Accurate early diagnosis of COVID-19 viral pneumonia, primarily in asymptomatic people, is essential to reduce the spread of the disease, the burden on healthcare capacity, and the overall death rate. It is essential to design affordable and accessible solutions to distinguish pneumonia caused by COVID-19 from other types of pneumonia. In this work, we propose a reliable approach based on deep transfer learning that requires few computations and converges faster. Experimental results demonstrate that our proposed framework for transfer learning is a potential and effective approach to detect and diagnose types of pneumonia from chest X-ray images with a test accuracy of 94.0%.

The recombination dynamics of neutral donor bound excitons (D^oX: I₄, I_6/6a) and near band edge defect-related emission in solution grown ZnO nanorods are investigated using steady state and time-resolved photoluminescence (PL) measurements. The effects of annealing are also studied. Low temperature steady state PL shows a systematic removal of the I₄ line after annealing at 450 °C and the subsequent domination of I_6a in these PL spectra. Additionally, the time decay of the I₄, I_6/6a, free exciton (FX), and basal plane stacking fault-related (BSF) PL transitions are studied as a function of annealing temperature. For the various annealing temperatures studied, the PL decay is described by a bi-exponential profile with a fast component (contribution from the surface) and slow component (related to bulk recombination). The fast component dominates in the case of as-grown and low temperature annealed samples (anneal temperatures up to 300 °C), suggesting the presence of surface adsorbed impurities. For samples annealed above 400 °C, the effects of the surface are reduced. The sample annealed at 850 °C produced an overall enhancement of the crystal quality. The underlying mechanisms for the observed PL characteristics are discussed based on near surface band bending caused by surface impurities.