As a deep learning network with an encoder-decoder architecture,UNet and its series of improved versions have been widely used in medical image segmentation with great ***,when used to segment targets in 3D medical im...
详细信息
As a deep learning network with an encoder-decoder architecture,UNet and its series of improved versions have been widely used in medical image segmentation with great ***,when used to segment targets in 3D medical images such as magnetic resonance imaging(MRI),computed tomography(CT),these models do not model the relevance of images in vertical space,resulting in poor accurate analysis of consecutive slices of the same *** the other hand,the large amount of detail lost during the encoding process makes these models incapable of segmenting small-scale tumor *** at the scene of small-scale target segmentation in 3D medical images,a fully new neural network model SUNet++is proposed on the basis of UNet and UNet++.SUNet++improves the existing models mainly in three aspects:1)the modeling strategy of slice superposition is used to thoroughly excavate the three dimensional information of the data;2)by adding an attention mechanism during the decoding process,small scale targets in the picture are retained and amplified;3)in the up-sampling process,the transposed convolution operation is used to further enhance the effect of the *** order to verify the effect of the model,we collected and produced a dataset of hyperintensity MRI liver-stage images containing over 400 cases of liver *** results on both public and proprietary datasets demonstrate the superiority of SUNet++in small-scale target segmentation of three-dimensional medical images.
Anomaly detection(AD) has been extensively studied and applied across various scenarios in recent years. However, gaps remain between the current performance and the desired recognition accuracy required for practical...
详细信息
Anomaly detection(AD) has been extensively studied and applied across various scenarios in recent years. However, gaps remain between the current performance and the desired recognition accuracy required for practical *** paper analyzes two fundamental failure cases in the baseline AD model and identifies key reasons that limit the recognition accuracy of existing approaches. Specifically, by Case-1, we found that the main reason detrimental to current AD methods is that the inputs to the recovery model contain a large number of detailed features to be recovered, which leads to the normal/abnormal area has not/has been recovered into its original state. By Case-2, we surprisingly found that the abnormal area that cannot be recognized in image-level representations can be easily recognized in the feature-level representation. Based on the above observations, we propose a novel recover-then-discriminate(ReDi) framework for *** takes a self-generated feature map(e.g., histogram of oriented gradients) and a selected prompted image as explicit input information to address the identified in Case-1. Additionally, a feature-level discriminative network is introduced to amplify abnormal differences between the recovered and input representations. Extensive experiments on two widely used yet challenging AD datasets demonstrate that ReDi achieves state-of-the-art recognition accuracy.
Existing methods in article recommendation fail to fully use the article information, or pay less attention to the correlations among articles and "User-Article"s, resulting in inaccurate recommendation perf...
详细信息
As a complex hot problem in the financial field,stock trend forecasting uses a large amount of data and many related indicators;hence it is difficult to obtain sustainable and effective results only by relying on empi...
详细信息
As a complex hot problem in the financial field,stock trend forecasting uses a large amount of data and many related indicators;hence it is difficult to obtain sustainable and effective results only by relying on empirical *** in the field of machine learning have proved that random forest can form better judgements on this kind of problem,and it has an auxiliary role in the prediction of stock *** study uses historical trading data of four listed companies in the USA stock market,and the purpose of this study is to improve the performance of random forest model in medium-and long-term stock trend *** study applies the exponential smoothing method to process the initial data,calculates the relevant technical indicators as the characteristics to be selected,and proposes the D-RF-RS method to optimize random *** the random forest is an ensemble learning model and is closely related to decision tree,D-RF-RS method uses a decision tree to screen the importance of features,and obtains the effective strong feature set of the model as ***,the parameter combination of the model is optimized through random parameter *** experimental results show that the average accuracy of random forest is increased by 0.17 after the above process optimization,which is 0.18 higher than the average accuracy of light gradient boosting machine *** with the performance of the ROC curve and Precision–Recall curve,the stability of the model is also guaranteed,which further demonstrates the advantages of random forest in medium-and long-term trend prediction of the stock market.
Software defect prediction plays a critical role in software development and quality assurance processes. Effective defect prediction enables testers to accurately prioritize testing efforts and enhance defect detecti...
详细信息
Software defect prediction plays a critical role in software development and quality assurance processes. Effective defect prediction enables testers to accurately prioritize testing efforts and enhance defect detection efficiency. Additionally, this technology provides developers with a means to quickly identify errors, thereby improving software robustness and overall quality. However, current research in software defect prediction often faces challenges, such as relying on a single data source or failing to adequately account for the characteristics of multiple coexisting data sources. This approach may overlook the differences and potential value of various data sources, affecting the accuracy and generalization performance of prediction results. To address this issue, this study proposes a multivariate heterogeneous hybrid deep learning algorithm for defect prediction (DP-MHHDL). Initially, Abstract Syntax Tree (AST), Code Dependency Network (CDN), and code static quality metrics are extracted from source code files and used as inputs to ensure data diversity. Subsequently, for the three types of heterogeneous data, the study employs a graph convolutional network optimization model based on adjacency and spatial topologies, a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) hybrid neural network model, and a TabNet model to extract data features. These features are then concatenated and processed through a fully connected neural network for defect prediction. Finally, the proposed framework is evaluated using ten promise defect repository projects, and performance is assessed with three metrics: F1, Area under the curve (AUC), and Matthews correlation coefficient (MCC). The experimental results demonstrate that the proposed algorithm outperforms existing methods, offering a novel solution for software defect prediction.
