Predicting Bugs in Software Code Changes Using Isolation Forest

He, Yueyang; Zhu, Xiaoyan; Wang, Guangtao; Sun, Heli; Wang, Yong

doi:10.1109/qrs.2017.40

Cited by 10 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with other anomaly detection algorithms, this algorithm has linear time complexity, and the accuracy is good when there are few or missing abnormal data in the training set. Isolated forest algorithm has many practical applications, such as monitoring production abnormalities [9] [10], abnormal target detection [11], and data error detection [12] [13]. In actual work, we have collected physical and chemical cigarette testing data with many characteristic dimensions.…”

Section: Introductionmentioning

confidence: 99%

Improved Isolation Forest Algorithm for Anomaly Test Data Detection

Yu-peng¹,

Dong²,

Zhou³

et al. 2021

JCC

View full text Add to dashboard Cite

The cigarette detection data contains a large amount of true sample data and a small amount of false sample data. The false sample data is regarded as abnormal data, and anomaly detection is performed to realize the identification of real and fake cigarettes. Binary particle swarm optimization algorithm is used to improve the isolation forest construction process, and isolation trees with high precision and large differences are selected, which improves the accuracy and efficiency of the algorithm. The distance between the obtained anomaly score and the clustering center of the k-means algorithm is used as the threshold for anomaly judgment. The experimental results show that the accuracy of the BPSO-iForest algorithm is improved compared with the standard iForest algorithm. The experimental results of multiple brand samples also show that the method in this paper can accurately use the detection data for authenticity identification.

show abstract

Section: Introductionmentioning

confidence: 99%

Improved Isolation Forest Algorithm for Anomaly Test Data Detection

Yu-peng¹,

Dong²,

Zhou³

et al. 2021

JCC

View full text Add to dashboard Cite

show abstract

“…The selection of components for unit testing can be modeled as a multiobjective optimization problem within the Search-Based Software Testing (SBST) area, which has attracted much attention in recent years (He et al, 2017). Within this research line is the pre-test effort, in which the test code is selected in order to guide the test construction to attain the maximum coverage based on several metrics.…”

Section: Introductionmentioning

confidence: 99%