Cross-Project Software Defect Prediction Based on SMOTE and Deep Canonical Correlation Analysis

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.

Investigation of point defect evolution and Voronoi cluster analysis for magnesium during nanoindentation

The present study investigates the effect of nanoindentation on single-crystal magnesium specimens using the embedded-atom method potential in molecular dynamics simulation.Analyses are done under dynamic loading where the load-bearing capacity and change in the structural configuration are studied on the basal(Z-direction)and two prismatic planes(X-and Y-directions)with varying indenter velocities.The investigation of structural evolution is done using atomic displacement analyses to measure the net magnitude of displacement,atomic strain analyses to evaluate the shear strain developed in the process,and Wigner-Seitz defect analyses to calculate the total vacancies at varied timesteps.Furthermore,Voronoi analyses are done when indented on the basal plane to identify the cluster distribution at different planar depths of the specimen.From the analyses,it has been observed that the load-bearing capacity of the specimen varies with the indentation velocity and the direction of indentation on the specimen.Additionally,it is seen that the observed shear and total atomic displacement in the Z-direction is the least in comparison to the other two axes.The partial dislocation 1/3<-12-10>is seen to be majorly present and the population of dislocation loops is more abundant for lower indenter velocities.Furthermore,clusters<0,4,4,6>and<0,6,0,8>are the major indices developed during nanoindentation on the basal plane where they exhibit symmetrical distribution as observed from the Z-direction.

Rail Surface Defect Detection Based on Improved UPerNet and Connected Component Analysis

To guarantee the safety of railway operations,the swift detection of rail surface defects becomes imperative.Traditional methods of manual inspection and conventional nondestructive testing prove inefficient,especially when scaling to extensive railway networks.Moreover,the unpredictable and intricate nature of defect edge shapes further complicates detection efforts.Addressing these challenges,this paper introduces an enhanced Unified Perceptual Parsing for Scene Understanding Network(UPerNet)tailored for rail surface defect detection.Notably,the Swin Transformer Tiny version(Swin-T)network,underpinned by the Transformer architecture,is employed for adept feature extraction.This approach capitalizes on the global information present in the image and sidesteps the issue of inductive preference.The model’s efficiency is further amplified by the windowbased self-attention,which minimizes the model’s parameter count.We implement the cross-GPU synchronized batch normalization(SyncBN)for gradient optimization and integrate the Lovász-hinge loss function to leverage pixel dependency relationships.Experimental evaluations underscore the efficacy of our improved UPerNet,with results demonstrating Pixel Accuracy(PA)scores of 91.39%and 93.35%,Intersection over Union(IoU)values of 83.69%and 87.58%,Dice Coefficients of 91.12%and 93.38%,and Precision metrics of 90.85%and 93.41%across two distinct datasets.An increment in detection accuracy was discernible.For further practical applicability,we deploy semantic segmentation of rail surface defects,leveraging connected component processing techniques to distinguish varied defects within the same frame.By computing the actual defect length and area,our deep learning methodology presents results that offer intuitive insights for railway maintenance professionals.

Simulation Analysis and Experimental Study of Defect Detection Underwater by ACFM Probe

This article studies the application of the alternating current field measurement （ACFM） method in defect detection for underwater structures. Numerical model of the ACFM system is built for structure surface defect detection in seawater environment. Finite element simulation is performed to investigate rules and characteristics of the electromagnetic signal distribution in the defected area. In respect of the simulation results, underwater artificial crack detection experiments are designed and conducted for the ACFM system. The experiment results show that the ACFM system can detect cracks in underwater structures and the detection accuracy is higher than 85%. This can meet the engineering requirement of underwater structure defect detection. The results in this article can be applied to establish technical foundation for the optimization and development of ACFM based underwater structure defects detection system.

Spatiotemporal Property Analysis of Birth Defects in Wuxi,China

Objective To describe the temporal trends and spatial patterns of birth defects occurring in Wuxi, a developed region of China. Methods Wavelet analysis was used to decompose the temporal trends of birth defect prevalence based on the birth defect rates over the past 16 years. Birth defect cases with detailed personal and family information were geo-coded and the relative risk in each village was calculated. General G statistic was used to test the spatial property with different scales. Results Wavelet analysis showed an increasing temporal trend of birth defects in this region. Clustering analysis revealed that changes continued in the spatial patterns with different scales. Conclusion Wuxi is confronted with severe challenges to reduce birth defect prevalence. The risk factors are stable and show no change with spatial scale but an increasing temporal trend. Interventions should be focused on villages with a higher prevalence of birth defects.

