Obesity in People with Learning Disabilities: the impact of nurse led health screenings and health promotion activities

Background. Obesity appears to be more common among people with intellectual disabilities, with few studies focusing on achieving weight reduction. Aim. Firstly, to follow up people identified as overweight and obese following special health screening clinics and to determine the actions taken. Secondly, to evaluate the impact of health promotion classes on participants' weight loss. Methods. A clinic led by two learning disbaility nurses was held for all people aged 10 years and over (n=464) who attended special services within the area of one Health and Social Services Trust in Northern Ireland. In a second study, the nurses organised health promotion classes for 20 people over a 6 - 8 week period. Findings. The health screen identified 64% of adults and 26% of 10 - 19 year olds as being overweight or obese. Moreover, those aged 40 - 49 years who were obese had significantly higher levels of blood pressure. However, information obtained from a follow up questionnaire sent after 3 months suggested that of the 122 people identified for wiehgt reduciton, action had been taken for only 34% of them and only three were reported to have lost weight. The health promotion classes, however, led to a significant reduction in weight and body mass index scores. Conclusion. Health screening per se has limited impact on reducing obesity levels in this client group. Rather, health personnel such as general practitioners, nurses and health promotion staff need to work in partnership with service staff, carers and people with intellectual disabiltieis to create more active lifestyles.

Prediction- and simulation-error based perceptron training: Solution space analysis and a novel combined training scheme

Previous papers have noted the difficulty in obtaining neural models which are stable under simulation when trained using prediction-error-based methods. Here the differences between series-parallel and parallel identification structures for training neural models are investigated. The effect of the error surface shape on training convergence and simulation performance is analysed using a standard algorithm operating in both training modes. A combined series-parallel/parallel training scheme is proposed, aiming to provide a more effective means of obtaining accurate neural simulation models. Simulation examples show the combined scheme is advantageous in circumstances where the solution space is known or suspected to be complex. (c) 2006 Elsevier B.V. All rights reserved.

Improving neural network training solutions using regularisation

This paper describes the application of regularisation to the training of feedforward neural networks, as a means of improving the quality of solutions obtained. The basic principles of regularisation theory are outlined for both linear and nonlinear training and then extended to cover a new hybrid training algorithm for feedforward neural networks recently proposed by the authors. The concept of functional regularisation is also introduced and discussed in relation to MLP and RBF networks. The tendency for the hybrid training algorithm and many linear optimisation strategies to generate large magnitude weight solutions when applied to ill-conditioned neural paradigms is illustrated graphically and reasoned analytically. While such weight solutions do not generally result in poor fits, it is argued that they could be subject to numerical instability and are therefore undesirable. Using an illustrative example it is shown that, as well as being beneficial from a generalisation perspective, regularisation also provides a means for controlling the magnitude of solutions. (C) 2001 Elsevier Science B.V. All rights reserved.