Transfer Convolutional Neural Network for Cross-Project Defect Prediction

Qiu, Shaojian; Xu, Hao; Deng, Jiehan; Jiang, Siyu; Lu, Lu

doi:10.3390/app9132660

Cited by 29 publications

(16 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the parallel distributed processing method, it is possible to perform a large number of calculations quickly. It can meet the real-time requirements of the defect inversion system [16][17][18]. By using this defect inversion system, various information such as the shape, location and size of the defect can be accurately detected.…”

Section: Ultrasonic Inspection Systemmentioning

confidence: 99%

Research on Ultrasonic Quantitative Evaluation Technology of Complex Defects Based on Neural Network

Li¹,

Liu

Lin³

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

As one of the five non-destructive testing methods, ultrasonic testing is widely used because of its accurate positioning, high sensitivity and simple operation, but the method is still difficult to locate and quantify complex shape defects. The large amount of data required for ultrasonic imaging leads to low detection efficiency. Based on this, the article establishes an inversion system for evaluating complex shape defects, which includes ultrasonic A-scan technology, BP neural network, image processing technology and signal processing technology. The system is verified by simulation and experiment. The results of the defect inversion are as follows: the similarity coefficients are all greater than 0.89, the maximum value can reach 0.95; the area error is less than 11%, the minimum value can reach 1.2%; the centroid x error is less than 12%, the minimum value can reach 1.58%; the centroid y error is less than 11%, the minimum value can reach 2.15%. The result of defect inversion further verifies the accuracy and reliability of the complex defect inversion system.

show abstract

Section: Ultrasonic Inspection Systemmentioning

confidence: 99%

Research on Ultrasonic Quantitative Evaluation Technology of Complex Defects Based on Neural Network

Li¹,

Liu

Lin³

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…Recently, because deep learning (DL) has been successfully used to solve problems in other fields such as image processing [24] and speech recognition [25], researchers have examined the utility of DL algorithms for defect prediction [26,27] and suggested that this approach promises to advance SDP. The most popular DL algorithm used in SDP is the convolutional neural network (CNN) [5,[28][29][30][31][32][33][34][35].…”

Section: Introductionmentioning

confidence: 99%

Software Defect Prediction Harnessing on Multi 1-Dimensional Convolutional Neural Network Structure

Pin¹,

Chang²,

Nam³

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Developing successful software with no defects is one of the main goals of software projects. In order to provide a software project with the anticipated software quality, the prediction of software defects plays a vital role. Machine learning, and particularly deep learning, have been advocated for predicting software defects, however both suffer from inadequate accuracy, overfitting, and complicated structure. In this paper, we aim to address such issues in predicting software defects. We propose a novel structure of 1-Dimensional Convolutional Neural Network (1D-CNN), a deep learning architecture to extract useful knowledge, identifying and modelling the knowledge in the data sequence, reduce overfitting, and finally, predict whether the units of code are defects prone. We design large-scale empirical studies to reveal the proposed model's effectiveness by comparing four established traditional machine learning baseline models and four state-of-the-art baselines in software defect prediction based on the NASA datasets. The experimental results demonstrate that in terms of f-measure, an optimal and modest 1D-CNN with a dropout layer outperforms baseline and state-of-the-art models by 66.79% and 23.88%, respectively, in ways that minimize overfitting and improving prediction performance for software defects. According to the results, 1D-CNN seems to be successful in predicting software defects and may be applied and adopted for a practical problem in software engineering. This, in turn, could lead to saving software development resources and producing more reliable software.

show abstract

“…Nevertheless, the manually extracted features ignore the rich semantic features of the program. Hence, in recent years, many studies [8], [20], [33], [41] have proposed to extract the abstract features hidden in semantics through deep learning (DL). Furthermore, they demonstrated that the DL-based methods could improve prediction performance.…”

Section: Introductionmentioning

confidence: 99%

An Adversarial Discriminative Convolutional Neural Network for Cross-Project Defect Prediction

Lei

Lin

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Cross-project defect prediction (CPDP) is a promising approach to help to allocate testing efforts efficiently and guarantee software reliability in the early software lifecycle. A CPDP method usually trains a software defect classifier based on labeled data sets. Then the trained classifier can predict new projects without labeled data. Most previous CPDP techniques focused on manually designing handcrafted features. However, these handcrafted features ignore the programs' semantic information. Moreover, some other existing defect prediction approaches learned semantic features from source code to build classifiers directly. However, they did not consider the distribution divergence between source and target projects. To address these limitations, we put forward a new method called Adversarial Discriminative Convolutional Neural Network (ADCNN). It can extract the transferable semantic features from source code for CPDP tasks. Specifically, we first parse source files into token vectors and then map them to integer vectors via word embedding. Second, we combine adversarial learning with discriminative feature learning to train the ADCNN model. The key of the ADCNN model is to learn the discriminative mapping of the target project to the source feature space by deceiving a domain discriminator. A domain discriminator tries to distinguish the target project files from the source project files. Finally, we use the extracted transferable semantic features to build a classifier for CPDP tasks. We evaluate our method on ten benchmark projects in terms of Fmeasure, AUC, and PofB20 (an effort-aware evaluation metric). The experimental results demonstrate that our ADCNN method performs better compared with other related CPDP methods. INDEX TERMS Cross-project defect prediction, transfer learning, adversarial learning, deep learning, convolutional neural network.

show abstract

Transfer Convolutional Neural Network for Cross-Project Defect Prediction

Cited by 29 publications

References 29 publications

Research on Ultrasonic Quantitative Evaluation Technology of Complex Defects Based on Neural Network

Research on Ultrasonic Quantitative Evaluation Technology of Complex Defects Based on Neural Network

Software Defect Prediction Harnessing on Multi 1-Dimensional Convolutional Neural Network Structure

An Adversarial Discriminative Convolutional Neural Network for Cross-Project Defect Prediction

Contact Info

Product

Resources

About