Prediction of central bursting defects in rod extrusion process with upper bound analysis method

The prediction of central bursting defects in the rod extrusion process through conical dies using the upper bound analysisis investigated. A kinematically admissible velocity field, including the radial and angular velocity components, is proposed. A newcriterion is presented to predict the occurrence of the central bursting defects. Parameter bobt, which represents the risk probability ofcracking, is proposed. It is calculated using the shape of the boundary at the entrance by minimizing the total power dissipationduring the extrusion process. When bobt is equal to or greater than bcr, central bursting occurs. Furthermore, the quantitativerelationships between central bursting defects and process parameters （semi die angle, reduction in area and frictional factor） arestudied. The results show that the central bursting defects are affected primarily by the reduction in area and the friction factor. Thepresented criterion is verified by comparing with the FEM simulation data and the results of the published paper.

Impact analysis of casting parts considering shrinkage cavity defect

Shrinkage cavity may be detrimental to mechanical performances of casting parts.As a consequence,design engineers often use overly large safety factors in many designs due to insufficient understanding of quantitative effects of shrinkage cavity defects.In this paper,process of Al alloy wheel impact test was computationally analyzed for both the wheel models with and without shrinkage cavity defects.Based on shrinkage cavity data obtained from industrial CT (Computerized Tomography),the shrinkage cavity defects were modeled with SSM (Shape Simplification Method),which reconstructs shrinkage cavity defects to hollow spheroid primitives.After the impact simulation was conducted,the results show that under impact test condition,the wheel considering shrinkage cavity defects may fracture while the sound-assumed wheel may not.

Feature Extraction of Fabric Defects Based on Complex Contourlet Transform and Principal Component Analysis

To extract features of fabric defects effectively and reduce dimension of feature space,a feature extraction method of fabric defects based on complex contourlet transform （CCT） and principal component analysis （PCA） is proposed.Firstly,training samples of fabric defect images are decomposed by CCT.Secondly,PCA is applied in the obtained low-frequency component and part of highfrequency components to get a lower dimensional feature space.Finally,components of testing samples obtained by CCT are projected onto the feature space where different types of fabric defects are distinguished by the minimum Euclidean distance method.A large number of experimental results show that,compared with PCA,the method combining wavdet low-frequency component with PCA （WLPCA）,the method combining contourlet transform with PCA （CPCA）,and the method combining wavelet low-frequency and highfrequency components with PCA （WPCA）,the proposed method can extract features of common fabric defect types effectively.The recognition rate is greatly improved while the dimension is reduced.

Meta analysis of Masquelet technology and Llizarov technology in the treatment of infectious bone defects

Objective: To systematically evaluate the clinical efficacy and safety of Masquelet technology and Llizarov group technology in the treatment of infectious bone defects by meta-analysis. Methods: The computer searched China Knowledge Network (CNKI), Wanfang, VIP, Chinese Biomedical Literature Database (CBM), Pubmed, Medline, Cochrane Llibrary databases. The retrieval time was from the time of the establishment of the database to January 2020. According to the inclusion and exclusion criteria, randomized controlled trials on the treatment of infectious bone defects using Masquelet technology and Llizarov technology were collected, and the retrieved literature was independently screened, evaluated, and data extracted by two researchers, and then RevMan5.3 software was used so for meta-analysis. Results: A total of 10 RCT documents were included, with a total of 496 patients, including 242 in the Masquelet group and 254 in the Llizarov group. The results of the meta-analysis showed that: in terms of bone defect healing time, total weight bearing time, treatment cost, and complication rate, the Masquelet group was significantly different from the Llizarov group, and the Masquelet group was better than the Llizarov group (P <0.05);In terms of knee joint Lowa score and SF-36 score, Masquelet group has significant differences compared with Llizarov group, Llizarov group is better than Masquelet group (P <0.05);in excellent rate, number of operations, ankle Lowa score, infection control rate In terms of excellent rate of affected limb function, there was no significant difference between Masquelet group and Llizarov group (P> 0.05). Conclusion:Compared with Llizarov technology, Masquelet technology has obvious advantages in the treatment of infectious bone defects in terms of bone defect healing time, total weight-bearing time, treatment cost, and complication rate. In terms of scoring, it has advantages over Masquelet technology, but in terms of excellent treatment rate, number of operations, and ankle lowa score. In terms of infection control rate and excellent function of affected limbs, there was no significant difference between Masquelet technology and Llizarov technology,However, due to the low quality of the included studies and the small sample size, the exact efficacy still needs to be confirmed by higher quality RCT studies.

