'Cooperative Automated worm Response and Detection ImmuNe ALgorithm (CARDINAL) inspired by T-cell Immunity and Tolerance'

The role of T-cells within the immune system is to confirm and assess anomalous situations and then either respond to or tolerate the source of the effect. To illustrate how these mechanisms can be harnessed to solve real-world problems, we present the blueprint of a T-cell inspired algorithm for computer security worm detection. We show how the three central T-cell processes, namely T-cell maturation, differentiation and proliferation, naturally map into this domain and further illustrate how such an algorithm fits into a complete immune inspired computer security system and framework.

'Artificial Immune Systems: A new Decision Making Paradigm for Operational Research'

Over the last few years, more and more heuristic decision making techniques have been inspired by nature, e.g. evolutionary algorithms, ant colony optimisation and simulated annealing. More recently, a novel computational intelligence technique inspired by immunology has emerged, called Artificial Immune Systems (AIS). This immune system inspired technique has already been useful in solving some computational problems. In this keynote, we will very briefly describe the immune system metaphors that are relevant to AIS. We will then give some illustrative real-world problems suitable for AIS use and show a step-by-step algorithm walkthrough. A comparison of AIS to other well-known algorithms and areas for future work will round this keynote off. It should be noted that as AIS is still a young and evolving field, there is not yet a fixed algorithm template and hence actual implementations might differ somewhat from the examples given here

'Artificial Immune Systems Tutorial'

The biological immune system is a robust, complex, adaptive system that defends the body from foreign pathogens. It is able to categorize all cells (or molecules) within the body as self-cells or non-self cells. It does this with the help of a distributed task force that has the intelligence to take action from a local and also a global perspective using its network of chemical messengers for communication. There are two major branches of the immune system. The innate immune system is an unchanging mechanism that detects and destroys certain invading organisms, whilst the adaptive immune system responds to previously unknown foreign cells and builds a response to them that can remain in the body over a long period of time. This remarkable information processing biological system has caught the attention of computer science in recent years. A novel computational intelligence technique, inspired by immunology, has emerged, called Artificial Immune Systems. Several concepts from the immune have been extracted and applied for solution to real world science and engineering problems. In this tutorial, we briefly describe the immune system metaphors that are relevant to existing Artificial Immune Systems methods. We will then show illustrative real-world problems suitable for Artificial Immune Systems and give a step-by-step algorithm walkthrough for one such problem. A comparison of the Artificial Immune Systems to other well-known algorithms, areas for future work, tips & tricks and a list of resources will round this tutorial off. It should be noted that as Artificial Immune Systems is still a young and evolving field, there is not yet a fixed algorithm template and hence actual implementations might differ somewhat from time to time and from those examples given here.

Artificial Immune Tissue using Self-Organizing Networks

As introduced by Bentley et al. (2005), artificial immune systems (AIS) are lacking tissue, which is present in one form or another in all living multi-cellular organisms. Some have argued that this concept in the context of AIS brings little novelty to the already saturated field of the immune inspired computational research. This article aims to show that such a component of an AIS has the potential to bring an advantage to a data processing algorithm in terms of data pre-processing, clustering and extraction of features desired by the immune inspired system. The proposed tissue algorithm is based on self-organizing networks, such as self-organizing maps (SOM) developed by Kohonen (1996) and an analogy of the so called Toll-Like Receptors (TLR) affecting the activation function of the clusters developed by the SOM.

Idiotypic Immune Networks in Mobile Robot Control

Jerne's idiotypic network theory postulates that the immune response involves inter-antibody stimulation and suppression as well as matching to antigens. The theory has proved the most popular Artificial Immune System (AIS) model for incorporation into behavior-based robotics but guidelines for implementing idiotypic selection are scarce. Furthermore, the direct effects of employing the technique have not been demonstrated in the form of a comparison with non-idiotypic systems. This paper aims to address these issues. A method for integrating an idiotypic AIS network with a Reinforcement Learning based control system (RL) is described and the mechanisms underlying antibody stimulation and suppression are explained in detail. Some hypotheses that account for the network advantage are put forward and tested using three systems with increasing idiotypic complexity. The basic RL, a simplified hybrid AIS-RL that implements idiotypic selection independently of derived concentration levels and a full hybrid AIS-RL scheme are examined. The test bed takes the form of a simulated Pioneer robot that is required to navigate through maze worlds detecting and tracking door markers.

