Simulating dynamic covariance structures for testing the adaptive behavior of variable selection algorithms (Invited Paper)

Variable selection for regression is a classical statistical problem, motivated by concerns that too large a number of covariates may bring about overfitting and unnecessarily high measurement costs. Novel difficulties arise in streaming contexts, where the correlation structure of the process may be drifting, in which case it must be constantly tracked so that selections may be revised accordingly. A particularly interesting phenomenon is that non-selected covariates become missing variables, inducing bias on subsequent decisions. This raises an intricate exploration-exploitation tradeoff, whose dependence on the covariance tracking algorithm and the choice of variable selection scheme is too complex to be dealt with analytically. We hence capitalise on the strength of simulations to explore this problem, taking the opportunity to tackle the difficult task of simulating dynamic correlation structures. © 2008 IEEE.

Phase-variable surface structures are required for infection of Campylobacter jejuni by bacteriophages.

This study characterizes the interaction between Campylobacter jejuni and the 16 phages used in the United Kingdom typing scheme by screening spontaneous mutants of the phage-type strains and transposon mutants of the sequenced strain NCTC 11168. We show that the 16 typing phages fall into four groups based on their patterns of activity against spontaneous mutants. Screens of transposon and defined mutants indicate that the phage-bacterium interaction for one of these groups appears to involve the capsular polysaccharide (CPS), while two of the other three groups consist of flagellatropic phages. The expression of CPS and flagella is potentially phase variable in C. jejuni, and the implications of these findings for typing and intervention strategies are discussed.

Models and algorithms for tracking of maneuvering objects using variable rate particle filters

Standard algorithms in tracking and other state-space models assume identical and synchronous sampling rates for the state and measurement processes. However, real trajectories of objects are typically characterized by prolonged smooth sections, with sharp, but infrequent, changes. Thus, a more parsimonious representation of a target trajectory may be obtained by direct modeling of maneuver times in the state process, independently from the observation times. This is achieved by assuming the state arrival times to follow a random process, typically specified as Markovian, so that state points may be allocated along the trajectory according to the degree of variation observed. The resulting variable dimension state inference problem is solved by developing an efficient variable rate particle filtering algorithm to recursively update the posterior distribution of the state sequence as new data becomes available. The methodology is quite general and can be applied across many models where dynamic model uncertainty occurs on-line. Specific models are proposed for the dynamics of a moving object under internal forcing, expressed in terms of the intrinsic dynamics of the object. The performance of the algorithms with these dynamical models is demonstrated on several challenging maneuvering target tracking problems in clutter. © 2006 IEEE.

Partial soi power LDMOS with a variable low-kappa; Dielectric buried layer and a buried P layer

A power LDMOS on partial silicon on insulator (PSOI) with a variable low-κ dielectric (VLKD) buried layer and a buried p (BP) layer is proposed (VLKD BPSOI). At a low κ value, the electric field strength in the buried dielectric (EI) is enhanced, and a Si window makes the substrate share the vertical voltage drop, leading to a high vertical breakdown voltage (BV). Moreover, three interface field peaks are introduced by the BP, the Si window, and the VLKD, which modulate the fields in the SOI layer, the VLKD layer, and the substrate; consequently, a high BV is obtained. Furthermore, the BP reduces the specific on-resistance (Ron), and the Si window alleviates the self-heating effect (SHE). The BV for VLKD BPSOI is enhanced by 34.5%, and Ron is decreased by 26.6%, compared with those for the conventional PSOI, and VLKD BPSOI also maintains a low SHE. © 2006 IEEE.