Discontinuous Features Research Articles

DSC-Net: Enhancing Blind Road Semantic Segmentation with Visual Sensor Using a Dual-Branch Swin-CNN Architecture.

In modern urban environments, visual sensors are crucial for enhancing the functionality of navigation systems, particularly for devices designed for visually impaired individuals. The high-resolution images captured by these sensors form the basis for understanding the surrounding environment and identifying key landmarks. However, the core challenge in the semantic segmentation of blind roads lies in the effective extraction of global context and edge features. Most existing methods rely on Convolutional Neural Networks (CNNs), whose inherent inductive biases limit their ability to capture global context and accurately detect discontinuous features such as gaps and obstructions in blind roads. To overcome these limitations, we introduce Dual-Branch Swin-CNN Net(DSC-Net), a new method that integrates the global modeling capabilities of the Swin-Transformer with the CNN-based U-Net architecture. This combination allows for the hierarchical extraction of both fine and coarse features. First, the Spatial Blending Module (SBM) mitigates blurring of target information caused by object occlusion to enhance accuracy. The hybrid attention module (HAM), embedded within the Inverted Residual Module (IRM), sharpens the detection of blind road boundaries, while the IRM improves the speed of network processing. In tests on a specialized dataset designed for blind road semantic segmentation in real-world scenarios, our method achieved an impressive mIoU of 97.72%. Additionally, it demonstrated exceptional performance on other public datasets.

Assessing the influence of image capture frequency and asynchronicity on the accuracy of digital image correlation for fatigue analysis

Efficiency of Digital Image Correlation (DIC) technique for fatigue analysis can be significantly increased by capturing images at periodic intervals for correlation. However, the scarcity of images to capture the history of deformation can cause inaccuracies in full-field measurements. In this study, a comprehensive analysis is conducted to quantitatively assess this error by considering various scenarios. These include skipping of frames within every cycle and across cycles, as well as deviations between intended and captured frames. DIC measurements based on a high density of frames in every cycle is assumed to be true solution to evaluate error for all the cases. Analysis indicates that the skipping frames within every cycle introduces error in full-field strain, which increases with the propagation of crack. Interestingly, magnitude of error for periodic skipping of frames across cycles is observed to be more than skipping of frames within cycle. Furthermore, error shows an increasing trend as the gap between periodic frames becomes larger. Analysis also shows that random deviations disturbing periodicity of skipped frames for DIC can further increase the error in full-field strains. Overall, accuracy of the accelerated approach is seen to strongly depend on presence of discontinuous features and local gradients in response.

Image inpainting algorithm based on double curvature-driven diffusion model with P-Laplace operator.

The method of partial differential equations for image inpainting achieves better repair results and is economically feasible with fast repair time. Addresses the inability of Curvature-Driven Diffusion (CDD) models to repair complex textures or edges when the input image is affected by severe noise or distortion, resulting in discontinuous repair features, blurred detail textures, and an inability to deal with the consistency of global image content, In this paper, we have the CDD model of P-Laplace operator term to image inpainting. In this method, the P-Laplace operator is firstly introduced into the diffusion term of CDD model to regulate the diffusion speed; then the improved CDD model is discretized, and the known information around the broken region is divided into two weighted average iterations to get the inpainting image; finally, the final inpainting image is obtained by weighted averaging the two image inpainting images according to the distancing. Experiments show that the model restoration results in this paper are more rational in terms of texture structure and outperform other models in terms of visualization and objective data. Comparing the inpainting images with 150, 1000 and 100 iterations respectively, Total Variation(TV) model and the CDD model inpainting algorithm always has inpainting traces in details, and TV model can't meet the visual connectivity, but the algorithm in this paper can remove the inpainting traces well, TV model and the CDD model inpainting algorithm always have inpainting traces in details, and TV model can't meet the visual connectivity, but the algorithm in this paper can remove the inpainting traces well. Of the images used for testing, the highest PSNR reached 38.7982, SSIM reached 0.9407, and FSIM reached 0.9781, the algorithm not only inpainting the effect and, but also has fewer iterations.