Biological Inspiration for Artificial Immune Systems

Artificial immune systems (AISs) to date have generally been inspired by naive biological metaphors. This has limited the effectiveness of these systems. In this position paper two ways in which AISs could be made more biologically realistic are discussed. We propose that AISs should draw their inspiration from organisms which possess only innate immune systems, and that AISs should employ systemic models of the immune system to structure their overall design. An outline of plant and invertebrate immune systems is presented, and a number of contemporary systemic models are reviewed. The implications for interdisciplinary research that more biologically-realistic AISs could have is also discussed.

Introducting Dendritic Cells as a Novel Immune-Inspired Algorithm for Anomaly Detection

Dendritic cells are antigen presenting cells that provide a vital link between the innate and adaptive immune system. Research into this family of cells has revealed that they perform the role of coordinating T-cell based immune responses, both reactive and for generating tolerance. We have derived an algorithm based on the functionality of these cells, and have used the signals and differentiation pathways to build a control mechanism for an artificial immune system. We present our algorithmic details in addition to some preliminary results, where the algorithm was applied for the purpose of anomaly detection. We hope that this algorithm will eventually become the key component within a large, distributed immune system, based on sound imnological concepts.

An Immune Inspired Approach to Anomaly Detection

The immune system provides a rich metaphor for computer security: anomaly detection that works in nature should work for machines. However, early artificial immune system approaches for computer security had only limited success. Arguably, this was due to these artificial systems being based on too simplistic a view of the immune system. We present here a second generation artificial immune system for process anomaly detection. It improves on earlier systems by having different artificial cell types that process information. Following detailed information about how to build such second generation systems, we find that communication between cells types is key to performance. Through realistic testing and validation we show that second generation artificial immune systems are capable of anomaly detection beyond generic system policies. The paper concludes with a discussion and outline of the next steps in this exciting area of computer security.

Oil Price Trackers Inspired by Immune Memory

We outline initial concepts for an immune inspired algorithm to evaluate and predict oil price time series data. The proposed solution evolves a short term pool of trackers dynamically, with each member attempting to map trends and anticipate future price movements. Successful trackers feed into a long term memory pool that can generalise across repeating trend patterns. The resulting sequence of trackers, ordered in time, can be used as a forecasting tool. Examination of the pool of evolving trackers also provides valuable insight into the properties of the crude oil market.

