Irregular Regions Research Articles

FusionGCN: Multi-focus image fusion using superpixel features generation GCN and pixel-level feature reconstruction CNN

In recent years, convolutional neural networks have demonstrated significant advancements in the domain of computer vision, effectively addressing numerous previously challenging issues. An increasing number of researchers are focusing their investigations on this field, proposing innovative network architectures. However, many existing networks necessitate intricate module designs and a substantial number of parameters to achieve satisfactory fusion outcomes, which poses challenges for lightweight devices with constrained computational resources. To mitigate this concern, the present study introduces a novel methodology that integrates block segmentation with pixel optimization. Specifically, we initially employ graph convolutional networks to execute flexible convolutions on large-scale, irregular regions generated through superpixel clustering, thereby achieving coarse segmentation at the block level. Subsequently, we utilize parallel lightweight convolutional networks to provide pixel-level guidance, ultimately resulting in a more accurate decision map. Furthermore, to leverage the strengths of both networks and facilitate the optimization of feature generation from the graph convolutional network for non-Euclidean data, we meticulously design a superpixel-based graph decoder alongside a pixel-based convolutional neural network extraction block to enhance feature acquisition and propagation. In comparison to numerous state-of-the-art methodologies, our approach demonstrates commendable competitiveness in both qualitative and quantitative analyses, as well as in efficiency evaluations. The code can be downloaded at https://github.com/ouyangbaicai/FusionGCN.

Monitoring of Ionospheric Variability Using the Low lAtitude Long Range Ionospheric raDar (LARID): Capabilities, Advantages and Limitations

AbstractA Low lAtitude long Range Ionospheric raDar (LARID), which was built recently at Dongfang (19.2°N, 108.8°E, magnetic latitude 13.9°), Hainan Is., China, is employed to study the ionospheric variability over a large region. The LARID consists of two high frequency (HF) coherent backscatter radars, looking toward east and west, respectively, with a field‐of‐view covering a wide longitude from Africa to Pacific. Here we report some results by the LARID, with main focus on its capabilities, advantages and limitations in monitoring ionospheric variability. The results show that the LARID can detect various ionospheric variations at low latitudes, including (a) sequentially generated equatorial plasma bubbles over a longitude span of ∼80°, (b) near‐range E region irregularities drifting across more than 1,000 km, (c) ionospheric background information retrieved from ground scatters, (d) traveling ionospheric disturbances, and (e) sporadic E structures reflecting HF radio waves at low elevation angles. It is demonstrated that the LARID provides an important tool for investigating different types of ionospheric variability over a broad region, especially over the Indian Ocean and west Pacific, and will contribute significantly to the regional ionospheric weather forecasting.

Entropy‐Based Assessment of Biodiversity, With Application to Ants' Nests Data

ABSTRACTThe present work takes an innovative point of view in the study of a marked point pattern dataset of two ants' species, over an irregular region with a spatial covariate. The approach, based on entropy measures, brings new insights to the interpretation of the behavior of such ants' nesting habits, which can be exploited in the general area of biodiversity evaluation. We make proper use of descriptive entropy measures and inferential approaches, performing a comparative study of their uncertainty and interpretability in the context of biodiversity. For the first time in the study of these ants' nests data, all the available information is fully exploited, and interpretation guidelines are given for assessing both the observed and the latent biodiversity of the system, with a simultaneous consideration of spatial structures, covariate and interpoint interaction effects. Computations are supported by the new release of our R package SpatEntropy.

