Occluded Gait Emotion Recognition Based on Multi-Scale Suppression Graph Convolutional Network

In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.

The application study on the multi-scales integrated prediction method to fractured reservoir description

In this paper,we implement three scales of fracture integrated prediction study by classifying it to macro-（ 1/4/λ）,meso-（ 1/100λ and 1/4λ） and micro-（ 1/100λ） scales.Based on the multi-scales rock physics modelling technique,the seismic azimuthal anisotropy characteristic is analyzed for distinguishing the fractures of meso-scale.Furthermore,by integrating geological core fracture description,image well-logging fracture interpretation,seismic attributes macro-scale fracture prediction and core slice micro-scale fracture characterization,an comprehensive multi-scale fracture prediction methodology and technique workflow are proposed by using geology,well-logging and seismic multi-attributes.Firstly,utilizing the geology core slice observation（Fractures description） and image well-logging data interpretation results,the main governing factors of fracture development are obtained,and then the control factors of the development of regional macro-scale fractures are carried out via modelling of the tectonic stress field.For the meso-scale fracture description,the poststack geometric attributes are used to describe the macro-scale fracture as well,the prestack attenuation seismic attribute is used to predict the meso-scale fracture.Finally,by combining lithological statistic inversion with superposed results of faults,the relationship of the meso-scale fractures,lithology and faults can be reasonably interpreted and the cause of meso-scale fractures can be verified.The micro-scale fracture description is mainly implemented by using the electron microscope scanning of cores.Therefore,the development of fractures in reservoirs is assessed by valuating three classes of fracture prediction results.An integrated fracture prediction application to a real field in Sichuan basin,where limestone reservoir fractures developed,is implemented.The application results in the study area indicates that the proposed multi-scales integrated fracture prediction method and the technique procedureare able to deal with the strong heterogeneity and multi-scales problems in fracture prediction.Moreover,the multi-scale fracture prediction technique integrated with geology,well-logging and seismic multi-information can help improve the reservoir characterization and sweet-spots prediction for the fractured hydrocarbon reservoirs.

Multi-scale fractures formation and distribution in tight sandstones—a case study of Triassic Chang 8 Member in the southwestern Ordos Basin

Fracture system is an important factor controlling tight oil accumulation in the Triassic Chang 8 Member,southwestern Ordos Basin,China.A systematic characterization of the multi-scale natural fractures is a basis for the efficient tight oil production.Based on outcrops,seismic reflections,well cores,well logs(image and conventional logging),casting thin sections,and scanning electron microscope observation,the multi-scale fractures occurrences and their influences on Chang 8 tight sandstone reservoirs are revealed.The results show that three periods of strike-slip faults and four scales of natural fractures developed,namely mega-scale(length>7×10^(7) mm),macro-scale(3.5×10^(5)<length<7×10^(7) mm),meso-scale(10<length<3.5×10^(5) mm),and micro-scale(length<10 mm)fractures.The mega-and macro-scale fractures developed by strike-slip faults are characterized by strike-segmentation and lateral zonation,which connect the source and reservoir.These scale fractures also influence the distribution and effectiveness of traps and reservoirs,which directly influence the hydrocarbon charging and distribution.The meso fractures include the tectonic,diagenetic,as well as hydrocarbon generation-related overpressure types.The meso-and micro-scale fractures improve the sandstone physical properties and also the tight oil well production performance.This integrated study helps to understand the distribution of multi-scale fractures in tight sandstones and provides a referable case and workflow for multi-scale fracture evaluation.

Fluid identification based on frequency-dependent AVO attribute inversion in multi-scale fracture media

A key problem in seismic inversion is the identification of the reservoir fluids. Elastic parameters, such as seismic wave velocity and formation density, do not have sufficient sensitivity, thus, the conventional amplitude-versus-offset（AVO） method is not applicable. The frequency-dependent AVO method considers the dependency of the seismic amplitude to frequency and uses this dependency to obtain information regarding the fluids in the reservoir fractures. We propose an improved Bayesian inversion method based on the parameterization of the Chapman model. The proposed method is based on 1） inelastic attribute inversion by the FDAVO method and 2） Bayesian statistics for fluid identification. First, we invert the inelastic fracture parameters by formulating an error function, which is used to match observations and model data. Second, we identify fluid types by using a Markov random field a priori model considering data from various sources, such as prestack inversion and well logs. We consider the inelastic parameters to take advantage of the viscosity differences among the different fluids possible. Finally, we use the maximum posteriori probability for obtaining the best lithology/fluid identification results.

