The infamous type Ⅳ failure within the fine-grained heat-affected zone (FGHAZ) in G115 steel weldments seriously threatens the safe operation of ultra-supercritical (USC) power plants.In this work,the traditional the...The infamous type Ⅳ failure within the fine-grained heat-affected zone (FGHAZ) in G115 steel weldments seriously threatens the safe operation of ultra-supercritical (USC) power plants.In this work,the traditional thermo-mechanical treatment was modified via the replacement of hot-rolling with cold rolling,i.e.,normalizing,cold rolling,and tempering (NCT),which was developed to improve the creep strength of the FGHAZ in G115 steel weldments.The NCT treatment effectively promoted the dissolution of preformed M_(23)C_(6)particles and relieved the boundary segregation of C and Cr during welding thermal cycling,which accelerated the dispersed reprecipitation of M_(23)C_(6) particles within the fresh reaustenitized grains during post-weld heat treatment.In addition,the precipitation of Cu-rich phases and MX particles was promoted evidently due to the deformation-induced dislocations.As a result,the interacting actions between precipitates,dislocations,and boundaries during creep were reinforced considerably.Following this strategy,the creep rupture life of the FGHAZ in G115 steel weldments can be prolonged by 18.6%,which can further push the application of G115 steel in USC power plants.展开更多
Fine-grained recognition of ships based on remote sensing images is crucial to safeguarding maritime rights and interests and maintaining national security.Currently,with the emergence of massive high-resolution multi...Fine-grained recognition of ships based on remote sensing images is crucial to safeguarding maritime rights and interests and maintaining national security.Currently,with the emergence of massive high-resolution multi-modality images,the use of multi-modality images for fine-grained recognition has become a promising technology.Fine-grained recognition of multi-modality images imposes higher requirements on the dataset samples.The key to the problem is how to extract and fuse the complementary features of multi-modality images to obtain more discriminative fusion features.The attention mechanism helps the model to pinpoint the key information in the image,resulting in a significant improvement in the model’s performance.In this paper,a dataset for fine-grained recognition of ships based on visible and near-infrared multi-modality remote sensing images has been proposed first,named Dataset for Multimodal Fine-grained Recognition of Ships(DMFGRS).It includes 1,635 pairs of visible and near-infrared remote sensing images divided into 20 categories,collated from digital orthophotos model provided by commercial remote sensing satellites.DMFGRS provides two types of annotation format files,as well as segmentation mask images corresponding to the ship targets.Then,a Multimodal Information Cross-Enhancement Network(MICE-Net)fusing features of visible and near-infrared remote sensing images,has been proposed.In the network,a dual-branch feature extraction and fusion module has been designed to obtain more expressive features.The Feature Cross Enhancement Module(FCEM)achieves the fusion enhancement of the two modal features by making the channel attention and spatial attention work cross-functionally on the feature map.A benchmark is established by evaluating state-of-the-art object recognition algorithms on DMFGRS.MICE-Net conducted experiments on DMFGRS,and the precision,recall,mAP0.5 and mAP0.5:0.95 reached 87%,77.1%,83.8%and 63.9%,respectively.Extensive experiments demonstrate that the proposed MICE-Net has more excellent performance on DMFGRS.Built on lightweight network YOLO,the model has excellent generalizability,and thus has good potential for application in real-life scenarios.展开更多
BACKGROUND:Disseminated intravascular coagulation(DIC)is associated with increased mortality in sepsis patients.In this study,we aimed to assess the clinical ability of sepsis-induced coagulopathy(SIC)and sepsis-assoc...BACKGROUND:Disseminated intravascular coagulation(DIC)is associated with increased mortality in sepsis patients.In this study,we aimed to assess the clinical ability of sepsis-induced coagulopathy(SIC)and sepsis-associated coagulopathy(SAC)criteria in identifying overt-DIC and preDIC status in sepsis patients.METHODS:Data from 419 sepsis patients were retrospectively collected from July 2018 to December 2022.The performances of the SIC and SAC were assessed to identify overt-DIC on days 1,3,7,or 14.The SIC status or SIC score on day 1,the SAC status or SAC score on day 1,and the sum of the SIC or SAC scores on days 1 and 3 were compared in terms of their ability to identify pre-DIC.The SIC or SAC status on day 1 was evaluated as a pre-DIC indicator for anticoagulant initiation.RESULTS:On day 1,the incidences of coagulopathy according to overt-DIC,SIC and SAC criteria were 11.7%,22.0%and 31.5%,respectively.The specificity of SIC for identifying overt-DIC was significantly higher than that of the SAC criteria from day 1 to day 14(P<0.05).On day 1,the SIC score with a cut-off value>3 had a significantly higher sensitivity(72.00%)and area under the curve(AUC)(0.69)in identifying pre-DIC than did the SIC or SAC status(sensitivity:SIC status 44.00%,SAC status 52.00%;AUC:SIC status 0.62,SAC status 0.61).The sum of the SIC scores on days 1 and 3 had a higher AUC value for identifying the pre-DIC state than that of SAC(0.79 vs.0.69,P<0.001).Favorable effects of anticoagulant therapy were observed in SIC(adjusted hazard ratio[HR]=0.216,95%confidence interval[95%CI]:0.060–0.783,P=0.018)and SAC(adjusted HR=0.146,95%CI:0.041–0.513,P=0.003).CONCLUSION:The SIC and SAC seem to be valuable for predicting overt-DIC.The sum of SIC scores on days 1 and 3 has the potential to help identify pre-DIC.展开更多
The fingerprinting-based approach using the wireless local area network(WLAN)is widely used for indoor localization.However,the construction of the fingerprint database is quite time-consuming.Especially when the posi...The fingerprinting-based approach using the wireless local area network(WLAN)is widely used for indoor localization.However,the construction of the fingerprint database is quite time-consuming.Especially when the position of the access point(AP)or wall changes,updating the fingerprint database in real-time is difficult.An appropriate indoor localization approach,which has a low implementation cost,excellent real-time performance,and high localization accuracy and fully considers complex indoor environment factors,is preferred in location-based services(LBSs)applications.In this paper,we proposed a fine-grained grid computing(FGGC)model to achieve decimeter-level localization accuracy.Reference points(RPs)are generated in the grid by the FGGC model.Then,the received signal strength(RSS)values at each RP are calculated with the attenuation factors,such as the frequency band,three-dimensional propagation distance,and walls in complex environments.As a result,the fingerprint database can be established automatically without manual measurement,and the efficiency and cost that the FGGC model takes for the fingerprint database are superior to previous methods.The proposed indoor localization approach,which estimates the position step by step from the approximate grid location to the fine-grained location,can achieve higher real-time performance and localization accuracy simultaneously.The mean error of the proposed model is 0.36 m,far lower than that of previous approaches.Thus,the proposed model is feasible to improve the efficiency and accuracy of Wi-Fi indoor localization.It also shows high-accuracy performance with a fast running speed even under a large-size grid.The results indicate that the proposed method can also be suitable for precise marketing,indoor navigation,and emergency rescue.展开更多
Objective:Lung adenocarcinoma exhibits diverse genetic and morphological backgrounds,in addition to considerable differences in clinical pathology and molecular biological characteristics.Among these,the phenomenon of...Objective:Lung adenocarcinoma exhibits diverse genetic and morphological backgrounds,in addition to considerable differences in clinical pathology and molecular biological characteristics.Among these,the phenomenon of spread through air space(STAS),a distinct mode of lung cancer infiltration,has rarely been reported.Therefore,this study aimed to explore the relationship between STAS tumor cells and the clinical and molecular characteristics of patients with lung adenocarcinoma,as well as their impact on prognosis.Methods:This study included 147 patients who were diagnosed with lung adenocarcinoma at the Inner Mongolia Autonomous Region Cancer Institute between January 2014 and December 2017.Surgical resection specimens were retrospectively analyzed.Using univariate and multivariate Cox analyses,we assessed the association between STAS and the clinicopathological features and molecular characteristics of patients with lung adenocarcinoma.Furthermore,we investigated the effects on patient prognosis.In addition,we developed a column–line plot prediction model and performed internal validation.Results:Patients with positive STAS had a significantly higher proportion of tumors with a diameter≥2 cm,with infiltration around the pleura,blood vessels,and nerves,and a pathological stage>IIB than in STAS-negative patients(P<0.05).Cox multivariate survival analysis revealed that clinical stage,STAS status,tumor size,and visceral pleural invasion were independent prognostic factors influencing the 5-year progression-free survival in patients with lung adenocarcinoma.The predictive values and P values from the Hosmer-Lemeshow test were 0.8 and 0.2,respectively,indicating no statistical difference.Receiver operating characteristic curve analysis demonstrated areas under the curve of 0.884 and 0.872 for the training and validation groups,respectively.The nomogram model exhibited the best fit with a value of 192.09.Conclusions:Clinical stage,pleural invasion,vascular invasion,peripheral nerve invasion,tumor size,and necrosis are independent prognostic factors for patients with STAS-positive lung adenocarcinoma.The nomogrambased on the clinical stage,pleural invasion,vascular invasion,peripheral nerve invasion,tumor size,and necrosis showed good accuracy,differentiation,and clinical practicality.展开更多
