In an increasingly data-driven world, artificial intelligence is expected to be a key tool for converting big data into tangible benefits and the healthcare domain is no exception to this. Machine learning aims to identify complex patterns in multi-dimensional data and use these uncovered patterns to classify new unseen cases or make data-driven predictions. In recent years, deep neural networks have shown to be capable of producing results that considerably exceed those of conventional machine learning methods for various classification and regression tasks. In this paper, we provide an accessible tutorial of the most important supervised machine learning concepts and methods, including deep learning, which are potentially the most relevant for the medical domain. We aim to take some of the mystery out of machine learning and depict how machine learning models can be useful for medical applications. Finally, this tutorial provides a few practical suggestions for how to properly design a machine learning model for a generic medical problem.
The need for reconfigurable, high power density, and low-cost configurations of DC-DC power electronic converters (PEC) in areas such as the transport electrification and the use of renewable energy has spread out the requirement to incorporate in a single circuit several topologies, which generally result in an increment of complexity about the modeling, control, and stability analyses. In this paper, a reconfigurable topology is presented which can be applied in alterative/changing power conversion scenarios and consists of a reconfigurable Buck, Boost, and Buck-Boost DC-DC converter (RBBC). A unified averaged model of the RBBC is obtained, a robust controller is designed through a polytopic representation, and a Lyapunov based switched stability analysis of the closed-loop system is presented. The reported RBBC provides a wide range of voltage operation, theoretically from −∞ to ∞ volts with a single power source. Robust stability, even under arbitrarily fast (bounded) parameter variations and reconfiguration changes, is reported including numerical and experimental results. The main advantages of the converter and the robust controller proposed are simple design, robustness against abrupt changes in the parameters, and low cost.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.