Background:Atrial septal defect(ASD)is a common form of adult congenital heart disease that can lead to long-term adverse outcomes if left untreated.Early closure of ASD has been associated with excellent outcomes and...Background:Atrial septal defect(ASD)is a common form of adult congenital heart disease that can lead to long-term adverse outcomes if left untreated.Early closure of ASD has been associated with excellent outcomes and lower complication rates.However,there is limited evidence regarding the prognosis of ASD closure in older adults.This study aims to evaluate the mortality rates in older ASD patients with and without closure.Methods:A retrospective cohort study was conducted on patients aged 40 years or older with ASD between 2001 and 2017.Patients were followed up to assess all-cause mortality.Univariable and multivariable analyses were performed to identify the predictors of mortality.A p-value of<0.05 was considered statistically significant.Results:The cohort consisted of 450 patients(mean age 56.6±10.4 years,77.3%female),with 66%aged between 40 and 60 years,and 34%over 60 years.Within the cohort,299 underwent ASD closure(201 with transcatheter and 98 with surgical closure).During the median follow-up duration of 7.9 years,51 patients died.The unadjusted cumulative 10-year rate of mortality was 3%in patients with ASD closure,and 28%in patients without ASD closure(log-rank p<0.001).Multivariable analysis revealed that age(hazard ratio[HR]1.04,95%confidence interval[CI]1.006–1.06,p=0.01),NYHA class(HR 2.75,95%CI 1.63–4.62,p<0.001),blood urea nitrogen(BUN)(HR 1.07,95%CI 1.03–1.12,p<0.001),right ventricular systolic pressure(RVSP)(HR 1.07,95%CI 1.003–1.04,p=0.01),and lack of ASD closure(HR 15.12,95%CI 5.63–40.59,p<0.001)were independently associated with mortality.Conclusion:ASD closure demonstrated favorable outcomes in older patients.Age,NYHA class,BUN,RVSP,and lack of ASD closure were identified as independent factors linked to mortality in this population.展开更多
Over the past decade, graphitic carbon nitride(g-C_(3)N_(4)) has emerged as a universal photocatalyst toward various sustainable carbo-neutral technologies. Despite solar applications discrepancy, g-C_(3)N_(4) is stil...Over the past decade, graphitic carbon nitride(g-C_(3)N_(4)) has emerged as a universal photocatalyst toward various sustainable carbo-neutral technologies. Despite solar applications discrepancy, g-C_(3)N_(4) is still confronted with a general fatal issue of insufficient supply of thermodynamically active photocarriers due to its inferior solar harvesting ability and sluggish charge transfer dynamics. Fortunately, this could be significantly alleviated by the “all-in-one” defect engineering strategy, which enables a simultaneous amelioration of both textural uniqueness and intrinsic electronic band structures. To this end, we have summarized an unprecedently comprehensive discussion on defect controls including the vacancy/non-metallic dopant creation with optimized electronic band structure and electronic density, metallic doping with ultraactive coordinated environment(M–N_(x), M–C_(2)N_(2), M–O bonding), functional group grafting with optimized band structure, and promoted crystallinity with extended conjugation π system with weakened interlayered van der Waals interaction. Among them, the defect states induced by various defect types such as N vacancy, P/S/halogen dopants, and cyano group in boosting solar harvesting and accelerating photocarrier transfer have also been emphasized. More importantly, the shallow defect traps identified by femtosecond transient absorption spectra(fs-TAS) have also been highlighted. It is believed that this review would pave the way for future readers with a unique insight into a more precise defective g-C_(3)N_(4) “customization”, motivating more profound thinking and flourishing research outputs on g-C_(3)N_(4)-based photocatalysis.展开更多
Sintered silver nanoparticles(AgNPs)arewidely used in high-power electronics due to their exceptional properties.However,the material reliability is significantly affected by various microscopic defects.In this work,t...Sintered silver nanoparticles(AgNPs)arewidely used in high-power electronics due to their exceptional properties.However,the material reliability is significantly affected by various microscopic defects.In this work,the three primary micro-defect types at potential stress concentrations in sintered AgNPs are identified,categorized,and quantified.Molecular dynamics(MD)simulations are employed to observe the failure evolution of different microscopic defects.The dominant mechanisms responsible for this evolution are dislocation nucleation and dislocation motion.At the same time,this paper clarifies the quantitative relationship between the tensile strain amount and the failure mechanism transitions of the three defect types by defining key strain points.The impact of defect types on the failure process is also discussed.Furthermore,traction-separation curves extracted from microscopic defect evolutions serve as a bridge to connect the macro-scale model.The validity of the crack propagation model is confirmed through tensile tests.Finally,we thoroughly analyze how micro-defect types influence macro-crack propagation and attempt to find supporting evidence from the MD model.Our findings provide a multi-perspective reference for the reliability analysis of sintered AgNPs.展开更多
In order to explore the effect of vacancy defects on the structural,electronic,magnetic and optical properties of CoS_(2) and FeS_(2),first-principles calculation method was used to investigate the alloys.The calculat...In order to explore the effect of vacancy defects on the structural,electronic,magnetic and optical properties of CoS_(2) and FeS_(2),first-principles calculation method was used to investigate the alloys.The calculated results of materials without vacancy are consistent with those reported in the literatures,while the results of materials with vacancy defect were different from those of literatures due to the difference vacancy concentration.The Co vacancy defect hardly changes the half-metallic characteristic of CoS_(2).The Fe vacancy defect changes FeS_(2) from semiconductor to half-metal,and the bottom of the spin-down conduction band changes from the p orbital state of S to the d(t_(2g))orbital state of Fe,while the top of the valence band remains the d orbital d(eg)state of Fe.The half-metallic Co vacancy defects of CoS_(2) and Fe vacancy defects of FeS_(2) are expected to be used in spintronic devices.S vacancy defects make both CoS_(2) and FeS_(2) metallic.Both the Co and S vacancy defects lead to the decrease of the magnetic moment of CoS_(2),while both the Fe and S vacancy defects lead to the obvious magnetic property of FeS_(2).Vacancy defects enhance the absorption coefficient of infrared band and long band of visible light obviously,and produce obvious red shift phenomenon,which is expected to be used in photoelectric devices.展开更多
As computer technology continues to advance,factories have increasingly higher demands for detecting defects.However,detecting defects in a plant environment remains a challenging task due to the presence of complex b...As computer technology continues to advance,factories have increasingly higher demands for detecting defects.However,detecting defects in a plant environment remains a challenging task due to the presence of complex backgrounds and defects of varying shapes and sizes.To address this issue,this paper proposes YOLO-DD,a defect detectionmodel based on YOLOv5 that is effective and robust.To improve the feature extraction process and better capture global information,the vanilla YOLOv5 is augmented with a new module called Relative-Distance-Aware Transformer(RDAT).Additionally,an Information Gap Filling Strategy(IGFS)is proposed to improve the fusion of features at different scales.The classic lightweight attention mechanism Squeeze-and-Excitation(SE)module is also incorporated into the neck section to enhance feature expression and improve the model’s performance.Experimental results on the NEU-DET dataset demonstrate that YOLO-DDachieves competitive results compared to state-of-the-art methods,with a 2.0% increase in accuracy compared to the original YOLOv5,achieving 82.41% accuracy and38.25FPS(framesper second).Themodel is also testedon a self-constructed fabric defect dataset,and the results show that YOLO-DD is more stable and has higher accuracy than the original YOLOv5,demonstrating its stability and generalization ability.The high efficiency of YOLO-DD enables it to meet the requirements of industrial high accuracy and real-time detection.展开更多
