Analysis focused on pivotal points where behaviour changed from exclusive breastfeeding to introducing formula, stopping breastfeeding or introducing solids. This enabled us to identify processes that decelerate or accelerate behaviour change and understand resolution processes afterwards.\n\nResults: The dominant goal motivating behaviour change was family wellbeing, check details rather than exclusive breastfeeding. Rather than one type of significant other emerging as the key influence, there was a complex interplay between the self-baby dyad, significant others, situations
and personal or vicarious feeding history. Following behaviour change women turned to those most likely to confirm or resolve their decisions and maintain their confidence as mothers.\n\nConclusions: Applying ecological models of behaviour would enable health service organisation, practice, policy and research to focus on enhancing family efficacy and wellbeing, improving family-centred communication and increasing opportunities for health professionals to be a constructive influence around pivotal points when feeding behaviour changes. A paradigm shift is recommended away from the dominant
approach of support and education of individual women towards a more holistic, family-centred narrative approach, whilst acknowledging BAY 63-2521 that breastfeeding is a practical skill that women and babies have to learn.”
“Gene expression this website data usually contain a large number of genes but a small number of samples. Feature selection for gene expression data aims at finding a set of genes that best discriminate biological samples
of different types. Using machine learning techniques, traditional gene selection based on empirical mutual information suffers the data sparseness issue due to the small number of samples. To overcome the sparseness issue, we propose a model-based approach to estimate the entropy of class variables on the model, instead of on the data themselves. Here, we use multivariate normal distributions to fit the data, because multivariate normal distributions have maximum entropy among all real-valued distributions with a specified mean and standard deviation and are widely used to approximate various distributions. Given that the data follow a multivariate normal distribution, since the conditional distribution of class variables given the selected features is a normal distribution, its entropy can be computed with the log-determinant of its covariance matrix. Because of the large number of genes, the computation of all possible log-determinants is not efficient. We propose several algorithms to largely reduce the computational cost.