In cold regions,understanding the freezing strength of the interface between soil and structure is crucial for designing frost-resistant foundations.To investigate how the content of cement powder in aeolian sand affe...In cold regions,understanding the freezing strength of the interface between soil and structure is crucial for designing frost-resistant foundations.To investigate how the content of cement powder in aeolian sand affects this strength,we conducted direct shear tests under various conditions such as different fine-grained soil content,normal stress,and initial moisture content of the soil.By analyzing parameters like soil properties,and volume of ice content,and using the Mohr-Coulomb strength theory to define interface strength,we aimed to indirectly measure the cementation strength of the interface.Our findings revealed that as the particle content increased,the interface stress-strain curves became noticeably stiffer.We also observed a positive linear relationship between freezing strength and silt content,while the initial moisture content of the soil did not significantly impact the strengthening effect of fine-grained soil on freezing strength.Moreover,we discovered that as the powder content increased,the force binding the ice to the interface decreased,while the friction angle at the interface increased.However,the cohesion force at the interface remained relatively unchanged.Overall,our analysis suggests that the increase in freezing strength due to fine-grained soil content is primarily due to the heightened friction between aeolian sand and the interface.展开更多
The geological conditions and processes of fine-grained gravity flow sedimentation in continental lacustrine basins in China are analyzed to construct the model of fine-grained gravity flow sedimentation in lacustrine...The geological conditions and processes of fine-grained gravity flow sedimentation in continental lacustrine basins in China are analyzed to construct the model of fine-grained gravity flow sedimentation in lacustrine basin,reveal the development laws of fine-grained deposits and source-reservoir,and identify the sweet sections of shale oil.The results show that fine-grained gravity flow is one of the important sedimentary processes in deep lake environment,and it can transport fine-grained clasts and organic matter in shallow water to deep lake,forming sweet sections and high-quality source rocks of shale oil.Fine-grained gravity flow deposits in deep waters of lacustrine basins in China are mainly fine-grained high-density flow,fine-grained turbidity flow(including surge-like turbidity flow and fine-grained hyperpycnal flow),fine-grained viscous flow(including fine-grained debris flow and mud flow),and fine-grained transitional flow deposits.The distribution of fine-grained gravity flow deposits in the warm and humid unbalanced lacustrine basins are controlled by lake-level fluctuation,flooding events,and lakebed paleogeomorphology.During the lake-level rise,fine-grained hyperpycnal flow caused by flooding formed fine-grained channel–levee–lobe system in the flat area of the deep lake.During the lake-level fall,the sublacustrine fan system represented by unconfined channel was developed in the flexural slope breaks and sedimentary slopes of depressed lacustrine basins,and in the steep slopes of faulted lacustrine basins;the sublacustrine fan system with confined or unconfined channel was developed on the gentle slopes and in axial direction of faulted lacustrine basins,with fine-grained gravity flow deposits possibly existing in the lower fan.Within the fourth-order sequences,transgression might lead to organic-rich shale and fine-grained hyperpycnal flow deposits,while regression might cause fine-grained high-density flow,surge-like turbidity flow,fine-grained debris flow,mud flow,and fine-grained transitional flow deposits.Since the Permian,in the shale strata of lacustrine basins in China,multiple transgression-regression cycles of fourth-order sequences have formed multiple source-reservoir assemblages.Diverse fine-grained gravity flow sedimentation processes have created sweet sections of thin siltstone consisting of fine-grained high-density flow,fine-grained hyperpycnal flow and surge-like turbidity flow deposits,sweet sections with interbeds of mudstone and siltstone formed by fine-grained transitional flows,and sweet sections of shale containing silty and muddy clasts and with horizontal bedding formed by fine-grained debris flow and mud flow.The model of fine-grained gravity flow sedimentation in lacustrine basin is significant for the scientific evaluation of sweet shale oil reservoir and organic-rich source rock.展开更多
Fine-grained image classification is a challenging research topic because of the high degree of similarity among categories and the high degree of dissimilarity for a specific category caused by different poses and scal...Fine-grained image classification is a challenging research topic because of the high degree of similarity among categories and the high degree of dissimilarity for a specific category caused by different poses and scales.A cul-tural heritage image is one of thefine-grained images because each image has the same similarity in most cases.Using the classification technique,distinguishing cultural heritage architecture may be difficult.This study proposes a cultural heri-tage content retrieval method using adaptive deep learning forfine-grained image retrieval.The key contribution of this research was the creation of a retrieval mod-el that could handle incremental streams of new categories while maintaining its past performance in old categories and not losing the old categorization of a cul-tural heritage image.The goal of the proposed method is to perform a retrieval task for classes.Incremental learning for new classes was conducted to reduce the re-training process.In this step,the original class is not necessary for re-train-ing which we call an adaptive deep learning technique.Cultural heritage in the case of Thai archaeological site architecture was retrieved through machine learn-ing and image processing.We analyze the experimental results of incremental learning forfine-grained images with images of Thai archaeological site architec-ture from world heritage provinces in Thailand,which have a similar architecture.Using afine-grained image retrieval technique for this group of cultural heritage images in a database can solve the problem of a high degree of similarity among categories and a high degree of dissimilarity for a specific category.The proposed method for retrieving the correct image from a database can deliver an average accuracy of 85 percent.Adaptive deep learning forfine-grained image retrieval was used to retrieve cultural heritage content,and it outperformed state-of-the-art methods infine-grained image retrieval.展开更多
A comparison between deep learning and standalone models in predicting the compaction parameters of soil is presented in this research.One hundred and ninety and fifty-three soil samples were randomly picked up from t...A comparison between deep learning and standalone models in predicting the compaction parameters of soil is presented in this research.One hundred and ninety and fifty-three soil samples were randomly picked up from two hundred and forty-three soil samples to create training and validation datasets,respectively.The performance and accuracy of the models were measured by root mean square error(RMSE),coefficient of determination(R2),Pearson product-moment correlation coefficient(r),mean absolute error(MAE),variance accounted for(VAF),mean absolute percentage error(MAPE),weighted mean absolute percentage error(WMAPE),a20-index,index of scatter(IOS),and index of agreement(IOA).Comparisons between standalone models demonstrate that the model MD 29 in Gaussian process regression(GPR)and model MD 101 in support vector machine(SVM)can achieve over 96%of accuracy in predicting the optimum moisture content(OMC)and maximum dry density(MDD)of soil,and outperformed other standalone models.The comparison between deep learning models shows that the models MD 46 and MD 146 in long short-term memory(LSTM)predict OMC and MDD with higher accuracy than ANN models.However,the LSTM models outperformed the GPR models in predicting the compaction parameters.The sensitivity analysis illustrates that fine content(FC),specific gravity(SG),and liquid limit(LL)highly influence the prediction of compaction parameters.展开更多
