Nonlocal Mechanism Research Articles

Onset of global instability in a premixed annular V-flame

We investigate self-excited axisymmetric oscillations of a lean premixed methane–air V-flame in a laminar annular jet. The flame is anchored near the rim of the centrebody, forming an inverted cone, while the strongest vorticity is concentrated along the outer shear layer of the annular jet. Consequently, the reaction and vorticity dynamics are largely separated, except where they coalesce near the flame tip. The global eigenmodes corresponding to the linearised reacting flow equations around the steady base state are computed in an axisymmetric setting. We identify an arc branch of eigenmodes exhibiting strong oscillations at the flame tip. The associated eigenvalues are robust with respect to domain truncation and numerical discretisation, and they become destabilised as the Reynolds number increases. The frequency of the leading eigenmode is found to correspond to the Lagrangian disturbance advection time from the nozzle outlet to the flame tip. The essential role of this convective mechanism is also supported by resolvent analysis, which finds that the same flame-tip disturbance structure and frequency are optimally amplified when the flame is subjected to external white noise forcing. Strong non-modal effects in the form of pseudo-resonance are not found. Nonlinear time-resolved simulation further reveals notable hysteresis phenomena in the subcritical regime prior to instability. Hence, even when the flame is linearly stable, perturbations of sufficient amplitude can trigger limit-cycle oscillations and higher-dimensional dynamics sustained by nonlinear feedback. A Monte Carlo simulation of passive tracers in the unsteady flame suggests a nonlinear non-local instability mechanism. Notably, linear analysis of the subcritical time-averaged limit-cycle state yields eigenvalues that do not match the nonlinear periodic oscillation frequencies. This mismatch is attributed to the fundamentally nonlinear dynamics of the subcritical V-flame instability, where the dichromatic, non-local interaction between the heat release rate along the flame surface and the vortex dynamics in the jet shear layer cannot be approximated as a simple distortion of the mean flow.

Photochromic YHO darkening: Local or non-local mechanism?

Photochromic yttrium oxyhydride (YHO) shows a very attractive color-neutral darkening upon photoactivation. However, the exact defect or state responsible for the visible light absorption or the mechanism for its creation is not fully understood. This makes it challenging to optimize and modify the material. In this work, we have investigated the relationship between photon absorption and darkening profile into a YHO film. The extinction coefficient k(λ) is obtained from spectroscopic ellipsometry, and the expected photon absorption profile is calculated. This is then compared to transmittance data during photodarkening by short-wavelength UV (254 nm). Our results show that the darkening is not homogeneous through the film, showing that photon absorption and darkening are positionally correlated, yet we show that the darkening stretches further into the film than the calculated photon absorption. A homogeneously darkened sample cannot always be assumed when assessing optical transmittance, absorbance, and ellipsometry data.

Stress-driven nonlocal homogenization method for cellular structures

Strong size-dependent mechanical behaviors can be observed in cellular structures violating the principle of scale separation and cannot be captured by classical homogenization methods. This paper proposes a stress-driven nonlocal homogenization method to capture the size-dependent mechanical behavior due to the nonlocal force of cellular structures. A nonlocal discrete element model is proposed first to describe the nonlocal deformation mechanism of cellular structures. Then, a continuum stress-driven nonlocal homogenization method is calibrated by deriving the continuum limit from the nonlocal discrete element model. The continuum homogenization method releases the assumption of scale separation by introducing an intrinsic length, which can be calibrated by high throughput numerical computation. Also, for efficient prediction of size-dependent mechanical behaviors, an offline dataset of the intrinsic length is constructed for different unit cells. With the help of the offline dataset, the proposed homogenization method improves the accuracy of the classic homogenization method and reduces the computational cost of the high-fidelity finite element method. Finally, a cellular rod under tension is used as an application to illustrate the efficiency and accuracy of the proposed homogenization method. Results indicate that compared with the classic homogenization method, the relative error of the proposed homogenization method is less than 1% which has a good consistency with the high-fidelity method. Moreover, the computational efficiency of the proposed homogenization method is more than five times that of the high-fidelity finite element method.

