Generalizing the majority voting scheme to spatially constrained voting.

Generating ensembles from multiple individual classifiers is a popular approach to raise the accuracy of the decision. As a rule for decision making, majority voting is a usually applied model. In this paper, we generalize classical majority voting by incorporating probability terms pn,k to constrain the basic framework. These terms control whether a correct or false decision is made if k correct votes are present among the total number of n. This generalization is motivated by object detection problems, where the members of the ensemble are image processing algorithms giving their votes as pixels in the image domain. In this scenario, the terms pn,k can be specialized by a geometric constraint. Namely, the votes should fall inside a region matching the size and shape of the object to vote together. We give several theoretical results in this new model for both dependent and independent classifiers, whose individual accuracies may also differ. As a real world example, we present our ensemble-based system developed for the detection of the optic disc in retinal images. For this problem, experimental results are shown to demonstrate the characterization capability of this system. We also investigate how the generalized model can help us to improve an ensemble with extending it by adding a new algorithm.

Characterization of human invasive isolates of Listeria monocytogenes in Sweden 1986-2007.

Since 1986, 68% of the Listeria monocytogenes isolates from human cases of invasive listeriosis in Sweden are available for retrospective studies. The aim of the present study was to characterize 601 human invasive isolates of L. monocytogenes in Sweden from 1986 to 2007 by using serotyping and pulsed-field gel electrophoresis. Since 1996, serovar 4b was permanently reduced to the second or third most common serovar in human cases in Sweden. During the latter period, 2000-2007, only 13% belonged to serovar 4b and 71% to 1/2a. The dendrogram, based on pulsovars, reveals two clusters with different serovars. Cluster 1 exhibits serovars 4b and 1/2b, whereas cluster 2 consists of serovar 1/2a. Serovar 1/2a seems to be more heterogeneous than serovar 4b.