1,721,175 research outputs found
Artificial Immune Recognition System (AIRS): Revisions and Refinements
No full textThis paper revisits the Artificial Immmune Recognition System (AIRS) that has been developed as an immune-inspired supervised learning algorithm. Certain unnecessary complications of the original algorithm are discussed and means of overcomming these complexities are proposed. Experimental evidence is presented to support these revisions which do not sacrifice the accuracy of the original algorihtm but, rather, maintain accuracy whilst increasing the simplicity and data reduction capabilities of AIRS
Hierarchy and Convergance of Immune Networks: Basic Ideas and Premilinary Results
No full textaiNet is an artificial immune network model originally developed to perform automatic data compression. Combined with graph theoretical and statistical clustering techniques, aiNet is a powerful data clustering and classification tool. However, the original aiNet model suffers from the lack of a well-defined stopping criterion and an ad hoc approach to parameter initialization, prior to the training process. This paper has two main goals. First, by assessing convergence criteria employed in a class of artificial neural networks, a suitable stopping criterion can be created for aiNet. Secondly, the paper demonstrates that through the use of a cooling schedule for some of these user-defined parameters, it is not only possible to reduce the importance of their initial values, but also this leads to possible derivation of a hierarchical tree of immune networks. Due to the very limited space available, only the basic ideas of a novel convergence criterion, and an approach to develop a tree of aiNets will be presented, together with an illustrative example
Generic, Scalable and Decentralized Fault Detection for Robot Swarms
No full textThis raw data archive includes the data on fault detection in a simulated swarm of 20 e-puck robots. The data was used in the paper Generic, Scalable and Decentralized Fault Detection for Robot Swarms by D. Tarapore et al. (2017). See readme.txt for more details.</span
Software Vaccination: An Artificial Immune Systems Approach
No full textOver time programming languages develop, paradigms evolve, development teams change. The effect of this is that test suites wear out, therefore these also need to evolve. Mutation testing is an effective fault-based testing approach, but it is computationally expensive. Any evolutionary based approach to this process needs to simultaneously manage execution costs. In this conceptual paper we adopt immune systems as a metaphor for the basis of an alternative mutation testing system. It is envisaged that through monitoring of the development environment, a minimal set of effective mutations and test cases can be developed - a 'vaccine' - that can be applied to the software development process to protect it from errors - from infections
Revisiting the Foundations of Artificial Immune Systems: A Problem Oriented Perspective
No full textSince their development, AIS have been used for a number of machine learning tasks including that of classification. Within the literature, there appears to be a lack of appreciation for the possible bias in the selection of various representations and affinity measures that may be introduced when employing AIS in classification tasks. Problems are then compounded when inductive bias of algorithms are not taken into account when applying seemingly generic AIS algorithms to specific application domains. This paper is an attempt at highlighting some of these issues. Using the example of classification, this paper explains the potential pitfalls in representation selection and the use of various affinity measures. Additionally, attention is given to the use of negative selection in classification and it is argued that this may be not an appropriate algorithm for such a task. This paper then presents ideas on avoiding unnecessary mistakes in the choice and design of AIS algorithms and ultimately delivered solutions
Negative Selection: How to Generate Detectors
No full textThe immune system is a remarkable and complex natural system, which has been shown to be of interest to computer scientists and engineers alike. This paper reports an on-going investigation into the usefulness of the negative selection metaphor for immune inspired fault tolerance. Various procedures to generate detectors for the negative selection algorithm are reviewed and compared in terms of time and space complexity for the production of competent detectors. A new algorithm has been identified and implemented. Experimentation was undertaken, and an analysis is presented on the effectiveness of the various algorithms. The outcome of this empirical analysis reveals that trade-offs have to be made in the choice of algorithm based on the time and space complexities, as well as the detection rate
Proceedings of 3rd International Conference on Artificial Immune Systems
No full textArtificial Immune Systems have come of age. They are no longer an obscure computer science technique, worked on by a couple of farsighted research groups. Today, researchers across the globe are working on new computer algorithms inspired by the workings of the immune system. This vigorous field of research investigates how immunobiology can assist our technology, and along the way is beginning to help biologists understand their unique problems. AIS is now old enough to understand its roots, its context in the research community, and its exciting future. It has grown too big to be confined to special sessions in evolutionary computation conferences. AIS researchers are now forming their own community and identity. The International Conference on Artificial Immune Systems is proud to be the premiere conference in the area. As its organizers, we are honoured to have such a variety of innovative and original scientific papers presented this year. ICARIS 2004 is the third international conference dedicated entirely to the field of Artificial Immune Systems (AIS). It was held in Catania, in the beautiful Island of Sicily, Italy, on September 13-16, 2004. While hosting the conference, the city of Catania gave the participants the opportunity to enjoy the