The Laser Scanner Technique: A Tool for Determining Shear Strength Parameters of Rock Mass Discontinuities

When evaluating the shear strength of rock mass discontinuities, certain challenges arise due to the difficulty in quantifying the roughness characteristics of surfaces and the strength of asperities. Recent research has focused on enhancing techniques for assessing these characteristics and exploring the application of laser scanning to aid in evaluating discontinuity features. The analysis of reflectivity values (I) obtained through a laser scanner survey presents an efficient method for assessing mechanical characteristics, such as joint compressive strength (JCS). Reflectivity measurements demonstrate correlations with Schmidt hammer rebound values (r). The laser scanner technique would enable the measurement of JCS without the direct application of the Schmidt hammer on rocks in areas where rebound values (r) measurements are unavailable. The use of a laser scanner allows for the acquisition of high-precision geometrical information concerning the 3D roughness and anisotropy of rock surfaces. In this study, an innovative technique was introduced that utilizes laser scanner data from six previous experimental surveys conducted on rock formations in Southern Italy. This technique facilitates the evaluation of roughness profiles, considering potential variations along kinematically admissible sliding directions, allowing for the estimation of the Joint Roughness Coefficient (JRC). This new methodology aids in evaluating the parameters of Barton’s equation to determine the strength characteristics of rock mass discontinuities.

ResACEUnet: An Improved Transformer Unet Model for 3D Seismic Fault Detection

AbstractDetecting fault constitutes a pivotal aspect of seismic interpretation, significantly influencing the outcomes of petroleum and gas exploration. As artificial intelligence advances, convolutional neural network (CNN) has proven effective in detecting faults in seismic interpretation. Nevertheless, the receptive field of a convolutional layer within CNN is inherently limited, focusing on extracting local features, which lead to the detection of fewer and discontinuous fault features. In this study, integrating the local feature extraction capabilities of CNN with the global feature extraction prowess of transformer, we proposed a U‐shaped hybrid architecture model named ResACEUnet (Attention‐Convolution Unet with Efficient block) to detect fault of three‐dimensional (3D) seismic data. In ResACEUnet, we introduced a module called ACE block, which integrates convolution and attention mechanisms. This module enabled the model to simultaneously extract local features and model global contextual information, capturing more accurate fault features. In addition, we utilized a joint loss function named BCEDice loss, which composed of BCE (binary cross‐entropy) loss and dice loss to tackle the challenge of imbalanced positive and negative samples. The model was trained on a synthetic data set, with a range of data augmentation techniques were employed to bolster its generalization capabilities and robustness. We implemented our proposed method on the offshore F3 seismic data from the Netherlands and seismic data from Kerry3D and Parihaka in New Zealand. Compared to conventional popular models such as Unet, ResUnet, and SwinUnetR, ResACEUnet demonstrated superior capabilities in capturing more features and identifying fault with higher accuracy and continuity.

Damage evolution of coal with a strong bursting liability and 3D measurement method for elastic deformation energy distribution

When coal with a strong bursting liability is disturbed by a load, catastrophic instability disasters and rockbursts can easily occur. Loaded coal with a strong bursting liability undergoes complex damage evolution and failure behavior due to the intricate interplay among loads, gangue, fractures, and the coal matrix. Intuitively quantifying and characterizing the complex discontinuous structural features, deformation fields, and energy fields within coal is the foundation for the scientific analysis and prevention of disaster mechanisms caused by rockbursts. Therefore, studying the distribution and evolutionary processes of deformation fields and energy fields caused by the evolution of discontinuous structures within coal is highly important for the prevention and control of coal mine rockburst disasters and the protection of coal mine safety during mining operations. In this study, a series of X-ray computed tomography (X-CT) tests were conducted on coal specimens with varying gangue contents under uniaxial compressive loading. The X-CT images clearly illustrated the internal damage evolution of coal with a strong bursting liability, revealing fracture propagation, shear bands, and localized failure under varying loading conditions. Image segmentation was employed to quantitatively analyze the development of damage in coal with a strong bursting liability, revealing the influence patterns of gangue content on the prepeak deformation localization and strength of coal. Additionally, using digital volume correlation, the 3D volumetric displacement and strain of loaded impact-prone coal were determined based on the changes in natural speckle images. The nonuniform distribution of strain was mainly caused by the nonuniform distribution of gangue and pore fractures at the microscopic scale, which explains the localized deformation in coal materials. Importantly, this study provides new full-field strain tensor data and a novel method for measuring the elastic deformation energy of the 3D deformation and cracking processes of loaded coal.