Emotional Inference from Speech Signals Informed by Multiple Stream DNNs Based Non-Local Attention Mechanism

Emotional Inference from Speech Signals Informed by Multiple Stream DNNs Based Non-Local Attention Mechanism

Field cabbage detection and positioning system based on improved YOLOv8n

BackgroundPesticide efficacy directly affects crop yield and quality, making targeted spraying a more environmentally friendly and effective method of pesticide application. Common targeted cabbage spraying methods often involve object detection networks. However, complex natural and lighting conditions pose challenges in the accurate detection and positioning of cabbage.ResultsIn this study, a cabbage detection algorithm based on the YOLOv8n neural network (YOLOv8-cabbage) combined with a positioning system constructed using a Realsense depth camera is proposed. Initially, four of the currently available high-performance object detection models were compared, and YOLOv8n was selected as the transfer learning model for field cabbage detection. Data augmentation and expansion methods were applied to extensively train the model, a large kernel convolution method was proposed to improve the bottleneck section, the Swin transformer module was combined with the convolutional neural network (CNN) to expand the perceptual field of feature extraction and improve edge detection effectiveness, and a nonlocal attention mechanism was added to enhance feature extraction. Ablation experiments were conducted on the same dataset under the same experimental conditions, and the improved model increased the mean average precision (mAP) from 88.8% to 93.9%. Subsequently, depth maps and colour maps were aligned pixelwise to obtain the three-dimensional coordinates of the cabbages via coordinate system conversion. The positioning error of the three-dimensional coordinate cabbage identification and positioning system was (11.2 mm, 10.225 mm, 25.3 mm), which meets the usage requirements.ConclusionsWe have achieved accurate cabbage positioning. The object detection system proposed here can detect cabbage in real time in complex field environments, providing technical support for targeted spraying applications and positioning.

IoT-Enhanced local attention dual networks for pathological image restoration in healthcare

High-resolution pathological images play a pivotal role in accurate disease diagnosis and are important in precision medicine. However, obtaining real-time high-resolution images faces challenges due to hardware limitations and scanning time constraints. Conventional image super-resolution restoration algorithms struggle to provide satisfactory results for pathological images, resulting in blurred and unrealistic restorations. In response to this challenge, this research proposes a pioneering approach by integrating Internet of Things (IoT) technology with Local Attention Dual Network (IOT-LAT) for super-resolution restoration of pathological images. The enhanced IOT-LATincorporates IoT-based data acquisition and processing, IoT-Enhanced non-local attention mechanisms, Gaussian constraint, and parameter-sharing strategies in up-sampling and down-sampling branches. This integration enables real-time super-resolution restoration of pathological images with improved accuracy. The reconstructed images exhibit a structural similarity of 0.914 and a peak signal-to-noise ratio of 30.84 dB. These results validate the effectiveness of the suggested approach in precisely reconstructing high-frequency details and improving modelling efficiency via a lightweight non-local attention mechanism enhanced by the Internet of Things. This work discusses IoT and non-local attention dual networks to improve pathological image super-resolution restoration. This allows for faster and more accurate disease diagnosis and treatment in precision medicine.

Brain tumor segmentation using neuro-technology enabled intelligence-cascaded U-Net model.

