Feature-FL: Feature-Based Fault Localization

Lei, Yan; Xie, Huan; Zhang, Tao; Yan, Meng; Zhou, Xu; Sun, Chengnian

doi:10.1109/tr.2022.3140453

Cited by 13 publications

(3 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hu et al [9] introduced a slow feature analysis approach to determine the direction of fault degradation and screen the fault degradation features based on it. A feature-based fault location technique was put forth by Lei et al [10] and employed feature selection and correlation analysis to identify suspicious program statements. By calculating the correlation between degradation features and life, Guo et al [11] selected six sensitive indicators as the input of the RNN network, and then used the created RNN-HI model to integrate the input indicators into a health indicator that reflects the deterioration of bearing performance.…”

Section: Introductionmentioning

confidence: 99%

Remaining useful life prediction method of rolling bearings based on improved 3σ and DBO-HKELM

Gao,

Li,

Zhang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

An improved 3σ method and dung beetle algorithm optimization hybrid kernel extreme learning machinebased (DBO-HKELM) approach for predicting the remaining useful life (RUL) of rolling bearings was suggested in order to increase prediction accuracy. Firstly, multi-dimensional degradation feature data is extracted from bearing vibration data. Considering the inﬂuence of noise signal on the prediction accuracy, an improved kernel principal component analysis (KPCA) method is proposed to reduce the noise of degraded features. Then, an improved 3σ method is proposed to determine the starting point of bearing degradation by combining bearing vibration signal data. Lastly, a DBO-HKELM life prediction model was put forth. The parameters of hybrid kernel extreme learning machine were optimized by dung beetle algorithm, and appropriate kernel parameters and regularization coeﬃcient were selected. The feature set of degradation indicators is input into the trained model to output the bearing remaining useful life prediction results starting from the determined degradation starting point. Multiple data sets were used to verify that the new remaining useful life prediction method signiﬁcantly improves the prediction accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Remaining useful life prediction method of rolling bearings based on improved 3σ and DBO-HKELM

Gao,

Li,

Zhang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“… The software defect location model is based on the traditional features related to program analysis information, such as information about test cases passing or failing. Spectrum‐based software defect location technology 6 is a typical example of software defect location using traditional features. The main idea of this method is to extract static features from source programs or program execution information.…”

Section: Introductionmentioning

confidence: 99%

“…3 The existing software defect location technologies can be divided into four categories. 4 The first category uses traditional feature methods related to program analysis information, 5,6 such as the information of test cases passing or failing. This method extracts static features from source code or execution information, which is a time-consuming process; the second type is the software defect location method based on information retrieval, [7][8][9] which measures the text similarity between the defect report and the class or method name in the source code file for a given defect report, to search and arrange the source files suspected of defects; the third category is software defect location method based on machine learning, 10 the method focus on feature engineering; it uses machine learning model to match the topic of error report with the topics of the source file or selects an appropriate classifier to classify the source file into multiple classes by using previously repaired files to locate defective source files; the fourth category is software defect location method based on deep learning 11,12 ; the method uses a deep neural network to extract semantic information of source files and defect reports and makes full use of text information, which is helpful to improve the effect of software defect location.…”

mentioning

confidence: 99%

Multi‐graph learning‐based software defect location

Yin

Shi

Zhao

et al. 2023

J Software Evolu Process

View full text Add to dashboard Cite

Software quality is key to the success of software systems. Modern software systems are growing in their worth based on industry needs and becoming more complex, which inevitably increases the possibility of more defects in software systems. Software repairing is time‐consuming, especially locating the source files related to specific software defect reports. To locate defective source files more quickly and accurately, automated software defect location technology is generated and has a huge application value. The existing deep learning‐based software defect location method focuses on extracting the semantic correlation between the source file and the corresponding defect reports. However, the extensive code structure information contained in the source files is ignored. To this end, we propose a software defect location method, namely, multi‐graph learning‐based software defect location (MGSDL). By extracting the program dependency graphs for functions, each source file is converted into a graph bag containing multiple graphs (i.e., multi‐graph). Further, a multi‐graph learning method is proposed, which learns code structure information from multi‐graph to establish the semantic association between source files and software defect reports. Experiments' results on four publicly available datasets, AspectJ, Tomcat, Eclipse UI, and SWT, show that MGSDL improves on average 3.88%, 5.66%, 13.23%, 9.47%, and 3.26% over the competitive methods in five evaluation metrics, rank@10, rank@5, MRR, MAP, and AUC, respectively.

show abstract