Irregular adaptive refinement network for semantic segmentation of high-resolution remote sensing images

The semantic segmentation of high-resolution remote sensing images has broad application prospects in land cover classification, road extraction, urban planning and other fields. To alleviate the influence of the large data volume and complex background of high-resolution remote sensing images, the usual approach is to downsample them or cut them into small pieces for separate processing. Even if combining the two methods can improve the segmentation efficiency, it ignores the differences between the middle and the edge regions. Therefore, we consider the characteristics of large and irregular region in high-resolution remote sensing images, and then propose an irregular adaptive refinement network to locate the irregular edge region, which will be refined adaptively. Specifically, on the basis of effectively preserving the global and local information, the prediction confidence is calculated to locate pixel points that are poorly segmented, so as to form irregular regions requiring further refinement, avoiding to ‘over-refine’ intermediate region with good segmentation. At the same time, considering the difference in the refinement degree of different pixels, we propose to adaptively integrate the local segmentation results to refine the coarse segmentation results. In addition, in order to bridge the gap between the two extreme ends of the scale space, we introduce a multi-scale framework. Finally, we conducted experiments on the Deepglobe dataset showing that the proposed method performed 0.37% to 0.87% better than the previous state-of-the-art methods in terms of mean Intersection over Union (mIoU).

Microstructure and wear resistance of laser cladding AlCoCrFeNiSiB high-entropy alloy with high boron content

In this study, a wear-resistant coating of high boron content Al1.5CoCr2Fe1.5NiSi0.5B2 high-entropy alloy (HEA) was prepared on X65 pipeline steel by laser cladding. The coating underwent microhardness testing, wear performance testing, and analyses including scanning electron microscope (SEM), transmission electron microscope (TEM), and X-ray diffraction (XRD). The results revealed a dual-phase structure of body-centered cube (BCC) and face-entered cube (FCC) in the coating, with the presence of Fe1.1Cr0.9B0.9 phase distributed within the BCC. Utilizing high-resolution transmission electron microscopy (HRTEM) characterization, irregular atomic arrangement regions within the BCC structure were observed. Through the calculation of the α2 and ε parameters of the coating, the degree of lattice distortion in the BCC and FCC phases was quantitatively described. The results suggested that the addition of a substantial amount of boron could strengthen the lattice distortion effect, leading to improved hardness and wear resistance of the coating. The average microhardness of the coating was 912 HV, about 5 times higher than X65 substrate, improved by more than 10 % compared with other AlCoCrFeNi-based high-entropy alloys and B-containing high-entropy alloys. The wear rate was 4.78 × 10−6 mm/N·m, wear performance is nearly 10 times higher than other AlCoCrFeNi HEA without boron, 2 times higher than HEA with born. The wear mechanism of the coating was identified as abrasive and oxidative wear.

Estimation of Fractal Dimension and Segmentation of Body Regions for Deep Learning-Based Gender Recognition

There are few studies utilizing only IR cameras for long-distance gender recognition, and they have shown low recognition performance due to their lack of color and texture information in IR images with a complex background. Therefore, a rough body segmentation-based gender recognition network (RBSG-Net) is proposed, with enhanced gender recognition performance achieved by emphasizing the silhouette of a person through a body segmentation network. Anthropometric loss for the segmentation network and an adaptive body attention module are also proposed, which effectively integrate the segmentation and classification networks. To enhance the analytic capabilities of the proposed framework, fractal dimension estimation was introduced into the system to gain insights into the complexity and irregularity of the body region, thereby predicting the accuracy of body segmentation. For experiments, near-infrared images from the Sun Yat-sen University multiple modality re-identification version 1 (SYSU-MM01) dataset and thermal images from the Dongguk body-based gender version 2 (DBGender-DB2) database were used. The equal error rates of gender recognition by the proposed model were 4.320% and 8.303% for these two databases, respectively, surpassing state-of-the-art methods.

Intra and Inter-Rater Variability in the Interpretation of White Blood Cell Scintigraphy of Hip and Knee Prostheses.