Segment Anything Model(SAM)is a cutting-edge model that has shown impressive performance in general object segmentation.The birth of the segment anything is a groundbreaking step towards creating a universal intellige...Segment Anything Model(SAM)is a cutting-edge model that has shown impressive performance in general object segmentation.The birth of the segment anything is a groundbreaking step towards creating a universal intelligent model.Due to its superior performance in general object segmentation,it quickly gained attention and interest.This makes SAM particularly attractive in industrial surface defect segmentation,especially for complex industrial scenes with limited training data.However,its segmentation ability for specific industrial scenes remains unknown.Therefore,in this work,we select three representative and complex industrial surface defect detection scenarios,namely strip steel surface defects,tile surface defects,and rail surface defects,to evaluate the segmentation performance of SAM.Our results show that although SAM has great potential in general object segmentation,it cannot achieve satisfactory performance in complex industrial scenes.Our test results are available at:https://github.com/VDT-2048/SAM-IS.展开更多
Background:The optimal surgical timing and clinical outcomes of ventricular septal defect(VSD)closure in neo-nates remain unclear.We aimed to evaluate the clinical outcomes of VSD closure in neonates(age≤30 days).Met...Background:The optimal surgical timing and clinical outcomes of ventricular septal defect(VSD)closure in neo-nates remain unclear.We aimed to evaluate the clinical outcomes of VSD closure in neonates(age≤30 days).Methods:We retrospectively reviewed 50 consecutive neonates who underwent VSD closure for isolated VSDs between August 2003 and June 2021.Indications for the procedure included congestive heart failure/failure to thrive and pulmonary hypertension.Major adverse events(MAEs)were defined as the composite of all-cause mortality,reoperation,persistent atrioventricular block,and significant(≥grade 2)valvular dysfunction.Results:The median age and body weight at operation were 26.0 days(interquartile range[IQR],18.8–28.3)and 3.7 kg(IQR,3.3–4.2),respectively.The median follow-up duration was 110.4 months(IQR,56.8–165.0).Seven patients required preoperative respiratory support,andfive had significant(≥grade 2)preoperative valvular dysfunction.One early mortality occurred due to irreversible cardiogenic shock;no late mortality was observed.One reopera-tion was due to hemodynamically significant residual VSD at 103.8 months postoperatively.The overall survival,freedom from reoperation,and freedom from MAE at 15-years were 98.0%,96.3%,and 94.4%,respectively.Pre-operative mechanical ventilation was associated with a longer duration of postoperative mechanical ventilation(p<0.001)and a longer length of intensive care unit stay(p<0.001).Conclusions:VSD closure with favorable outcomes without morbidities is feasible even in neonates.However,neonates requiring preoperative respiratory support may require careful postoperative management considering the long-term postoperative risks.Overall,surgical VSD closure might be indicated earlier in neonates with respiratory compromise.展开更多
With the advent of Industry 4.0,marked by a surge in intelligent manufacturing,advanced sensors embedded in smart factories now enable extensive data collection on equipment operation.The analysis of such data is pivo...With the advent of Industry 4.0,marked by a surge in intelligent manufacturing,advanced sensors embedded in smart factories now enable extensive data collection on equipment operation.The analysis of such data is pivotal for ensuring production safety,a critical factor in monitoring the health status of manufacturing apparatus.Conventional defect detection techniques,typically limited to specific scenarios,often require manual feature extraction,leading to inefficiencies and limited versatility in the overall process.Our research presents an intelligent defect detection methodology that leverages deep learning techniques to automate feature extraction and defect localization processes.Our proposed approach encompasses a suite of components:the high-level feature learning block(HLFLB),the multi-scale feature learning block(MSFLB),and a dynamic adaptive fusion block(DAFB),working in tandem to extract meticulously and synergistically aggregate defect-related characteristics across various scales and hierarchical levels.We have conducted validation of the proposed method using datasets derived from gearbox and bearing assessments.The empirical outcomes underscore the superior defect detection capability of our approach.It demonstrates consistently high performance across diverse datasets and possesses the accuracy required to categorize defects,taking into account their specific locations and the extent of damage,proving the method’s effectiveness and reliability in identifying defects in industrial components.展开更多
Non-destructive detection of wire bonding defects in integrated circuits(IC)is critical for ensuring product quality after packaging.Image-processing-based methods do not provide a detailed evaluation of the three-dim...Non-destructive detection of wire bonding defects in integrated circuits(IC)is critical for ensuring product quality after packaging.Image-processing-based methods do not provide a detailed evaluation of the three-dimensional defects of the bonding wire.Therefore,a method of 3D reconstruction and pattern recognition of wire defects based on stereo vision,which can achieve non-destructive detection of bonding wire defects is proposed.The contour features of bonding wires and other electronic components in the depth image is analysed to complete the 3D reconstruction of the bonding wires.Especially to filter the noisy point cloud and obtain an accurate point cloud of the bonding wire surface,a point cloud segmentation method based on spatial surface feature detection(SFD)was proposed.SFD can extract more distinct features from the bonding wire surface during the point cloud segmentation process.Furthermore,in the defect detection process,a directional discretisation descriptor with multiple local normal vectors is designed for defect pattern recognition of bonding wires.The descriptor combines local and global features of wire and can describe the spatial variation trends and structural features of wires.The experimental results show that the method can complete the 3D reconstruction and defect pattern recognition of bonding wires,and the average accuracy of defect recognition is 96.47%,which meets the production requirements of bonding wire defect detection.展开更多
Urban sewer pipes are a vital infrastructure in modern cities,and their defects must be detected in time to prevent potential malfunctioning.In recent years,to relieve the manual efforts by human experts,models based ...Urban sewer pipes are a vital infrastructure in modern cities,and their defects must be detected in time to prevent potential malfunctioning.In recent years,to relieve the manual efforts by human experts,models based on deep learning have been introduced to automatically identify potential defects.However,these models are insufficient in terms of dataset complexity,model versatility and performance.Our work addresses these issues with amulti-stage defect detection architecture using a composite backbone Swin Transformer.Themodel based on this architecture is trained using a more comprehensive dataset containingmore classes of defects.By ablation studies on the modules of combined backbone Swin Transformer,multi-stage detector,test-time data augmentation and model fusion,it is revealed that they all contribute to the improvement of detection accuracy from different aspects.The model incorporating all these modules achieves the mean Average Precision(mAP)of 78.6% at an Intersection over Union(IoU)threshold of 0.5.This represents an improvement of 14.1% over the ResNet50 Faster Region-based Convolutional Neural Network(R-CNN)model and a 6.7% improvement over You Only Look Once version 6(YOLOv6)-large,the highest in the YOLO methods.In addition,for other defect detection models for sewer pipes,although direct comparison with themis infeasible due to the unavailability of their private datasets,our results are obtained from a more comprehensive dataset and have superior generalization capabilities.展开更多