A semi-analytical model for coupled flow in stress-sensitive multi-scale shale reservoirs with fractal characteristics

A large number of nanopores and complex fracture structures in shale reservoirs results in multi-scale flow of oil. With the development of shale oil reservoirs, the permeability of multi-scale media undergoes changes due to stress sensitivity, which plays a crucial role in controlling pressure propagation and oil flow. This paper proposes a multi-scale coupled flow mathematical model of matrix nanopores, induced fractures, and hydraulic fractures. In this model, the micro-scale effects of shale oil flow in fractal nanopores, fractal induced fracture network, and stress sensitivity of multi-scale media are considered. We solved the model iteratively using Pedrosa transform, semi-analytic Segmented Bessel function, Laplace transform. The results of this model exhibit good agreement with the numerical solution and field production data, confirming the high accuracy of the model. As well, the influence of stress sensitivity on permeability, pressure and production is analyzed. It is shown that the permeability and production decrease significantly when induced fractures are weakly supported. Closed induced fractures can inhibit interporosity flow in the stimulated reservoir volume (SRV). It has been shown in sensitivity analysis that hydraulic fractures are beneficial to early production, and induced fractures in SRV are beneficial to middle production. The model can characterize multi-scale flow characteristics of shale oil, providing theoretical guidance for rapid productivity evaluation.

Multi-scale physics-informed neural networks for solving high Reynolds number boundary layer flows based on matched asymptotic expansions

Multi-scale system remains a classical scientific problem in fluid dynamics,biology,etc.In the present study,a scheme of multi-scale Physics-informed neural networks is proposed to solve the boundary layer flow at high Reynolds numbers without any data.The flow is divided into several regions with different scales based on Prandtl's boundary theory.Different regions are solved with governing equations in different scales.The method of matched asymptotic expansions is used to make the flow field continuously.A flow on a semi infinite flat plate at a high Reynolds number is considered a multi-scale problem because the boundary layer scale is much smaller than the outer flow scale.The results are compared with the reference numerical solutions,which show that the msPINNs can solve the multi-scale problem of the boundary layer in high Reynolds number flows.This scheme can be developed for more multi-scale problems in the future.

Characteristics of proppant transport and placement within rough hydraulic fractures

A three-dimensional reconstruction of rough fracture surfaces of hydraulically fractured rock outcrops is carried out by casting process,a large-scale experimental setup for visualizing rough fractures is built to perform proppant transport experiments.The typical characteristics of proppant transport and placement in rough fractures and its intrinsic mechanisms are investigated,and the influences of fracture inclination,fracture width and fracturing fluid viscosity on proppant transport and placement in rough fractures are analyzed.The results show that the rough fractures cause variations in the shape of the flow channel and the fluid flow pattern,resulting in the bridging buildup during proppant transport to form unfilled zone,the emergence of multiple complex flow patterns such as channeling,reverse flow and bypassing of sand-carrying fluid,and the influence on the stability of the sand dune.The proppant has a higher placement rate in inclined rough fractures,with a maximum increase of 22.16 percentage points in the experiments compared to vertical fractures,but exhibits poor stability of the sand dune.Reduced fracture width aggravates the bridging of proppant and induces higher pumping pressure.Increasing the viscosity of the fracturing fluid can weaken the proppant bridging phenomenon caused by the rough fractures.

Effect of fracture fluid flowback on shale microfractures using CT scanning

The field data of shale fracturing demonstrate that the flowback performance of fracturing fluid is different from that of conventional reservoirs,where the flowback rate of shale fracturing fluid is lower than that of conventional reservoirs.At the early stage of flowback,there is no single-phase flow of the liquid phase in shale,but rather a gas-water two-phase flow,such that the single-phase flow model for tight oil and gas reservoirs is not applicable.In this study,pores and microfractures are extracted based on the experimental results of computed tomography(CT)scanning,and a spatial model of microfractures is established.Then,the influence of rough microfracture surfaces on the flow is corrected using the modified cubic law,which was modified by introducing the average deviation of the microfracture height as a roughness factor to consider the influence of microfracture surface roughness.The flow in the fracture network is simulated using the modified cubic law and the lattice Boltzmann method(LBM).The results obtained demonstrate that most of the fracturing fluid is retained in the shale microfractures,which explains the low fracturing fluid flowback rate in shale hydraulic fracturing.