Photoluminescence Analysis of Injection-Enhanced Annealing of Electron Irradiation-Induced Defects in GaAs Middle Cells for Triple-Junction Solar Cells

Photolumineseenee measurements are carried out to investigate the injection-enhanced annealing behavior of electron radiation-induced defects in a GaAs middle cell for GaInP/GaAs/Ge triple-junction solar cells which are irradiated by 1.8 MeV with a fluence of i ~ 1015 cm-2. Minority-carrier injection under forward bias is observed to enhance the defect annealing in the GaAs middle cell, and the removal rate of the defect is determined with photoluminescenee radiative efficiency recovery. Furthermore, the injection-enhanced defect removal rates obey a simple Arrhenius law. Therefore, the annealing activation energy is acquired and is equal to 0.58eV. Finally, in comparison of the annealing activation energies, the E5 defect is identified as a primary non-radiative recombination center.

Expert Network for Die Casing Defect Analysis

Due to the competition and high cost associated with die casting defects, it is urgent to adopt a rapid and effective method for defect analysis. In this research, a novel expert network approach was proposed to avoid some disadvantages of rule-based expert system. The main objective of the system is to assist die casting engineer in identifying defect, determining the probable causes of defect and proposing remedies to eliminate the defect. 14 common die casting defects could be identified quickly by expert system on the basis of their characteristics. BP neural network in combination with expert system was applied to map the complex relationship between causes and defects, and further explained the cause determination process. Cause determination gives due consideration to practical process conditions. Finally, corrective measures were recommended to eliminate the defect and implemented in the sequence of difficulty.

Comprehensive Detection and Analysis of Defects in Foundation Pile of Bridge

In the process of piling ,there are many various defects in foundation pile of bridge such as mud-bearing,sediment-bearing, isolation, honeycomb, broken piles, and so on, showing physical and mechanical features of low-density and low-intensity. In fact, by using the comprehensive detection of acoustic transmission method, the reflected wave method as well as drill coring sample method, and the rational utilization of engineering geological condition in field, the characteristics, size and location of common defects of foundation pile of bridge can be accurately detected and judged and the integrity of piles and the quality of concrete can be impersonally estimated.comprehensive detecting and analyzing methods on this kind of piles are introduced briefly. The physical characters of defects and basic features of detecting curves and their corresponding relation are emphasized, and causes are analyzed in in detail in this paper.

Multivariate Image Analysis in Gaussian Multi-Scale Space for Defect Detection

Inspired by the coarse-to-fine visual perception process of human vision system,a new approach based on Gaussian multi-scale space for defect detection of industrial products was proposed.By selecting different scale parameters of the Gaussian kernel,the multi-scale representation of the original image data could be obtained and used to constitute the multi- variate image,in which each channel could represent a perceptual observation of the original image from different scales.The Multivariate Image Analysis (MIA) techniques were used to extract defect features information.The MIA combined Principal Component Analysis (PCA) to obtain the principal component scores of the multivariate test image.The Q-statistic image, derived from the residuals after the extraction of the first principal component score and noise,could be used to efficiently reveal the surface defects with an appropriate threshold value decided by training images.Experimental results show that the proposed method performs better than the gray histogram-based method.It has less sensitivity to the inhomogeneous of illumination,and has more robustness and reliability of defect detection with lower pseudo reject rate.

FEATURE ANALYSIS AND EXTRACTION OF INNER DEFECTS FOR SPOT WELD NUGGET OF ALUMINUM ALLOY

１ＩＮＴＲＯＤＵＣＴＩＯＮＳｐｏｔｗｅｌｄｉｎｇｈａｓｂｅｅｎｗｉｄｅｌｙｕｓｅｄｉｎａｌｕｍｉｎｕｍａｌｏｙｓｔｒｕｃｔｕｒｅｓｏｆｓｐａｃｅｃｒａｆｔａｎｄａｉｒｃｒａｆｔｄｕｅｔｏｉｔｓｃｈａｒａｃｔｅｒｉｓｔｉｃｓｏｆｔｅｃｈｎｏｌｏｇｙ．...

Description and Classification of Leather Defects Based on Principal Component Analysis

The accurate extraction and classification of leather defects is an important guarantee for the automation and quality evaluation of leather industry. Aiming at the problem of data classification of leather defects,a hierarchical classification for defects is proposed.Firstly,samples are collected according to the method of minimum rectangle,and defects are extracted by image processing method.According to the geometric features of representation, they are divided into dot,line and surface for rough classification. From analysing the data which extracting the defects of geometry,gray and texture,the dominating characteristics can be acquired. Each type of defect by choosing different and representative characteristics,reducing the dimension of the data,and through these characteristics of clustering to achieve convergence effectively,realize extracted accurately,and digitized the defect characteristics,eventually establish the database. The results showthat this method can achieve more than 90% accuracy and greatly improve the accuracy of classification.