Time-series data provide important information in many fields,and their processing and analysis have been the focus of much research.However,detecting anomalies is very difficult due to data imbalance,temporal depende...Time-series data provide important information in many fields,and their processing and analysis have been the focus of much research.However,detecting anomalies is very difficult due to data imbalance,temporal dependence,and noise.Therefore,methodologies for data augmentation and conversion of time series data into images for analysis have been studied.This paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance,temporal dependence,and robustness to noise.The method of data augmentation is set as the addition of noise.It involves adding Gaussian noise,with the noise level set to 0.002,to maximize the generalization performance of the model.In addition,we use the Markov Transition Field(MTF)method to effectively visualize the dynamic transitions of the data while converting the time series data into images.It enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the data.For anomaly detection,the PatchCore model is applied to show excellent performance,and the detected anomaly areas are represented as heat maps.It allows for the detection of anomalies,and by applying an anomaly map to the original image,it is possible to capture the areas where anomalies occur.The performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to images.Additionally,when processed as images rather than as time series data,there was a significant reduction in both the size of the data and the training time.The proposed method can provide an important springboard for research in the field of anomaly detection using time series data.Besides,it helps solve problems such as analyzing complex patterns in data lightweight.展开更多
Good crystallinity can reduce the charge recombination centers caused by defects,whilst structures with strong polycondensation have high charge mobility,leading to more charge transfer to the material surface for rea...Good crystallinity can reduce the charge recombination centers caused by defects,whilst structures with strong polycondensation have high charge mobility,leading to more charge transfer to the material surface for reaction.Much effort has been put into the preparation of a highly efficient g-C_(3)N_(4) with defects to improve its application potential under the premise in high crystallinity.Hence,this review paper emphasizes the importance to balance the defect and crystallinity of g-C_(3)N_(4).In addition,detailed discussion on the relationship between defects and activity of g-C_(3)N_(4) was carried out based on its applications in environmental purification(e.g.,VOCs oxidation,NO_(x) oxidation,H_(2)O_(2) evolution,sterilization,pesticide oxidation)and energy conversion(H_(2) evolution,N_(2) fixation and CO_(2) reduction).Lastly,the challenge in developing more efficient defective g-C_(3)N_(4) photocatalytic materials is summarized.展开更多
Insulator defect detection plays a vital role in maintaining the secure operation of power systems.To address the issues of the difficulty of detecting small objects and missing objects due to the small scale,variable...Insulator defect detection plays a vital role in maintaining the secure operation of power systems.To address the issues of the difficulty of detecting small objects and missing objects due to the small scale,variable scale,and fuzzy edge morphology of insulator defects,we construct an insulator dataset with 1600 samples containing flashovers and breakages.Then a simple and effective surface defect detection method of power line insulators for difficult small objects is proposed.Firstly,a high-resolution featuremap is introduced and a small object prediction layer is added so that the model can detect tiny objects.Secondly,a simplified adaptive spatial feature fusion(SASFF)module is introduced to perform cross-scale spatial fusion to improve adaptability to variable multi-scale features.Finally,we propose an enhanced deformable attention mechanism(EDAM)module.By integrating a gating activation function,the model is further inspired to learn a small number of critical sampling points near reference points.And the module can improve the perception of object morphology.The experimental results indicate that concerning the dataset of flashover and breakage defects,this method improves the performance of YOLOv5,YOLOv7,and YOLOv8.In practical application,it can simply and effectively improve the precision of power line insulator defect detection and reduce missing detection for difficult small objects.展开更多
As the protective component,steel plate had attracted extensive attention because of frequently threats of explosive loads.In this paper,the evolution of microstructure and the mechanism of damage in the quasi-crackin...As the protective component,steel plate had attracted extensive attention because of frequently threats of explosive loads.In this paper,the evolution of microstructure and the mechanism of damage in the quasi-cracking area of steel plate subjected to explosive load were discussed and the relationships between micro defects and dynamic mechanical response were revealed.After the explosion experiment,five observation points were selected equidistant from the quasi-cracking area of the section of the steel plate along the thickness direction,and the characteristics of micro defects at the observation points were analyzed by optical microscope(OM),scanning electron microscope(SEM) and electron backscattered diffraction(EBSD).The observation result shows that many slip bands(SBs) appeared,and the grain orientation changed obviously in the steel plate,the two were the main damage types of micro defects.In addition,cracks,peeling pits,grooves and other lager micro defects were appeared in the lower area of the plate.The stress parameters of the observation points were obtained through an effective numerical model.The mechanism of damage generation and crack propagation in the quasicracking area were clarified by comparing the specific impulse of each observation point with the corresponding micro defects.The result shows that the generation and expansion of micro defects are related to the stress area(i.e.the upper compression area,the neutral plane area,and the lower tension area).The micro defects gather and expand at the grain boundary,and will become macroscopic damage under the continuous action of tensile stress.Besides,the micro defects at the midpoint of the section of the steel plate in the direction away from the explosion center(i.e.the horizontal direction) were also studied.It was found that the specific impulse at these positions were much smaller than that in the thickness direction,the micro defects were only SBs and a few micro cracks,and the those decreased with the increase of the distance from the explosion center.展开更多
When a customer uses the software, then it is possible to occur defects that can be removed in the updated versions of the software. Hence, in the present work, a robust examination of cross-project software defect pr...When a customer uses the software, then it is possible to occur defects that can be removed in the updated versions of the software. Hence, in the present work, a robust examination of cross-project software defect prediction is elaborated through an innovative hybrid machine learning framework. The proposed technique combines an advanced deep neural network architecture with ensemble models such as Support Vector Machine (SVM), Random Forest (RF), and XGBoost. The study evaluates the performance by considering multiple software projects like CM1, JM1, KC1, and PC1 using datasets from the PROMISE Software Engineering Repository. The three hybrid models that are compared are Hybrid Model-1 (SVM, RandomForest, XGBoost, Neural Network), Hybrid Model-2 (GradientBoosting, DecisionTree, LogisticRegression, Neural Network), and Hybrid Model-3 (KNeighbors, GaussianNB, Support Vector Classification (SVC), Neural Network), and the Hybrid Model 3 surpasses the others in terms of recall, F1-score, accuracy, ROC AUC, and precision. The presented work offers valuable insights into the effectiveness of hybrid techniques for cross-project defect prediction, providing a comparative perspective on early defect identification and mitigation strategies. .展开更多