The welding arc,as a carrier for the conversion of electrical energy to thermal energy,has a direct impact on the quality of welding by its properties and *** the tungsten inert gas(TIG)welding process under the condi...
详细信息
The welding arc,as a carrier for the conversion of electrical energy to thermal energy,has a direct impact on the quality of welding by its properties and *** the tungsten inert gas(TIG)welding process under the condition of Ar-He alternating gas supply,the arc is alternately converted between Ar arc and He arc with an alternating gas supply cycle,which has obvious arc change *** FLUENT software was used to numerically simulate the characteristics of the TIG arc under the condition of alternating gas supply,and the arc temperature field,arc pressure,electric potential and current density distribution under the condition of alternating gas supply were *** with the real-time data of arc pressure measured by the water-cooled copper plate with holes,it is proved that the TIG arc has obvious dynamic characteristics under the condition of Ar-He alternating gas *** unique dynamic TIG arc acts on the 5A06 aluminum alloy weld,causing the molten pool to stir,resulting in uniform microstructure and grain refinement at the weld,and thereby improving the mechanical properties of the welded joint.
The interfacial structure of the α-Mg/14H-LPSO phase in rare earth-including magnesium alloy was investigated via high-angle annular dark-field scanning transmission electron microscopy(HAADFSTEM) imaging and first-p...
详细信息
The interfacial structure of the α-Mg/14H-LPSO phase in rare earth-including magnesium alloy was investigated via high-angle annular dark-field scanning transmission electron microscopy(HAADFSTEM) imaging and first-principles calculations of density-functional *** possible interfacial models were constructed according to the different terminations of the LPSO phase,and the corresponding interfacial energies were calculated,from which the four most stable structures(Terl-MgY-hollow,Ter2-Zn-hollow,Ter3-MgYII-hollow and Ter4-Mg-bridge) were *** interfacial phase diagrams related to the Y chemical potentials were obtained from the calculations,and the most stable interfacial structure was ***-MgY-hollow and Ter2-Zn-hollow have the lowest interfacial energies in the range of-0.7 eV <Δμγ<-0.6 eV,where fluctuating change of state is the minimized and the interface is the most *** separation work of the two models was calculated to predict the bonding strength of the structures at both ends of the *** calculation results show that the maximum interfacial separation work is 1.45 J/m^(2) for the interface model of α-Mg and 14H-LPSO phase structure with Ter2-Zn-hollow termination.
When the ground communication base stations in the target area are severely destroyed,the deployment of Unmanned Aerial Vehicle(UAV)ad hoc networks can provide people with temporary communication ***,it is necessary t...
详细信息
Rubber-based composites based on ethylene propylene diene monomer(EPDM)with excellent non-linear electrical conductivity are preferred to serve as reinforced insu-lation in cable accessories,which can self-adaptively ...
详细信息
Rubber-based composites based on ethylene propylene diene monomer(EPDM)with excellent non-linear electrical conductivity are preferred to serve as reinforced insu-lation in cable accessories,which can self-adaptively regulate electric field distribution and avoid electric field concentration due to the non-linear *** conductive carbon nanotubes(CNT)are filled into EPDM to improve the non-linear conductivity,while the insulating hexagonal boron nitride nanosheets(h-BN)are used to reconcile the electric breakdown *** results show that with the increase of CNT loading content,the non-linear conductivity of CNT/h-BN/EPDM com-posites becomes more prominent,accompanying the decrease of threshold field strength and increase of non-linear ***,the electric breakdown strength of CNT/h-BN/EPDM composites seriously deteriorates due to the increase of CNT content and *** incorporating 10 wt.%h-BN into the com-posites,the reduction percentage of breakdown strength can be significantly lowered,which is 19.95%of neat EPDM and 13.74%of CNT/h-BN/EPDM composites at 70℃,*** COMSOL Multiphysics simulation results demonstrate that using the CNT/h-BN/EPDM composite as the reinforced insulation can eliminate the electric field concentration of the cable accessory as well as enable the cable accessory with good lightning shock resistance.
Background: Knowledge representation learning aims at mapping entity and relational data in knowledge graphs to a low-dimensional space in the form of vectors. The existing work has mainly focused on structured inform...
详细信息
暂无评论