Power system parameters forecasting using Hilbert-Huang transform and machine learning

A novel hybrid data-driven approach is developed for forecasting power system parameters with the goal of increasing the efficiency of short-term forecasting studies for non-stationary time-series. The proposed approach is based on mode decomposition and a feature analysis of initial retrospective data using the Hilbert-Huang transform and machine learning algorithms. The random forests and gradient boosting trees learning techniques were examined. The decision tree techniques were used to rank the importance of variables employed in the forecasting models. The Mean Decrease Gini index is employed as an impurity function. The resulting hybrid forecasting models employ the radial basis function neural network and support vector regression. A part from introduction and references the paper is organized as follows. The second section presents the background and the review of several approaches for short-term forecasting of power system parameters. In the third section a hybrid machine learningbased algorithm using Hilbert-Huang transform is developed for short-term forecasting of power system parameters. Fourth section describes the decision tree learning algorithms used for the issue of variables importance. Finally in section six the experimental results in the following electric power problems are presented: active power flow forecasting, electricity price forecasting and for the wind speed and direction forecasting.

Novel insights into the inflammatory basis of gastrointestinal disease

It has become clear that inflammation is beneficial to man, there are situations though that the inflammatory response causes damage to the host that is harmful to health. When the inflammatory response fails or is too strong, the health of the host is damaged and disease can occur. The implication of intestinal disease caused by an ineffective immune response is of great social and economic burden to society. The overarching purpose of this thesis is to assess inflammatory signalling targets associated with immune mediated disorders such as IBD, IBS and inflammatory liver disease. By assessing these targets and modifying their function I hope to contribute and expand further the pre-existing information on these disorders and improve the therapeutic interventions available in these debilitating conditions. I will assess the role of inflammation in disorders of the GI tract and liver IBD, IBS, hepatic inflammatory injury and furthermore, I will use pharmaceutical agents to activate and suppress components of the immune system. I will examine the inflammatory response in experimental models of disease for IBD and liver injury, I will attempt to alter these pathways using pharmaceutical intervention to delineate the disease causing mechanism that may lead to clinically relevant therapeutic interventions. In regards to IBS, I will attempt to improve the existing knowledge that exists in relation to the pathogenesis of this functional bowel disorder. I will attempt to define a mechanism by which the low grade mucosal inflammation that has been demonstrated by others arises and what this inflammation is induced by. The overall aim of this thesis is to attempt to further understand the mechanisms behind GI and liver disease. Looking at the inflammatory response in these specific conditions and how they can be altered may lead to exciting new therapies for inflammatory conditions in the gastrointestinal tract.