This study aims to propose a novel deep learning framework, i.e., efficient DenseNet, for identifying diabetic retinopathy severity levels in retinal images. Diabetic retinopathy is an eye condition that damages blood vessels in the retina. Detecting diabetic retinopathy at the early stage can avoid retinal detachment and effects leading to blindness in diabetic adults. A thin-layered efficient DenseNet model has been proposed with fewer training learnable parameters, leading to higher classification accuracy than the other deep learning models. The proposed deep learning framework for diabetic retinopathy severity level detection has an inbuilt automatic pre-processing module. Afterward, the efficient DenseNet model and classifier will provide data augmentation and higher-level feature extraction. The proposed efficient DenseNet framework is trained and tested using 13000 retinal fundus images within the diabetic retinopathy database and combined with the k-nearest neighbor classifier demonstrating the best classification accuracy of 98.40%.

No abstract

Structural aspects, such as grain size, pore size, and crack-free film morphology, of porous silicon (PS), etc., play a vital role in the sensing of volatile organic compounds (VOCs). This chapter discusses a novel method for sensing of VOCs using porous silicon coated with a layer of ZnO (PS-ZnO). It was noted that the sensing ability of the PS sensor has increased due to the transconductance mechanism, as a result of the coating of ZnO over PS. Initially, porous silicon is formed by electrochemical wet etching of silicon and by electrophoretic deposition (EPD), ZnO is coated over porous silicon. An increase in the selectivity is due to the increase in surface-to-volume ratio and uniformity in the pore structures. The thickness of ZnO layer can be tuned up to 25 nm by applying a DC voltage between the copper electrode and the conductive silicon substrate immersed in a suspension of ZnO quantum dots. The influence of quantum dot concentration on the final layer thickness was studied by X-ray diffraction (XRD). The change in resistance for ethanol was found to be 12.8-16 MΩ and 8-16 MΩ for methanol.