Complication rates after direct anterior vs posterior approach for hip hemiarthroplasty in elderly individuals with femoral neck fractures

BACKGROUND Dislocation rates after hemiarthroplasty reportedly vary from 1%to 17%.This serious complication is associated with increased morbidity and mortality rates.Approaches to this surgery are still debated,with no consensus regarding the superiority of any single approach.AIM To compare early postoperative complications after implementing the direct anterior and posterior approaches(PL)for hip hemiarthroplasty after femoral neck fractures.METHODS This is a comparative,retrospective,single-center cohort study conducted at a university hospital.Between March 2008 and December 2018,273 patients(a total of 280 hips)underwent bipolar hemiarthroplasties(n=280)for displaced femoral neck fractures using either the PL(n=171)or the minimally invasive direct anterior approach(DAA)(n=109).The choice of approach was related to the surgeons’practices;the implant types were similar and unrelated to the approach.Dislocation rates and other complications were reviewed after a minimum followup of 6 mo.RESULTS Both treatment groups had similarly aged patients(mean age:82 years),sex ratios,patient body mass indexes,and patient comorbidities.Surgical data(surgery delay time,operative time,and blood loss volume)did not differ significantly between the groups.The 30 d mortality rate was higher in the PL group(9.9%)than in the DAA group(3.7%),but the difference was not statistically significant(P=0.052).Among the one-month survivors,a significantly higher rate of dislocation was observed in the PL group(14/154;9.1%)than in the DAA group(0/105;0%)(P=0.002).Of the 14 patients with dislocation,8 underwent revision surgery for recurrent instability(posterior group),and one of them had 2 additional procedures due to a deep infection.The rate of other complications(e.g.,perioperative and early postoperative periprosthetic fractures and infection-related complications)did not differ significantly between the groups.CONCLUSION These findings suggest that the DAA to bipolar hemiarthroplasty for patients with femoral neck fractures is associated with a lower dislocation rate(<1%)than the PL.

Evaluating the stability and volumetric flowback rate of proppant packs in hydraulic fractures using the lattice Boltzmann-discrete element coupling method

The stability and mobility of proppant packs in hydraulic fractures during hydrocarbon production are numerically investigated by the lattice Boltzmann-discrete element coupling method(LB-DEM).This study starts with a preliminary proppant settling test,from which a solid volume fraction of 0.575 is calibrated for the proppant pack in the fracture.In the established workflow to investigate proppant flowback,a displacement is applied to the fracture surfaces to compact the generated proppant pack as well as further mimicking proppant embedment under closure stress.When a pressure gradient is applied to drive the fluid-particle flow,a critical aperture-to-diameter ratio of 4 is observed,above which the proppant pack would collapse.The results also show that the volumetric proppant flowback rate increases quadratically with the fracture aperture,while a linear variation between the particle flux and the pressure gradient is exhibited for a fixed fracture aperture.The research outcome contributes towards an improved understanding of proppant flowback in hydraulic fractures,which also supports an optimised proppant size selection for hydraulic fracturing operations.

Integrated multi-scale approach combining global homogenization and local refinement for multi-field analysis of high-temperature superconducting composite magnets

Second-generation high-temperature superconducting(HTS)conductors,specifically rare earth-barium-copper-oxide(REBCO)coated conductor(CC)tapes,are promising candidates for high-energy and high-field superconducting applications.With respect to epoxy-impregnated REBCO composite magnets that comprise multilayer components,the thermomechanical characteristics of each component differ considerably under extremely low temperatures and strong electromagnetic fields.Traditional numerical models include homogenized orthotropic models,which simplify overall field calculation but miss detailed multi-physics aspects,and full refinement(FR)ones that are thorough but computationally demanding.Herein,we propose an extended multi-scale approach for analyzing the multi-field characteristics of an epoxy-impregnated composite magnet assembled by HTS pancake coils.This approach combines a global homogenization(GH)scheme based on the homogenized electromagnetic T-A model,a method for solving Maxwell's equations for superconducting materials based on the current vector potential T and the magnetic field vector potential A,and a homogenized orthotropic thermoelastic model to assess the electromagnetic and thermoelastic properties at the macroscopic scale.We then identify“dangerous regions”at the macroscopic scale and obtain finer details using a local refinement(LR)scheme to capture the responses of each component material in the HTS composite tapes at the mesoscopic scale.The results of the present GH-LR multi-scale approach agree well with those of the FR scheme and the experimental data in the literature,indicating that the present approach is accurate and efficient.The proposed GH-LR multi-scale approach can serve as a valuable tool for evaluating the risk of failure in large-scale HTS composite magnets.

