preserve minute details in the denoised images. Without using Image augmentation, the proposed model is trained on a limited dataset to show its resilience in restricted training settings. Three essential inputs are processed by the architecture: gradient estimations, the predicted noisy image, and the original noisy grey image. These inputs work together to steer the U-Net’s encoding and decoding stages to generate high-quality denoised outputs. According to our experimental results, KU-Net performs better than traditional models, as demonstrated by its superiority on common metrics like the Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR). KU-Net notably attains a PSNR of 26.60 dB at a noise level of 50, highlighting its efficacy and potential for more widespread use in image denoising.

A lightweight object detection approach based on edge computing for mining industry

AbstractCoal Mining enterprises deploy numerous monitoring devices to ensure safe and efficient production using target detection technologies. However, deploying deep detection models on edge devices poses challenges due to high computational loads, impacting detection speed and accuracy. A mining target detection dataset has been created to address these issues, featuring key targets in coal mining scenes such as miners, safety helmets, and coal gangue. A model is proposed to improve real‐time performance for edge mining detection tasks. Detection performance is enhanced by incorporating a Pixel‐wise Normalization Spatial Attention Module (PN‐SAM) into the MobileNet‐v3 bneck structure and replacing the h‐swish activation function with Mish, providing more prosperous gradient information transfer. The proposed model, YOLO‐v4‐LSAM, shows a 3.2% mAP improvement on the VOC2012 dataset and a 2.4% improvement on the mining target dataset compared to YOLO‐v4‐Tiny, demonstrating its effectiveness in mining environments. These enhancements enable more accurate and efficient detection in resource‐constrained edge environments, contributing to safer and more reliable monitoring in coal mining operations.

Unwrap Intractable C‐Band Coseismic Interferograms: An Improved SNAPHU Method With Range Offset Gradients as Prior Information

AbstractC‐band Interferometric Synthetic Aperture Radar (InSAR) data are widely used to map coseismic deformation. However, phase unwrapping errors are commonly distributed near faults owing to decorrelation and steep phase gradients from short radar wavelengths. Here, we propose an improved SNAPHU phase‐unwrapping algorithm that considers the prior information of the range offset gradients (P‐SNAPHU) to overcome the constraints imposed by the phase continuity assumption. P‐SNAPHU exploits median filtering of homogeneous pixels for initial denoising of range offset and then refines range offset gradients divisionally through saliency extraction. The derived gradients are used to estimate the expected values of the cost functions for the low‐coherence fringes. The synthetic experiments show significant improvements in the phase‐unwrapping accuracy of the P‐SNAPHU method compared with classical unwrapping methods. We apply the P‐SNAPHU method to unwrap Sentinel‐1 coseismic interferograms of three large (Mw > 6.5) strike‐slip earthquake events that the existing classical methods could not successfully unwrap. In the comparison of the unwrapped interferograms with the external global navigation satellite system (GNSS) displacements and those from the classical methods, we find that P‐SNAPHU significantly reduces the phase unwrapping errors with the mean absolute error of 7.2, 2.3, and 1.8 cm for the 2023 Kahramanmaraş earthquake doublet, the 2016 Kumamoto earthquake, and the 2019 Ridgecrest earthquakes, respectively. Based on the unwrapped results derived from P‐SNAPHU, an estimate is made regarding the shallow slip deficit of the 2023 Kahramanmaraş earthquake doublet, which is approximately 7%. Therefore, P‐SNAPHU is useful for developing and applying C‐band InSAR data for large earthquakes and volcanic activity.

Integrating small data and shape prior knowledge with gradient-enhanced Kriging through adaptive knowledge sampling

Integrating prior knowledge into surrogate models constitutes an advanced approach to tackling the challenges posed by small data. The existing gradient-enhanced Kriging (GEK) method can enhance accuracy by incorporating gradient points of shape prior knowledge. Nonetheless, our findings indicate that the strategy employed for setting gradient points significantly impacts accuracy, even when the number of gradient points remains constant. To enhance the efficient utilization of gradient information, we propose a novel Adaptive Knowledge Sampling (AKS) strategy with an innovative acquisition function that balances local exploitation and global exploration, effectively extracting gradient points from shape prior knowledge. The acquisition function consists of three parts: (1) The Local Information Filling Criterion (LIFC), designed to mitigate model error; (2) The Global Information Filling Criterion (GIFC), aimed at reducing model uncertainty in data-sparse areas; and (3) The Minimum Distance Constraint (MDC), implemented to prevent excessive clustering of gradient points. To strike a balance between model accuracy and computational cost, an adaptive stopping condition is introduced to regulate the number of gradient points sampled. The impact of hyperparameters in the AKS strategy was analyzed in detail, and the method’s performance was compared to existing approaches using six benchmark functions and a missile aerodynamic prediction case. The results demonstrate that AKS-GEK offers higher prediction accuracy and robustness when integrating small data with shape prior knowledge.