Managing organizational discontinuity in a corporate museum: case study of the Polish Vodka Museum

The article explains how corporate museums employ rhetorical history to construct a narrative of continuity against discontinuities in the organizational past. By analyzing the exhibition narratives and what these communicate to the stakeholders, the article ex- plores the case of the Polish Vodka Museum in Warsaw, which was established in the revitalized remains of a defunct vodka plant. The analysis has revealed that features of the former plant that represented continuity, such as the location, buildings, and brands, were emphasized in the narrative, while discontinuous features, such as ownership, legal status, and the core business were downplayed. The article contributes to the literature on rhetorical history, or the strategic uses of the past, by providing a case study of how corporate museums deal with organizational discontinuity by applying rhetorical tools. The case study is a corporate museum from Eastern Europe, an underrepresented region in the business history field characterized by political and socio-economic discontinuities.

Study on mechanical properties and failure mechanism of hard rock with stiff discontinuities based on 3D printing

To examine the influence of stiff discontinuities with different angles and roughness on the stability of deep hard rock engineering, RLSD is created through the integration of 3D scanning, digital modeling, and 3D printing. The specimen's composition truly reflects the mineral components of the original rock. The impact of angle and roughness on the strength, deformation, and failure characteristics of RLSD is explored by uniaxial tests. The failure process and mechanism of specimens under the influence of stiff discontinuity feature are investigated through the integration of DIC, AE, and SEM test. The study results demonstrate that achieving highly similar specimen of hard rock containing stiff discontinuities with different angles and roughness is attainable by utilizing rock-like materials based on original rock mineral components and employing a combination of 3D scanning and 3D printing techniques. The peak strength, peak strain and elastic modulus of RLSD increase with the increase of JRC, and there is a V-shaped trend of“decrease first and then increase” with the increase of angle. The failure mode of RLSD shows the change rule of tension failure - tension-shear composite failure - shear failure - tension-shear composite failure - tension failure with the increase of angle. At angles of 60° and 75°, a sudden increase in hit and energy of AE feature is observed in RLSD, resulting in brittle failure. The cumulative energy exhibits a positive correlation with JRC. Based on the test results, an empirical estimation formula is established for the uniaxial compressive strength of RLSD, considering the influence of angle and JRC. The research results can provide reference for estimating the strength of surrounding rock in deep underground engineering as well as disaster prevention and control.

Discrete element analysis of hydraulic stimulation in a slate geothermal reservoir using the ubiquitous foliation model

This study employs the discrete element method for a series of coupled hydro-mechanical analyses aimed at investigating the hydraulic stimulation effect on a slate geothermal reservoir. Initially, a ubiquitous foliation model (UFM) is devised to characterize the mechanical properties of slate. The UFM consists of a foliation model for near-field discontinuity features and a ubiquitous model for far-field anisotropic rock behavior. The devised model undergoes validation through an established benchmark analysis considering isotropic conditions. The analysis is subsequently extended to investigate anisotropic shear response influenced by the foliation. In cases where the anisotropic angle equals 90°, new fractures initiate along the foliation, which leads to a concentrated and severe damage pattern. In contrast, models with the anisotropic angle of 45° and 135° exhibit minor failures due to foliation orientation hindering fracture propagation. Lastly, an anisotropic hydraulic-mechanical analysis is undertaken to assess the hydraulic stimulation influence and its consequential effects on a slate geothermal reservoir. The results indicate that higher injection rates amplify damage to the rock matrix and the propagation of fractures, which are concentrated between open fractures and adjacent foliations.

Domain Decomposition Strategy for Combining Nonlinear and Linear Reduced-Order Models

Increasingly ubiquitous reliance on expensive, high-fidelity numerical simulations has led to the emergence of reduced-order modeling as an effective method to predict high-dimensional, spatially discretized field outputs in an efficient manner. This study presents a method to construct parametric, nonintrusive reduced-order models (ROMs) by leveraging domain decomposition (DD) to enable using multiple dimension reduction (DR) techniques within different spatial subdomains of the field to construct a single predictive ROM. To enforce smoothness of solutions across subdomains, points at domain interfaces are reconstructed using the data-driven gappy proper orthogonal decomposition method. The method is assessed on three high-dimensional test cases with shocks, including one with two-dimensional turbulent flow around the RAE2822. Results show that fully nonlinear ROMs predict fields more accurately in the vicinity of discontinuous features compared to their linear counterparts, which are more accurate in regions that are far from these discontinuities. Furthermore, irrespective of the DR method, DD-based ROMs outperformed their global counterparts in all test cases. Finally, models that used a combination of DR methods simultaneously showed superior performance near shockwaves and a significant improvement in total error compared to existing approaches that employ a single DR method in all subdomains.