Additive manufacturing(AM)has revolutionized the design and manufacturing of patient-specific,three-dimensional(3D),complex porous structures known as scaffolds for tissue engineering applications.The use of advanced ...Additive manufacturing(AM)has revolutionized the design and manufacturing of patient-specific,three-dimensional(3D),complex porous structures known as scaffolds for tissue engineering applications.The use of advanced image acquisition techniques,image processing,and computer-aided design methods has enabled the precise design and additive manufacturing of anatomically correct and patient-specific implants and scaffolds.However,these sophisticated techniques can be timeconsuming,labor-intensive,and expensive.Moreover,the necessary imaging and manufacturing equipment may not be readily available when urgent treatment is needed for trauma patients.In this study,a novel design and AM methods are proposed for the development of modular and customizable scaffold blocks that can be adapted to fit the bone defect area of a patient.These modular scaffold blocks can be combined to quickly form any patient-specific scaffold directly from two-dimensional(2D)medical images when the surgeon lacks access to a 3D printer or cannot wait for lengthy 3D imaging,modeling,and 3D printing during surgery.The proposed method begins with developing a bone surface-modeling algorithm that reconstructs a model of the patient’s bone from 2D medical image measurements without the need for expensive 3D medical imaging or segmentation.This algorithm can generate both patient-specific and average bone models.Additionally,a biomimetic continuous path planning method is developed for the additive manufacturing of scaffolds,allowing porous scaffold blocks with the desired biomechanical properties to be manufactured directly from 2D data or images.The algorithms are implemented,and the designed scaffold blocks are 3D printed using an extrusion-based AM process.Guidelines and instructions are also provided to assist surgeons in assembling scaffold blocks for the self-repair of patient-specific large bone defects.展开更多
The purpose of software defect prediction is to identify defect-prone code modules to assist software quality assurance teams with the appropriate allocation of resources and labor.In previous software defect predicti...The purpose of software defect prediction is to identify defect-prone code modules to assist software quality assurance teams with the appropriate allocation of resources and labor.In previous software defect prediction studies,transfer learning was effective in solving the problem of inconsistent project data distribution.However,target projects often lack sufficient data,which affects the performance of the transfer learning model.In addition,the presence of uncorrelated features between projects can decrease the prediction accuracy of the transfer learning model.To address these problems,this article propose a software defect prediction method based on stable learning(SDP-SL)that combines code visualization techniques and residual networks.This method first transforms code files into code images using code visualization techniques and then constructs a defect prediction model based on these code images.During the model training process,target project data are not required as prior knowledge.Following the principles of stable learning,this paper dynamically adjusted the weights of source project samples to eliminate dependencies between features,thereby capturing the“invariance mechanism”within the data.This approach explores the genuine relationship between code defect features and labels,thereby enhancing defect prediction performance.To evaluate the performance of SDP-SL,this article conducted comparative experiments on 10 open-source projects in the PROMISE dataset.The experimental results demonstrated that in terms of the F-measure,the proposed SDP-SL method outperformed other within-project defect prediction methods by 2.11%-44.03%.In cross-project defect prediction,the SDP-SL method provided an improvement of 5.89%-25.46% in prediction performance compared to other cross-project defect prediction methods.Therefore,SDP-SL can effectively enhance within-and cross-project defect predictions.展开更多
The Message Passing Interface (MPI) is a widely accepted standard for parallel computing on distributed memorysystems.However, MPI implementations can contain defects that impact the reliability and performance of par...The Message Passing Interface (MPI) is a widely accepted standard for parallel computing on distributed memorysystems.However, MPI implementations can contain defects that impact the reliability and performance of parallelapplications. Detecting and correcting these defects is crucial, yet there is a lack of published models specificallydesigned for correctingMPI defects. To address this, we propose a model for detecting and correcting MPI defects(DC_MPI), which aims to detect and correct defects in various types of MPI communication, including blockingpoint-to-point (BPTP), nonblocking point-to-point (NBPTP), and collective communication (CC). The defectsaddressed by the DC_MPI model include illegal MPI calls, deadlocks (DL), race conditions (RC), and messagemismatches (MM). To assess the effectiveness of the DC_MPI model, we performed experiments on a datasetconsisting of 40 MPI codes. The results indicate that the model achieved a detection rate of 37 out of 40 codes,resulting in an overall detection accuracy of 92.5%. Additionally, the execution duration of the DC_MPI modelranged from 0.81 to 1.36 s. These findings show that the DC_MPI model is useful in detecting and correctingdefects in MPI implementations, thereby enhancing the reliability and performance of parallel applications. TheDC_MPImodel fills an important research gap and provides a valuable tool for improving the quality ofMPI-basedparallel computing systems.展开更多
Cross-Project Defect Prediction(CPDP)is a method that utilizes historical data from other source projects to train predictive models for defect prediction in the target project.However,existing CPDP methods only consi...Cross-Project Defect Prediction(CPDP)is a method that utilizes historical data from other source projects to train predictive models for defect prediction in the target project.However,existing CPDP methods only consider linear correlations between features(indicators)of the source and target projects.These models are not capable of evaluating non-linear correlations between features when they exist,for example,when there are differences in data distributions between the source and target projects.As a result,the performance of such CPDP models is compromised.In this paper,this paper proposes a novel CPDP method based on Synthetic Minority Oversampling Technique(SMOTE)and Deep Canonical Correlation Analysis(DCCA),referred to as S-DCCA.Canonical Correlation Analysis(CCA)is employed to address the issue of non-linear correlations between features of the source and target projects.S-DCCA extends CCA by incorporating the MlpNet model for feature extraction from the dataset.The redundant features are then eliminated by maximizing the correlated feature subset using the CCA loss function.Finally,cross-project defect prediction is achieved through the application of the SMOTE data sampling technique.Area Under Curve(AUC)and F1 scores(F1)are used as evaluation metrics.This paper conducted experiments on 27 projects from four public datasets to validate the proposed method.The results demonstrate that,on average,our method outperforms all baseline approaches by at least 1.2%in AUC and 5.5%in F1 score.This indicates that the proposed method exhibits favorable performance characteristics.展开更多
Urban underground pipelines are an important infrastructure in cities,and timely investigation of problems in underground pipelines can help ensure the normal operation of cities.Owing to the growing demand for defect...Urban underground pipelines are an important infrastructure in cities,and timely investigation of problems in underground pipelines can help ensure the normal operation of cities.Owing to the growing demand for defect detection in urban underground pipelines,this study developed an improved defect detection method for urban underground pipelines based on fully convolutional one-stage object detector(FCOS),called spatial pyramid pooling-fast(SPPF)feature fusion and dual detection heads based on FCOS(SDH-FCOS)model.This study improved the feature fusion component of the model network based on FCOS,introduced an SPPF network structure behind the last output feature layer of the backbone network,fused the local and global features,added a top-down path to accelerate the circulation of shallowinformation,and enriched the semantic information acquired by shallow features.The ability of the model to detect objects with multiple morphologies was strengthened by introducing dual detection heads.The experimental results using an open dataset of underground pipes show that the proposed SDH-FCOS model can recognize underground pipe defects more accurately;the average accuracy was improved by 2.7% compared with the original FCOS model,reducing the leakage rate to a large extent and achieving real-time detection.Also,our model achieved a good trade-off between accuracy and speed compared with other mainstream methods.This proved the effectiveness of the proposed model.展开更多
基金This study was approved by the Siriraj Institutional Review Board(SIRB),Faculty of Medicine Siriraj Hospital,Mahidol University(COA no.Si 760/2021).The need for consent was waived by the board due to its retrospective nature and as all personal identifying information was obliterated.The study protocol conforms to the ethical guidelines of the 1975 Declaration of Helsinki.
