Jun Ai

Dr. Jun Ai

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 December 2020 in IEEE Transactions on Reliability
Verified
Journal Article
Closed access
JXJiaxi Xu
Jiaxi Xu
FWFei Wang
Fei Wang
JAJun Ai
Jun Ai
To optimize the process of software testing and to improve software quality and reliability, many attempts have been made to develop more effective methods for predicting software defects. Previous work on defect prediction has used machine learning and artificial software metrics. Unfortunately, artificial metrics are unable to represent the features of syntactic, semantic, and context information of defective modules. In this article, therefore, we propose a practical approach for identifying software defect patterns via the combination of semantics and context information using abstract syntax tree representation learning. Graph neural networks are also leveraged to capture the latent defect information of defective subtrees, which are pruned based on a fix-inducing change. To validate the proposed approach for predicting defects, we define mining rules based on the GitHub workflow and collect 6052 defects from 307 projects. The experiments indicate that the proposed approach performs better than the state-of-the-art approach and five traditional machine learning baselines. An ablation study shows that the information about code concepts leads to a significant increase in accuracy.

19 April 2022 in IEEE Transactions on Reliability
Verified
Journal Article
Closed access
JXJiaxi Xu
Jiaxi Xu
JAJun Ai
Jun Ai
JLJingyu Liu
Jingyu Liu
TSTao Shi
Tao Shi
Recognizing and repairing defects to enhance quality in software life circle has become a critical research topic. Unfortunately, it is difficult to guarantee the validity of the defect prediction method based on manually designed features proposed in previous studies. Numerous scholars have endeavored to use a single model to obtain prediction results for different types of fault, but this is difficult to perform. This article improves the defect representation and prediction model in software defect prediction, proposing Augmented-Code Property Graph (CPG) based defect prediction method (ACGDP). Augmented-CPG is a novel encoding graph format introduced in this article. Based on Augmented-CPG, we suggested defect region candidate extraction approach linked to the defect category. Graph neural networks are used for obtaining defect characteristics. Experiments on three distinct types of defects indicate that ACGDP can predict certain classed of defects effectively.

18 February 2022 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
XDXiaoting Du
Xiaoting Du
YSYulei Sui
Yulei Sui
ZLZhihao Liu
Zhihao Liu
JAJun Ai
Jun Ai
Deep learning frameworks play a key rule to bridge the gap between deep learning theory and practice. With the growing of safety- and security-critical applications built upon deep learning frameworks, their reliability is becoming increasingly important. To ensure the reliability of these frameworks, several efforts have been taken to study the causes and symptoms of bugs in deep learning frameworks, however, relatively little progress has been made in investigating the fault triggering conditions of those bugs. This paper presents the first comprehensive empirical study on fault triggering conditions in three widely-used deep learning frameworks (i.e., TensorFlow, MXNET, and PaddlePaddle). We have collected 3,555 bug reports from GitHub repositories of these frameworks. A bug classification is performed based on fault triggering conditions, followed by the analysis of frequency distribution of different bug types and the evolution features. The correlations between bug types and fixing time are investigated. Moreover, we have also studied the root causes of Bohrbugs and Mandelbugs and investigated the important consequences of each bug type. Finally, the analysis of regression bugs in deep learning frameworks is conducted. We have revealed 12 important findings based on our empirical results and have provided 10 implications for developers and users.

9 September 2020 in IEEE Access
Verified
Journal Article
Open access
LWLixiang Wang
Lixiang Wang
WDWei Dai
Wei Dai
JAJun Ai
Jun Ai
WDWeiwei Duan
Weiwei Duan
YZYu Zhao
Yu Zhao
Due to failure, partial failure, or maintenance, the capacity of each machine is multi-state. Therefore, the limited relationship between the capacity of each machine and the input raw materials has to be considered. Additionally, in order to utilize the machine more effectively, the capacity of the buffers cannot be ignored, too. In this paper, a dynamic adaptive fuzzy reasoning Petri net is proposed to evaluate reliability of a manufacturing system with multiple production lines. Firstly, the model of manufacturing system is conducted, and from the perspective of demand, the minimum capacity vector and loading vector of each machine are determined. Secondly, knowledge representation and rules are formulated to establish weighted fuzzy petri nets. And the weighted fuzzy Petri net is adaptive based on the real-time level of buffers, the minimum capacity vector and loading vector. Moreover, the efficiency of product production can be improved while ensuring system reliability by adjusting the buffer level. Finally, a numerical experiment is used to demonstrate the application of our method.

29 October 2023 in Neural Networks
Verified
Journal Article
Closed access
SKShiyi Kong
Shiyi Kong
JAJun Ai
Jun Ai
MLMinyan Lu
Minyan Lu
YGYiang Gong
Yiang Gong

19 September 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SHShi Haoxiang
Shi Haoxiang
JAJun Ai
Jun Ai
JLJingyu Liu
Jingyu Liu
JXJiaxi Xu
Jiaxi Xu
Software defect prediction is a popular method for optimizing software testing and improving software quality and reliability. However, software defect datasets usually have quality problems, such as class imbalance and data noise. Oversampling by generating the minority class samples is one of the most well-known methods to improving the quality of datasets; however, it often introduces overfitting noise to datasets. To better improve the quality of these datasets, this paper proposes a method called US-PONR, which uses undersampling to remove duplicate samples from version iterations and then uses oversampling through propensity score matching to reduce class imbalance and noise samples in datasets. The effectiveness of this method was validated in a software prediction experiment that involved 24 versions of software data in 11 projects from PROMISE in noisy environments that varied from 0% to 30% noise level. The experiments showed a significant improvement in the quality of datasets pre-processed by US-PONR in noisy imbalanced datasets, especially the noisiest ones, compared with 12 other advanced dataset processing methods. The experiments also demonstrated that the US-PONR method can effectively identify the label noise samples and remove them.