Correlative Scan Matching Position Estimation Method by Fusing Visual and Radar Line Features

Millimeter-wave radar and optical cameras are one of the primary sensing combinations for autonomous platforms such as self-driving vehicles and disaster monitoring robots. The millimeter-wave radar odometry can perform self-pose estimation and environmental mapping. However, cumulative errors can arise during extended measurement periods. In particular scenes where loop closure conditions are absent and visual geometric features are discontinuous, existing loop detection methods based on back-end optimization face challenges. To address this issue, this study introduces a correlative scan matching (CSM) pose estimation method that integrates visual and radar line features (VRL-SLAM). By making use of the pose output and the occupied grid map generated by the front end of the millimeter-wave radar’s simultaneous localization and mapping (SLAM), it compensates for accumulated errors by matching discontinuous visual line features and radar line features. Firstly, a pose estimation framework that integrates visual and radar line features was proposed to reduce the accumulated errors generated by the odometer. Secondly, an adaptive Hough transform line detection method (A-Hough) based on the projection of the prior radar grid map was introduced, eliminating interference from non-matching lines, enhancing the accuracy of line feature matching, and establishing a collection of visual line features. Furthermore, a Gaussian mixture model clustering method based on radar cross-section (RCS) was proposed, reducing the impact of radar clutter points online feature matching. Lastly, actual data from two scenes were collected to compare the algorithm proposed in this study with the CSM algorithm and RI-SLAM.. The results demonstrated a reduction in long-term accumulated errors, verifying the effectiveness of the method.

Complex motion of steerable vesicular robots filled with active colloidal rods

While the collective motion of active particles has been studied extensively, effective strategies to navigate particle swarms without external guidance remain elusive. We introduce a method to control the trajectories of two-dimensional swarms of active rod-like particles by confining the particles to rigid bounding membranes (vesicles) with non-uniform curvature. We show that the propelling agents spontaneously form clusters at the membrane wall and collectively propel the vesicle, turning it into an active superstructure. To further guide the motion of the superstructure, we add discontinuous features to the rigid membrane boundary in the form of a kinked tip, which acts as a steering component to direct the motion of the vesicle. We report that the system’s geometrical and material properties, such as the aspect ratio and Péclet number of the active rods as well as the kink angle and flexibility of the membrane, determine the stacking of active particles close to the kinked confinement and induce a diverse set of dynamical behaviors of the superstructure, including linear and circular motion both in the direction of, and opposite to, the kink. From a systematic study of these various behaviors, we design vesicles with switchable and reversible locomotions by tuning the confinement parameters. The observed phenomena suggest a promising mechanism for particle transportation and could be used as a basic element to navigate active matter through complex and tortuous environments.

A mixed pressure-velocity formulation to model flow in heterogeneous porous media with physics-informed neural networks

Current implementations of Physics Informed Neural Networks (PINNs) can experience convergence problems in simulating fluid flow in porous media with highly heterogeneous domains. The objective of this work is to develop an accurate implementation of PINNs to model fluid flow in heterogeneous porous media that avoids alternative approaches in the literature that tend to impose unphysical continuity of the hydraulic conductivity field. The proposed implementation is inspired by the mixed formulation of the governing equations, which separates the mass continuity equation and Darcy's law. This methodology has been used with the mixed finite element method and is known to provide accurate pressure and velocity fields in highly heterogeneous domains. In this work, a similar methodology is applied to PINNs, where the training loss function is based on the decoupled continuity equation and Darcy's law. The separation of the continuity equation and Darcy's law allows for calculating the residual term in the learning loss function without evaluating the spatial derivatives of the discontinuous hydraulic conductivity and associated non-differentiable functions. This approach provides more accurate automatic differentiation of the neural networks for pressure and velocity fields. The new implementation of PINNs can be applied to simulate flow in porous media, regardless of the type and level of heterogeneity with a discontinuous hydraulic conductivity distribution. A variety of structures of the new implementation are investigated. Numerical experiments show that the structure based on different neural networks for the pressure and each component of the velocity field provides the highest accuracy with equivalent training time as other structures. The proposed methodology presents a novel approach to broaden the scope of PINNs in modeling fluid flow in porous media, while preserving the precise representation of the domain's discontinuous features.

