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.

A systematic review of the psychobiological burden of informal caregiving for patients with dementia: focus on cognitive and biological markers of chronic stress

As the physiological impact of chronic stress is difficult to study in humans, naturalistic stressors are invaluable sources of information in this area. This review systematically evaluates the research literature examining biomarkers of chronic stress, including neurocognition, in informal dementia caregivers. We identified 151 papers for inclusion in the final review, including papers examining differences between caregivers and controls as well as interventions aimed at counteracting the biological burden of chronic caregiving stress. Results indicate that cortisol was increased in caregivers in a majority of studies examining this biomarker. There was mixed evidence for differences in epinephrine, norepinephrine and other cardiovascular markers. There was a high level of heterogeneity in immune system measures. Caregivers performed more poorly on attention and executive functioning tests. There was mixed evidence for memory performance. Interventions to reduce stress improved cognition but had mixed effects on cortisol. Risk of bias was generally low to moderate. Given the rising need for family caregivers worldwide, the implications of these findings can no longer be neglected.