According to experts in neurology, brain tumours pose a serious risk to human health. The clinical identification and treatment of brain tumours rely heavily on accurate segmentation. The varied sizes, forms, and locations of brain tumours make accurate automated segmentation a formidable obstacle in the field of neuroscience. U-Net, with its computational intelligence and concise design, has lately been the go-to model for fixing medical picture segmentation issues. Problems with restricted local receptive fields, lost spatial information, and inadequate contextual information are still plaguing artificial intelligence. A convolutional neural network (CNN) and a Mel-spectrogram are the basis of this cough recognition technique. First, we combine the voice in a variety of intricate settings and improve the audio data. After that, we preprocess the data to make sure its length is consistent and create a Mel-spectrogram out of it. A novel model for brain tumor segmentation (BTS), Intelligence Cascade U-Net (ICU-Net), is proposed to address these issues. It is built on dynamic convolution and uses a non-local attention mechanism. In order to reconstruct more detailed spatial information on brain tumours, the principal design is a two-stage cascade of 3DU-Net. The paper's objective is to identify the best learnable parameters that will maximize the likelihood of the data. After the network's ability to gather long-distance dependencies for AI, Expectation-Maximization is applied to the cascade network's lateral connections, enabling it to leverage contextual data more effectively. Lastly, to enhance the network's ability to capture local characteristics, dynamic convolutions with local adaptive capabilities are used in place of the cascade network's standard convolutions. We compared our results to those of other typical methods and ran extensive testing utilising the publicly available BraTS 2019/2020 datasets. The suggested method performs well on tasks involving BTS, according to the experimental data. The Dice scores for tumor core (TC), complete tumor, and enhanced tumor segmentation BraTS 2019/2020 validation sets are 0.897/0.903, 0.826/0.828, and 0.781/0.786, respectively, indicating high performance in BTS.

Deep local-to-global feature learning for medical image super-resolution

Medical images play a vital role in medical analysis by providing crucial information about patients’ pathological conditions. However, the quality of these images can be compromised by many factors, such as limited resolution of the instruments, artifacts caused by movements, and the complexity of the scanned areas. As a result, low-resolution (LR) images cannot provide sufficient information for diagnosis. To address this issue, researchers have attempted to apply image super-resolution (SR) techniques to restore the high-resolution (HR) images from their LR counterparts. However, these techniques are designed for generic images, and thus suffer from many challenges unique to medical images. An obvious one is the diversity of the scanned objects; for example, the organs, tissues, and vessels typically appear in different sizes and shapes, and are thus hard to restore with standard convolution neural networks (CNNs). In this paper, we develop a dynamic-local learning framework to capture the details of these diverse areas, consisting of deformable convolutions with adjustable kernel shapes. Moreover, the global information between the tissues and organs is vital for medical diagnosis. To preserve global information, we propose pixel–pixel and patch–patch global learning using a non-local mechanism and a vision transformer (ViT), respectively. The result is a novel CNN-ViT neural network with Local-to-Global feature learning for medical image SR, referred to as LGSR, which can accurately restore both local details and global information. We evaluate our method on six public datasets and one large-scale private dataset, which include five different types of medical images (i.e., Ultrasound, OCT, Endoscope, CT, and MRI images). Experiments show that the proposed method achieves superior PSNR/SSIM and visual performance than the state of the arts with competitive computational costs, measured in network parameters, runtime, and FLOPs. What is more, the experiment conducted on OCT image segmentation for the downstream task demonstrates a significantly positive performance effect of LGSR.

CDI-NSTSEG: A clinical diagnosis-inspired effective and efficient framework for non-salient small tumor segmentation.

To accurately segment various clinical lesions from computed tomography(CT) images is a critical task for the diagnosis and treatment of many diseases. However, current segmentation frameworks are tailored to specific diseases, and limited frameworks can detect and segment different types of lesions. Besides, it is another challenging problem for current segmentation frameworks to segment visually inconspicuous and small-scale tumors (such as small intestinal stromal tumors and pancreatic tumors). Our proposed framework, CDI-NSTSEG, efficiently segments small non-salient tumors using multi-scale visual information and non-local target mining. CDI-NSTSEG follows the diagnostic process of clinicians, including preliminary screening, localization, refinement, and segmentation. Specifically, we first explore to extract the unique features at three different scales (1×, 0.5×, and 1.5×) based on the scale space theory. Our proposed scale fusion module (SFM) hierarchically fuses features to obtain a comprehensive representation, similar to preliminary screening in clinical diagnosis. The global localization module (GLM) is designed with a non-local attention mechanism. It captures the long-range semantic dependencies of channels and spatial locations from the fused features. GLM enables us to locate the tumor from a global perspective and output the initial prediction results. Finally, we design the layer focusing module (LFM) to gradually refine the initial results. LFM mainly conducts context exploration based on foreground and background features, focuses on suspicious areas layer-by-layer, and performs element-by-element addition and subtraction to eliminate errors. Our framework achieves state-of-the-art segmentation performance on small intestinal stromal tumor and pancreatic tumor datasets. CDI-NSTSEG outperforms the best comparison segmentation method by 7.38% Dice on small intestinal stromal tumors.