New Formula on the Conjugate Gradient Method for Unconstrained Optimization and its Application

In this paper, we have presented a new formula by applying the conjugacy condition for the second-order Taylor expansion. In comparison with classic conjugate gradient methods, the new formula uses both available gradient and function value information. The formula's global convergence findings are described. Numerical results demonstrate that this strategy is effective and its application.

Texture Analysis and Classification using Local Binary Patterns and Statistical Features

Texture analysis and classification are crucial in many applications such as medical applications, satellite imagery analysis, and so on. This paper presents a new technique that incorporates the LBP with the HOG to improve the texture analysis and classification. LBP is famous for finding out the local texture descriptors by comparing the pixel intensities it deals with and can challenge light variations and image transformations. On the other hand, there is HOG which emphasizes edge and gradient information to detect the orientation and shape of a texture in a given image. While LBP describes the local micro-patterns HOG gives the perspective of the global gradient orientation. The combined use of local and global texture information is helpful in the presented problem when prioritizing the recognition of complex texture patterns that cannot be deciphered by a single algorithm. To demonstrate the efficiency of the proposed hybrid method, several experiments are performed on several texture databases. According to the findings, the proposed LBP-HOG strategy proves more beneficial than basic LBP and HOG techniques concerning the classification rate and computing time. The combination method shows improved performance in terms of agreement with the reference of fine and coarse level of texture descriptions along with providing large-scale description of the texture which results in the improved discriminatory power of the texture classes.

Quantitative method for the probability of structural damage based on moment theory

In the context of uncertainty in the inverse problem of damage identification, this study proposes a moment theory based probabilistic damage identification (MbPDI) method. Noise errors in the identification process are treated as uncertain parameters, while structural stiffness parameters are treated as functions of noise errors. A limit state function for damage identification is defined, and its probability is computed. Utilizing the concept of moment theory, the expansion series is performed for the limit state function around the most probable point of failure, with gradient information derived using sensitivity matrices. Based on the gradient information and uncertainty inputs, damage probabilities for various elements can be obtained. Additionally, this paper addresses the calculation of structural damage probabilities under the non-normal distribution of random variables by transforming non-normal variables into equivalent normal variables. The proposed probability index and expected index of structural damage in the probabilistic damage identification method has a clear physical meaning, and the calculation has high accuracy. The proposed method is validated through a mathematical example and a numerical simulation. Meanwhile, the influence of damage extent, noise level, and modal order on identification results are analyzed. Experimental validation of the method is also presented.

MFR-Net: A multi-feature fusion phase unwrapping method for different speckle noises

Phase unwrapping is a crucial step in laser interferometry for obtaining accurate physical measurement of object. To reduce the impact of speckle noise on wrapped phase during actual measurement and improve the subsequent measurement accuracy, a multi-feature fusion phase unwrapping method for different speckle noises named MFR-Net is proposed in this paper. The network is composed of a front-end multi-module filter processing layer and a back-end network with dilated convolution and coordinate attention mechanism. By reducing random phase differences introduced by different levels of noise, the network enhances its capability to extract spatial features such as gradient information between pixels under speckle noise, so that it successfully unwraps the wrapped phase with different speckle noises and accurately recovers the real phase information. Taking the wrapped phases with multiplicative speckle noise and additive random noise as dataset, the results of ablation and comparison experiments show that the MFR-Net has superior unwrapped results. Under three different levels of speckle noise, the average values of MSE, SSIM, PSNR and AU for MFR-Net are at least improved by 84.80 %, 10.99 %, 29.00 % and 7.72 %, respectively, compared to PDVQG, TIE, DLPU and VURNet algorithms. When the standard deviation of speckle noise varies continuously in the range [1.0, 2.0], the average values of four indexes reaches 0.12 rad, 0.91, 31.80 dB and 99.96 %, respectively, indicating the stronger robustness of MFR-Net. In addition, the phase step unwrapping is performed by MFR-Net. Compared to DLPU and VURNet, MFR-Net method reduced MSE by 80 % and 87.35 %, respectively, demonstrating the outstanding generalization capability. The proposed MFR-Net can realize the correct phase unwrapping under different speckle noises. It may be applied in laser interferometry applications such as digital holography and interferometric synthetic aperture radar.

A structurally informed data assimilation approach for nonlinear partial differential equations

Ensemble-based Kalman filtering data assimilation is often used to combine available observations with numerical simulations to obtain statistically accurate and reliable state representations in dynamical systems. However, it is well known that the commonly used Gaussian distribution assumption introduces biases for state variables that admit discontinuous profiles, which are prevalent in nonlinear partial differential equations. This investigation designs a new structurally informed prior that exploits statistical information from the simulated state variables. In particular, based on the second moment information of the state variable gradient, we construct a new weighting matrix for the numerical simulation contribution in the data assimilation objective function. This replaces the typical prior covariance matrix used for this purpose. We further adapt our weighting matrix to include information in discontinuity regions via a clustering technique. Our numerical experiments demonstrate that this new approach yields more accurate estimates than those obtained using standard ensemble-based Kalman filtering on shallow water equations, even when it is enhanced with inflation and localization techniques.