Study on Chloride Diffusion Behaviors of Recycled Concrete of Random Aggregates

Based on the chloride ions (Cl−) diffusion model and aggregate grading theory, PYTHON and COMSOL are used to construct a mesoscopic model of recycled concrete random polygon aggregate and verify its validity in combination with existing experimental results. The diffusion law of Cl− in recycled concrete and the law of influence of critical factors on the Cl− erosion resistance are studied by calculating and analyzing the Cl− erosion resistance of recycled concrete under different working conditions such as the diffusivity of new and old mortar, the thickness of old mortar and the replacement ratio of recycled aggregate. The results show that the simulation results agree well with the test results, and the method can better reproduce the Cl− diffusion process inside the recycled concrete. There are discontinuous features based on the relationship curves between the Cl− concentration and the depth of the recycled concrete. The Cl− concentration inside the concrete gradually increases with the increase of the diffusion rate of the old and new mortars. The resistance behavior of the recycled concrete to Cl− attack decreases with the increase of the thickness of the old mortar.

Study on Global Imperfection of Modular integrated Construction Structures for Second‐order Analysis

AbstractThe global imperfection significantly influences the stability design of the Modular integrated Construction (MiC) buildings. Currently, the initial global imperfection shapes recommended for MiC structures are formulated based on steel frames whose members are continuously connected. In practice, the columns and beams in MiC structures are composed of the members of adjacent module units, which are discontinuously connected through the special joints. Ignorance of such discontinuous features in MiC structures leads to an inappropriate estimation of the structural resistance. This paper introduces a new initial imperfection shape for MiC structures considering out‐of‐verticality of module columns and eccentricity between modules, capturing the discontinuous feature. Random initial imperfection shapes were generated using Monte‐Carlo simulation based on tolerances in regulations. The proposed imperfection shape is adopted in the analysis of a typical MiC structure and the result is compared with results from existing global imperfections in design codes. This research provides a practical global imperfection for the second‐order analysis and design of steel MiC structures. Recommendation for basic value of the proposed imperfection shape is also provided.

Low-Dimensional Multi-Trace Impedance Inversion in Sparse Space with Elastic Half Norm Constraint

Recently, multi-trace impedance inversion has attracted great interest in seismic exploration because it improves the horizontal continuity and fidelity of the inversion results by exploiting the lateral structure information of the strata. However, computational inefficiency affects its practical application. Furthermore, in terms of vertical constraints on the model parameters, it only considers smooth features while ignoring sharp discontinuity features. This leads to yielding an over-smooth solution that does not accurately reflect the distribution of underground rock. To deal with the above situations, we first develop a low-dimensional multi-trace impedance inversion (LMII) framework. Inspired by compressed sensing, this framework utilizes low-dimensional measurements in sparse space containing the maximum information of the signal to construct the objective function for multi-trace inversion, which can significantly reduce the size of the inversion problem and improve the inverse efficiency. Then, we introduce the elastic half (EH) norm as a vertical constraint on the model parameters in the LMII framework and formulate a novel constrained LMII model for impedance inversion. Because the introduced EH norm takes into account both the smoothness and blockiness of rock impedance, the constrained LMII model can effectively raise the inversion accuracy of complex strata. Finally, an efficient alternating multiplier iteration algorithm is derived based on the variable splitting technique to optimize the constrained LMII model. The performance of the developed approaches is tested using synthetic and practical data, and the results prove their feasibility and superiority.

Automatic identification of rock discontinuity and stability analysis of tunnel rock blocks using terrestrial laser scanning

Local geometric information and discontinuity features are key aspects of the analysis of the evolution and failure mechanisms of unstable rock blocks in rock tunnels. This study demonstrates the integration of terrestrial laser scanning (TLS) with distinct element method for rock mass characterization and stability analysis in tunnels. TLS records detailed geometric information of the surrounding rock mass by scanning and collecting the positions of millions of rock surface points without contact. By conducting a fuzzy K-means method, a discontinuity automatic identification algorithm was developed, and a method for obtaining the geometric parameters of discontinuities was proposed. This method permits the user to visually identify each discontinuity and acquire its spatial distribution features (e.g. occurrences, spacings, trace lengths) in great detail. Compared with hand mapping in conventional geotechnical surveys, the geometric information of discontinuities obtained by this approach is more accurate and the identification is more efficient. Then, a discrete fracture network with the same statistical characteristics as the actual discontinuities was generated with the distinct element method, and a representative numerical model of the jointed surrounding rock mass was established. By means of numerical simulation, potential unstable rock blocks were assessed, and failure mechanisms were analyzed. This method was applied to detection and assessment of unstable rock blocks in the spillway and sand flushing tunnel of the Hongshiyan hydropower project after a collapse. The results show that the noncontact detection of blocks was more labor-saving with lower safety risks compared with manual surveys, and the stability assessment was more reliable since the numerical model built by this method was more consistent with the distribution characteristics of actual joints. This study can provide a reference for geological survey and unstable rock block hazard mitigation in tunnels subjected to complex geology and active rockfalls.