文摘Background:Atrial septal defect(ASD)is a common form of adult congenital heart disease that can lead to long-term adverse outcomes if left untreated.Early closure of ASD has been associated with excellent outcomes and lower complication rates.However,there is limited evidence regarding the prognosis of ASD closure in older adults.This study aims to evaluate the mortality rates in older ASD patients with and without closure.Methods:A retrospective cohort study was conducted on patients aged 40 years or older with ASD between 2001 and 2017.Patients were followed up to assess all-cause mortality.Univariable and multivariable analyses were performed to identify the predictors of mortality.A p-value of<0.05 was considered statistically significant.Results:The cohort consisted of 450 patients(mean age 56.6±10.4 years,77.3%female),with 66%aged between 40 and 60 years,and 34%over 60 years.Within the cohort,299 underwent ASD closure(201 with transcatheter and 98 with surgical closure).During the median follow-up duration of 7.9 years,51 patients died.The unadjusted cumulative 10-year rate of mortality was 3%in patients with ASD closure,and 28%in patients without ASD closure(log-rank p<0.001).Multivariable analysis revealed that age(hazard ratio[HR]1.04,95%confidence interval[CI]1.006–1.06,p=0.01),NYHA class(HR 2.75,95%CI 1.63–4.62,p<0.001),blood urea nitrogen(BUN)(HR 1.07,95%CI 1.03–1.12,p<0.001),right ventricular systolic pressure(RVSP)(HR 1.07,95%CI 1.003–1.04,p=0.01),and lack of ASD closure(HR 15.12,95%CI 5.63–40.59,p<0.001)were independently associated with mortality.Conclusion:ASD closure demonstrated favorable outcomes in older patients.Age,NYHA class,BUN,RVSP,and lack of ASD closure were identified as independent factors linked to mortality in this population.
基金the support of the Australia Research Council (ARC) through the Discovery Project (DP230101040)the Natural Science Foundation of Shandong Province (ZR2022QB139, No. ZR2020KF025)+3 种基金the Starting Research Fund (Grant No. 20210122) from the Ludong Universitythe Natural Science Foundation of China (12274190) from the Ludong Universitythe support of the Shandong Youth Innovation Team Introduction and Education Programthe Special Fund for Taishan Scholars Project (No. tsqn202211186) in Shandong Province。
文摘Over the past decade, graphitic carbon nitride(g-C_(3)N_(4)) has emerged as a universal photocatalyst toward various sustainable carbo-neutral technologies. Despite solar applications discrepancy, g-C_(3)N_(4) is still confronted with a general fatal issue of insufficient supply of thermodynamically active photocarriers due to its inferior solar harvesting ability and sluggish charge transfer dynamics. Fortunately, this could be significantly alleviated by the “all-in-one” defect engineering strategy, which enables a simultaneous amelioration of both textural uniqueness and intrinsic electronic band structures. To this end, we have summarized an unprecedently comprehensive discussion on defect controls including the vacancy/non-metallic dopant creation with optimized electronic band structure and electronic density, metallic doping with ultraactive coordinated environment(M–N_(x), M–C_(2)N_(2), M–O bonding), functional group grafting with optimized band structure, and promoted crystallinity with extended conjugation π system with weakened interlayered van der Waals interaction. Among them, the defect states induced by various defect types such as N vacancy, P/S/halogen dopants, and cyano group in boosting solar harvesting and accelerating photocarrier transfer have also been emphasized. More importantly, the shallow defect traps identified by femtosecond transient absorption spectra(fs-TAS) have also been highlighted. It is believed that this review would pave the way for future readers with a unique insight into a more precise defective g-C_(3)N_(4) “customization”, motivating more profound thinking and flourishing research outputs on g-C_(3)N_(4)-based photocatalysis.
基金supported by the China Scholarship Council (CSC) (No.202206020149)the Academic Excellence Foundation of BUAA for PhD Students,the Funding Project of Science and Technology on Reliability and Environmental Engineering Laboratory (No.6142004210106).
文摘Sintered silver nanoparticles(AgNPs)arewidely used in high-power electronics due to their exceptional properties.However,the material reliability is significantly affected by various microscopic defects.In this work,the three primary micro-defect types at potential stress concentrations in sintered AgNPs are identified,categorized,and quantified.Molecular dynamics(MD)simulations are employed to observe the failure evolution of different microscopic defects.The dominant mechanisms responsible for this evolution are dislocation nucleation and dislocation motion.At the same time,this paper clarifies the quantitative relationship between the tensile strain amount and the failure mechanism transitions of the three defect types by defining key strain points.The impact of defect types on the failure process is also discussed.Furthermore,traction-separation curves extracted from microscopic defect evolutions serve as a bridge to connect the macro-scale model.The validity of the crack propagation model is confirmed through tensile tests.Finally,we thoroughly analyze how micro-defect types influence macro-crack propagation and attempt to find supporting evidence from the MD model.Our findings provide a multi-perspective reference for the reliability analysis of sintered AgNPs.
基金Funded by the Scientific and Technologial Innovation Programs of Higher Education Institutions in Shanxi (No. 2020L0628)the Taiyuan Institute of Technology Scientific Research Initial Funding (No. 2022KJ072)+2 种基金the Program for the (Reserved) Discipline Leaders of Taiyuan Institute of Technologythe Fundamental Research Funds for the Central Universities (Nos. 2017TS004, 2017TS006, and GK201704005)Supported by HZWTECH for providing computational facilities
文摘In order to explore the effect of vacancy defects on the structural,electronic,magnetic and optical properties of CoS_(2) and FeS_(2),first-principles calculation method was used to investigate the alloys.The calculated results of materials without vacancy are consistent with those reported in the literatures,while the results of materials with vacancy defect were different from those of literatures due to the difference vacancy concentration.The Co vacancy defect hardly changes the half-metallic characteristic of CoS_(2).The Fe vacancy defect changes FeS_(2) from semiconductor to half-metal,and the bottom of the spin-down conduction band changes from the p orbital state of S to the d(t_(2g))orbital state of Fe,while the top of the valence band remains the d orbital d(eg)state of Fe.The half-metallic Co vacancy defects of CoS_(2) and Fe vacancy defects of FeS_(2) are expected to be used in spintronic devices.S vacancy defects make both CoS_(2) and FeS_(2) metallic.Both the Co and S vacancy defects lead to the decrease of the magnetic moment of CoS_(2),while both the Fe and S vacancy defects lead to the obvious magnetic property of FeS_(2).Vacancy defects enhance the absorption coefficient of infrared band and long band of visible light obviously,and produce obvious red shift phenomenon,which is expected to be used in photoelectric devices.
基金supported in part by the National Natural Science Foundation of China under Grants 32171909,51705365,52205254The Guangdong Basic and Applied Basic Research Foundation under Grants 2020B1515120050,2023A1515011255+2 种基金The Guangdong Key R&D projects under Grant 2020B0404030001the Scientific Research Projects of Universities in Guangdong Province under Grant 2020KCXTD015The Ji Hua Laboratory Open Project under Grant X220931UZ230.
