An empirical study based on semi-supervised hybrid self-organizing map for software fault prediction

作者：

Highlights：

• We proposed a software fault detection model using semi-supervised hybrid self-organizing map (HySOM).

• The HySOM minimize the role of experts for identifying fault prone modules.

• The advantage of HySOM is the ability to predict the label of the modules in a semi-supervised manner.

• The experimental results show improvement in false negative rate and overall error rate in 80% and 60% with NASA data sets.

摘要

•We proposed a software fault detection model using semi-supervised hybrid self-organizing map (HySOM).•The HySOM minimize the role of experts for identifying fault prone modules.•The advantage of HySOM is the ability to predict the label of the modules in a semi-supervised manner.•The experimental results show improvement in false negative rate and overall error rate in 80% and 60% with NASA data sets.

论文关键词：Artificial neural network,Clustering,Self-organizing maps,Semi-supervised,Software fault prediction,Threshold

论文评审过程：Received 20 September 2014, Revised 29 October 2014, Accepted 31 October 2014, Available online 8 November 2014.

论文官网地址：https://doi.org/10.1016/j.knosys.2014.10.017