In this article we address the task of automatic text structuring into linear and nonoverlapping thematic episodes at a coarse level of granularity. In particular, we deal with topic segmentation on multi-party meeting recording transcripts, which pose specific challenges for topic segmentation models. We present a comparative study of two probabilistic mixture models. Based on lexical features...

In this paper we propose a new procedure to select differentially expressed genes between several conditions in microarray experiments. Asymptotic properties for the false discovery rate are proved under mild conditions. We compare by simulations and on a pseudo-real data set our procedure to the Benjamini and Hochberg's procedure and a procedure based on mixture models.

MOTIVATION The statistical analysis of single-cell data is a challenge in cell biological studies. Tailored statistical models and computational methods are required to resolve the subpopulation structure, i.e. to correctly identify and characterize subpopulations. These approaches also support the unraveling of sources of cell-to-cell variability. Finite mixture models have shown promise, but ...

Studies in experimental grasslands have shown variation in plant individual performance in response to neighbourhood diversity. To which extent these responses are due to phenotypic plasticity or genetic variation is largely unknown. We collected seed families of five herbaceous species (Cirsium oleraceum, Crepis biennis, Plantago lanceolata, Plantago media and Rumex acetosa) in monocultures an...

The paper describes a structural framework for the design of a speaker recognition system based on multiple models. This combination is not only at the recognition level, but also at a joint training of the models. This unified training of the models uses a common structure : a decomposition tree of the set of data of normalization speakers. For the experiments, the Gaussian Mixture Model and t...

Dye diffusion study to obtain the horizontal diffusivity is often carried now a day. Data obtained by Indomer coastal hydraulics by conducting dye tracing experiments at several parts of coastal India, were used and have been analyzed to estimate horizontal mixing coefficients. The data of these studies are used to find out the dispersion coefficients and the oceanic diffusivity is reviewed. An...

With respect to best currently available pulse sequences, a 10-fold reduction in minimum experiment time together with significant resolution enhancement can be achieved in 3D DOSY homonuclear experiments by means of Hadamard encoding, as illustrated here for the 3D DOSY-TOCSY experiment.

Five flavonoids (rutin, asebotin, 3-hydroxyasebotin, quercetin-3-O-beta-D-xylopyranoside, and a racemic mixture of catechin) and caffeic acid were isolated and identified for the first time from seagrass, Thalassodendron ciliatum, collected from the Hurghada region in Egypt. The crude extract and the isolated pure compounds were evaluated for their cytotoxic activities against HCT-116, HEPG, MC...

Particle Swarm Optimization (PSO) is a meta-heuristic algorithm that has been shown to be successful in finding the optimum solution or close to the optimum for a wide variety of real and complicated optimization problems in engineering and computer science. This paper adapts PSO methodology by first solving an optimization problem on the hypercube and then projecting the solution onto the q-si...