文摘As computer technology continues to advance,factories have increasingly higher demands for detecting defects.However,detecting defects in a plant environment remains a challenging task due to the presence of complex backgrounds and defects of varying shapes and sizes.To address this issue,this paper proposes YOLO-DD,a defect detectionmodel based on YOLOv5 that is effective and robust.To improve the feature extraction process and better capture global information,the vanilla YOLOv5 is augmented with a new module called Relative-Distance-Aware Transformer(RDAT).Additionally,an Information Gap Filling Strategy(IGFS)is proposed to improve the fusion of features at different scales.The classic lightweight attention mechanism Squeeze-and-Excitation(SE)module is also incorporated into the neck section to enhance feature expression and improve the model’s performance.Experimental results on the NEU-DET dataset demonstrate that YOLO-DDachieves competitive results compared to state-of-the-art methods,with a 2.0% increase in accuracy compared to the original YOLOv5,achieving 82.41% accuracy and38.25FPS(framesper second).Themodel is also testedon a self-constructed fabric defect dataset,and the results show that YOLO-DD is more stable and has higher accuracy than the original YOLOv5,demonstrating its stability and generalization ability.The high efficiency of YOLO-DD enables it to meet the requirements of industrial high accuracy and real-time detection.
基金supported by the National Natural Science Foundation of China(51805078)Project of National Key Laboratory of Advanced Casting Technologies(CAT2023-002)the 111 Project(B16009).
文摘Segment Anything Model(SAM)is a cutting-edge model that has shown impressive performance in general object segmentation.The birth of the segment anything is a groundbreaking step towards creating a universal intelligent model.Due to its superior performance in general object segmentation,it quickly gained attention and interest.This makes SAM particularly attractive in industrial surface defect segmentation,especially for complex industrial scenes with limited training data.However,its segmentation ability for specific industrial scenes remains unknown.Therefore,in this work,we select three representative and complex industrial surface defect detection scenarios,namely strip steel surface defects,tile surface defects,and rail surface defects,to evaluate the segmentation performance of SAM.Our results show that although SAM has great potential in general object segmentation,it cannot achieve satisfactory performance in complex industrial scenes.Our test results are available at:https://github.com/VDT-2048/SAM-IS.
基金This retrospective study was approved by the Seoul National University Hospital Institutional Review Board(approval number:H-2106-179-1230).The requirement for informed consent was waived.
文摘Background:The optimal surgical timing and clinical outcomes of ventricular septal defect(VSD)closure in neo-nates remain unclear.We aimed to evaluate the clinical outcomes of VSD closure in neonates(age≤30 days).Methods:We retrospectively reviewed 50 consecutive neonates who underwent VSD closure for isolated VSDs between August 2003 and June 2021.Indications for the procedure included congestive heart failure/failure to thrive and pulmonary hypertension.Major adverse events(MAEs)were defined as the composite of all-cause mortality,reoperation,persistent atrioventricular block,and significant(≥grade 2)valvular dysfunction.Results:The median age and body weight at operation were 26.0 days(interquartile range[IQR],18.8–28.3)and 3.7 kg(IQR,3.3–4.2),respectively.The median follow-up duration was 110.4 months(IQR,56.8–165.0).Seven patients required preoperative respiratory support,andfive had significant(≥grade 2)preoperative valvular dysfunction.One early mortality occurred due to irreversible cardiogenic shock;no late mortality was observed.One reopera-tion was due to hemodynamically significant residual VSD at 103.8 months postoperatively.The overall survival,freedom from reoperation,and freedom from MAE at 15-years were 98.0%,96.3%,and 94.4%,respectively.Pre-operative mechanical ventilation was associated with a longer duration of postoperative mechanical ventilation(p<0.001)and a longer length of intensive care unit stay(p<0.001).Conclusions:VSD closure with favorable outcomes without morbidities is feasible even in neonates.However,neonates requiring preoperative respiratory support may require careful postoperative management considering the long-term postoperative risks.Overall,surgical VSD closure might be indicated earlier in neonates with respiratory compromise.
基金supported by the Natural Science Foundation of Heilongjiang Province(Grant Number:LH2021F002).
文摘With the advent of Industry 4.0,marked by a surge in intelligent manufacturing,advanced sensors embedded in smart factories now enable extensive data collection on equipment operation.The analysis of such data is pivotal for ensuring production safety,a critical factor in monitoring the health status of manufacturing apparatus.Conventional defect detection techniques,typically limited to specific scenarios,often require manual feature extraction,leading to inefficiencies and limited versatility in the overall process.Our research presents an intelligent defect detection methodology that leverages deep learning techniques to automate feature extraction and defect localization processes.Our proposed approach encompasses a suite of components:the high-level feature learning block(HLFLB),the multi-scale feature learning block(MSFLB),and a dynamic adaptive fusion block(DAFB),working in tandem to extract meticulously and synergistically aggregate defect-related characteristics across various scales and hierarchical levels.We have conducted validation of the proposed method using datasets derived from gearbox and bearing assessments.The empirical outcomes underscore the superior defect detection capability of our approach.It demonstrates consistently high performance across diverse datasets and possesses the accuracy required to categorize defects,taking into account their specific locations and the extent of damage,proving the method’s effectiveness and reliability in identifying defects in industrial components.
基金Intelligent Manufacturing and Robot Technology Innovation Project of Beijing Municipal Commission of Science and Technology and Zhongguancun Science and Technology Park Management Committee,Grant/Award Number:Z221100000222016National Natural Science Foundation of China,Grant/Award Number:62076014Beijing Municipal Education Commission and Beijing Natural Science Foundation,Grant/Award Number:KZ202010005004。
文摘Non-destructive detection of wire bonding defects in integrated circuits(IC)is critical for ensuring product quality after packaging.Image-processing-based methods do not provide a detailed evaluation of the three-dimensional defects of the bonding wire.Therefore,a method of 3D reconstruction and pattern recognition of wire defects based on stereo vision,which can achieve non-destructive detection of bonding wire defects is proposed.The contour features of bonding wires and other electronic components in the depth image is analysed to complete the 3D reconstruction of the bonding wires.Especially to filter the noisy point cloud and obtain an accurate point cloud of the bonding wire surface,a point cloud segmentation method based on spatial surface feature detection(SFD)was proposed.SFD can extract more distinct features from the bonding wire surface during the point cloud segmentation process.Furthermore,in the defect detection process,a directional discretisation descriptor with multiple local normal vectors is designed for defect pattern recognition of bonding wires.The descriptor combines local and global features of wire and can describe the spatial variation trends and structural features of wires.The experimental results show that the method can complete the 3D reconstruction and defect pattern recognition of bonding wires,and the average accuracy of defect recognition is 96.47%,which meets the production requirements of bonding wire defect detection.
基金supported by the Science and Technology Development Fund of Macao(Grant No.0079/2019/AMJ)the National Key R&D Program of China(No.2019YFE0111400).
文摘Urban sewer pipes are a vital infrastructure in modern cities,and their defects must be detected in time to prevent potential malfunctioning.In recent years,to relieve the manual efforts by human experts,models based on deep learning have been introduced to automatically identify potential defects.However,these models are insufficient in terms of dataset complexity,model versatility and performance.Our work addresses these issues with amulti-stage defect detection architecture using a composite backbone Swin Transformer.Themodel based on this architecture is trained using a more comprehensive dataset containingmore classes of defects.By ablation studies on the modules of combined backbone Swin Transformer,multi-stage detector,test-time data augmentation and model fusion,it is revealed that they all contribute to the improvement of detection accuracy from different aspects.The model incorporating all these modules achieves the mean Average Precision(mAP)of 78.6% at an Intersection over Union(IoU)threshold of 0.5.This represents an improvement of 14.1% over the ResNet50 Faster Region-based Convolutional Neural Network(R-CNN)model and a 6.7% improvement over You Only Look Once version 6(YOLOv6)-large,the highest in the YOLO methods.In addition,for other defect detection models for sewer pipes,although direct comparison with themis infeasible due to the unavailability of their private datasets,our results are obtained from a more comprehensive dataset and have superior generalization capabilities.
