Eating Data Is Good for Your Immune System: An Artificial Metabolism for Data Clustering Using Systemic Computation

Abstract

Abstract. Previous work suggests that innate immunity and representations of tissue can be useful when combined with artificial immune systems. Here we provide a new implementation of tissue for AIS using systemic computation, a new model of computation and corresponding computer architecture based on a systemics world-view and supplemented by the incorporation of natural characteristics. We show using systemic computation how to create an artificial organism, a program with metabolism that eats data, expels waste, clusters cells based on the nature of its food and emits danger signals suitable for an artificial immune system. The implementation is tested by application to a standard machine learning set and shows excellent abilities to recognise anomalies in its diet.

Systemic Computation Using Graphics Processors

“…Systemic computation is a new bio-inspired model of computation that has shown considerable success for biological modeling and bio-inspired computation [6][7][8][9][10][11][12][13][14]. However until now it has only been available as a serial simulation running on conventional processors.…”

“…The simulation was implemented in ANSI C on a PowerBook Macintosh G4, enabling systemic computation programs to be simulated using conventional computer processors. Later work by Le Martelot created a second implementation on PCs with a higher-level language and visualization tools [2,[6][7][8][9][10][11][12]14]. Other work provided a discussion on the use of sensor networks to implement a systemic computer [13].…”

“…To date, two simulations of this architecture have been developed, with corresponding machine and programming languages, compilers and graphical visualiser [1,6]. Extensive work has shown how this form of computer enables useful biological modeling and bio-inspired algorithms to be implemented with ease [7][8][9][10][11] and how it enables properties such as fault-tolerance and self-repairing code [12]. Research is ongoing in the improvement of the PC-based simulator, refining the systemic computation language and visualiser [10,14].…”

Adapting to dynamically changing noise during learning of heart sounds

“…Le Martelot provided a simple implementation of "artificial tissue" for AIS using systemic computation [2,3], which serves as the foundation of our work. He created an artificial organism, a program with metabolism that "eats" data, expels waste, clusters cells based on the nature of its food and emits danger signals suitable for an artificial immune system.…”

“…We based on our model on [3] to implement the full function of AIS with antigens being "eaten" continuously into the organism and inspired the secretion of antibodies which serves as the classifier to recognize later-come antigens. More specifically, data from the same category is regarded as sharing a same/similar feature which in the scenario of AIS would correspond to antigen.…”