An Online Expectation-Maximization Algorithm for Changepoint Models

Changepoint models are widely used to model the heterogeneity of sequential data. We present a novel sequential Monte Carlo (SMC) online Expectation-Maximization (EM) algorithm for estimating the static parameters of such models. The SMC online EM algorithm has a cost per time which is linear in the number of particles and could be particularly important when the data is representable as a long sequence of observations, since it drastically reduces the computational requirements for implementation. We present an asymptotic analysis for the stability of the SMC estimates used in the online EM algorithm and demonstrate the performance of this scheme using both simulated and real data originating from DNA analysis.

An Online Expectation-Maximization Algorithm for Changepoint Models

Changepoint models are widely used to model the heterogeneity of sequential data. We present a novel sequential Monte Carlo (SMC) online Expectation-Maximization (EM) algorithm for estimating the static parameters of such models. The SMC online EM algorithm has a cost per time which is linear in the number of particles and could be particularly important when the data is representable as a long sequence of observations, since it drastically reduces the computational requirements for implementation. We present an asymptotic analysis for the stability of the SMC estimates used in the online EM algorithm and demonstrate the performance of this scheme using both simulated and real data originating from DNA analysis.

Identification of Cj1051c as a Major determinant for the restriction barrier of Campylobacter jejuni StrainNCTC11168

Campylobacter jejuni is a leading cause of human diarrheal illness in the world, and research on it has benefitted greatly by the completion of several genome sequences and the development of molecular biology tools. However, many hurdles remain for a full understanding of this unique bacterial pathogen. One of the most commonly used strains for genetic work with C. jejuni is NCTC11168. While this strain is readily transformable with DNA for genomic recombination, transformation with plasmids is problematic. In this study, we have identified a determinant of this to be cj1051c, predicted to encode a restriction-modification type IIG enzyme. Knockout mutagenesis of this gene resulted in a strain with a 1,000-fold-enhanced transformation efficiency with a plasmid purified from a C. jejuni host. Additionally, this mutation conferred the ability to be transformed by plasmids isolated from an Escherichia coli host. Sequence analysis suggested a high level of variability of the specificity domain between strains and that this gene may be subject to phase variation. We provide evidence that cj1051c is active in NCTC11168 and behaves as expected for a type IIG enzyme. The identification of this determinant provides a greater understanding of the molecular biology of C. jejuni as well as a tool for plasmid work with strain NCTC11168. © 2012, American Society for Microbiology.

Beyond 2D-grids: A dependence maximization view on image browsing

Ideally, one would like to perform image search using an intuitive and friendly approach. Many existing image search engines, however, present users with sets of images arranged in some default order on the screen, typically the relevance to a query, only. While this certainly has its advantages, arguably, a more flexible and intuitive way would be to sort images into arbitrary structures such as grids, hierarchies, or spheres so that images that are visually or semantically alike are placed together. This paper focuses on designing such a navigation system for image browsers. This is a challenging task because arbitrary layout structure makes it difficult - if not impossible - to compute cross-similarities between images and structure coordinates, the main ingredient of traditional layouting approaches. For this reason, we resort to a recently developed machine learning technique: kernelized sorting. It is a general technique for matching pairs of objects from different domains without requiring cross-domain similarity measures and hence elegantly allows sorting images into arbitrary structures. Moreover, we extend it so that some images can be preselected for instance forming the tip of the hierarchy allowing to subsequently navigate through the search results in the lower levels in an intuitive way. Copyright 2010 ACM.