In this study, an ultrasensitive biological boron nitride-based nanotube (Bio-BNNT) sensor is modeled and investigated by means of neural approach. The type of configuration studied is a cantilevered BNNT resonator sensor with an attached mass at the tip. The idea behind our resonator sensor is based on the determination of the natural BNNT frequency shift induced by added biological mass. A multilayer perceptron neural network is used to predict the attached mass, which causes a variation of the BNNTs frequency shift with different diameters and lengths. This model is implemented in the form of a component in the ORCAD-PSPICE electric simulator library. The component should reproduce faithfully the biological sensor behavior. Moreover, we have developed an inverse model called intelligent sensor in order to remove the nonlinearity response provided by the sensor. The association of this ANN-based corrector has brought significant improvement for high sensing performance.

Iron thin films were deposited on glass substrates using RF magnetron sputtering and their optimal deposition conditions were determined. The structure properties were analyzed using x-ray diffraction (XRD) and their magnetic hysteresis loops were obtained by Vibrating Sample Magnetometer (VSM) at room temperature. In this situation, the magnetic field is either parallel or perpendicular to the substrate plane. The main contribution of this work is to characterize the thin layers and present a mathematical model that can get best fit of the characteristics B(H). By using Preisach model, good agreement was obtained between theoretical and experimental results in both cases.

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.