Application of Artificial Immune Systems Paradigm for Developing Software Fault Prediction Models

1. Introduction

Today’s software systems are becoming more and more complex and their lines of codes will reach to billions from millions of lines of code in near future. Therefore, innovative Validation & Verification (V&V) techniques are required more than ever to manage the complexity of current and future systems. Software Engineering Institute (SEI) published a report in 2006 and proposed a research agenda for U.S. Department of Defense about ultra-large-scale systems which will likely to have billions of lines of code. These kind of systems and large scale systems pose extraordinary challenges in Validation and Verification area and this chapter’s subject, software fault prediction, is a proven quality assurance activity in achieving highly reliable systems.

Artificial Immune Systems (AIS) embody the principles and advantages of vertebrate immune systems. They are used for intrusion detection, classification, optimization, clustering and search problems. Recently, there is an increasing interest in the use of AIS paradigm to solve complex problems. In this chapter, a popular AIS based classification algorithm, AIRS, is explored on a software fault prediction dataset. The scope of this chapter is shown in Figure 1 and the yellow point which has “software fault prediction” label shows that this model is the intersection of AIS paradigm and a software engineering problem.

Figure 1.

The scope of this chapter

Immune system has two mechanisms that interact with each other. The first one is the innate immune system and there is no need being interacted with the relevant pathogen in the past for this type of mechanism. The second one is the adaptive immune system that enhances its ability in order to detect more pathogens after the interaction. Lymphocytes are classified as B-cells and T-cells. Each lymphocyte can bind to a particular invader which is known as antigens. The similarity degree between B-cell and antigen is called affinity. If the antigen is detected by B-cell, B-cell is cloned with a process called “clonal expansion”. These clones are mutated using “somatic hypermutation process” according to the affinity level. Some of these clones are differentiated into B memory cells in order to respond rapidly for the next attack from same invader and therefore immune system is said to have memory feature. Best matching clones with antigens survive and this process is known as “clonal selection”.

The rest of this chapter is organized as follows: Section 2 describes the role of Artificial Immune System in software engineering domain along with its background and contemporary works. Section 3 elaborates the basic AIRS algorithm for software fault prediction followed by sequential diagrammatic representation of the algorithm in 3.1. Case study example is presented to validate the algorithm in section 4 and section 4.1. Section 5 gives conclusion.