Multi-scale non-local attention network for image super-resolution

Natural images tend to recur similar patterns within the same scale and across different scales. Some recent progress on Single Image Super-Resolution (SISR) have elaborated on applying non-local attention mechanism to explore intrinsic feature correlation on multi-scale similarity to improve SR performance. However, recent advanced non-local attention-based methods typically utilize fixed-scale image patches to mine the correlations between local and global features, which is unreliable to judge the similarity between the non-local image patches across various scales. In this paper, we develop a novel Multi-Scale Non-Local Attention Network (MSNLAN) for SISR. The MSNLAN consists of a serial of Residual Groups (RGs) and an embedded Multi-Scale Non-Local Attention Block (MSNLAB) located at the middle of those RGs. Each RG is comprised of several Residual Multi-scale Attention Blocks (RMABs) which learns multi-scale features extracted from different receptive fields to fully capture diverse and complementary feature representations. MSNLAB is applied to establish more long-range dependencies by exploring multi-scale patches within the same feature map to seek more faithful and relevant non-local features. Moreover, we utilize Dense Skip Connections (DSC) between each RG and the MSNLAB to enhance the interaction of different context features, which is propitious for generating more impressive image details. Extensive experiments demonstrate that the proposed MSNLAN outperforms other state-of-the-art competitors in terms of both quantitative and qualitative quality assessment results. The code will be available at https://github.com/kbzhang0505/MSNLAN.

Design of a MobilNetV2-Based Retrieval System for Traditional Cultural Artworks

Aiming at the problem that it is difficult for art teachers to take into account each student in the art appreciation education in colleges and universities, this paper proposes a retrieval system for traditional cultural works of art. Dense connections are used to replace residual connections between bottlenecks in MobileNetV2 network and gradient transmission in the network. The dilution factor is used to control the size of the network to solve the problem of the rapid increase in the number of network channels. In addition, the non-local attention mechanism is effectively combined with the improved MobileNetV2 network structure, which effectively improves the classification accuracy of the network. Compared with VGG16, ResNet18, and ResNet34, the classification accuracy is increased by 21.3%, 9.2%, and 3%, respectively. The method in this paper has achieved good results in the classification of art works. According to the images of art works to be appreciated, it helps students understand the relevant cultural knowledge independently and reduce the burden of teachers.

A multi-level wavelet-based underwater image enhancement network with color compensation prior

Due to the scattering of light and the influence of different water types, underwater images usually suffer from different type of hybrid degradation, e.g. color distortion, blurred details and low contrast. Existing underwater image enhancement methods are weak at handling hybrid degradation simultaneously, resulting in low quality results. Inspired by the fact that wavelet-based enhancement methods can correct color and enhance details in frequency domain and the color compensation prior can compensate missing color information in spatial domain, we design the Multi-level Wavelet-based Underwater Image Enhancement Network (MWEN) with the color compensation prior to enhance image in both frequency domain and spatial domain. Specifically, we integrate the multi-level wavelet transform and the color compensation prior into a multi-stage enhancement framework, where each stage consists of a Multi-level Wavelet-based Enhancement Module (MWEM), a Color Compensation Prior Extraction Module (CCPEM) and a color filter with prior-aware weights. The MWEM decomposes image features into low frequency and high frequency by a wavelet transform, and then enhances them by a low frequency enhancement branch and several high frequency enhancement branches, respectively. The low frequency reduces the color distortion of different water types using Instance Normalization for style transfer, while the high frequency enhancement enhances sparse details using a non-local sparse attention mechanism. After the inverse wavelet transform, the preliminary enhanced result by the MWEM is obtained. Then, the color filter whose weights are customized by the color compensation information extracted from the CCPEM dynamically is applied to output of the MWEM for color compensation. Such an operation enables network to adapt to hybrid degradation and achieve better performance. The experiments demonstrate MWEN outperforms existing UIE methods quantitatively and qualitatively.

