Search

Nowadays the bio-synthesized silver nanoparticles have been gained increasing research attention due to their non-toxic, inexpensive, and eco-friendly nature. In the present research, the silver nanoparticle was bio-synthesized using Garcinia gummi-guttaleaf extract as a reducing agent. The functional groups in plant extract which is responsible for the reduction of silver were assessed by FTIR (Fourier transform infrared spectroscopy) and the formation, stability of the particles were characterized by UV–visible spectroscopy. TEM (transmission electron microscopy) and XRD (X-ray diffraction) patterns were assessed for the size and shape of silver nanoparticles (Ag-NPs). The obtained nanoparticle was mixed with epoxy; electron spin coating technique was employed and tested the corrosion inhibition performance by EIS (electrochemical impedance spectroscopy), and PDP (potentiodynamic polarization). A protective barrier was formed over the mild steel by epoxy/Ag-NP composite and PDP results show that epoxy/Ag-NP composite can inhibit both cathodic and anodic reactions. The surface morphology of the metal sample was evaluated by FESEM (field emission scanning electron microscopy) and surface roughness by AFM (atomic force microscopy). The results indicate that Ag-NPs can restrict the degradation of material to a great extent.

Age-related Macular Degeneration (AMD) is the prime reason for vision impairment observed in major countries worldwide. Hence an accurate early detection of the disease is vital for more research in this area. Also, having a thorough eye diagnosis to detect AMD is a complex job. This paper introduces a Directed Acyclic Graph (DAG) structure-based Convolutional Neural network (CNN) architecture to better classify Dry or Wet AMD. The DAG architecture can combine features from multiple layers to provide better results. The DAG model also has the capacity to learn multi-level visual properties to increase classification accuracy. Fine tuning of DAG-based CNN model helps in improving the performance of the network. The training and testing of the proposed model are carried out with the Mendeley data set and achieved an accuracy of 99.2% with an AUC value of 0.9999. The proposed model also obtains better results for other parameters such as precision, recall and F1-score. Performance of the proposed network is also compared to that of the related works performed on the same data set. This shows ability of the proposed method to grade AMD images to help early detection of the disease. The model also performs computationally efficient for real-time applications as it does the classification process with few learnable parameters and fewer Floating-Point Operations (FLOPs).