Showing papers on "Artificial immune system published in 1998"

Artificial Immune Systems and Their Applications

Abstract: This is a pioneering work on the emerging field of artificial immune systems-highly distributed systems based on the principles of the natural system. Like artificial neural networks, artificial immune systems can learn new information and recall previously learned information. This book provides an overview of artificial immune systems, explaining its applications in areas such as immunological memory, anomaly detection algorithms, and modeling the effects of prior infection on vaccine efficacy.

Producing robust schedules via an artificial immune system

Abstract: This paper describes an artificial immune system (AIS) approach to producing robust schedules for a dynamic job-shop scheduling problem in which jobs arrive continually, and the environment is subject to change due to practical reasons. We investigate whether an AIS can be evolved using a genetic algorithm (GA), and then used to produce sets of schedules which together cover a range of contingencies, both foreseeable and unforeseeable. We compare the quality of the schedules to those produced using a genetic algorithm specifically designed for tackling job-shop scheduling problems, and find that the schedules produced from the evolved AIS compare favourably to those produced by the GA. Furthermore, we find that the AIS schedules are robust in that there are large similarities between each schedule in the set, indicating that a switch from one schedule to another could be performed with minimal disruption if rescheduling is required.

Immune algorithm for n-TSP

Abstract: As the neural networks or genetic algorithms, adaptive algorithms become popular and these techniques are applied to many kinds of optimization problems. The immune system is one of the adaptive biological system whose functions are to identify and to eliminate foreign material. In this paper, we propose an optimization algorithm based on immune model and applied to the n-th agents' travelling salesman problem called n-TSP. Some computer simulations are designed to investigate the performance of the immune algorithm. The results of simulations represent that the immune algorithm shows good performance for the combinatorial optimization problems.

An artificial immune system as a multi-agent decision support system

Abstract: The paper proposes a general framework for building an intelligent decision support system based on immunological principles. We examine various recognition and response mechanisms of the immune system to develop a massively parallel adaptive decision support system. Such an integrated system can also be viewed as a multi-agent system where the functionalities and the capabilities of different types of agents vary. Moreover, the agents may move and interact freely in the environment with other agents. They can mutually recognize each others activities and can produce specific response based on pre-defined decision strategies. The purpose of this research is to demonstrate that such a collaborative multi-agent system can enhance the decision making process, and can solve complex tasks more precisely and efficiently. A prototype system is currently under implementation in an object-oriented software paradigm with visualization tools.

Emergent construction of behavior arbitration mechanism based on the immune system

Abstract: We have been investigating a new behavior arbitration mechanism based on the biological immune system. The behavior arbitration mechanism and the biological immune system share certain similarities since both systems deal with various sensory inputs (antigens) through interactions among multiple competence modules (lymphocytes and/or antibodies). We have demonstrated the flexible arbitration abilities of our proposed method, however, we have not previously shown a solution to the problem: how do we prepare an appropriate repertoire of competence modules? In this paper, in order to construct an appropriate immune network without human intervention, we try to incorporate an off-line metadynamics function into our previously proposed mechanism. The metadynamics function is an adaptation realized by varying the structure of the immune network. To accomplish this function, we use a genetic algorithm with a devised crossover operator. Finally, we verify our method by carrying out simulations.

Application of an immune algorithm to multi-optimization problems

Abstract: An immune system has powerful abilities such as memory, recognition, and learning to respond to invading antigens. The concept is expected to be applicable to many engineering applications. This paper proposes an optimization algorithm that imitates the immune system in order to solve multi-optimization problems partly by using a genetic algorithm. Through illustrative examples of multimodal functions such as the Shubert function, the proposed algorithm is shown to be effective in searching for a set of global solutions. © 1998 Scripta Technica. Electr Eng Jpn, 122(2): 30–37, 1998

Immunology Viewed as the Study of an Autonomous Decentralized System

Abstract: Arguments are given for the tenet that although the immune system has no long term goals, it does have short term goals-which are often contradictory. Simple models illustrate how feedbacks can (i) harmonize conflicting goals, (ii) improve the performance of a given type of effector cell, (iii) cause the preferential amplification of more potent effectors. It is shown that spatial organization can allow non-specific chemical signals to select specific immune elements that contribute to system goals. Comparison is made with other autonomous decentralized systems.

Modeling immune cognition

Abstract: We believe that organism's defences have gradually evolved into a real cognitive system after cell membrane receptors underwent diversification in early fish, some 300 million years ago. The somatic repertoires grow by combinatorial power, as receptors are assembled from germ line information, by an aleatory and error prone process. There is no doubt that a cellular automaton is well suited as the vehicle for modeling these aspects of the immune response. In its simplest form, the model consists of a 15/spl times/15 bidimensional grid, containing different cell types, each expressing receptors in a form of 8-bit binary strings. Antigens and antibodies interact if they meet within a site and if the respective bits are complementary. The rules and cell programs are drawn with a keen eye to current biological consensus, and the model behaves like an immune system. We review the principle and the achievements of the IMMSIM model and present preliminary results of the combined cellular and humoral responses to a viral infection.