Studies on the protective immune response to Plasmodium chabaudi in mice

Inbred strains of C5731 and NIH nice infected with the A/S strain of Plasmodium chaubaudi usually developed high parasitaemias but infections were rarely fatal in immunocompetent mice and in most mice the parasites could be eradicated within 53 days or less. The immune response of C57B1 and NTH mice to infection with the A/S strain of P. chabaudi was studied. The principle method used in this study for investigating the immune response of the mice was to examine the immunity conferred on syngeneic mice, either X-irradiated or non-irradiated, by transferring to them lymphoid cells or serum from immune or semi-immune donors. The lymphoid cell populations examined were unfractionated spleen cells, nylon wool column enriched subpopulations of thymus-derived lymphocytes (T cells) and the so-called bursa-derived lymphocytes (B cells), bone marrow cells and phagocytic cells. In the course of these experiments observations were made on the effect of X-irradiation on the subsequent growth and multiplication of the parasite. In addition, an in vitro assay for antibody-dependent cell mediated cytotoxicity was used to investigate the activity of splenic K cells during malaria infection. K cells are lymphoid cells which may include lymphocytes of an undefined category, but possess receptors for the Fc portion of antibody on their surface and have the ability to non-specifically lyse target cells coated in antibodies. a) The adoptive transfer of immunity to P.chabaudi with immune spleen cells. Spleen cells from mice which had previously been infected with P.chabaudi were able to confer some immunity on syngeneic mice which had been irradiated with 600 or 800 rads. The protection was detected as a shortened patent parasitaemia in immune cell recipients compared to controls. The early experiments indicated the value of using irradiated recipients rather than non-irradiated recipients. In irradiated mice, a) smaller numbers of immune cells were required to promote detectable immunity than in non-irradiated mice, b) there was an amplification of the difference in the duration of primary parasitaemias in recipients of immune cells and normal cells compared to non-irradiated mice and c) as the irradiated host is immunodepressed, the protective effect of donor cells can be examined with a reduced contribution by the hosts own immune system. An initial non-specific resistance to P.chabaudi infection was observed in irradiated mice, although the infection in most of these mice was subsequently more severe than in non-irradiated mice. The non-specific resistance could be reduced or abolished by injecting lymphoid cells into mice shortly after irradiation or by infecting irradiated mice more than 15 days after irradiation. Other workers suggest that following irradiation, the reticulo-endothelial system is stimulated at the time that the non-specific resistance to P.chabaudi was observed. b) the adoptive transfer of immunity in syngeneic mice with enriched subpopulations of splenic immune T cells, B. cells, bone marrow cells and phagocytes. Immunity to P.chabaudi could be adoptively transferred with enriched spleen subpopulations of immune T cells or immune B cells in mice which had been irradiated 600 or 300 rads. The protective effects of unfractionated immune cells was, however, usually better than that of either immune T or F cell subpopulations. In most experiments enriched immune T cell recipients were more likely to suffer relapsing patent parasitaemias than either enriched immune B cell recipients or unfractionated immune cell recipients. In one experiment a comparison was made of the course of P.chabaudi infection in mice which had been irradiated with either 600 rads or 300 rads and which received injections of different immune cells. A dose of 600 rads permits the immune system of mice to recover from the effects of irradiation, but a dose of 800 rads is lethal to mice unless lymphoid cells are injected after irradiation. It was found that in recipients of enriched immune T or B cells, which had been irradiated with 600 rads, the parasitaemia became subpatent before their equivalents irradiated with 800 rads, but that there was little difference in parasitaemias between recipients of unfractionated immune cells given 600 or 800 rads. Experiments in which enriched immune T cells and B cells were recombined and injected into syngeneic mice gave inconclusive results as to whether the immune subpopulations acted synergistically. Similar experiments in which immune subpopulations of lymphoid cells were recombined with normal subpopulations of lymphoid cells demonstrated that the latter cells did not enhance the protective effect of the former cells. Bone marrow cells from immune mice were able to confer some protection on syngeneic recipients, but were not as protective as enriched immune T cells or B cells. The results obtained in adoptive transfer experiments using phagocytic cells from the spleen of immune mice depended on the length of time spleen cells were incubated in petri-dishes at 37° C before harvesting the phagocytes. Using C57B1 mice, phagocytes harvested after 15 hours incubation were as protective as unfractionated immune cells in a cell transfer experiment, but phagocytes harvested after 16 hours incubation were not protective. Examination of NIH phagocytic cells after 2.5 hours incubation at 37°C, which were as protective as unfractionated immune spleen cells in a cell transfer experiment, demonstrated that the petri-dish adherent cells may have contained B lymphocytes. c) The passive transfer of immunity with serum from P.chabaudi infected mice. The passive transfer of serum from C57B1 mice which had been previously infected with P.chabaudi to normal or irradiated syngeneic mice demonstrated that the serum recipients were initially protected from infection. Irradiated mice, however, were delayed longer in the onset of parasitaemia compared to non-irradiated mice. Using NIH mice, sera were collected from unfractionated immune spleen cell recipients, enriched immune T cell recipients and normal spleen recipients on the 11th day of a P.chabaudi infection, just after peak parasitaemia, and also on the 14th day of infection. On day 14, all immune cells recipients and most of the enriched immune T cell recipients had become subpatent but all normal cell recipients still had patent infections. Sera collected from the different spleen cell recipients on the 11th day of infection and passively transferred to irradiated mice demonstrated little protection. Sera collected on the 14th day of infect ion, however, reflected the immune status of the donors in their protective properties in mice infected with P.chabaudi. The serum from unfractionated immune cell recipients was the most protective of the 3 sera when compared to normal NIH serum and the serum from enriched immune T cell recipients was slightly protective, but the serum from normal cell recipients produced an enhanced infection in mice infected with P.chabaudi. d) Antibody-dependent cell-mediated cytotoxicity of spleen cells in P.chabaudi infected mice. In a preliminary investigation of K cell activity in the spleens of P.chabaudi infected mice, it was found that there was an increased activity of K cells collected at around peak parasitaemia compared to the activity of K cells in non-infected mice, and that this increased activity could also be found in mice which had recently become subpatent. As the target cell for antibody-dependent cell-mediated cytotoxicity employed was the thick red blood cell, it is not known whether the K cell is involved in the killing of P.chabaudi parasites. These results suggest that both T cells and B cells and antibody may be important in the immune response to P.chabaudi in mice. Primed T cells may act as helper cells in the production of malarial antibodies, but, as enriched primed T cells could confer protection on immunodepressed mice, it is possible that a cell-mediated mechanism of immunity may also exist.

