Neural network based equalizers can easily compensate channel impairments; such additive noise and inter symbol interference (ISI). The authors present a new approach to improve the training efficiency of the multilayer perceptron (MLP) based equalizer. Their improvement consists on modifying the back propagation (BP) algorithm, by adapting the activation function in addition to the other parameters of the MLP structure. The authors report on experiment results evaluating the performance of the proposed approach namely the back propagation with adaptive activation function (BPAAF) next to the BP algorithm. To further prove its effectiveness, the proposed approach is also compared beside a so known nonlinear equalizer explicitly the multilayer perceptron with decision feedback equalizer MLPDFE. The authors consider various performance measures specifically: signal resorted quality, lower steady state MSE reached and minimum bit error rate (BER) achieved, where nonlinear channel equalization problems are employed.

In this paper, a new TiO2-based UV photodetector including back triangular texturization morphology has been investigated numerically using accurate solutions of Maxwell’s equations. A quantitative study of the device optical parameters like responsivity, sensitivity, detectivity, derived current capability and signal to noise ratio have been carried out in order to review the device overall optical performance for UV optical communication applications. Based on the obtained results, we have found that the device performance figures-of-merit (FoMs) governing the optical behavior is strongly improved as compared to its conventional planar counterpart, where the proposed design offers superior photocurrent, higher responsivity and sensitivity in comparison with those provided by the planar structure. These results led us to suggest the optimization of the proposed morphology using genetic algorithm (GA), in order to improve the electric field confinement and UV-light trapping in TiO2 absorber layer, where excellent ability has been recorded in enhancing the device absorbance. In this context, photodetector with optimized triangular texturization exhibits a 432% improvement, in term of responsivity, over planar structures and 120% improvement over the textured device without optimization. Thus, these encouraging results make the proposed device an extremely efficient candidate for high performance optoelectronic applications.

In this paper, we propose a new optically controlled field effect transistor, OC-FET, based on both surface texturization and graded gate doping engineering. The proposed design consists of a gate with both graded doping and surface texturization aspects to ensure high efficient light absorption and low dark current, respectively. Moreover, using an analytical investigation, an overall performance comparison of the proposed dual texturized gate (DTG) OC-FET device and conventional OC-FETs has been studied in order to confirm the enhanced optical and electrical performance of the proposed design in terms of increased photoresponsivity (R), optical gain (Formula presented.) ratio, drain current driving capability (Formula presented.) and high signal to noise ratio. Simulations show very good agreement between the results of the developed analytical models and those of TCAD software for wide range of design parameters. The developed analytical models are used to formulate the objective functions to optimize the device performance using a multi-objective genetic algorithm (MOGA). The proposed MOGA-based approach is used to search the optimal design parameters, for which the electrical and optical device performance is maximized. The obtained superior electrical performance suggests that our DTG OC-FET offers great promise as optical sensors and transducers for CMOS-based optical communications.

The objective of this paper is to develop a novel combined MPPT-pitch angle robust control system of a variable-speed wind turbine. The direct driven wind turbine using the permanent magnet synchronous generator (PMSG) is connected to the grid by means of fully controlled frequency converters, which consist of a pulse width-modulation PWM rectifier connected to an inverter via an intermediate DC bus. In order to maximize the exploited wind power and benefit from a wide range of the wind speed, a novel combined maximum power point tracking (MPPT)-Pitch angle control is developed using only one low cost circuit based on Neural Network (ANN), which allows the PMSG to operate at an optimal speed to extract maximum power when this last is lower than nominal power, and limit the extra power. To achieve feeding the grid with high-power and good quality of electrical energy, the inverter is controlled by (PWM) in a way to deliver only the active power into the grid, and thus to obtain a unit power factor. DC-link voltage is also controlled by the inverter. The dynamic and steady-state performances of the wind energy conversion system (WECS) are carried by using Matlab Simulink.