Transfer learning framework for multi-scale crack type classification with sparse microseismic networks

Rock fracture mechanisms can be inferred from moment tensors(MT)inverted from microseismic events.However,MT can only be inverted for events whose waveforms are acquired across a network of sensors.This is limiting for underground mines where the microseismic stations often lack azimuthal coverage.Thus,there is a need for a method to invert fracture mechanisms using waveforms acquired by a sparse microseismic network.Here,we present a novel,multi-scale framework to classify whether a rock crack contracts or dilates based on a single waveform.The framework consists of a deep learning model that is initially trained on 2400000+manually labelled field-scale seismic and microseismic waveforms acquired across 692 stations.Transfer learning is then applied to fine-tune the model on 300000+MT-labelled labscale acoustic emission waveforms from 39 individual experiments instrumented with different sensor layouts,loading,and rock types in training.The optimal model achieves over 86%F-score on unseen waveforms at both the lab-and field-scale.This model outperforms existing empirical methods in classification of rock fracture mechanisms monitored by a sparse microseismic network.This facilitates rapid assessment of,and early warning against,various rock engineering hazard such as induced earthquakes and rock bursts.

Comparative efficacy of proximal femoral nail vs dynamic condylar screw in treating unstable intertrochanteric fractures

BACKGROUND Among the most frequent hip fractures are trochanteric fractures,which usually occur from low-energy trauma like minor falls,especially in older people with osteoporotic bones.AIM To evaluate the treatment efficacy of dynamic condylar screws(DCS)and proximal femoral nails(PFN)for unstable intertrochanteric fractures.METHODS To find pertinent randomized controlled trials and retrospective observational studies comparing PFN with DCS for the management of unstable femoral intertrochanteric fractures,a thorough search was carried out.For research studies published between January 1996 and April 2024,PubMed,EMBASE,Scopus,Web of Science,Cochrane Library,and Google Scholar were all searched.The complete texts of the papers were retrieved,vetted,and independently examined by two investigators.Disputes were settled by consensus,and any disagreements that persisted were arbitrated by a third author.RESULTS This study included six articles,comprising a total of 173 patients.Compared to the DCS,the PFN had a shorter operation time[mean difference(MD):-41.7 min,95%confidence interval(95%CI):-63.04 to-20.35,P=0.0001],higher success rates with closed reduction techniques[risk ratio(RR):34.05,95%CI:11.12-104.31,P<0.00001],and required less intraoperative blood transfusion(MD:-1.4 units,95%CI:-1.80 to-1.00,P<0.00001).Additionally,the PFN showed shorter fracture union time(MD:-6.92 wk,95%CI:-10.27 to-3.57,P<0.0001)and a lower incidence of reoperation(RR:0.37,95%CI:0.17-0.82,P=0.01).However,there was no discernible variation regarding hospital stay,implant-related complications,and infections.CONCLUSION Compared to DCS,PFN offers shorter operative times,reduces the blood transfusions requirements,achieves higher closed reduction success,enables faster fracture healing,and lowers reoperation incidence.

Multiple damage zones around hydraulic fractures generated by high-frequency pulsating hydraulic fracturing

Pulsating hydraulic fracturing(PHF)is a promising fracturing method and can generate a dynamic periodic pressure.The periodic pressure can induce fatigue failure of rocks and decrease initiation pressure of fracture.If the frequency of periodic pressure exceeds 10 Hz,the distribution of pressure along the main fracture will be heterogeneous,which is much different from the one induced by the common fracturing method.In this study,the impact of this special spatial feature of pressure on hydraulic fracture is mainly investigated.A coupled numerical simulation model is first proposed and verified through experimental and theoretical solutions.The mechanism of secondary fracture initiation around the main fracture is then discovered.In addition,sensitivity studies are conducted to find out the application potential of this new method.The results show that(1)this coupled numerical simulation model is accurate.Through comparison with experimental and theoretical data,the average error of this coupled model is less than 1.01%.(2)Even if a reservoir has no natural fracture,this heterogeneous distribution pressure can also cause many secondary fractures around the main fracture.(3)The mechanism of secondary fracture initiation is that this heterogeneous distribution pressure causes tensile stress at many locations along the main fracture.(4)Through adjusting the stimulation parameters,the stimulation efficiency can be improved.The average and amplitude of pressure can increase possibility of secondary fracture initiation.The frequency of this periodic pressure can increase number of secondary fractures.Even 6 secondary fractures along a 100 m-length main fracture can be generated.(5)The influence magnitudes of stimulation parameters are larger than ones of geomechanical properties,therefore,this new fracturing method has a wide application potential.