Sensors produce a large amount of multivariate time series data to record the states of Internet of Things(IoT)systems.Multivariate time series timestamp anomaly detection(TSAD)can identify timestamps of attacks and m...Sensors produce a large amount of multivariate time series data to record the states of Internet of Things(IoT)systems.Multivariate time series timestamp anomaly detection(TSAD)can identify timestamps of attacks and malfunctions.However,it is necessary to determine which sensor or indicator is abnormal to facilitate a more detailed diagnosis,a process referred to as fine-grained anomaly detection(FGAD).Although further FGAD can be extended based on TSAD methods,existing works do not provide a quantitative evaluation,and the performance is unknown.Therefore,to tackle the FGAD problem,this paper first verifies that the TSAD methods achieve low performance when applied to the FGAD task directly because of the excessive fusion of features and the ignoring of the relationship’s dynamic changes between indicators.Accordingly,this paper proposes a mul-tivariate time series fine-grained anomaly detection(MFGAD)framework.To avoid excessive fusion of features,MFGAD constructs two sub-models to independently identify the abnormal timestamp and abnormal indicator instead of a single model and then combines the two kinds of abnormal results to detect the fine-grained anomaly.Based on this framework,an algorithm based on Graph Attention Neural Network(GAT)and Attention Convolutional Long-Short Term Memory(A-ConvLSTM)is proposed,in which GAT learns temporal features of multiple indicators to detect abnormal timestamps and A-ConvLSTM captures the dynamic relationship between indicators to identify abnormal indicators.Extensive simulations on a real-world dataset demonstrate that the proposed algorithm can achieve a higher F1 score and hit rate than the extension of existing TSAD methods with the benefit of two independent sub-models for timestamp and indicator detection.展开更多
Mining more discriminative temporal features to enrich temporal context representation is considered the key to fine-grained action recog-nition.Previous action recognition methods utilize a fixed spatiotemporal windo...Mining more discriminative temporal features to enrich temporal context representation is considered the key to fine-grained action recog-nition.Previous action recognition methods utilize a fixed spatiotemporal window to learn local video representation.However,these methods failed to capture complex motion patterns due to their limited receptive field.To solve the above problems,this paper proposes a lightweight Temporal Pyramid Excitation(TPE)module to capture the short,medium,and long-term temporal context.In this method,Temporal Pyramid(TP)module can effectively expand the temporal receptive field of the network by using the multi-temporal kernel decomposition without significantly increasing the computational cost.In addition,the Multi Excitation module can emphasize temporal importance to enhance the temporal feature representation learning.TPE can be integrated into ResNet50,and building a compact video learning framework-TPENet.Extensive validation experiments on several challenging benchmark(Something-Something V1,Something-Something V2,UCF-101,and HMDB51)datasets demonstrate that our method achieves a preferable balance between computation and accuracy.展开更多
Image captioning involves two different major modalities(image and sentence)that convert a given image into a language that adheres to visual semantics.Almost all methods first extract image features to reduce the dif...Image captioning involves two different major modalities(image and sentence)that convert a given image into a language that adheres to visual semantics.Almost all methods first extract image features to reduce the difficulty of visual semantic embedding and then use the caption model to generate fluent sentences.The Convolutional Neural Network(CNN)is often used to extract image features in image captioning,and the use of object detection networks to extract region features has achieved great success.However,the region features retrieved by this method are object-level and do not pay attention to fine-grained details because of the detection model’s limitation.We offer an approach to address this issue that more properly generates captions by fusing fine-grained features and region features.First,we extract fine-grained features using a panoramic segmentation algorithm.Second,we suggest two fusion methods and contrast their fusion outcomes.An X-linear Attention Network(X-LAN)serves as the foundation for both fusion methods.According to experimental findings on the COCO dataset,the two-branch fusion approach is superior.It is important to note that on the COCO Karpathy test split,CIDEr is increased up to 134.3%in comparison to the baseline,highlighting the potency and viability of our method.展开更多
The continuously collected cores from the Permo-Carboniferous coal-bearing strata of the eastern Ordos Basin are essential for studying the hydrocarbon potential in this region.This study adopted sedimentological and ...The continuously collected cores from the Permo-Carboniferous coal-bearing strata of the eastern Ordos Basin are essential for studying the hydrocarbon potential in this region.This study adopted sedimentological and geochemical methods to analyze the sedimentary environment,material composition,and geochemical characteristics of the coal-bearing strata.The differences in depositional and paleoclimatic conditions were compared;and the factors influencing the organic matter content of fine-grained sediments were explored.The depositional environment of the Benxi and Jinci formations was lagoon to tidal flat with weakly reduced waters with low salinity and dry-hot paleoclimatic conditions;while that of the Taiyuan Formation was a carbonate platform and shallow water delta front,where the water was highly reductive.The xerothermic climate alternated with the warm and humid climate.The period of maximum transgression in the Permo-Carboniferous has the highest water salinity.The Shanxi Formation was deposited in a shallow water delta front with a brackish and fresh water environment and alternative weak reductiveness.And the paleoclimate condition is dry-hot.The TOC content in fine-grained samples was averaging 1.52%.The main controlling mechanism of organic matter in this area was the input conditions according to the analysis on input and preservation of organic matter.展开更多
The remote sensing ships’fine-grained classification technology makes it possible to identify certain ship types in remote sensing images,and it has broad application prospects in civil and military fields.However,th...The remote sensing ships’fine-grained classification technology makes it possible to identify certain ship types in remote sensing images,and it has broad application prospects in civil and military fields.However,the current model does not examine the properties of ship targets in remote sensing images with mixed multi-granularity features and a complicated backdrop.There is still an opportunity for future enhancement of the classification impact.To solve the challenges brought by the above characteristics,this paper proposes a Metaformer and Residual fusion network based on Visual Attention Network(VAN-MR)for fine-grained classification tasks.For the complex background of remote sensing images,the VAN-MR model adopts the parallel structure of large kernel attention and spatial attention to enhance the model’s feature extraction ability of interest targets and improve the classification performance of remote sensing ship targets.For the problem of multi-grained feature mixing in remote sensing images,the VAN-MR model uses a Metaformer structure and a parallel network of residual modules to extract ship features.The parallel network has different depths,considering both high-level and lowlevel semantic information.The model achieves better classification performance in remote sensing ship images with multi-granularity mixing.Finally,the model achieves 88.73%and 94.56%accuracy on the public fine-grained ship collection-23(FGSC-23)and FGSCR-42 datasets,respectively,while the parameter size is only 53.47 M,the floating point operations is 9.9 G.The experimental results show that the classification effect of VAN-MR is superior to that of traditional CNNs model and visual model with Transformer structure under the same parameter quantity.展开更多
Existing explanation methods for Convolutional Neural Networks(CNNs)lack the pixel-level visualization explanations to generate the reliable fine-grained decision features.Since there are inconsistencies between the e...Existing explanation methods for Convolutional Neural Networks(CNNs)lack the pixel-level visualization explanations to generate the reliable fine-grained decision features.Since there are inconsistencies between the explanation and the actual behavior of the model to be interpreted,we propose a Fine-Grained Visual Explanation for CNN,namely F-GVE,which produces a fine-grained explanation with higher consistency to the decision of the original model.The exact backward class-specific gradients with respect to the input image is obtained to highlight the object-related pixels the model used to make prediction.In addition,for better visualization and less noise,F-GVE selects an appropriate threshold to filter the gradient during the calculation and the explanation map is obtained by element-wise multiplying the gradient and the input image to show fine-grained classification decision features.Experimental results demonstrate that F-GVE has good visual performances and highlights the importance of fine-grained decision features.Moreover,the faithfulness of the explanation in this paper is high and it is effective and practical on troubleshooting and debugging detection.展开更多
