Gossip-based solutions for discrete rendezvous in populations of communicating agents.

The objective of the rendezvous problem is to construct a method that enables a population of agents to agree on a spatial (and possibly temporal) meeting location. We introduce the buffered gossip algorithm as a general solution to the rendezvous problem in a discrete domain with direct communication between decentralized agents. We compare the performance of the buffered gossip algorithm against the well known uniform gossip algorithm. We believe that a buffered solution is preferable to an unbuffered solution, such as the uniform gossip algorithm, because the use of a buffer allows an agent to use multiple information sources when determining its desired rendezvous point, and that access to multiple information sources may improve agent decision making by reinforcing or contradicting an initial choice. To show that the buffered gossip algorithm is an actual solution for the rendezvous problem, we construct a theoretical proof of convergence and derive the conditions under which the buffered gossip algorithm is guaranteed to produce a consensus on rendezvous location. We use these results to verify that the uniform gossip algorithm also solves the rendezvous problem. We then use a multi-agent simulation to conduct a series of simulation experiments to compare the performance between the buffered and uniform gossip algorithms. Our results suggest that the buffered gossip algorithm can solve the rendezvous problem faster than the uniform gossip algorithm; however, the relative performance between these two solutions depends on the specific constraints of the problem and the parameters of the buffered gossip algorithm.

GFAM: evolving Fuzzy ARTMAP neural networks.

This paper focuses on the evolution of Fuzzy ARTMAP neural network classifiers, using genetic algorithms, with the objective of improving generalization performance (classification accuracy of the ART network on unseen test data) and alleviating the ART category proliferation problem (the problem of creating more than necessary ART network categories to solve a classification problem). We refer to the resulting architecture as GFAM. We demonstrate through extensive experimentation that GFAM exhibits good generalization and is of small size (creates few ART categories), while consuming reasonable computational effort. In a number of classification problems, GFAM produces the optimal classifier. Furthermore, we compare the performance of GFAM with other competitive ARTMAP classifiers that have appeared in the literature and addressed the category proliferation problem in ART. We illustrate that GFAM produces improved results over these architectures, as well as other competitive classifiers.

Intelligent automated control of life support systems using proportional representations.

Effective automatic control of Advanced Life Support Systems (ALSS) is a crucial component of space exploration. An ALSS is a coupled dynamical system which can be extremely sensitive and difficult to predict. As a result, such systems can be difficult to control using deliberative and deterministic methods. We investigate the performance of two machine learning algorithms, a genetic algorithm (GA) and a stochastic hill-climber (SH), on the problem of learning how to control an ALSS, and compare the impact of two different types of problem representations on the performance of both algorithms. We perform experiments on three ALSS optimization problems using five strategies with multiple variations of a proportional representation for a total of 120 experiments. Results indicate that although a proportional representation can effectively boost GA performance, it does not necessarily have the same effect on other algorithms such as SH. Results also support previous conclusions that multivector control strategies are an effective method for control of coupled dynamical systems.

Iron porphyrin treatment extends survival in a transgenic animal model of amyotrophic lateral sclerosis.

Oxidative damage, produced by mutant Cu/Zn superoxide dismutase (SOD1), may play a role in the pathogenesis of amyotrophic lateral sclerosis (ALS), a devastating motor neuron degenerative disease. A novel approach to antioxidant therapy is the use of metalloporphyrins that catalytically scavenge a wide range of reactive oxygen and reactive nitrogen species. In this study, we examined the therapeutic potential of iron porphyrin (FeTCPP) in the G93A mutant SOD1 transgenic mouse model of ALS. We found that intraperitoneal injection of FeTCPP significantly improved motor function and extended survival in G93A mice. Similar results were seen with a second group of mice wherein treatment with FeTCPP was initiated at the onset of hindlimb weakness-roughly equivalent to the time at which treatment would begin in human patients. FeTCPP-treated mice also showed a significant reduction in levels of malondialdehyde (a marker of lipid peroxidation), in total content of protein carbonyls (a marker of protein oxidation), and increased neuronal survival in the spinal cord. These results therefore provide further evidence of oxidative damage in a mouse model of ALS, and suggest that FeTCPP could be beneficial for the treatment of ALS patients.