Background: White blood cell (WBC) scintigraphy plays a major role in the diagnostic approach to periprosthetic infections. Although the procedure has been standardized by the publication of several guidelines, the interpretation of this technique may be susceptible to intra and inter-variability. We aimed to assess the reproducibility of interpretation between nuclear medicine physicians and by the same physician and to demonstrate that Cohen's coefficient is more unstable than Gwet's coefficient, as the latter is influenced by the prevalence rates. Methods: We enrolled 59 patients who performed a Technetium-99m WBC (99mTc-WBC) scintigraphy for suspected hip or knee prosthesis infection. Three physicians, blinded to all patient clinical data, performed two image readings. Each WBC study was assessed both visually and semi-quantitatively according to the guidelines of the European Association of Nuclear Medicine (EANM). For semi-quantitative analysis, readers drew an irregular Region of Interest (ROI) over the suspected infectious lesion and copied it to the normal contralateral bone. The mean counts per ROI were used to calculate lesion-to-reference tissue (LR) ratios for both late and delayed images. An increase in LR over time (LRlate> LRdelayed) of more than 20% was considered indicative of infection. Agreement between readers and between readings was assessed by the first-order agreement coefficient (Gwet's AC1). Reading time for each scan was compared between the three readers in both the first and the second reading, using the Generalized Linear Mixed Model. Results: An excellent agreement was found among all three readers: 0.90 for the first reading and 0.94 for the second reading. Both inter- and intra-variability showed values ≥0.86. Gwet's method demonstrated greater robustness than the Cohen coefficient when assessing the intra and inter-rater variability, since it is not influenced by the prevalence rate. Conclusions: These studies can contribute to improving the reliability of nuclear medicine imaging techniques and to evaluating the effectiveness of trainee preparation.

Analysis of Correlation Effects of Double Mutations in Enzymes: A Revised Residual-Contact Network Clique Model.

The relationship between amino acid mutations and enzyme bioactivity is a significant challenge in modern bio-industrial applications. Despite many successful designs relying on complex correlations among mutations at different enzyme sites, the underlying mechanisms of these correlations still need to be explored. In this study, we introduced a revised version of the residual-contact network clique model to investigate the additive effect of double mutations based on the mutation occurrence topology, secondary structures, and physicochemical properties. The model was applied to a set of 182 double mutations reported in three extensively studied enzymes, and it successfully identified over 90% of additive double mutations and a majority of non-additive double mutations. The calculations revealed that the mutation additivity depends intensely on the studied mutation sites' topology and physicochemical properties. For example, double mutations on irregular secondary structure regions tend to be non-additive. Our method provides valuable tools for facilitating enzyme design and optimization. The code and relevant data are available at Github.

Dynamic response and failure characteristics of the fluid-filled concave multicell structure under combined blast and fragments loading

The deformation and damage characteristics of the fluid-filled concave multicell structure under the charge explosion with preset fragments are investigated to assess its performance against combined blast and fragments loading. The failure characteristics of the structure, the propagation process of loads, and the dynamic response characteristics of the structure are analyzed using experimental research and SPH-ALE numerical simulation. The results indicate that the deformation of the structure, caused by the explosion of a charge with preset fragments, is 400% greater than the deformation caused by the explosion alone. The propagation of the load is influenced by the panels of the structure and the irregular regions where fluid is filled. The deformation and failure of the fluid-filled concave multicell structure occur in two stages. The failure mode of this structure can be seen as a combination of the failure modes of individual single-cell structures, based on the method of fluid filling. The strength distribution of the structure plays a crucial role in determining the failure of the fluid-filled concave multicell structure.

Effect of Dry Processing of Coconut Oil on the Structure and Physicochemical Properties of Coconut Isolate Proteins.

The effects of the dry processing of coconut oil on the amino acid composition, molecular weight, secondary structure, solubility, surface hydrophobicity, microstructure, total sulfhydryl and free sulfhydryl content, free amino acid content, thermal properties, and water-holding, oil-holding, foaming, and emulsifying properties of coconut isolate protein were investigated. The results showed that the dry processing altered the amino acid composition of coconut isolate proteins as well as resulted in fewer irregular structural regions and more homogeneous particle sizes, leading to an improvement in the thermal stability of the proteins. SDS-PAGE analysis showed that globular proteins located at ~34 kDa in coconut isolate proteins underwent slight degradation during the dry processing of coconut oil. The dry processing reduced the surface hydrophobicity, total and free sulfhydryl groups, solubility, and free amino acid content of coconut isolate proteins. In addition, the water-holding capacity, oil-holding capacity, and foam stability of coconut isolate proteins were improved to different degrees after the dry processing. Therefore, the development and utilization of copra meal protein is of great significance to increase its added value.

