How Do We Evaluate Artificial Immune Systems?

What is an artificial immune system (AIS)? One answer is that an AIS is a model of the immune system that can be used by immunologists for explanation, experimentation and prediction activities that would be difficult or impossible in ‘wet-lab’ experiments. This is also known as ‘computational immunology.’ Another answer is that an AIS is an abstraction of one or more immunological processes. Since these processes protect us on a daily basis, from the ever-changing onslaught of biological and biochemical entities that seek to prosper at our expense, it is reasoned that they may be computationally useful. It is this form of AIS—methods based on immune abstractions—that will be studied here.

Although AIS is a relatively young field, advancing on many fronts, some central themes have become apparent—the question is, are these AIS delivering anything useful, or are they just another addition to the increasingly long line of approaches that are biologically inspired? These approaches include established paradigms such as genetic and evolutionary computation (GEC), artificial neural networks (ANN) and various forms of artificial life; as well as less established topics such as ant colony dynamics (Dorigo, 1992; Dorigo, 1999) and cell membrane computing (Paun, 2002). The intention here is to provide an assessment of prior developments in AIS, its current strengths, weaknesses and its overall usefulness.

Perhaps the biggest difficulty faced by AIS is that it has few application types for which it is undisputedly the most effective method. Despite the many points in its favor, this single point is enough to allow it to be ignored by many. Although two important areas have been identified in which AIS is unique in its ability to provide solutions, further impressive demonstrations of effectiveness will be required if AIS is to be pushed to the fore.