Fine-grained magnesium was tested under stress-controlled tension-tension cyclic loading at -30 ℃ and the tested sample was observed using scanning electron microscope and electron backscatter diffraction to explore ...Fine-grained magnesium was tested under stress-controlled tension-tension cyclic loading at -30 ℃ and the tested sample was observed using scanning electron microscope and electron backscatter diffraction to explore the fatigue behavior and crack propagation. The fatigue data showed that the material experienced cyclic softening followed by cyclic hardening before the final fracture failure. The microscopic observations demonstrated that the cracks were almost perpendicular to the loading direction with some zigzags and the cracks progressed along both small angle grain boundaries and large angle grain boundaries. Although the cracks were mainly propagated along large angle grain boundaries, the value of grain boundary angle was not the primary factor to determine the crack propagation direction. The local residual strain from the rolling process was released due to the crack propagation and there was more strain relaxation at regions closer to the cracks.展开更多
With the rapid development of deepfake technology,the authenticity of various types of fake synthetic content is increasing rapidly,which brings potential security threats to people’s daily life and social stability....With the rapid development of deepfake technology,the authenticity of various types of fake synthetic content is increasing rapidly,which brings potential security threats to people’s daily life and social stability.Currently,most algorithms define deepfake detection as a binary classification problem,i.e.,global features are first extracted using a backbone network and then fed into a binary classifier to discriminate true or false.However,the differences between real and fake samples are often subtle and local,and such global feature-based detection algorithms are not optimal in efficiency and accuracy.To this end,to enhance the extraction of forgery details in deep forgery samples,we propose a multi-branch deepfake detection algorithm based on fine-grained features from the perspective of fine-grained classification.First,to address the critical problem in locating discriminative feature regions in fine-grained classification tasks,we investigate a method for locating multiple different discriminative regions and design a lightweight feature localization module to obtain crucial feature representations by augmenting the most significant parts of the feature map.Second,using information complementation,we introduce a correlation-guided fusion module to enhance the discriminative feature information of different branches.Finally,we use the global attention module in the multi-branch model to improve the cross-dimensional interaction of spatial domain and channel domain information and increase the weights of crucial feature regions and feature channels.We conduct sufficient ablation experiments and comparative experiments.The experimental results show that the algorithm outperforms the detection accuracy and effectiveness on the FaceForensics++and Celeb-DF-v2 datasets compared with the representative detection algorithms in recent years,which can achieve better detection results.展开更多
Rationale:Disseminated tuberculosis involves the central nervous system in up to a third of cases.However,meningitis and spondylodiscitis due to miliary tuberculosis rarely occur together,particularly in the immuno-co...Rationale:Disseminated tuberculosis involves the central nervous system in up to a third of cases.However,meningitis and spondylodiscitis due to miliary tuberculosis rarely occur together,particularly in the immuno-competent population.Patient concerns:A 37-year-old immunocompetent male presented with altered level of consciousness for one week and lower back pain with evening pyrexia for one month.Examination revealed spastic paraplegia and left hemiparesis.Diagnosis:Disseminated tuberculosis presenting with meningitis and spondylodiscitis.Interventions:Category I anti-tuberculous therapy with a tapering regimen of intravenous dexamethasone was administered.Outcomes:There was clinical improvement after nine months of treatment.Lessons:Tuberculosis may present with atypical clinical manifestations.Contrast enhanced computed tomography scan or magnetic resonance imaging combined with histopathological features,a high index of suspicion and clinical improvement with anti-tuberculous treatment can confirm the diagnosis in the absence of microbiological evidence,especially in extrapulmonary tuberculosis.展开更多
In recent years,the development of deep learning has further improved hash retrieval technology.Most of the existing hashing methods currently use Convolutional Neural Networks(CNNs)and Recurrent Neural Networks(RNNs)...In recent years,the development of deep learning has further improved hash retrieval technology.Most of the existing hashing methods currently use Convolutional Neural Networks(CNNs)and Recurrent Neural Networks(RNNs)to process image and text information,respectively.This makes images or texts subject to local constraints,and inherent label matching cannot capture finegrained information,often leading to suboptimal results.Driven by the development of the transformer model,we propose a framework called ViT2CMH mainly based on the Vision Transformer to handle deep Cross-modal Hashing tasks rather than CNNs or RNNs.Specifically,we use a BERT network to extract text features and use the vision transformer as the image network of the model.Finally,the features are transformed into hash codes for efficient and fast retrieval.We conduct extensive experiments on Microsoft COCO(MS-COCO)and Flickr30K,comparing with baselines of some hashing methods and image-text matching methods,showing that our method has better performance.展开更多
BACKGROUND Forehead osteoma is a commonly encountered benign facial bone tumor.Endoscopic excision of benign forehead masses is widely performed.Here,we report a rare case of recurrent forehead osteoma that disseminat...BACKGROUND Forehead osteoma is a commonly encountered benign facial bone tumor.Endoscopic excision of benign forehead masses is widely performed.Here,we report a rare case of recurrent forehead osteoma that disseminated after a previous osteoma excision.CASE SUMMARY A 54-year-old female patient had previously undergone endoscopic removal of a single forehead osteoma at 30 years of age.However,she had a recurrent osteoma around the same site and underwent another endoscopic resection at 40 years of age.During her first visit to our outpatient clinic,she presented with a cobblestone-like irregular surface on the forehead and a 3D facial bone computed tomography scan revealed a widely ragged surface of the inoculated osteoma on the outer table of the frontal bone.Under general anesthesia,we performed a radical complete excision of the disseminated osteoma through a bicoronal incision using an osteotome,chisel,mallet,and rasping.We hypothesized that the recurrence may have been caused by the inoculation of residual osteoma remnants from the previous procedure.Craniofacial surgeons should be cautious when removing osteoma particles,particularly when using an endoscopic approach.CONCLUSION To prevent recurrence,it is essential to conduct additional meticulous burring and a thorough inspection of the surface after copious irrigation.展开更多
基金financially supported by the National Key R&D Program of China(No.2022YFB3705300)the National Natural Science Foundation of China(Nos.U1960204 and 51974199)the Postdoctoral Fellowship Program of CPSF(No.GZB20230515)。
文摘The infamous type Ⅳ failure within the fine-grained heat-affected zone (FGHAZ) in G115 steel weldments seriously threatens the safe operation of ultra-supercritical (USC) power plants.In this work,the traditional thermo-mechanical treatment was modified via the replacement of hot-rolling with cold rolling,i.e.,normalizing,cold rolling,and tempering (NCT),which was developed to improve the creep strength of the FGHAZ in G115 steel weldments.The NCT treatment effectively promoted the dissolution of preformed M_(23)C_(6)particles and relieved the boundary segregation of C and Cr during welding thermal cycling,which accelerated the dispersed reprecipitation of M_(23)C_(6) particles within the fresh reaustenitized grains during post-weld heat treatment.In addition,the precipitation of Cu-rich phases and MX particles was promoted evidently due to the deformation-induced dislocations.As a result,the interacting actions between precipitates,dislocations,and boundaries during creep were reinforced considerably.Following this strategy,the creep rupture life of the FGHAZ in G115 steel weldments can be prolonged by 18.6%,which can further push the application of G115 steel in USC power plants.
