Modeling of boron nitride-based nanotube biological sensor using neural networks

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.