Design and Simulation of Plasmonic Sensor and Optimization Using Random Forest Regression

This study introduces a refractive index sensor based on a metal-insulator-metal (MIM) waveguide integrated with a plus-shaped resonator. Spectral analysis reveals outstanding sensitivity, achieving a value of ۶۸۰ nm/RIU. To reduce computational cost and design time, a random forest regression model was employed to predict the resonant wavelength of the structure. The results indicate that the model developed using the random forest algorithm to predict the resonant wavelength of the structure yields a low error of approximately RMSE=۰.۰۲۳۴. This small value reflects the high accuracy of our model. This structure demonstrates strong potential for further development as a biosensor.

کلیدواژه ها:

Prediction ، Machine Learning ، MIM Waveguide ، FDTD ، Biosensor