文摘Fine-grained recognition of ships based on remote sensing images is crucial to safeguarding maritime rights and interests and maintaining national security.Currently,with the emergence of massive high-resolution multi-modality images,the use of multi-modality images for fine-grained recognition has become a promising technology.Fine-grained recognition of multi-modality images imposes higher requirements on the dataset samples.The key to the problem is how to extract and fuse the complementary features of multi-modality images to obtain more discriminative fusion features.The attention mechanism helps the model to pinpoint the key information in the image,resulting in a significant improvement in the model’s performance.In this paper,a dataset for fine-grained recognition of ships based on visible and near-infrared multi-modality remote sensing images has been proposed first,named Dataset for Multimodal Fine-grained Recognition of Ships(DMFGRS).It includes 1,635 pairs of visible and near-infrared remote sensing images divided into 20 categories,collated from digital orthophotos model provided by commercial remote sensing satellites.DMFGRS provides two types of annotation format files,as well as segmentation mask images corresponding to the ship targets.Then,a Multimodal Information Cross-Enhancement Network(MICE-Net)fusing features of visible and near-infrared remote sensing images,has been proposed.In the network,a dual-branch feature extraction and fusion module has been designed to obtain more expressive features.The Feature Cross Enhancement Module(FCEM)achieves the fusion enhancement of the two modal features by making the channel attention and spatial attention work cross-functionally on the feature map.A benchmark is established by evaluating state-of-the-art object recognition algorithms on DMFGRS.MICE-Net conducted experiments on DMFGRS,and the precision,recall,mAP0.5 and mAP0.5:0.95 reached 87%,77.1%,83.8%and 63.9%,respectively.Extensive experiments demonstrate that the proposed MICE-Net has more excellent performance on DMFGRS.Built on lightweight network YOLO,the model has excellent generalizability,and thus has good potential for application in real-life scenarios.
基金supported by the National Key Research and Development Program of China(2021YFC2501800)Shanghai Committee of Science and Technology(20Y11900100,21MC1930400,and 20DZ2261200)Clinical Research Plan of Shanghai Hospital Development Center(SHDC2020CR4059)。
文摘BACKGROUND:Disseminated intravascular coagulation(DIC)is associated with increased mortality in sepsis patients.In this study,we aimed to assess the clinical ability of sepsis-induced coagulopathy(SIC)and sepsis-associated coagulopathy(SAC)criteria in identifying overt-DIC and preDIC status in sepsis patients.METHODS:Data from 419 sepsis patients were retrospectively collected from July 2018 to December 2022.The performances of the SIC and SAC were assessed to identify overt-DIC on days 1,3,7,or 14.The SIC status or SIC score on day 1,the SAC status or SAC score on day 1,and the sum of the SIC or SAC scores on days 1 and 3 were compared in terms of their ability to identify pre-DIC.The SIC or SAC status on day 1 was evaluated as a pre-DIC indicator for anticoagulant initiation.RESULTS:On day 1,the incidences of coagulopathy according to overt-DIC,SIC and SAC criteria were 11.7%,22.0%and 31.5%,respectively.The specificity of SIC for identifying overt-DIC was significantly higher than that of the SAC criteria from day 1 to day 14(P<0.05).On day 1,the SIC score with a cut-off value>3 had a significantly higher sensitivity(72.00%)and area under the curve(AUC)(0.69)in identifying pre-DIC than did the SIC or SAC status(sensitivity:SIC status 44.00%,SAC status 52.00%;AUC:SIC status 0.62,SAC status 0.61).The sum of the SIC scores on days 1 and 3 had a higher AUC value for identifying the pre-DIC state than that of SAC(0.79 vs.0.69,P<0.001).Favorable effects of anticoagulant therapy were observed in SIC(adjusted hazard ratio[HR]=0.216,95%confidence interval[95%CI]:0.060–0.783,P=0.018)and SAC(adjusted HR=0.146,95%CI:0.041–0.513,P=0.003).CONCLUSION:The SIC and SAC seem to be valuable for predicting overt-DIC.The sum of SIC scores on days 1 and 3 has the potential to help identify pre-DIC.
基金the Open Project of Sichuan Provincial Key Laboratory of Philosophy and Social Science for Language Intelligence in Special Education under Grant No.YYZN-2023-4the Ph.D.Fund of Chengdu Technological University under Grant No.2020RC002.
文摘The fingerprinting-based approach using the wireless local area network(WLAN)is widely used for indoor localization.However,the construction of the fingerprint database is quite time-consuming.Especially when the position of the access point(AP)or wall changes,updating the fingerprint database in real-time is difficult.An appropriate indoor localization approach,which has a low implementation cost,excellent real-time performance,and high localization accuracy and fully considers complex indoor environment factors,is preferred in location-based services(LBSs)applications.In this paper,we proposed a fine-grained grid computing(FGGC)model to achieve decimeter-level localization accuracy.Reference points(RPs)are generated in the grid by the FGGC model.Then,the received signal strength(RSS)values at each RP are calculated with the attenuation factors,such as the frequency band,three-dimensional propagation distance,and walls in complex environments.As a result,the fingerprint database can be established automatically without manual measurement,and the efficiency and cost that the FGGC model takes for the fingerprint database are superior to previous methods.The proposed indoor localization approach,which estimates the position step by step from the approximate grid location to the fine-grained location,can achieve higher real-time performance and localization accuracy simultaneously.The mean error of the proposed model is 0.36 m,far lower than that of previous approaches.Thus,the proposed model is feasible to improve the efficiency and accuracy of Wi-Fi indoor localization.It also shows high-accuracy performance with a fast running speed even under a large-size grid.The results indicate that the proposed method can also be suitable for precise marketing,indoor navigation,and emergency rescue.
基金Funded by the Health Science and Technology Program of Inner Mongolia Autonomous Region(no.202201061)Supported by the Joint Project of theMillion Science and Technology Initiatives of Inner Mongolia Medical University(no.YKD2020KJBW(LH)057).
