Next‐Generation Application‐Based Artificial Intelligence in Modeling and Estimation for Ni/n‐GaAs/In Schottky Barrier Diode

Abstract

Herein, for Ni/n-GaAs/In Schottky barrier diode, experimental measurement, modeling, data generation from the model, and parameter estimation processes are simultaneously carried out. In the experimental step, Ni/n-GaAs/In Schottky barrier diodes are fabricated and annealed from the temperature of 200 °C up to 600 °C with 100 °C steps. Current values are recorded by applying voltage to the diode contacts from À1 V up to 0.5 V. In the modeling step, 1503 experimental current-voltage data are used for 19 different regression models. For Adaptive Neuro Fuzzy System (ANFIS), when root mean square error, mean square error, mean absolute error, and coefficient of determination are calculated 6.0341e-07, 3.6410e-13, 2.3873e-07, and 0.9999 for training, they are obtained 5.8904e-07, 3.4697e-13, 2.3083e-07, and 0.9999 for testing. In the estimation step, the values of electrical parameters are estimated by using Mayfly algorithm. Estimations are performed for all annealing temperatures. In addition, current-voltage data for the annealing temperature of 350 °C are produced by the ANFIS model. Thus, a new-generation artificial intelligence application, that includes measurement, modeling, and estimation for the Ni/n-GaAs/In Schottky barrier diode with varying annealing temperatures, is realized and a new perspective is provided to researchers and practitioners.