Robust face recognition with partial occlusion, illumination variation and limited training data by optimal feature selection

This study investigates face recognition with partial occlusion, illumination variation and their combination, assuming no prior information about the mismatch, and limited training data for each person. The authors extend their previous posterior union model (PUM) to give a new method capable of dealing with all these problems. PUM is an approach for selecting the optimal local image features for recognition to improve robustness to partial occlusion. The extension is in two stages. First, authors extend PUM from a probability-based formulation to a similarity-based formulation, so that it operates with as little as one single training sample to offer robustness to partial occlusion. Second, they extend this new formulation to make it robust to illumination variation, and to combined illumination variation and partial occlusion, by a novel combination of multicondition relighting and optimal feature selection. To evaluate the new methods, a number of databases with various simulated and realistic occlusion/illumination mismatches have been used. The results have demonstrated the improved robustness of the new methods.

Selection for cuticular melanism reveals immune function and life-history trade-offs in Spodoptera littoralis

Several insect species show an increase in cuticular melanism in response to high densities. In some species, there is evidence that this melanism is correlated with an up-regulation of certain immune system components, particularly phenoloxidase (PO) activity, and with the down-regulation of lysozyme activity, suggesting a trade-off between the two traits. As melanism has a genetic component, we selected both melanic and nonmelanic lines of the phase-polyphenic lepidopteran, Spodoptera littoralis, in order to test for a causative genetic link between melanism, PO activity and lysozyme activity, and to establish if there are any life-history costs associated with the melanic response. We found that, in fact, melanic lines had lower PO activity and higher lysozyme activity than nonmelanic lines, confirming a genetic trade-off between the two immune responses, but also indicating a genetic trade-off between melanism and PO activity. In addition, we found that lines with high PO activity had slower development rates suggesting that investment in PO, rather than in melanism, is costly.

Locally regularised two-stage learning algorithm for RBF network centre selection

Nonlinear models constructed from radial basis function (RBF) networks can easily be over-fitted due to the noise on the data. While information criteria, such as the final prediction error (FPE), can provide a trade-off between training error and network complexity, the tunable parameters that penalise a large size of network model are hard to determine and are usually network dependent. This article introduces a new locally regularised, two-stage stepwise construction algorithm for RBF networks. The main objective is to produce a parsomous network that generalises well over unseen data. This is achieved by utilising Bayesian learning within a two-stage stepwise construction procedure to penalise centres that are mainly interpreted by the noise.

Use of weaning protocols for reducing duration of mechanical ventilation in critically ill adult patients: Cochrane systematic review and meta-analysis.

Objective To investigate the effects of weaning protocols on the total duration of mechanical ventilation, mortality, adverse events, quality of life, weaning duration, and length of stay in the intensive care unit and hospital.

Design Systematic review.

Data sources Cochrane Central Register of Controlled Trials, Medline, Embase, CINAHL, LILACS, ISI Web of Science, ISI Conference Proceedings, Cambridge Scientific Abstracts, and reference lists of articles. We did not apply language restrictions.

Review methods We included randomised and quasi-randomised controlled trials of weaning from mechanical ventilation with and without protocols in critically ill adults.

Data selection Three authors independently assessed trial quality and extracted data. A priori subgroup and sensitivity analyses were performed. We contacted study authors for additional information.

Results Eleven trials that included 1971 patients met the inclusion criteria. Compared with usual care, the geometric mean duration of mechanical ventilation in the weaning protocol group was reduced by 25% (95% confidence interval 9% to 39%, P=0.006; 10 trials); the duration of weaning was reduced by 78% (31% to 93%, P=0.009; six trials); and stay in the intensive care unit length by 10% (2% to 19%, P=0.02; eight trials). There was significant heterogeneity among studies for total duration of mechanical ventilation (I(2)=76%, P

Conclusion There is evidence of a reduction in the duration of mechanical ventilation, weaning, and stay in the intensive care unit when standardised weaning protocols are used, but there is significant heterogeneity among studies and an insufficient number of studies to investigate the source of this heterogeneity. Some studies suggest that organisational context could influence outcomes, but this could not be evaluated as it was outside the scope of this review.