RESUMEN
In this paper, a reflective microring resonator (MRR)-based microwave photonic (MWP) sensor incorporating a self-attention convolutional neural network (CNN) is presented. An MRR cascaded with an inverse-designed optical reflector is adopted as the sensor probe to allow for utilizing the responses generated from both the clockwise and counterclockwise resonant modes. Through the MWP interrogation, the cascaded resonant modes can be transformed into distinctive deep radio-frequency (RF) spectral notches under different modulator bias conditions. By using a self-attention assisted CNN processing to leverage both the local and global features of the RF spectra, a sensing model with improved accuracy can be established. As a proof of concept, the proposed scheme is experimentally demonstrated in temperature sensing. Even with a small dataset, the root-mean-square error of the sensing model established after training is achieved at 0.026°C, which shows a 10-fold improvement in sensing accuracy compared to that of the traditional linear fitting model.