Comparison Of Three Methods for Calculation of Sacroiliac Joint Index in Different Age Groups in Bone Scintigraphy

Objective: The aim of this study is to evaluate three techniques for calculating the sacroiliac joint (SIJ) index by bone scintigraphy in patients. Materials and Methods: Patients (n:160) who did not exhibit abnormalities on bone scan were analyzed and were divided into 4 groups; 3-20 years, 21-40 years, 41-60 years, 61-86 years, respectively. Irregular and rectangular region of interest (ROI) were used for first and second methods, respectively. Horizontal rectangular ROI was selected for the last technique. The SIJ index was calculated by the following formula: SIJ count/sacrum count. Results: There was no difference between the averages of all three methods according to right and left SIJ index (p>0.05). The averages of all SIJ values differed for three methods (p

Definition of a beam-like reduced order model element by means of a mixed dimensional coupling

The use of Reduced Dimensional Models (RDM) discretized like beams, plates and shell elements drastically decreases the computational cost of solving a full 3D elastic problem with a Finite Element Method (FEM). However, its kinematic assumptions are only applicable to bodies with regular sections or continuous layouts. For the correct analysis of irregular regions, it is necessary to rely on bi-dimensional or solid models that fully reproduce the geometry of the body and its behavior but have a much higher computational cost. The Mixing Dimensional Coupling (MDC) technique allows linking models discretized with elements of different topologies, allowing the possibility of considering the most cost-effective model in each region. This coupling takes place at the interface that delimits both models and relies on the equilibrium of work and reactions on its two faces. In this paper, the formulation is presented for coupling beams with laminar sections and 2D Plane-Stress (PS) models demonstrating its proper behavior. Finally, this coupling is used for defining a new beam element, the Beam-Like Reduced Order Model (BLROM), which is obtained from a Plane-Stress model of their longitudinal section.

Shadow removal method for high-resolution aerial remote sensing images based on region group matching

Shadow removal is a critical step in preprocessing high-resolution aerial remote sensing images. The presence of shadows reduces the information in high-resolution aerial remote sensing images, lowers the image quality, and seriously interferes with the work of feature classification, object detection, and information extraction. Therefore, this paper proposes a high-resolution aerial remote sensing image shadow removal method based on region group matching. The method starts from both spatial information and color information, and is able to take into account the whole and the local, and recover the detailed features of different features inside the shadows. Firstly, this paper proposes an irregular region color transfer method based on three-dimensional color space, which can effectively restore the original color and texture information of the features in the shadow region. Secondly, considering the random and variable direction of feature distribution in remote sensing images, the direction of texture feature extraction cannot be set in advance. Therefore, in this paper, the texture details of the features are extracted based on the rotationally invariant light-independent texture feature extraction method to exclude the abnormal interference. Then, the shadow and light regions of the image are segmented internally and grouped according to the type of features to avoid subsequent matching anomalies due to the small size of the image blocks. Next, construct an average texture feature vector for each group of image blocks for grouping matching. The matched light groups are then used to guide the shadow groups for local feature information enhancement, which ensures that on top of the overall shadow removal, the detail recovery of different local features is enhanced. Finally, for the boundary effect after shadow removal, a boundary optimization method with dynamically assigned weights is proposed, which can ensure the natural coherence of the resultant image in the boundary part. The experimental results show that the proposed method balances both overall and local shadow removal effects and can effectively achieve high-resolution aerial remote sensing image shadow removal. Compared with existing methods, the proposed method achieves the best quality of shadow removal results and restores more realistic ground features in shadow region.

