ABSTRACT
In recent years, spread of infection due to virus became whirlwind and creates threat to life in multiple ways. Hence there is in need to sense virus as early as possible in easier way. In this work we propose a multi virus sensor which senses IBV, H5N1, H9N2, and H4N6.Very low refractive index is sensed in this work with increased birefringence due to its elliptical core, where the samples are infiltrated. Numerical analysis is done using Finite Element Method. Among these 4 viruses, IBV has higher sensitivity, birefringence and lower confinement loss which belong to COVID family.88.56% of sensitivity is obtained at 1550nm with low confinement loss. © 2022 IEEE.
ABSTRACT
In this study, we analyse the impact of the Universal Adversarial Perturbation Attack on the Inception-ResNet-v1 model using the lung CT scan dataset for COVID-19 classification and the retinal OCT scan dataset for Diabetic Macular Edema (DME) classification. The effectiveness of adversarial retraining as a suitable defense mechanism against this attack is examined. This study is categorised into three sections-The implementation of the Inception-ResNet-v1 model, the effect of the attack and the adversarial retraining. © 2023 IEEE.