基金This research was financially supported by the Ministry of Trade,Industry,and Energy(MOTIE),Korea,under the“Project for Research and Development with Middle Markets Enterprises and DNA(Data,Network,AI)Universities”(AI-based Safety Assessment and Management System for Concrete Structures)(ReferenceNumber P0024559)supervised by theKorea Institute for Advancement of Technology(KIAT).
文摘Time-series data provide important information in many fields,and their processing and analysis have been the focus of much research.However,detecting anomalies is very difficult due to data imbalance,temporal dependence,and noise.Therefore,methodologies for data augmentation and conversion of time series data into images for analysis have been studied.This paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance,temporal dependence,and robustness to noise.The method of data augmentation is set as the addition of noise.It involves adding Gaussian noise,with the noise level set to 0.002,to maximize the generalization performance of the model.In addition,we use the Markov Transition Field(MTF)method to effectively visualize the dynamic transitions of the data while converting the time series data into images.It enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the data.For anomaly detection,the PatchCore model is applied to show excellent performance,and the detected anomaly areas are represented as heat maps.It allows for the detection of anomalies,and by applying an anomaly map to the original image,it is possible to capture the areas where anomalies occur.The performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to images.Additionally,when processed as images rather than as time series data,there was a significant reduction in both the size of the data and the training time.The proposed method can provide an important springboard for research in the field of anomaly detection using time series data.Besides,it helps solve problems such as analyzing complex patterns in data lightweight.
基金supported by the National Natural Science Foundation of China(Grant No.52370109)China Postdoctoral Science Foundation(2022M710830)+4 种基金Venture and Innovation Support Program for Chongqing Overseas Returnees(cx2022005)the Natural Science Foun-dation Project of CQ CSTC(CSTB2022NSCQ-MSX1267)Research Project of Chongqing Education Commission Foundation(KJQN201800826)Science and Technology Research Program of Chongqing Municipal Education Commission of China(KJZD-K202100801)Post-doctoral Program Funded by Chongqing,and Chongqing Technology and Business University,China(CXQT21023).
文摘Good crystallinity can reduce the charge recombination centers caused by defects,whilst structures with strong polycondensation have high charge mobility,leading to more charge transfer to the material surface for reaction.Much effort has been put into the preparation of a highly efficient g-C_(3)N_(4) with defects to improve its application potential under the premise in high crystallinity.Hence,this review paper emphasizes the importance to balance the defect and crystallinity of g-C_(3)N_(4).In addition,detailed discussion on the relationship between defects and activity of g-C_(3)N_(4) was carried out based on its applications in environmental purification(e.g.,VOCs oxidation,NO_(x) oxidation,H_(2)O_(2) evolution,sterilization,pesticide oxidation)and energy conversion(H_(2) evolution,N_(2) fixation and CO_(2) reduction).Lastly,the challenge in developing more efficient defective g-C_(3)N_(4) photocatalytic materials is summarized.
基金State Grid Jiangsu Electric Power Co.,Ltd.of the Science and Technology Project(Grant No.J2022004).
文摘Insulator defect detection plays a vital role in maintaining the secure operation of power systems.To address the issues of the difficulty of detecting small objects and missing objects due to the small scale,variable scale,and fuzzy edge morphology of insulator defects,we construct an insulator dataset with 1600 samples containing flashovers and breakages.Then a simple and effective surface defect detection method of power line insulators for difficult small objects is proposed.Firstly,a high-resolution featuremap is introduced and a small object prediction layer is added so that the model can detect tiny objects.Secondly,a simplified adaptive spatial feature fusion(SASFF)module is introduced to perform cross-scale spatial fusion to improve adaptability to variable multi-scale features.Finally,we propose an enhanced deformable attention mechanism(EDAM)module.By integrating a gating activation function,the model is further inspired to learn a small number of critical sampling points near reference points.And the module can improve the perception of object morphology.The experimental results indicate that concerning the dataset of flashover and breakage defects,this method improves the performance of YOLOv5,YOLOv7,and YOLOv8.In practical application,it can simply and effectively improve the precision of power line insulator defect detection and reduce missing detection for difficult small objects.
基金supported by the Science and Technology Project of Fire Rescue Bureau of Ministry of Emergency Management (Grant No.2022XFZD05)S&T Program of Hebei(Grant No.22375419D)National Natural Science Foundation of China (Grant No.11802160)。
文摘As the protective component,steel plate had attracted extensive attention because of frequently threats of explosive loads.In this paper,the evolution of microstructure and the mechanism of damage in the quasi-cracking area of steel plate subjected to explosive load were discussed and the relationships between micro defects and dynamic mechanical response were revealed.After the explosion experiment,five observation points were selected equidistant from the quasi-cracking area of the section of the steel plate along the thickness direction,and the characteristics of micro defects at the observation points were analyzed by optical microscope(OM),scanning electron microscope(SEM) and electron backscattered diffraction(EBSD).The observation result shows that many slip bands(SBs) appeared,and the grain orientation changed obviously in the steel plate,the two were the main damage types of micro defects.In addition,cracks,peeling pits,grooves and other lager micro defects were appeared in the lower area of the plate.The stress parameters of the observation points were obtained through an effective numerical model.The mechanism of damage generation and crack propagation in the quasicracking area were clarified by comparing the specific impulse of each observation point with the corresponding micro defects.The result shows that the generation and expansion of micro defects are related to the stress area(i.e.the upper compression area,the neutral plane area,and the lower tension area).The micro defects gather and expand at the grain boundary,and will become macroscopic damage under the continuous action of tensile stress.Besides,the micro defects at the midpoint of the section of the steel plate in the direction away from the explosion center(i.e.the horizontal direction) were also studied.It was found that the specific impulse at these positions were much smaller than that in the thickness direction,the micro defects were only SBs and a few micro cracks,and the those decreased with the increase of the distance from the explosion center.
文摘When a customer uses the software, then it is possible to occur defects that can be removed in the updated versions of the software. Hence, in the present work, a robust examination of cross-project software defect prediction is elaborated through an innovative hybrid machine learning framework. The proposed technique combines an advanced deep neural network architecture with ensemble models such as Support Vector Machine (SVM), Random Forest (RF), and XGBoost. The study evaluates the performance by considering multiple software projects like CM1, JM1, KC1, and PC1 using datasets from the PROMISE Software Engineering Repository. The three hybrid models that are compared are Hybrid Model-1 (SVM, RandomForest, XGBoost, Neural Network), Hybrid Model-2 (GradientBoosting, DecisionTree, LogisticRegression, Neural Network), and Hybrid Model-3 (KNeighbors, GaussianNB, Support Vector Classification (SVC), Neural Network), and the Hybrid Model 3 surpasses the others in terms of recall, F1-score, accuracy, ROC AUC, and precision. The presented work offers valuable insights into the effectiveness of hybrid techniques for cross-project defect prediction, providing a comparative perspective on early defect identification and mitigation strategies. .