'Cooperative Automated worm Response and Detection ImmuNe ALgorithm (CARDINAL) inspired by T-cell Immunity and Tolerance'

The role of T-cells within the immune system is to confirm and assess anomalous situations and then either respond to or tolerate the source of the effect. To illustrate how these mechanisms can be harnessed to solve real-world problems, we present the blueprint of a T-cell inspired algorithm for computer security worm detection. We show how the three central T-cell processes, namely T-cell maturation, differentiation and proliferation, naturally map into this domain and further illustrate how such an algorithm fits into a complete immune inspired computer security system and framework.

'Artificial Immune Systems Tutorial'

The biological immune system is a robust, complex, adaptive system that defends the body from foreign pathogens. It is able to categorize all cells (or molecules) within the body as self-cells or non-self cells. It does this with the help of a distributed task force that has the intelligence to take action from a local and also a global perspective using its network of chemical messengers for communication. There are two major branches of the immune system. The innate immune system is an unchanging mechanism that detects and destroys certain invading organisms, whilst the adaptive immune system responds to previously unknown foreign cells and builds a response to them that can remain in the body over a long period of time. This remarkable information processing biological system has caught the attention of computer science in recent years. A novel computational intelligence technique, inspired by immunology, has emerged, called Artificial Immune Systems. Several concepts from the immune have been extracted and applied for solution to real world science and engineering problems. In this tutorial, we briefly describe the immune system metaphors that are relevant to existing Artificial Immune Systems methods. We will then show illustrative real-world problems suitable for Artificial Immune Systems and give a step-by-step algorithm walkthrough for one such problem. A comparison of the Artificial Immune Systems to other well-known algorithms, areas for future work, tips & tricks and a list of resources will round this tutorial off. It should be noted that as Artificial Immune Systems is still a young and evolving field, there is not yet a fixed algorithm template and hence actual implementations might differ somewhat from time to time and from those examples given here.

Artificial Immune Tissue using Self-Organizing Networks

As introduced by Bentley et al. (2005), artificial immune systems (AIS) are lacking tissue, which is present in one form or another in all living multi-cellular organisms. Some have argued that this concept in the context of AIS brings little novelty to the already saturated field of the immune inspired computational research. This article aims to show that such a component of an AIS has the potential to bring an advantage to a data processing algorithm in terms of data pre-processing, clustering and extraction of features desired by the immune inspired system. The proposed tissue algorithm is based on self-organizing networks, such as self-organizing maps (SOM) developed by Kohonen (1996) and an analogy of the so called Toll-Like Receptors (TLR) affecting the activation function of the clusters developed by the SOM.

'Investigating Artificial Immune Systems For Job Shop Rescheduling In Changing Environments'

ABSTRACT Artificial immune system can be used to generate schedules in changing environments and it has been proven to be more robust than schedules developed using a genetic algorithm. Good schedules can be produced especially when the number of the antigens is increased. However, an increase in the range of the antigens had somehow affected the fitness of the immune system. In this research, we are trying to improve the result of the system by rescheduling the same problem using the same method while at the same time maintaining the robustness of the schedules.

The Danger Theory and Its Application to Artificial Immune Systems

Over the last decade, a new idea challenging the classical self-non-self viewpoint has become popular amongst immunologists. It is called the Danger Theory. In this conceptual paper, we look at this theory from the perspective of Artificial Immune System practitioners. An overview of the Danger Theory is presented with particular emphasis on analogies in the Artificial Immune Systems world. A number of potential application areas are then used to provide a framing for a critical assessment of the concept, and its relevance for Artificial Immune Systems.