文摘Objective:Lung adenocarcinoma exhibits diverse genetic and morphological backgrounds,in addition to considerable differences in clinical pathology and molecular biological characteristics.Among these,the phenomenon of spread through air space(STAS),a distinct mode of lung cancer infiltration,has rarely been reported.Therefore,this study aimed to explore the relationship between STAS tumor cells and the clinical and molecular characteristics of patients with lung adenocarcinoma,as well as their impact on prognosis.Methods:This study included 147 patients who were diagnosed with lung adenocarcinoma at the Inner Mongolia Autonomous Region Cancer Institute between January 2014 and December 2017.Surgical resection specimens were retrospectively analyzed.Using univariate and multivariate Cox analyses,we assessed the association between STAS and the clinicopathological features and molecular characteristics of patients with lung adenocarcinoma.Furthermore,we investigated the effects on patient prognosis.In addition,we developed a column–line plot prediction model and performed internal validation.Results:Patients with positive STAS had a significantly higher proportion of tumors with a diameter≥2 cm,with infiltration around the pleura,blood vessels,and nerves,and a pathological stage>IIB than in STAS-negative patients(P<0.05).Cox multivariate survival analysis revealed that clinical stage,STAS status,tumor size,and visceral pleural invasion were independent prognostic factors influencing the 5-year progression-free survival in patients with lung adenocarcinoma.The predictive values and P values from the Hosmer-Lemeshow test were 0.8 and 0.2,respectively,indicating no statistical difference.Receiver operating characteristic curve analysis demonstrated areas under the curve of 0.884 and 0.872 for the training and validation groups,respectively.The nomogram model exhibited the best fit with a value of 192.09.Conclusions:Clinical stage,pleural invasion,vascular invasion,peripheral nerve invasion,tumor size,and necrosis are independent prognostic factors for patients with STAS-positive lung adenocarcinoma.The nomogrambased on the clinical stage,pleural invasion,vascular invasion,peripheral nerve invasion,tumor size,and necrosis showed good accuracy,differentiation,and clinical practicality.
文摘In cold regions,understanding the freezing strength of the interface between soil and structure is crucial for designing frost-resistant foundations.To investigate how the content of cement powder in aeolian sand affects this strength,we conducted direct shear tests under various conditions such as different fine-grained soil content,normal stress,and initial moisture content of the soil.By analyzing parameters like soil properties,and volume of ice content,and using the Mohr-Coulomb strength theory to define interface strength,we aimed to indirectly measure the cementation strength of the interface.Our findings revealed that as the particle content increased,the interface stress-strain curves became noticeably stiffer.We also observed a positive linear relationship between freezing strength and silt content,while the initial moisture content of the soil did not significantly impact the strengthening effect of fine-grained soil on freezing strength.Moreover,we discovered that as the powder content increased,the force binding the ice to the interface decreased,while the friction angle at the interface increased.However,the cohesion force at the interface remained relatively unchanged.Overall,our analysis suggests that the increase in freezing strength due to fine-grained soil content is primarily due to the heightened friction between aeolian sand and the interface.
基金Supported by the Petrochina Science and Technology Project(2021DJ18).
文摘The geological conditions and processes of fine-grained gravity flow sedimentation in continental lacustrine basins in China are analyzed to construct the model of fine-grained gravity flow sedimentation in lacustrine basin,reveal the development laws of fine-grained deposits and source-reservoir,and identify the sweet sections of shale oil.The results show that fine-grained gravity flow is one of the important sedimentary processes in deep lake environment,and it can transport fine-grained clasts and organic matter in shallow water to deep lake,forming sweet sections and high-quality source rocks of shale oil.Fine-grained gravity flow deposits in deep waters of lacustrine basins in China are mainly fine-grained high-density flow,fine-grained turbidity flow(including surge-like turbidity flow and fine-grained hyperpycnal flow),fine-grained viscous flow(including fine-grained debris flow and mud flow),and fine-grained transitional flow deposits.The distribution of fine-grained gravity flow deposits in the warm and humid unbalanced lacustrine basins are controlled by lake-level fluctuation,flooding events,and lakebed paleogeomorphology.During the lake-level rise,fine-grained hyperpycnal flow caused by flooding formed fine-grained channel–levee–lobe system in the flat area of the deep lake.During the lake-level fall,the sublacustrine fan system represented by unconfined channel was developed in the flexural slope breaks and sedimentary slopes of depressed lacustrine basins,and in the steep slopes of faulted lacustrine basins;the sublacustrine fan system with confined or unconfined channel was developed on the gentle slopes and in axial direction of faulted lacustrine basins,with fine-grained gravity flow deposits possibly existing in the lower fan.Within the fourth-order sequences,transgression might lead to organic-rich shale and fine-grained hyperpycnal flow deposits,while regression might cause fine-grained high-density flow,surge-like turbidity flow,fine-grained debris flow,mud flow,and fine-grained transitional flow deposits.Since the Permian,in the shale strata of lacustrine basins in China,multiple transgression-regression cycles of fourth-order sequences have formed multiple source-reservoir assemblages.Diverse fine-grained gravity flow sedimentation processes have created sweet sections of thin siltstone consisting of fine-grained high-density flow,fine-grained hyperpycnal flow and surge-like turbidity flow deposits,sweet sections with interbeds of mudstone and siltstone formed by fine-grained transitional flows,and sweet sections of shale containing silty and muddy clasts and with horizontal bedding formed by fine-grained debris flow and mud flow.The model of fine-grained gravity flow sedimentation in lacustrine basin is significant for the scientific evaluation of sweet shale oil reservoir and organic-rich source rock.
基金This research was funded by King Mongkut’s University of Technology North Bangkok(Contract no.KMUTNB-62-KNOW-026).
文摘Fine-grained image classification is a challenging research topic because of the high degree of similarity among categories and the high degree of dissimilarity for a specific category caused by different poses and scales.A cul-tural heritage image is one of thefine-grained images because each image has the same similarity in most cases.Using the classification technique,distinguishing cultural heritage architecture may be difficult.This study proposes a cultural heri-tage content retrieval method using adaptive deep learning forfine-grained image retrieval.The key contribution of this research was the creation of a retrieval mod-el that could handle incremental streams of new categories while maintaining its past performance in old categories and not losing the old categorization of a cul-tural heritage image.The goal of the proposed method is to perform a retrieval task for classes.Incremental learning for new classes was conducted to reduce the re-training process.In this step,the original class is not necessary for re-train-ing which we call an adaptive deep learning technique.Cultural heritage in the case of Thai archaeological site architecture was retrieved through machine learn-ing and image processing.We analyze the experimental results of incremental learning forfine-grained images with images of Thai archaeological site architec-ture from world heritage provinces in Thailand,which have a similar architecture.Using afine-grained image retrieval technique for this group of cultural heritage images in a database can solve the problem of a high degree of similarity among categories and a high degree of dissimilarity for a specific category.The proposed method for retrieving the correct image from a database can deliver an average accuracy of 85 percent.Adaptive deep learning forfine-grained image retrieval was used to retrieve cultural heritage content,and it outperformed state-of-the-art methods infine-grained image retrieval.
