Model Selection in SVMs Using Differential Evolution

To improve the performance of classification using Support Vector Machines (SVMs) while reducing the model selection time, this paper introduces Differential Evolution, a heuristic method for model selection in two-class SVMs with a RBF kernel. The model selection method and related tuning algorithm are both presented. Experimental results from application to a selection of benchmark datasets for SVMs show that this method can produce an optimized classification in less time and with higher accuracy than a classical grid search. Comparison with a Particle Swarm Optimization (PSO) based alternative is also included.

Differential effects of magnetic pulses on the orientation of naturally migrating birds

In migratory passerine birds, strong magnetic pulses are thought to be diagnostic of the remagnetization of iron minerals in a putative sensory system contained in the beak. Previous evidence suggests that while such a magnetic pulse affects the orientation of migratory birds in orientation cages, no effect was present when pulse-treated birds were tested in natural migration. Here we show that two migrating passerine birds treated with a strong magnetic pulse, designed to alter the magnetic sense, migrated in a direction that differed significantly from that of controls when tested in natural conditions. The orientation of treated birds was different depending on the alignment of the pulse with respect to the magnetic field. These results can aid in advancing understanding of how the putative iron-mineral-based receptors found in birds' beaks may be used to detect and signal the intensity and/or direction of the Earth's magnetic field.