Improved GSA Method Based on Deep Convolutional Features

With the rapid development of remote sensing platforms, sensors and other technologies, remote sensing, as an important technical means of collecting information on land cover and its changes, plays an important role in land cover classification and dynamic monitoring. Due to the limitation of the imaging mechanism of in-orbit optical remote sensing sensors, it is difficult for to take into account both spatial resolution and spectral resolution. There is a need for complementary use of different sensor images and to improve the accuracy of feature interpretation. In this study, based on the Gram-Schmidt Adaptive (GSA) and its classical extension, a neural network-based multi-source remote sensing image fusion method is proposed by combining the U-Net coding and decoding structure with the Non-Local spatial attention mechanism. Using two sets of experimental datasets, three kinds of fusion evaluation metrics without reference and three kinds of fusion evaluation metrics with reference, the improved method and the existing fusion method are compared.

Dark Energy from Cosmological Energy Conservation

The value of the gravitational wave energy density is unknown. Current progress in gravitational wave detection suggests that the energy density of the stochastic gravitational wave background (SGWB) will be estimated in the next decades. A derivation of its value is presented under the assumption that energy lost due to cosmic redshift is fully responsible for the energy gained by the cosmological constant in the expanding universe. This unknown nonlocal mechanism of energy conservation on the cosmic scale could explain dark energy and hint at a property of a theory of quantum gravity.

Non-local attention and multi-task learning based lung segmentation in chest X-ray

Precise segmentation of lung field is a crucial step in chest radiographic computer-aided diagnosis system. With the development of deep learning, fully convolutional network based models for lung field segmentation have achieved great effect but are poor at accurate identification of the boundary and preserving lung field consistency. To solve this problem, this paper proposed a lung segmentation algorithm based on non-local attention and multi-task learning. Firstly, an encoder-decoder convolutional network based on residual connection was used to extract multi-scale context and predict the boundary of lung. Secondly, a non-local attention mechanism to capture the long-range dependencies between pixels in the boundary regions and global context was proposed to enrich feature of inconsistent region. Thirdly, a multi-task learning to predict lung field based on the enriched feature was conducted. Finally, experiments to evaluate this algorithm were performed on JSRT and Montgomery dataset. The maximum improvement of Dice coefficient and accuracy were 1.99% and 2.27%, respectively, comparing with other representative algorithms. Results show that by enhancing the attention of boundary, this algorithm can improve the accuracy and reduce false segmentation.

Nonlocal phase coupling in turbulence spreading across the magnetic island

We study the nonlocal phase coupling during turbulence spreading across the magnetic island. It is found that the coherent convective cells (sharing similar features to quasi-coherent mode in experiment) on both sides of the O-point boundary are accumulated during the island formation. The phase entrainment of the convective cells on the turbulence both in the inner and the outer regions of the magnetic island sets up a nonlocal phase coupling channel and leads to a fast spreading of the outer turbulence into the magnetic island by conquering the flow shear at the O-point boundary. This nonlocal coupling mechanism of turbulence spreading is analogous to a turbulence version of the well-known enhanced diffusion of passive scalars in laminar convective flows of neutral fluid system.

Monocular catadioptric panoramic depth estimation via improved end-to-end neural network model.