文摘A comparison between deep learning and standalone models in predicting the compaction parameters of soil is presented in this research.One hundred and ninety and fifty-three soil samples were randomly picked up from two hundred and forty-three soil samples to create training and validation datasets,respectively.The performance and accuracy of the models were measured by root mean square error(RMSE),coefficient of determination(R2),Pearson product-moment correlation coefficient(r),mean absolute error(MAE),variance accounted for(VAF),mean absolute percentage error(MAPE),weighted mean absolute percentage error(WMAPE),a20-index,index of scatter(IOS),and index of agreement(IOA).Comparisons between standalone models demonstrate that the model MD 29 in Gaussian process regression(GPR)and model MD 101 in support vector machine(SVM)can achieve over 96%of accuracy in predicting the optimum moisture content(OMC)and maximum dry density(MDD)of soil,and outperformed other standalone models.The comparison between deep learning models shows that the models MD 46 and MD 146 in long short-term memory(LSTM)predict OMC and MDD with higher accuracy than ANN models.However,the LSTM models outperformed the GPR models in predicting the compaction parameters.The sensitivity analysis illustrates that fine content(FC),specific gravity(SG),and liquid limit(LL)highly influence the prediction of compaction parameters.
基金supported in part by the National Natural Science Foundation of China under Grant 62272062the Researchers Supporting Project number.(RSP2023R102)King Saud University+5 种基金Riyadh,Saudi Arabia,the Open Research Fund of the Hunan Provincial Key Laboratory of Network Investigational Technology under Grant 2018WLZC003the National Science Foundation of Hunan Province under Grant 2020JJ2029the Hunan Provincial Key Research and Development Program under Grant 2022GK2019the Science Fund for Creative Research Groups of Hunan Province under Grant 2020JJ1006the Scientific Research Fund of Hunan Provincial Transportation Department under Grant 202143the Open Fund of Key Laboratory of Safety Control of Bridge Engineering,Ministry of Education(Changsha University of Science Technology)under Grant 21KB07.
文摘Sensors produce a large amount of multivariate time series data to record the states of Internet of Things(IoT)systems.Multivariate time series timestamp anomaly detection(TSAD)can identify timestamps of attacks and malfunctions.However,it is necessary to determine which sensor or indicator is abnormal to facilitate a more detailed diagnosis,a process referred to as fine-grained anomaly detection(FGAD).Although further FGAD can be extended based on TSAD methods,existing works do not provide a quantitative evaluation,and the performance is unknown.Therefore,to tackle the FGAD problem,this paper first verifies that the TSAD methods achieve low performance when applied to the FGAD task directly because of the excessive fusion of features and the ignoring of the relationship’s dynamic changes between indicators.Accordingly,this paper proposes a mul-tivariate time series fine-grained anomaly detection(MFGAD)framework.To avoid excessive fusion of features,MFGAD constructs two sub-models to independently identify the abnormal timestamp and abnormal indicator instead of a single model and then combines the two kinds of abnormal results to detect the fine-grained anomaly.Based on this framework,an algorithm based on Graph Attention Neural Network(GAT)and Attention Convolutional Long-Short Term Memory(A-ConvLSTM)is proposed,in which GAT learns temporal features of multiple indicators to detect abnormal timestamps and A-ConvLSTM captures the dynamic relationship between indicators to identify abnormal indicators.Extensive simulations on a real-world dataset demonstrate that the proposed algorithm can achieve a higher F1 score and hit rate than the extension of existing TSAD methods with the benefit of two independent sub-models for timestamp and indicator detection.
基金supported by the research team of Xi’an Traffic Engineering Institute and the Young and middle-aged fund project of Xi’an Traffic Engineering Institute (2022KY-02).
文摘Mining more discriminative temporal features to enrich temporal context representation is considered the key to fine-grained action recog-nition.Previous action recognition methods utilize a fixed spatiotemporal window to learn local video representation.However,these methods failed to capture complex motion patterns due to their limited receptive field.To solve the above problems,this paper proposes a lightweight Temporal Pyramid Excitation(TPE)module to capture the short,medium,and long-term temporal context.In this method,Temporal Pyramid(TP)module can effectively expand the temporal receptive field of the network by using the multi-temporal kernel decomposition without significantly increasing the computational cost.In addition,the Multi Excitation module can emphasize temporal importance to enhance the temporal feature representation learning.TPE can be integrated into ResNet50,and building a compact video learning framework-TPENet.Extensive validation experiments on several challenging benchmark(Something-Something V1,Something-Something V2,UCF-101,and HMDB51)datasets demonstrate that our method achieves a preferable balance between computation and accuracy.
基金supported in part by the National Natural Science Foundation of China(NSFC)under Grant 6150140in part by the Youth Innovation Project(21032158-Y)of Zhejiang Sci-Tech University.
文摘Image captioning involves two different major modalities(image and sentence)that convert a given image into a language that adheres to visual semantics.Almost all methods first extract image features to reduce the difficulty of visual semantic embedding and then use the caption model to generate fluent sentences.The Convolutional Neural Network(CNN)is often used to extract image features in image captioning,and the use of object detection networks to extract region features has achieved great success.However,the region features retrieved by this method are object-level and do not pay attention to fine-grained details because of the detection model’s limitation.We offer an approach to address this issue that more properly generates captions by fusing fine-grained features and region features.First,we extract fine-grained features using a panoramic segmentation algorithm.Second,we suggest two fusion methods and contrast their fusion outcomes.An X-linear Attention Network(X-LAN)serves as the foundation for both fusion methods.According to experimental findings on the COCO dataset,the two-branch fusion approach is superior.It is important to note that on the COCO Karpathy test split,CIDEr is increased up to 134.3%in comparison to the baseline,highlighting the potency and viability of our method.
基金founded by the National Natural Science Foundation of China(Grant No.41772130)the Postgraduate Research&Practice Innovation Program of Jiangsu Province(Grant No.KYCX22_2602)+1 种基金the Graduate Innovation Program of China University of Mining and Technology(Grant No.2022WLKXJ035)the Fundamental Research Program of Shanxi Province(Grant No.202103021223283)。
文摘The continuously collected cores from the Permo-Carboniferous coal-bearing strata of the eastern Ordos Basin are essential for studying the hydrocarbon potential in this region.This study adopted sedimentological and geochemical methods to analyze the sedimentary environment,material composition,and geochemical characteristics of the coal-bearing strata.The differences in depositional and paleoclimatic conditions were compared;and the factors influencing the organic matter content of fine-grained sediments were explored.The depositional environment of the Benxi and Jinci formations was lagoon to tidal flat with weakly reduced waters with low salinity and dry-hot paleoclimatic conditions;while that of the Taiyuan Formation was a carbonate platform and shallow water delta front,where the water was highly reductive.The xerothermic climate alternated with the warm and humid climate.The period of maximum transgression in the Permo-Carboniferous has the highest water salinity.The Shanxi Formation was deposited in a shallow water delta front with a brackish and fresh water environment and alternative weak reductiveness.And the paleoclimate condition is dry-hot.The TOC content in fine-grained samples was averaging 1.52%.The main controlling mechanism of organic matter in this area was the input conditions according to the analysis on input and preservation of organic matter.
文摘The remote sensing ships’fine-grained classification technology makes it possible to identify certain ship types in remote sensing images,and it has broad application prospects in civil and military fields.However,the current model does not examine the properties of ship targets in remote sensing images with mixed multi-granularity features and a complicated backdrop.There is still an opportunity for future enhancement of the classification impact.To solve the challenges brought by the above characteristics,this paper proposes a Metaformer and Residual fusion network based on Visual Attention Network(VAN-MR)for fine-grained classification tasks.For the complex background of remote sensing images,the VAN-MR model adopts the parallel structure of large kernel attention and spatial attention to enhance the model’s feature extraction ability of interest targets and improve the classification performance of remote sensing ship targets.For the problem of multi-grained feature mixing in remote sensing images,the VAN-MR model uses a Metaformer structure and a parallel network of residual modules to extract ship features.The parallel network has different depths,considering both high-level and lowlevel semantic information.The model achieves better classification performance in remote sensing ship images with multi-granularity mixing.Finally,the model achieves 88.73%and 94.56%accuracy on the public fine-grained ship collection-23(FGSC-23)and FGSCR-42 datasets,respectively,while the parameter size is only 53.47 M,the floating point operations is 9.9 G.The experimental results show that the classification effect of VAN-MR is superior to that of traditional CNNs model and visual model with Transformer structure under the same parameter quantity.