Semi-analytical method for calculating ground vibrations from a tunnel in a homogeneous half-space with an irregular surface

This paper proposes a novel two-dimensional (2D) semi-analytical method for calculating ground vibrations from a tunnel situated in a homogeneous half-space with an irregular surface. The circular tunnel is conceptualized as an elastic solid, while the soil is modelled as an elastic, isotropic, and homogeneous half-space with an irregular surface. A virtual horizontal interface is introduced to divide the soil domain into an irregular region with an arbitrary-shaped surface and a half-space with a circular hollow. The wavefield scattered by the irregular surface is simulated by the boundary integral equation. Through the application of the discrete wavenumber approach and expansion of wavefield on the irregular surface, the boundary integral equation is transformed into a set of simultaneous matrix equations containing unknown expansion coefficients. By utilizing the transformation between cylindrical and plane waves, the boundary conditions on soil-tunnel interface are satisfied, yielding a solution for a harmonic point load acting on the tunnel in a half-space with an irregular surface. The proposed method can simulate topographies with arbitrary shapes and only requires the discretization of the irregular part of the ground surface, which provides a highly efficient tool to investigate the propagation characteristics of train-induced vibrations in complex topographies. The proposed method is verified through comparisons with the existing analytical methods and the finite element method. The dynamic responses of a tunnel embedded in a half-space with a Gaussian-shaped surface are meticulously investigated. A case study involving a site for the Shenzhen metro line 5 is performed. The numerical results demonstrate that the presence of irregular topography alters the distribution of ground vibrations, leading to significant differences in responses within the irregular region and certain disparities in the regular region. The effect of the location, size, and undulating direction of the irregular topography on ground vibrations is frequency-dependent.

ELA-Net: An Efficient Lightweight Attention Network for Skin Lesion Segmentation.

In clinical conditions limited by equipment, attaining lightweight skin lesion segmentation is pivotal as it facilitates the integration of the model into diverse medical devices, thereby enhancing operational efficiency. However, the lightweight design of the model may face accuracy degradation, especially when dealing with complex images such as skin lesion images with irregular regions, blurred boundaries, and oversized boundaries. To address these challenges, we propose an efficient lightweight attention network (ELANet) for the skin lesion segmentation task. In ELANet, two different attention mechanisms of the bilateral residual module (BRM) can achieve complementary information, which enhances the sensitivity to features in spatial and channel dimensions, respectively, and then multiple BRMs are stacked for efficient feature extraction of the input information. In addition, the network acquires global information and improves segmentation accuracy by putting feature maps of different scales through multi-scale attention fusion (MAF) operations. Finally, we evaluate the performance of ELANet on three publicly available datasets, ISIC2016, ISIC2017, and ISIC2018, and the experimental results show that our algorithm can achieve 89.87%, 81.85%, and 82.87% of the mIoU on the three datasets with a parametric of 0.459 M, which is an excellent balance between accuracy and lightness and is superior to many existing segmentation methods.

Hemispheric analysis of the magnetic flux in regular and irregular solar active regions

ABSTRACT Studying the hemispheric distribution of active regions (ARs) with different magnetic morphologies may clarify the features of the dynamo process that is hidden under the photospheric level. The magnetic flux data for 3047 ARs from the CrAO catalogue (https://sun.crao.ru/databases/catalog-mmc-ars), between May 1996 and December 2021 (cycles 23 and 24) were used to study ARs cyclic variations and perform correlation analysis. According to the magneto-morphological classification (MMC) of ARs proposed earlier, subsets of the regular (obeying empirical rules for sunspots) and irregular (violating these rules) ARs were considered separately. Our analysis shows the following: For ARs of each MMC type, in each of the hemispheres, time profiles demonstrate a multipeak structure. The double-peak structure of a cycle is formed by ARs of both MMC types in both hemispheres. For the irregular ARs, the pronounced peaks occur in the second maxima (close to the polar field reversal). Their significant hemispheric imbalance might be caused by a weakening of the toroidal field in one of the hemispheres due to the interaction between the dipolar and quadrupolar components of the global field, which facilitates the manifestation of the turbulent component of the dynamo. The similarity of the irregular ARs activity that was found in adjacent cycles in different hemispheres also hints at realization of the mix-parity dynamo solution. For the quadrupolar-like component of the flux (compiled in the simple axisymmetric approximation), signs of oscillations with a period of about 15 years are found, and they are pronounced specifically for the irregular groups. This MMC type ARs might also contribute in $\alpha$-quenching.

