In this paper entropy based methods are compared and used to measure structural diversity of an ensemble of 21 classifiers. This measure is mostly applied in ecology, whereby species counts are used as a measure of diversity. The measures used were Shannon entropy, Simpsons and the Berger Parker diversity indexes. As the diversity indexes increased so did the accuracy of the ensemble. An ensemble dominated by classifiers with the same structure produced poor accuracy. Uncertainty rule from information theory was also used to further define diversity. Genetic algorithms were used to find the optimal ensemble by using the diversity indices as the cost function. The method of voting was used to aggregate the decisions.I.
This paper presents a novel single-phase (SP) active-neutral point clamped (ANPC) five-level bidirectional converter (FLBC) for enhancing the power quality (PQ) during the grid-to-vehicle (G2V) and vehicle-to-grid (V2G) operation of an electric vehicle (EV) charger connected in series. This EV charger is based on a dual-active half-bridge DC-DC converter (DAHBC) with a high frequency isolation transformer. Unlike the comparable ANPC topologies found in literature, the proposed one has two more switches, i.e., ten instead of eight. However, with the addition of these components, the proposed multilevel converter not only becomes capable of properly balancing the voltage of the DC-link split capacitors under various step-changing conditions but it achieves a better efficiency, a lower stress of the switching devices and a more even distribution of the power losses. The resulting grid-tied ANPC-SPFLBC and DAHBC are accurately controlled with a cascaded control strategy and a single-phase shift (SPS) control technique, respectively. The simulation results obtained with MATLAB-SimPowerSystems as well as the experimental results obtained in laboratory validate the proposed ANPC-SPFLBC for a set of exhaustive tests in both V2G and G2V modes. A detailed power quality analysis carried out with a Fluke 43B alike demonstrates the good performance of the proposed topology.
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.