基金This work was partially supported by Beijing Natural Science Foundation(No.4222038)by Open Research Project of the State Key Laboratory of Media Convergence and Communication(Communication University of China),by the National Key RD Program of China(No.2021YFF0307600)and by Fundamental Research Funds for the Central Universities.
文摘Existing explanation methods for Convolutional Neural Networks(CNNs)lack the pixel-level visualization explanations to generate the reliable fine-grained decision features.Since there are inconsistencies between the explanation and the actual behavior of the model to be interpreted,we propose a Fine-Grained Visual Explanation for CNN,namely F-GVE,which produces a fine-grained explanation with higher consistency to the decision of the original model.The exact backward class-specific gradients with respect to the input image is obtained to highlight the object-related pixels the model used to make prediction.In addition,for better visualization and less noise,F-GVE selects an appropriate threshold to filter the gradient during the calculation and the explanation map is obtained by element-wise multiplying the gradient and the input image to show fine-grained classification decision features.Experimental results demonstrate that F-GVE has good visual performances and highlights the importance of fine-grained decision features.Moreover,the faithfulness of the explanation in this paper is high and it is effective and practical on troubleshooting and debugging detection.
基金the support from the Basic Energy Sciences Office at the US Department of Energy under Award no.DESC0016333。
文摘Fine-grained magnesium was tested under stress-controlled tension-tension cyclic loading at -30 ℃ and the tested sample was observed using scanning electron microscope and electron backscatter diffraction to explore the fatigue behavior and crack propagation. The fatigue data showed that the material experienced cyclic softening followed by cyclic hardening before the final fracture failure. The microscopic observations demonstrated that the cracks were almost perpendicular to the loading direction with some zigzags and the cracks progressed along both small angle grain boundaries and large angle grain boundaries. Although the cracks were mainly propagated along large angle grain boundaries, the value of grain boundary angle was not the primary factor to determine the crack propagation direction. The local residual strain from the rolling process was released due to the crack propagation and there was more strain relaxation at regions closer to the cracks.
基金supported by the 2023 Open Project of Key Laboratory of Ministry of Public Security for Artificial Intelligence Security(RGZNAQ-2304)the Fundamental Research Funds for the Central Universities of PPSUC(2023JKF01ZK08).
文摘With the rapid development of deepfake technology,the authenticity of various types of fake synthetic content is increasing rapidly,which brings potential security threats to people’s daily life and social stability.Currently,most algorithms define deepfake detection as a binary classification problem,i.e.,global features are first extracted using a backbone network and then fed into a binary classifier to discriminate true or false.However,the differences between real and fake samples are often subtle and local,and such global feature-based detection algorithms are not optimal in efficiency and accuracy.To this end,to enhance the extraction of forgery details in deep forgery samples,we propose a multi-branch deepfake detection algorithm based on fine-grained features from the perspective of fine-grained classification.First,to address the critical problem in locating discriminative feature regions in fine-grained classification tasks,we investigate a method for locating multiple different discriminative regions and design a lightweight feature localization module to obtain crucial feature representations by augmenting the most significant parts of the feature map.Second,using information complementation,we introduce a correlation-guided fusion module to enhance the discriminative feature information of different branches.Finally,we use the global attention module in the multi-branch model to improve the cross-dimensional interaction of spatial domain and channel domain information and increase the weights of crucial feature regions and feature channels.We conduct sufficient ablation experiments and comparative experiments.The experimental results show that the algorithm outperforms the detection accuracy and effectiveness on the FaceForensics++and Celeb-DF-v2 datasets compared with the representative detection algorithms in recent years,which can achieve better detection results.
文摘Rationale:Disseminated tuberculosis involves the central nervous system in up to a third of cases.However,meningitis and spondylodiscitis due to miliary tuberculosis rarely occur together,particularly in the immuno-competent population.Patient concerns:A 37-year-old immunocompetent male presented with altered level of consciousness for one week and lower back pain with evening pyrexia for one month.Examination revealed spastic paraplegia and left hemiparesis.Diagnosis:Disseminated tuberculosis presenting with meningitis and spondylodiscitis.Interventions:Category I anti-tuberculous therapy with a tapering regimen of intravenous dexamethasone was administered.Outcomes:There was clinical improvement after nine months of treatment.Lessons:Tuberculosis may present with atypical clinical manifestations.Contrast enhanced computed tomography scan or magnetic resonance imaging combined with histopathological features,a high index of suspicion and clinical improvement with anti-tuberculous treatment can confirm the diagnosis in the absence of microbiological evidence,especially in extrapulmonary tuberculosis.
基金This work was partially supported by Science and Technology Project of Chongqing Education Commission of China(KJZD-K202200513)National Natural Science Foundation of China(61370205)+1 种基金Chongqing Normal University Fund(22XLB003)Chongqing Education Science Planning Project(2021-GX-320).
文摘In recent years,the development of deep learning has further improved hash retrieval technology.Most of the existing hashing methods currently use Convolutional Neural Networks(CNNs)and Recurrent Neural Networks(RNNs)to process image and text information,respectively.This makes images or texts subject to local constraints,and inherent label matching cannot capture finegrained information,often leading to suboptimal results.Driven by the development of the transformer model,we propose a framework called ViT2CMH mainly based on the Vision Transformer to handle deep Cross-modal Hashing tasks rather than CNNs or RNNs.Specifically,we use a BERT network to extract text features and use the vision transformer as the image network of the model.Finally,the features are transformed into hash codes for efficient and fast retrieval.We conduct extensive experiments on Microsoft COCO(MS-COCO)and Flickr30K,comparing with baselines of some hashing methods and image-text matching methods,showing that our method has better performance.
文摘BACKGROUND Forehead osteoma is a commonly encountered benign facial bone tumor.Endoscopic excision of benign forehead masses is widely performed.Here,we report a rare case of recurrent forehead osteoma that disseminated after a previous osteoma excision.CASE SUMMARY A 54-year-old female patient had previously undergone endoscopic removal of a single forehead osteoma at 30 years of age.However,she had a recurrent osteoma around the same site and underwent another endoscopic resection at 40 years of age.During her first visit to our outpatient clinic,she presented with a cobblestone-like irregular surface on the forehead and a 3D facial bone computed tomography scan revealed a widely ragged surface of the inoculated osteoma on the outer table of the frontal bone.Under general anesthesia,we performed a radical complete excision of the disseminated osteoma through a bicoronal incision using an osteotome,chisel,mallet,and rasping.We hypothesized that the recurrence may have been caused by the inoculation of residual osteoma remnants from the previous procedure.Craniofacial surgeons should be cautious when removing osteoma particles,particularly when using an endoscopic approach.CONCLUSION To prevent recurrence,it is essential to conduct additional meticulous burring and a thorough inspection of the surface after copious irrigation.