Quench dynamics in lattices above one dimension: The free fermionic case

We begin a systematic investigation of quench dynamics in higher-dimensional lattice systems considering the case of noninteracting fermions with conserved particle number. We prepare the system in a translational-invariant nonequilibrium initial state, the simplest example being a classical configuration with fermions at fixed positions on the lattice, and let it evolve in time. We characterize the system's dynamics by measuring the entanglement between a finite connected region and its complement. We observe the transmutation of entanglement entropy into thermodynamic entropy and investigate how this process depends on the shape and orientation of the region with respect to the underlying lattice. Interestingly, we find that irregular regions display a distinctive multislope entanglement growth, while the dependence on the orientation angle is generically fairly weak. This is particularly true for regions with a large (discrete) rotational symmetry group. The main tool of our analysis is the celebrated quasiparticle picture of Calabrese and Cardy, which we generalize to describe the case at hand. Specifically, we show that for generic initial configurations (even when restricting to classical ones) one has to allow for the production of multiplets involving n>2 quasiparticles and carrying nondiagonal correlations. We obtain quantitatively accurate predictions, tested against exact numerics, and propose an efficient Monte Carlo based scheme to evaluate them for arbitrary connected regions of generic higher-dimensional lattices. Published by the American Physical Society 2024

Coupled multiphysics solver for irregular regions based on graph neural network

Multiphysics analysis, involving the coupled phenomena of various physics fields, such as electro-mechanical, thermofluidic, thermoelectric, and thermo-hygric phenomena, plays a critical role in advancing technology and engineering disciplines. Conventional numerical algorithms are generally time-consuming and resource-demanding. Thanks to the rapid development in deep learning (DL), data-driven, physics-informed, and operator learning methods have been proposed to accelerate the calculation process. However, existing DL methods, encompassing convolutional neural network (CNN) and graph neural network (GNN) based approaches, exhibit limitations in effectively handling irregular regions and addressing the challenges posed by multiphysics tasks. To tackle these problems, we propose a DL framework based on GNN with a coupled solver. In the solving process of the proposed framework, a graph is generated according to the given region, and then a graph coupled-field solving network (GCFSN) is adopted. We have conducted three experiments using GCFSN to solve the coupled-field and the mean relative error is about 5%. The experimental results have verified the superior performance and generalization ability of the GCFSN method in solving the thermal-coupled physics problems on an irregular region.

Constructive approach and randomization of a two-parameter chaos system for securing data

Secure communication techniques are important due to the increase in the number of technology users across the world. Likewise, a more random encryption algorithm suitable to secure data from unauthorised users is highly expected. This paper proposes a two-parameter nonlinear chaos map that is sensitive to the trio seed (s0, \alpha, \lambda) and has better information encryption. We introduce the parameter \alpha to linearise the conventional chaos system, which in turn brings a delay in the cryptosystems. The delay is a phenomenon that changes the chaotic features of a system. A small delay in the system leads to more aperiodicity and the unpredictability of the chaotic attractions. We normalise the new chaos map and use the Lipschitz and pseudo-contractive operators to obtain its irregularity region in Hilbert spaces. We also analyse the chaos map in terms of trajectory, Lyapunov exponent, complexity, and information entropy. Results obtained show that the new chaos map has a wide chaotic range and better statistical properties. It also maintains low complexity due to its linearity and produces more key spaces than most existing chaotic maps.

An ant colony path planning optimization based on opposition-based learning for AUV in irregular regions

An ant colony path planning optimization based on opposition-based learning for AUV in irregular regions