Rapid and Efficient Bug Assignment Using ELM for IOT Software

Abstract

The reliable implementation of software in an Internet system directly influences information transmission especially for the Internet of Things (IoT) system. Once defects in the system are found, the communication between things and things and the interaction between people and things in the IoT will be greatly affected. Therefore, rapid and effective defect assignment to the right developer is the key to ensuring software quality and bringing down time consumption in the IoT software life cycle. However, as the size of the software becomes increasing larger, the requirement of users grows, and a large number of software bugs will be found every day. It is difficult for managers to assign the software defects to the appropriate developers. In this paper, a novel hybrid method based on a diversified feature selection and an ensemble extreme learning machine (ELM) is proposed. First, the useful information is extracted from defect reports; then, the data are preprocessed to establish a vector space model; and the diversified feature selection is preprocessed in order to select a smallest set of representative non-redundant features with maximal statistical information. Finally, an ensemble GA-based ELM training classifier is used. Experimental results show that, compared to SVM, C4.5, NaiveBayes, and KNN classifiers, the proposed ELM-based bug triage approach with representative feature selection techniques in this paper significantly improves the efficiency and the effectiveness of bug triages.