Thermal Defect Analysis on Transformer Using a RLC Network and Thermography

Electrical transformers are vital components found virtually in most power-operated equipments. These transformers spontaneously radiate heat in both operation and steady-state mode. Should this thermal radiation inherent in transformers rises above allowable threshold a reduction in efficiency of operation occurs. In addition, this could cause other components in the system to malfunction. The aim of this work is to detect the remote causes of this undesirable thermal rise in transformers such as oil distribution transformers and ways to control this prevailing thermal problem. Oil transformers consist of these components: windings usually made of copper or aluminum conductor, the core normally made of silicon steel, the heat radiators, and the dielectric materials such as transformer oil, cellulose insulators and other peripherals. The Resistor-Inductor-Capacitor Thermal Network (RLCTN) model at architectural level identifies with these components to have ensemble operational mode as oil transformer. The Inductor represents the windings, the Resistor representing the core and the Capacitor represents the dielectrics. Thermography of transformer under various loading conditions was analyzed base on Infrared thermal gradient. Mathematical, experimental, and simulation results gotten through RLCTN with respect to time and thermal image analysis proved that the capacitance of the dielectric is inversely proportional to the thermal rise.

Temporal Patterns of Software Evolution Defects: A Comparative Analysis of Open Source and Closed Source Projects

This study examines temporal patterns of software systems defects using the Autoregressive Integrated Moving Average (ARIMA) approach. Defect reports from ten software application projects are analyzed;five of these projects are open source and five are closed source from two software vendors. Across all sampled projects, the ARIMA time series modeling technique provides accurate estimates of reported defects during software maintenance, with organizationally dependent parameterization. In contrast to causal models that require extraction of source-code level metrics, this approach is based on readily available defect report data and is less computation intensive. This approach can be used to improve software maintenance and evolution resource allocation decisions and to identify outlier projects—that is, to provide evidence of unexpected defect reporting patterns that may indicate troubled projects.

A Brief Analysis of the Differences and Defects of Subtitling Compared to Dubbing——Harry Potter and the Philosopher’s Stone

Compared to the dubbing, the version of subtitling has many defects, including the faults purely in language translation and the inaccuracy in the cultural images. As a media of cultural communication, the translator of the subtitling has to pay enough attention to the art of language, and has to take strategies centering on the audience, promoting the cultural communication and reducing the cultural differences.

Classification Method for Mechanical Defects in GIS Equipment Based on Mode Function Analysis and Improved Relevance Vector Machines

Mechanical defects,in gas-insulated switchgear(GIS)equipment,have weak response characteristics,leading to significant difficulties in the classification of defects.Therefore,this paper proposes a novel mechanical defect feature extraction and classification method that combines independent intrinsic mode function(IIMF)analysis and an improved multikernel mapping fast multi-classification relevance vector machine(MKF-mRVM).Enlightened by the differences in the GIS operating vibration mode,the IIMF series were first obtained based on regenerated phase-shifted sinusoid-assisted empirical mode decomposition(RPSEMD)and modal judgments.Then singular value decomposition and time-frequency conversions were performed to construct combined feature matrices.Finally,multikernel mapping and domain sampling were introduced to improve the calculation speed and recognition accuracy of the mRVM,which was more suitable for on-line monitoring.Results show that the proposed RPSEMD-MKF-mRVM model achieves a faster training speed(14.23 s)and higher accuracy(98.21%)than other algorithms,and it can adapt to variable loads.

Jumbo Bionic Trabecular Metal Acetabular Cups Improve Cup Stability During Acetabular Bone Defect Reconstruction:A Finite Element Analysis Study

The biomechanical effects of acetabular revision with jumbo cups are unclear.This study aimed to compare the biomechanical effects of bionic trabecular metal vs.titanium jumbo cups for the revision of acetabular bone defects.We designed and reconstructed American Academy of Orthopaedic Surgeons(AAOS)type I–III acetabular bone defect models using computed tomography scans of a man without acetabular bone defects.The implantation of titanium and trabecular metal jumbo cups was simulated.Stress distribution and relative micromotion between the cup and host bone were assessed using finite element analysis.Contact stress on the screws fixing the cups was also analyzed.The contact stress analysis showed that the peak contact stress between the titanium jumbo cup and the host bone was 21.7,20.1,and 23.8 MPa in the AAOS I–III models,respectively;the corresponding values for bionic tantalum jumbo cups decreased to 4.7,6.7,and 11.1 MPa.Analysis of the relative micromotion showed that the peak relative micromotion between the host bone and the titanium metal cup was 10.2,9.1,and 11.5μm in the AAOS I–III models,respectively;the corresponding values for bionic trabecular metal cups were 17.2,18.2,and 31.3μm.The peak contact stress on the screws was similar for the 2 cup types,and was concentrated on the screw rods.Hence,acetabular reconstruction with jumbo cups is biomechanically feasible.We recommend trabecular metal cups due to their superior stress distribution and higher relative micromotion,which is within the threshold for adequate bone ingrowth.