Visualization and characterization of experimental hydraulic fractures interacting with karst fracture-cavity distributions

Karst fracture-cavity carbonate reservoirs,in which natural cavities are connected by natural fractures to form cavity clusters in many circumstances,have become significant fields of oil and gas exploration and exploitation.Proppant fracturing is considered as the best method for exploiting carbonate reservoirs;however,previous studies primarily focused on the effects of individual types of geological formations,such as natural fractures or cavities,on fracture propagation.In this study,true-triaxial physical simulation experiments were systematically performed under four types of stress difference conditions after the accurate prefabrication of four types of different fracture-cavity distributions in artificial samples.Subsequently,the interaction mechanism between the hydraulic fractures and fracture-cavity structures was systematically analyzed in combination with the stress distribution,cross-sectional morphology of the main propagation path,and three-dimensional visualization of the overall fracture network.It was found that the propagation of hydraulic fractures near the cavity was inhibited by the stress concentration surrounding the cavity.In contrast,a natural fracture with a smaller approach angle(0°and 30°)around the cavity can alleviate the stress concentration and significantly facilitate the connection with the cavity.In addition,the hydraulic fracture crossed the natural fracture at the 45°approach angle and bypassed the cavity under higher stress difference conditions.A new stimulation effectiveness evaluation index was established based on the stimulated reservoir area(SRA),tortuosity of the hydraulic fractures(T),and connectivity index(CI)of the cavities.These findings provide new insights into the fracturing design of carbonate reservoirs.

A novel dandelion-based bionic proppant and its transportation mechanism in different types of fractures

Low-permeability reservoirs are generally characterized by low porosity and low permeability.Obtaining high production using the traditional method is technologically challenging because it yields a low reservoir recovery factor.In recent years,hydraulic fracturing technology is widely applied for efficiently exploiting and developing low-permeability reservoirs using a low-viscosity fluid as a fracturing fluid.However,the transportation of the proppant is inefficient in the low-viscosity fluid,and the proppant has a low piling-up height in fracture channels.These key challenges restrict the fluid(natural gas or oil)flow in fracture channels and their functional flow areas,reducing the profits of hydrocarbon exploitation.This study aimed to explore and develop a novel dandelion-bionic proppant by modifying the surface of the proppant and the fiber.Its structure was similar to that of dandelion seeds,and it had high transport and stacking efficiency in low-viscosity liquids compared with the traditional proppant.Moreover,the transportation efficiency of this newly developed proppant was investigated experimentally using six different types of fracture models(tortuous fracture model,rough fracture model,narrow fracture model,complex fracture model,large-scale single fracture model,and small-scale single fracture model).Experimental results indicated that,compared with the traditional proppant,the transportation efficiency and the packing area of the dandelion-based bionic proppant significantly improved in tap water or low-viscosity fluid.Compared with the traditional proppant,the dandelionbased bionic proppant had 0.1-4 times longer transportation length,0.3-5 times higher piling-up height,and 2-10 times larger placement area.The newly developed proppant also had some other extraordinary features.The tortuosity of the fracture did not influence the transportation of the novel proppant.This proppant could easily enter the branch fracture and narrow fracture with a high packing area in rough surface fractures.Based on the aforementioned characteristics,this novel proppant technique could improve the proppant transportation efficiency in the low-viscosity fracturing fluid and increase the ability of the proppant to enter the secondary fracture.This study might provide a new solution for effectively exploiting low-permeability hydrocarbon reservoirs.