Gravity waves in strong magnetic fields

ABSTRACT Strong magnetic fields in the cores of stars are expected to significantly modify the behaviour of gravity waves: this is likely the origin of suppressed dipole modes observed in many red giants. However, a detailed understanding of how such fields alter the spectrum and spatial structure of magnetogravity waves has been elusive. For a dipole field, we analytically characterize the horizontal eigenfunctions of magnetogravity modes, assuming that the wavevector is primarily radial. For axisymmetric modes (m = 0), the magnetogravity wave eigenfunctions become Hough functions, and they have a radial turning point for sufficiently strong magnetic fields. For non-axisymmetric modes (m ≠ 0), the interaction between the discrete g-mode spectrum and a continuum of Alfvén waves produces nearly discontinuous features in the fluid displacements at critical latitudes associated with a singularity in the fluid equations. We find that magnetogravity modes cannot propagate in regions with sufficiently strong magnetic fields, instead becoming evanescent. When encountering strong magnetic fields, ingoing gravity waves are likely refracted into outgoing slow magnetic waves. These outgoing waves approach infinite radial wavenumbers, which are likely to be damped efficiently. However, it may be possible for a small fraction of the wave power to escape the stellar core as pure Alfvén waves or magnetogravity waves confined to a very narrow equatorial band. The artificially sharp features in the Wentzel–Kramers–Brillouin-separated solutions suggest the need for global mode solutions which include small terms neglected in our analysis.

Autonomous Planning of Discontinuous Terrain-Dependent Crawling for Space Dobby Robots

Complex space missions require more space robotic extravehicular operations required to crawl on spacecraft surfaces with discontinuous features at the graspable point, greatly increasing the difficulty of space robot motion manipulation. Therefore, this paper proposes an autonomous planning method for space dobby robots based on dynamic potential fields. This method can realize the autonomous crawling of space dobby robots in discontinuous environments while considering the task objectives and the self-collision problem of robotic arms when crawling. In this method, a hybrid event-time trigger with event triggering as the main trigger is proposed by combining the working characteristics of space dobby robots and improving the gait timing trigger; the dynamic potential field function is designed to adjust the space robot robotic arm grasping point adaptively according to the space robot state. Simulation results verify the effectiveness of the proposed autonomous planning method.

An enhanced vision transformer with wavelet position embedding for histopathological image classification

Histopathological image classification is a fundamental task in pathological diagnosis workflow. It remains a huge challenge due to the complexity of histopathological images. Recently, hybrid methods combining convolutional neural networks(CNN) with vision transformers(ViT) are proposed to this field. These methods can well represent the global and local contextual information and achieve excellent classification performances. However, the downsampling operation like max-pooling which ignores the sampling theorem transmits the jagged artifacts into transformer, which would lead to an aliasing phenomenon. It makes the subsequent feature maps focus on the incorrect regions and influences the final classification results. In this work, we propose an enhanced vision transformer with wavelet position embedding to tackle this challenge. In particular, a wavelet position embedding module, which introduces the wave transform into position embedding, is employed to enhance the smoothness of discontinuous feature information by decomposing sequences into amplitude and phase in pathological feature maps. In addition, an external multi-head attention is proposed to replace self-attention in the transformer block with two linear layers. It reduces the cost of computation and excavates potential correlations between different samples. We evaluate the proposed method on three public histopathological classification challenging datasets, and perform a quantitative comparison with previous state-of-the-art methods. The results empirically demonstrate that our method achieves the best accuracy. Furthermore, it has the least parameters and a very low FLOPs. In conclusion, the enhanced vision transformer shows high classification performances and demonstrates significant potential for assisting pathologists in pathological diagnosis.