文摘Additive manufacturing(AM)has revolutionized the design and manufacturing of patient-specific,three-dimensional(3D),complex porous structures known as scaffolds for tissue engineering applications.The use of advanced image acquisition techniques,image processing,and computer-aided design methods has enabled the precise design and additive manufacturing of anatomically correct and patient-specific implants and scaffolds.However,these sophisticated techniques can be timeconsuming,labor-intensive,and expensive.Moreover,the necessary imaging and manufacturing equipment may not be readily available when urgent treatment is needed for trauma patients.In this study,a novel design and AM methods are proposed for the development of modular and customizable scaffold blocks that can be adapted to fit the bone defect area of a patient.These modular scaffold blocks can be combined to quickly form any patient-specific scaffold directly from two-dimensional(2D)medical images when the surgeon lacks access to a 3D printer or cannot wait for lengthy 3D imaging,modeling,and 3D printing during surgery.The proposed method begins with developing a bone surface-modeling algorithm that reconstructs a model of the patient’s bone from 2D medical image measurements without the need for expensive 3D medical imaging or segmentation.This algorithm can generate both patient-specific and average bone models.Additionally,a biomimetic continuous path planning method is developed for the additive manufacturing of scaffolds,allowing porous scaffold blocks with the desired biomechanical properties to be manufactured directly from 2D data or images.The algorithms are implemented,and the designed scaffold blocks are 3D printed using an extrusion-based AM process.Guidelines and instructions are also provided to assist surgeons in assembling scaffold blocks for the self-repair of patient-specific large bone defects.
基金supported by the NationalNatural Science Foundation of China(Grant No.61867004)the Youth Fund of the National Natural Science Foundation of China(Grant No.41801288).
文摘The purpose of software defect prediction is to identify defect-prone code modules to assist software quality assurance teams with the appropriate allocation of resources and labor.In previous software defect prediction studies,transfer learning was effective in solving the problem of inconsistent project data distribution.However,target projects often lack sufficient data,which affects the performance of the transfer learning model.In addition,the presence of uncorrelated features between projects can decrease the prediction accuracy of the transfer learning model.To address these problems,this article propose a software defect prediction method based on stable learning(SDP-SL)that combines code visualization techniques and residual networks.This method first transforms code files into code images using code visualization techniques and then constructs a defect prediction model based on these code images.During the model training process,target project data are not required as prior knowledge.Following the principles of stable learning,this paper dynamically adjusted the weights of source project samples to eliminate dependencies between features,thereby capturing the“invariance mechanism”within the data.This approach explores the genuine relationship between code defect features and labels,thereby enhancing defect prediction performance.To evaluate the performance of SDP-SL,this article conducted comparative experiments on 10 open-source projects in the PROMISE dataset.The experimental results demonstrated that in terms of the F-measure,the proposed SDP-SL method outperformed other within-project defect prediction methods by 2.11%-44.03%.In cross-project defect prediction,the SDP-SL method provided an improvement of 5.89%-25.46% in prediction performance compared to other cross-project defect prediction methods.Therefore,SDP-SL can effectively enhance within-and cross-project defect predictions.
基金the Deanship of Scientific Research at King Abdulaziz University,Jeddah,Saudi Arabia under the Grant No.RG-12-611-43.
文摘The Message Passing Interface (MPI) is a widely accepted standard for parallel computing on distributed memorysystems.However, MPI implementations can contain defects that impact the reliability and performance of parallelapplications. Detecting and correcting these defects is crucial, yet there is a lack of published models specificallydesigned for correctingMPI defects. To address this, we propose a model for detecting and correcting MPI defects(DC_MPI), which aims to detect and correct defects in various types of MPI communication, including blockingpoint-to-point (BPTP), nonblocking point-to-point (NBPTP), and collective communication (CC). The defectsaddressed by the DC_MPI model include illegal MPI calls, deadlocks (DL), race conditions (RC), and messagemismatches (MM). To assess the effectiveness of the DC_MPI model, we performed experiments on a datasetconsisting of 40 MPI codes. The results indicate that the model achieved a detection rate of 37 out of 40 codes,resulting in an overall detection accuracy of 92.5%. Additionally, the execution duration of the DC_MPI modelranged from 0.81 to 1.36 s. These findings show that the DC_MPI model is useful in detecting and correctingdefects in MPI implementations, thereby enhancing the reliability and performance of parallel applications. TheDC_MPImodel fills an important research gap and provides a valuable tool for improving the quality ofMPI-basedparallel computing systems.
基金NationalNatural Science Foundation of China,Grant/AwardNumber:61867004National Natural Science Foundation of China Youth Fund,Grant/Award Number:41801288.
文摘Cross-Project Defect Prediction(CPDP)is a method that utilizes historical data from other source projects to train predictive models for defect prediction in the target project.However,existing CPDP methods only consider linear correlations between features(indicators)of the source and target projects.These models are not capable of evaluating non-linear correlations between features when they exist,for example,when there are differences in data distributions between the source and target projects.As a result,the performance of such CPDP models is compromised.In this paper,this paper proposes a novel CPDP method based on Synthetic Minority Oversampling Technique(SMOTE)and Deep Canonical Correlation Analysis(DCCA),referred to as S-DCCA.Canonical Correlation Analysis(CCA)is employed to address the issue of non-linear correlations between features of the source and target projects.S-DCCA extends CCA by incorporating the MlpNet model for feature extraction from the dataset.The redundant features are then eliminated by maximizing the correlated feature subset using the CCA loss function.Finally,cross-project defect prediction is achieved through the application of the SMOTE data sampling technique.Area Under Curve(AUC)and F1 scores(F1)are used as evaluation metrics.This paper conducted experiments on 27 projects from four public datasets to validate the proposed method.The results demonstrate that,on average,our method outperforms all baseline approaches by at least 1.2%in AUC and 5.5%in F1 score.This indicates that the proposed method exhibits favorable performance characteristics.
基金supported by the National Natural Science Foundation of China under Grant No.61976226the Research and Academic Team of South-CentralMinzu University under Grant No.KTZ20050.
文摘Urban underground pipelines are an important infrastructure in cities,and timely investigation of problems in underground pipelines can help ensure the normal operation of cities.Owing to the growing demand for defect detection in urban underground pipelines,this study developed an improved defect detection method for urban underground pipelines based on fully convolutional one-stage object detector(FCOS),called spatial pyramid pooling-fast(SPPF)feature fusion and dual detection heads based on FCOS(SDH-FCOS)model.This study improved the feature fusion component of the model network based on FCOS,introduced an SPPF network structure behind the last output feature layer of the backbone network,fused the local and global features,added a top-down path to accelerate the circulation of shallowinformation,and enriched the semantic information acquired by shallow features.The ability of the model to detect objects with multiple morphologies was strengthened by introducing dual detection heads.The experimental results using an open dataset of underground pipes show that the proposed SDH-FCOS model can recognize underground pipe defects more accurately;the average accuracy was improved by 2.7% compared with the original FCOS model,reducing the leakage rate to a large extent and achieving real-time detection.Also,our model achieved a good trade-off between accuracy and speed compared with other mainstream methods.This proved the effectiveness of the proposed model.