Management of geriatric acetabular fractures:Contemporary treatment strategies

Acetabular fractures in the geriatric population are typically low-energy fractures resulting from a fall from standing height.Compromised bone quality in the elderly,as well as this population’s concomitant medical comorbidities,render the management of such fractures challenging and controversial.Non-operative management remains the mainstay of treatment,although such a choice is associated with numerous and serious complications related to both the hip joint as well as the general condition of the patient.On the other hand,operatively treating acetabular fractures(e.g.,with osteosynthesis or total hip arthroplasty)is gaining popularity.Osteosynthesis can be performed with open reduction and internal fixation or with minimally invasive techniques.Total hip arthroplasty could be performed either in the acute phase combined with osteosynthesis or as a delayed procedure after a period of non-operative management or after failed osteosynthesis of the acetabulum.Regardless of the implemented treatment,orthogeriatric co-management is considered extremely crucial,and it is currently one of the pillars of a successful outcome after an acetabular fracture.

Beyond the imaging evaluation of fractures of the lateral process of the talus:Let’s not forget concomitant injuries

Fractures of the lateral process of the talus(FLPT)are uncommon fractures that represent a clinical challenge.Traditional radiological classification systems rely predominantly on radiographic findings.However,due to the high rate of FLPT misdiagnosis and the limited accuracy in evaluating concomitant talar injuries through plain radiographs,novel imaging classification systems have been developed that aim to enhance the diagnosis of concomitant talar injuries,thereby optimizing patient management and reducing the incidence of long-term complications.

Stress tensor determination by modified hydraulic tests on pre-existing fractures:Method and stress constraints

The hydraulic testing of pre-existing fractures(HTPF)is one of the most promising in situ stress measurement methods,particularly for three-dimensional stress tensor determination.However,the stress tensor determination based on the HTPF method requires at least six tests or a minimum of 14-15 tests(under different conditions)for reliable results.In this study,we modified the HTPF method by considering the shear stress on each pre-existing fracture,which increased the number of equations for the stress tensor determination and decreased the number of tests required.Different shear stresses were attributed to different fractures by random sampling;therefore,the stress tensors were obtained by searching for the optimal solution using the least squares criterion based on the Monte Carlo method.Thereafter,we constrained the stress tensor based on the tensile strength criterion,compressive strength criterion,and vertical stress constraints.The inverted stress tensors were presented and analyzed based on the tensorial nature of the stress using the Euclidean mean stress tensor.Two stress-measurement campaigns in Weifang(Shandong Province,China)and Mercantour road tunnel(France)were implemented to highlight the validity and efficiency of the modified HTPF(M-HTPF)method.The results showed that the M-HTPF method can be applied for stress tensor inversion using only three to four tests on pre-existing fractures,neglecting the stress gradient.The inversion results were confined to relatively small distribution dispersions and were significantly reliable and stable due to the shear stresses on the fractures and the stress constraints employed.The M-HTPF method is highly feasible and efficient for complete stress tensor determination in a single borehole.

MSD-Net: Pneumonia Classification Model Based on Multi-Scale Directional Feature Enhancement

Computer-aided diagnosis of pneumonia based on deep learning is a research hotspot.However,there are some problems that the features of different sizes and different directions are not sufficient when extracting the features in lung X-ray images.A pneumonia classification model based on multi-scale directional feature enhancement MSD-Net is proposed in this paper.The main innovations are as follows:Firstly,the Multi-scale Residual Feature Extraction Module(MRFEM)is designed to effectively extract multi-scale features.The MRFEM uses dilated convolutions with different expansion rates to increase the receptive field and extract multi-scale features effectively.Secondly,the Multi-scale Directional Feature Perception Module(MDFPM)is designed,which uses a three-branch structure of different sizes convolution to transmit direction feature layer by layer,and focuses on the target region to enhance the feature information.Thirdly,the Axial Compression Former Module(ACFM)is designed to perform global calculations to enhance the perception ability of global features in different directions.To verify the effectiveness of the MSD-Net,comparative experiments and ablation experiments are carried out.In the COVID-19 RADIOGRAPHY DATABASE,the Accuracy,Recall,Precision,F1 Score,and Specificity of MSD-Net are 97.76%,95.57%,95.52%,95.52%,and 98.51%,respectively.In the chest X-ray dataset,the Accuracy,Recall,Precision,F1 Score and Specificity of MSD-Net are 97.78%,95.22%,96.49%,95.58%,and 98.11%,respectively.This model improves the accuracy of lung image recognition effectively and provides an important clinical reference to pneumonia Computer-Aided Diagnosis.