Design, construction and evaluation of systems to predict risk in obstetrics.

We present a systematic, practical approach to developing risk prediction systems, suitable for use with large databases of medical information. An important part of this approach is a novel feature selection algorithm which uses the area under the receiver operating characteristic (ROC) curve to measure the expected discriminative power of different sets of predictor variables. We describe this algorithm and use it to select variables to predict risk of a specific adverse pregnancy outcome: failure to progress in labour. Neural network, logistic regression and hierarchical Bayesian risk prediction models are constructed, all of which achieve close to the limit of performance attainable on this prediction task. We show that better prediction performance requires more discriminative clinical information rather than improved modelling techniques. It is also shown that better diagnostic criteria in clinical records would greatly assist the development of systems to predict risk in pregnancy.

Evaluation of two-phase induction motor drives for low-cost applications

An experimental evaluation of small two-phase induction motor drives operating with different inverter topologies is described. Results show that a PWM-based four-switch inverter, having only low-side switches is attractive for high-speed low-cost applications where speeds greater than those that can be obtained using single phase induction motors are required.

Evaluation of wave drag reduction by flow control

An analytical expression is proposed to estimate the wave drag of an aerofoil equipped with shock control. The analysis extends the conventional approach for a single normal shock wave, based on the knowledge that all types of successful shock control on transonic aerofoils cause bifurcated λ-shock structures. The influence of surface curvature on the λ-shock structure has been taken into account. The extended method has been found to produce fairly good agreement with the results obtained by CFD methods while requiring negligible computational effort. This new formulation is expected to be beneficial in the industrial design process of transonic aerofoils and wings where a large number of computational simulations have to be performed.