richness of its historical and cultural atmosphere and the beauty of its natural resources, the sea, and the Etna Volcano. With respect to the previous two AIS Conference, ICARIS 2004 had some new and exciting features. First, there was a tutorial day, a new track where leading scientists presented the background and the future directions of the Artificial Immune Systems discipline. In particular, four extended tutorials were presented: * the first was an introduction to Artificial Immune Systems by Dr. J. Timmis; * the second tutorial delivered by Dr. Filippo Castiglione faced the Immune System and related pathologies using in silico methodologies; * the third tutorial of Prof. R. Callard described the modelling of the immune system; * the last tutorial offered by Dr. Leandro de Castro illustrated the emerging engineering applications of Artificial Immune Systems. There was also a plenary lecture, delivered by Prof. Alan S. Perelson, on the current state-of-art on Computational and Theoretical Immunology. Moreover, the organizing committee devoted a special session to the topic of ''Immunoinformatics'' run by Dr. Darren Flower. Immunoinformatics is a new discipline that aims to apply computer science techniques to molecules of the Immune System and to use bioinformatics tools for a better understanding of the immune functions. We had more submissions than ever this year, and because our acceptance rate is based purely on quality, we were able to accept only 59% of the submitted papers. More in details, 58 papers were submitted, and each one was independently reviewed by at least three members of the programme committee in a blind review process. So, in these proceedings you will find the extended abstract of the plenary lecturer and 34 papers written by leading scientists in the field, from 21 different countries in 4 continents, describing an impressive array of ideas, technologies and applications for AIS. We couldn't have organized this conference without these researchers, so we thank them all for coming. We also couldn't have organized ICARIS without the excellent work of all of the programme committee, our publicity chair, Simon Garrett, our conference secretary, Jenny Oatley, and as local organizer, Mario Pavone. We would like to express our appreciation to the plenary lecturer who accepted our invitation, to the tutorial speakers, and to all authors who submitted research papers to ICARIS 2004
Fault detection in a swarm of physical robots based on behavioral outlier detection
No full textThe ability to reliably detect faults is essential in many real-world tasks that robot swarms have the potential to perform. Most studies on fault detection in swarm robotics have been conducted exclusively in simulation, and they have focused on a single type of fault or a specific task. In a series of previous studies, we have developed a robust fault-detection approach in which robots in a swarm learn to distinguish between normal and faulty behaviors online. In this paper, we assess the performance of our fault-detection approach on a swarm of seven physical mobile robots. We experiment with three classic swarm robotics tasks and consider several types of faults in both sensors and actuators. Experimental results show that the robots are able to reliably detect the presence of hardware faults in one another even when the swarm behavior is changed during operation. This paper is thus an important step toward making robot swarms sufficiently reliable and dependable for real-world applications
Generic, scalable and decentralized fault detection for robot swarms
Full text linkRobot swarms are large-scale multirobot systems with decentralized control which means that each robot acts based only on local perception and on local coordination with neighboring robots. The decentralized approach to control confers number of potential benefits. In particular, inherent scalability and robustness are often highlighted as key distinguishing features of robot swarms compared with systems that rely on traditional approaches to multirobot coordination. It has, however, been shown that swarm robotics systems are not always fault tolerant. To realize the robustness potential of robot swarms, it is thus essential to give systems the capacity to actively detect and accommodate faults. In this paper, we present a generic fault-detection system for robot swarms. We show how robots with limited and imperfect sensing capabilities are able to observe and classify the behavior of one another. In order to achieve this, the underlying classifier is an immune system-inspired algorithm that learns to distinguish between normal behavior and abnormal behavior online. Through a series of experiments, we systematically assess the performance of our approach in a detailed simulation environment. In particular, we analyze our system’s capacity to correctly detect robots with faults, false positive rates, performance in a foraging task in which each robot exhibits a composite behavior, and performance under perturbations of the task environment. Results show that our generic fault-detection system is robust, that it is able to detect faults in a timely manner, and that it achieves a low false positive rate. The developed fault-detection system has the potential to enable long-term autonomy for robust multirobot systems, thus increasing the usefulness of robots for a diverse repertoire of upcoming applications in the area of distributed intelligent automation
Software Product Line Engineering for Robotics
No full textThe cost of creating new robotics products is significantly related to the complexity of developing robotic software applications that are flexible enough
to easily accommodate frequently changing requirements. In various application domains, software product line (SPL) development has proven to be the most effective approach to achieving software flexibility and to face this kind of challenges. This chapter reviews the fundamental concepts in SPL from a robotics perspective and defines guidelines for the adoption of software product line engineering in robotics. In particular, it discusses the concepts of software variability, domain analysis and modelling, reference architectures, and system configuration
- …