Augmenting an artificial immune network

Abstract: The human immune system can provide many metaphors that can be utilised effectively in the field of machine learning. These metaphors have been successfully applied to the complex real world problem of mortgage fraud detection, using a learning system known as Jisys. The Jisys system identifies patterns in mortgage fraud data by constructing an immune network, which is then evolved through the analysis of additional fraudulent and no-fraudulent applications. By viewing this network, a human expert can gain a better understanding of the fraudulent behavior. This paper describes significant developments over the original Jisys system. For example, the network is currently a flat structure with significant groupings within it. However, it can be difficult to identify these groups, to analyse them and then determine their significance. This paper describes some advances, which significantly improve the interpretation of the network. We also consider various statistical techniques which can be used to enhance the performance of the Jisys system as well as exploiting inherent properties of the network which enable significant performance improvements to be implemented (with not loss of information content). Finally, the paper presents some analysis of the structures generated by the Jisys system and relates them back to the known structures in the training data set.

Immune Network Dynamics for Inductive Problem Solving

Abstract: This paper develops an inductive computation algorithm upon biological mechanisms discovered by the immunology We build an evolutionary search algorithm based on a model of the immune network dynamics According to it, the concentration of lymphocyte clone-like solutions is determined by the degree of recognition of antigens, as well as the extent of behavioral interaction with other members of the population The antigen-like examples also change their concentration to gear up solutions matching slightly covered examples These dynamic features are incorporated in the fitness function of the immune algorithm in order to achieve high diversity and efficient search navigation Empirical evidence for the superiority of this immune version before the simple genetic algorithm on automata induction tasks are presented

Artificial intelligence and mathematical methods in pavement and geomechanical systems : proceedings of the international workshop on artificial intelli[n]gence and mathematical methods in pavement and geomecahnical systems, Florida/USA/5-6 November, 1998

Abstract: The book covers a wide range of Artificial Intelligence (AI) and Mathematical Methods issues, research and applications in the area of pavement, geomechanical and few examples on geo-environmental systems: Application of Artificial Neural Networks; Data mining applications; Stochastic Finite Element; Fuzzy Set Theory; Artificial Immune Systems; Probabilistic Reasoning; System Identification Techniques; Image Processing. This collection of papers provides researchers and engineers with a current comprehensive look at available and emerging AI and Mathematical Methods within pavement and geomechanical systems.

Artificial immune system based on syndromes-response approach: recognition of the patterns of immune response and prognosis of therapy outcome

Abstract: How can one make a prediction for an individual outcome, given ill-structured and multi-scaled data about a small group of other similar individuals? To answer this question, we develop a robust combinatorial-statistical optimization method for doing pattern recognition based on such data. This method is based on the simulation of recognition processes in the immune system. Our method demonstrates higher robustness and predictive power compared to the classification and regression trees (CART) method in predicting the outcome of immunotherapy for superficial bladder cancer based on immunological measurements.

Artificial immune system for multispectral feature extraction

Abstract: We use an algorithm based on the natural immune system for classification of aerial multispectral imagery. Our artificial immune system works by maintaining a population of detectors that remove undesired patterns, but pass a specified training set of positive examples. Any detectors reacting with input patterns are optimized to remove as many of them as possible while not removing ones similar to the training examples. This paper consists of an introduction to the natural and artificial immune systems (AIS), explanation of the AIS algorithm, results of forest and water classification using multispectral data, and discussion of sources of error and possible improvements.

Artificial Immune Network and Its Application to Robotics

Abstract: Conventional Artificial Intelligence (AI) techniques have been criticized for their brittleness under dynamically changing environments In recent years, therefore, much attention has been focused on the reactive planning approach such as behavior-based AI However, in the behavior-based artificial AI approach, there are following problems that have to be resolved: 1) how do we construct an appropriate arbitration mechanism, and 2) how do we prepare appropriate behavior primitives (competence modules) On the other hand, biological information processing systems have various interesting characteristics viewed from the engineering standpoint Among them, in this study, we particularly pay close attention to the immune system We try to construct a decentralized consensus-making mechanism inspired by the immune network hypothesis To tackle the above-mentioned problems in the behavior-based AI, we apply the proposed method to behavior arbitration for an autonomous mobile robot by carrying out some simulations and experiments using a real robot In addition, we investigate two types of adaptation mechanisms to construct an appropriate artificial immune network without human intervention