Variational inference for Student-t MLP models

This paper presents a novel methodology to infer parameters of probabilistic models whose output noise is a Student-t distribution. The method is an extension of earlier work for models that are linear in parameters to nonlinear multi-layer perceptrons (MLPs). We used an EM algorithm combined with variational approximation, the evidence procedure, and an optimisation algorithm. The technique was tested on two regression applications. The first one is a synthetic dataset and the second is gas forward contract prices data from the UK energy market. The results showed that forecasting accuracy is significantly improved by using Student-t noise models.

Ametropia and ocular biometry in a UK university student population

Purpose. The prevalence of myopia is known to vary with age, ethnicity, level of education, and socioeconomic status, with a high prevalence reported in university students and in people from East Asian countries. This study determines the prevalence of ametropia in a mixed ethnicity U.K. university student population and compares associated ocular biometric measures. Methods. Refractive error and related ocular component data were collected on 373 first-year U.K. undergraduate students (mean age = 19.55 years ± 2.99, range = 17-30 years) at the start of the academic year at Aston University, Birmingham, and the University of Bradford, West Yorkshire. The ethnic variation of the students was as follows: white 38.9%, British Asian 58.2%, Chinese 2.1%, and black 0.8%. Noncycloplegic refractive error was measured with an infrared open-field autorefractor, the Shin-Nippon NVision-K 5001 (Shin Nippon, Ryusyo Industrial Co. Ltd, Osaka, Japan). Myopia was defined as a mean spherical equivalent (MSE) less than or equal to -0.50 D. Hyperopia was defined as an MSE greater than or equal to +0.50 D. Axial length, corneal curvature, and anterior chamber depth were measured using the Zeiss IOLMaster (Carl Zeiss, Jena, GmBH). Results. The analysis was carried out only for white and British Asian groups. The overall distribution of refractive error exhibited leptokurtosis, and prevalence levels were similar for white and British Asian (the predominant ethnic group) students across each ametropic group: myopia (50% vs. 53.4%), hyperopia (18.8% vs. 17.3%), and emmetropia (31.2% vs. 29.3%). There were no significant differences in the distribution of ametropia and biometric components between white and British Asian samples. Conclusion. The absence of a significant difference in refractive error and ocular components between white and British Asian students exposed to the same educational system is of interest. However, it is clear that a further study incorporating formal epidemiologic methods of analysis is required to address adequately the recent proposal that juvenile myopia develops principally from myopiagenic environments and is relatively independent of ethnicity.

Impacts of distributed generation on low-voltage distribution network protection

This paper reports work of a MEng student final year project, which looks in detail at the impacts that distributed generation can have on existing low-voltage distribution network protection systems. After a review of up-to-date protection issues, this paper will investigate several key issues that face distributed generation connections when it comes to network protection systems. These issues include, the blinding of protection systems, failure to automatically reclose, unintentional islanding, loss of mains power and the false tripping of feeders. Each of these problems impacts on protection systems in its own way. This study aims to review and investigate these problems via simulation demonstrations on one representative network to recommend solutions to practices.