:Cross-project defect prediction(CPDP)aims to predict the defects on target project by using a prediction model built on source projects.The main problem in CPDP is the huge distribution gap between the source project...:Cross-project defect prediction(CPDP)aims to predict the defects on target project by using a prediction model built on source projects.The main problem in CPDP is the huge distribution gap between the source project and the target project,which prevents the prediction model from performing well.Most existing methods overlook the class discrimination of the learned features.Seeking an effective transferable model from the source project to the target project for CPDP is challenging.In this paper,we propose an unsupervised domain adaptation based on the discriminative subspace learning(DSL)approach for CPDP.DSL treats the data from two projects as being from two domains and maps the data into a common feature space.It employs crossdomain alignment with discriminative information from different projects to reduce the distribution difference of the data between different projects and incorporates the class discriminative information.Specifically,DSL first utilizes subspace learning based domain adaptation to reduce the distribution gap of data between different projects.Then,it makes full use of the class label information of the source project and transfers the discrimination ability of the source project to the target project in the common space.Comprehensive experiments on five projects verify that DSL can build an effective prediction model and improve the performance over the related competing methods by at least 7.10%and 11.08%in terms of G-measure and AUC.展开更多
This paper presents a predictive defect detection method for prototype additive manufacturing(AM)based on multilayer susceptibility discrimination(MSD).Most current methods are significantly limited by merely captured...This paper presents a predictive defect detection method for prototype additive manufacturing(AM)based on multilayer susceptibility discrimination(MSD).Most current methods are significantly limited by merely captured images,disregarding the differences between layer-by-layer manufacturing approaches,without combining transcendental knowledge.The visible parts,originating from the prototype of conceptual design,are determined based on spherical flipping and convex hull theory,on the basis of which theoretical template image(TTI)is rendered according to photorealistic technology.In addition,to jointly consider the differences in AM processes,the finite element method(FEM)of transient thermal-structure coupled analysis was conducted to probe susceptible regions where defects appeared with a higher possibility.Driven by prior knowledge acquired from the FEM analysis,the MSD with an adaptive threshold,which discriminated the sensitivity and susceptibility of each layer,was implemented to determine defects.The anomalous regions were detected and refined by superimposing multiple-layer anomalous regions and comparing the structural features extracted using the Chan-Vese(CV)model.A physical experiment was performed via digital light processing(DLP)with photosensitive resin of a non-faceted scaled V-shaped engine block prototype with cylindrical holes using a non-contact profilometer.This MSD method is practical for detecting defects and is valuable for a deeper exploration of barely visible impact damage(BVID),thereby reducing the defect of prototypical mechanical parts in engineering machinery or process equipment via intellectualized machinevision.展开更多
We proposed a detection method for wood defects based on linear discriminant analysis (LDA) and the use of compressed sensor images. Wood surface images were captured, using a camera Oscar F810C IRF camera, and then t...We proposed a detection method for wood defects based on linear discriminant analysis (LDA) and the use of compressed sensor images. Wood surface images were captured, using a camera Oscar F810C IRF camera, and then the image segmentation was performed, and the defect features were extracted from wood board images. To reduce the processing time, LDA algorithm was used to integrate these features and reduce their dimensions. Features after fusion were used to construct a data dictionary and a compressed sensor was designed to recognize the wood defects types. Of the three major defect types, 50 images live knots, dead knots, and cracks were used to test the effects of this method. The average time for feature fusion and classification was 0.446 ms with the classification accuracy of 94%.展开更多
基金This paper was supported by the National Natural Science Foundation of China(61772286,61802208,and 61876089)China Postdoctoral Science Foundation Grant 2019M651923Natural Science Foundation of Jiangsu Province of China(BK0191381).
文摘:Cross-project defect prediction(CPDP)aims to predict the defects on target project by using a prediction model built on source projects.The main problem in CPDP is the huge distribution gap between the source project and the target project,which prevents the prediction model from performing well.Most existing methods overlook the class discrimination of the learned features.Seeking an effective transferable model from the source project to the target project for CPDP is challenging.In this paper,we propose an unsupervised domain adaptation based on the discriminative subspace learning(DSL)approach for CPDP.DSL treats the data from two projects as being from two domains and maps the data into a common feature space.It employs crossdomain alignment with discriminative information from different projects to reduce the distribution difference of the data between different projects and incorporates the class discriminative information.Specifically,DSL first utilizes subspace learning based domain adaptation to reduce the distribution gap of data between different projects.Then,it makes full use of the class label information of the source project and transfers the discrimination ability of the source project to the target project in the common space.Comprehensive experiments on five projects verify that DSL can build an effective prediction model and improve the performance over the related competing methods by at least 7.10%and 11.08%in terms of G-measure and AUC.
基金funded by the National Key Research and Development Project of China(Grant No.2022YFB3303303)Zhejiang Scientific Research and Development Project(Grant No.LZY22E060002)+2 种基金Key Program of the National Natural Science Foundation of China(Grant Nos.51935009,U22A6001)The Ng Teng Fong Charitable Foundation in the form of a ZJU-SUTD IDEA Grant(Grant No.188170-11102)Zhejiang University President Special Fund financed by Zhejiang province(Grant No.2021XZZX008).
文摘This paper presents a predictive defect detection method for prototype additive manufacturing(AM)based on multilayer susceptibility discrimination(MSD).Most current methods are significantly limited by merely captured images,disregarding the differences between layer-by-layer manufacturing approaches,without combining transcendental knowledge.The visible parts,originating from the prototype of conceptual design,are determined based on spherical flipping and convex hull theory,on the basis of which theoretical template image(TTI)is rendered according to photorealistic technology.In addition,to jointly consider the differences in AM processes,the finite element method(FEM)of transient thermal-structure coupled analysis was conducted to probe susceptible regions where defects appeared with a higher possibility.Driven by prior knowledge acquired from the FEM analysis,the MSD with an adaptive threshold,which discriminated the sensitivity and susceptibility of each layer,was implemented to determine defects.The anomalous regions were detected and refined by superimposing multiple-layer anomalous regions and comparing the structural features extracted using the Chan-Vese(CV)model.A physical experiment was performed via digital light processing(DLP)with photosensitive resin of a non-faceted scaled V-shaped engine block prototype with cylindrical holes using a non-contact profilometer.This MSD method is practical for detecting defects and is valuable for a deeper exploration of barely visible impact damage(BVID),thereby reducing the defect of prototypical mechanical parts in engineering machinery or process equipment via intellectualized machinevision.
基金supported by the State Forestry Administration‘‘948’’projects(2015-4-52)Fundamental Research Funds for the Central Universities(2572016BB05)+1 种基金Natural Science Foundation of Heilongjiang Province(C2015054)Heilongjiang Postdoctoral Research Fund(LBH-Q14014)
文摘We proposed a detection method for wood defects based on linear discriminant analysis (LDA) and the use of compressed sensor images. Wood surface images were captured, using a camera Oscar F810C IRF camera, and then the image segmentation was performed, and the defect features were extracted from wood board images. To reduce the processing time, LDA algorithm was used to integrate these features and reduce their dimensions. Features after fusion were used to construct a data dictionary and a compressed sensor was designed to recognize the wood defects types. Of the three major defect types, 50 images live knots, dead knots, and cracks were used to test the effects of this method. The average time for feature fusion and classification was 0.446 ms with the classification accuracy of 94%.
