A Framework based on Deep Neural Network for Ranking-oriented Software Defect Prediction

Jiapeng Dai1; Xiaoxing Yang1; Bingding Huang1; Xiaofen Lu2

10.1109/QRS60937.2023.00016

2023

2693-9185

979-8-3503-1959-0

2023 IEEE 23rd International Conference on Software Quality, Reliability, and Security (QRS)

60-71

22-26 Oct. 2023

Chiang Mai, Thailand

Software systems are getting larger and more complex than ever before. In order to improve software reliability, software defect prediction is applied to assist developers in bug discovery. The ranking-oriented software defect prediction aims to rank software modules according to the predicted defect counts. However, existing ranking-oriented defect prediction models are constructed based on traditional hand-crafted features, which might overlook the rich syntactic information buried inside the source codes. In this paper, we propose a universal deep learning-based framework called United Deep Network for ranking-oriented software defect prediction. This framework utilizes deep neural networks to automatically generate features from source code with the syntactic and structural information preserved, and it can combine extracted features with traditional hand-crafted features in order to take advantage of both kinds of features to construct prediction models. Experimental results over 29 sets of data show the good performance of the proposed framework for building ranking-oriented defect prediction models.

ranking-oriented software defect prediction deep neural network convolutional neural network recurrent neural network

其他

EI

20240315398983

Convolutional neural networks ; Defects ; Forecasting ; Recurrent neural networks ; Software reliability ; Syntactics

Ergonomics and Human Factors Engineering:461.4 ; Materials Science:951

IEEE

1.College of Big Data and Internet, Shenzhen Technology University, Shenzhen, China
2.Department of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China

Jiapeng Dai,Xiaoxing Yang,Bingding Huang,et al. A Framework based on Deep Neural Network for Ranking-oriented Software Defect Prediction[C],2023:60-71.