In this paper, we propose a monocular catadioptric panoramic depth estimation algorithm based on an improved end-to-end neural network model. First, we use an enhanced concentric circle approximation unfolding algorithm to unfold the panoramic images captured by the catadioptric panoramic camera and then extract the effective regions. In addition, the integration of the Non-local attention mechanism is exploited to improve image understanding. Finally, a depth smoothness loss strategy is implemented to further enhance the reliability and precision of the estimated depths. Experimental results confirm that this refined algorithm is capable of providing highly accurate estimates of object depth.

Patch merging refiner embedding UNet for image denoising

Image denoising is a fundamental task in low-level computer vision. The well-known CNN-UNet model with encoder and decoder has shown excellent denoising performance. The encoder adopts downsample modules such as pooling, convolution and patch merging to reduce the feature map size. The downsample module is very important for feature transformation between adjacent feature layers. However, these plain downsample modules are incapable of removing noise during feature transformation. It is expected that the downsample module can play the role of removing noise while executing feature transformation. Therefore, we design a patch merging refiner (PMR) downsample module, which utilizes subspace projection to learn a set of restoration basis from the feature space and projects the patch merging feature onto such space, to remove noise and retain the authentic information of feature space while executing feature transformation. Subsequently, from the perspective of the non-local mechanism, we carry out group convolution (GC) block module on PMR to restore high-frequency detail. Finally, by integrating the two modules into the commonly-used UNet model, we construct a PMR-UNet architecture. Experiments on synthetic and real-world noise images demonstrate that our architecture has stronger anti-noise power and surpasses the state-of-the-art denoisers in both quantitative measure and visual perception.

Modelling of viscoelastic materials using non-ordinary state-based peridynamics

This paper proposes a framework for implementing viscoelastic constitutive model from the classical continuum mechanics (CCM) theory within non-ordinary state-based peridynamics (NOSBPD). The motivation stems from the inadequacy of CCM to model very complex material behaviours such as initiation and propagation of cracks and nonlocal behaviour due to size effects. The proposed formulation leverages on the constitutive correspondence between NOSBPD and CCM to incorporate a CCM viscoelastic constitutive model based on hereditary integral into NOSBPD. The combination of hereditary constitutive model and NOSBPD effectively makes this formulation a nonlocal time–space viscoelastic framework where temporal nonlocality is incorporated by a hereditary viscoelastic model which stipulates that the behaviour of a material at any point in time depends on both the present action and the complete history of previous actions on the material, and spatial nonlocality on the other hand is incorporated via the nonlocal mechanism provided by the NOSBPD. For model validation, three benchmark problems were solved using the proposed framework. Results obtained were compared to results from analytical solution and solutions from referenced literature. In addition, parametric study was conducted to determine the influence of nonlocality on numerical prediction. Conclusions drawn from the validation studies presented are that the proposed framework is able to predict viscoelastic responses that agree well with local macro models as well as nonlocal micromodels/nanomodels as reported in the literature.

A Hyperspectral Image Classification Method Based on the Nonlocal Attention Mechanism of a Multiscale Convolutional Neural Network.

Recently, convolution neural networks have been widely used in hyperspectral image classification and have achieved excellent performance. However, the fixed convolution kernel receptive field often leads to incomplete feature extraction, and the high redundancy of spectral information leads to difficulties in spectral feature extraction. To solve these problems, we propose a nonlocal attention mechanism of a 2D-3D hybrid CNN (2-3D-NL CNN), which includes an inception block and a nonlocal attention module. The inception block uses convolution kernels of different sizes to equip the network with multiscale receptive fields to extract the multiscale spatial features of ground objects. The nonlocal attention module enables the network to obtain a more comprehensive receptive field in the spatial and spectral dimensions while suppressing the information redundancy of the spectral dimension, making the extraction of spectral features easier. Experiments on two hyperspectral datasets, Pavia University and Salians, validate the effectiveness of the inception block and the nonlocal attention module. The results show that our model achieves an overall classification accuracy of 99.81% and 99.42% on the two datasets, respectively, which is higher than the accuracy of the existing model.