One of the most prevalent chronic conditions that can result in permanent vision loss is diabetic retinopathy (DR). Diabetic retinopathy occurs in five stages: no DR, and mild, moderate, severe, and proliferative DR. The early detection of DR is essential for preventing vision loss in diabetic patients. In this paper, we propose a method for the detection and classification of DR stages to determine whether patients are in any of the non-proliferative stages or in the proliferative stage. The hybrid approach based on image preprocessing and ensemble features is the foundation of the proposed classification method. We created a convolutional neural network (CNN) model from scratch for this study. Combining Local Binary Patterns (LBP) and deep learning features resulted in the creation of the ensemble features vector, which was then optimized using the Binary Dragonfly Algorithm (BDA) and the Sine Cosine Algorithm (SCA). Moreover, this optimized feature vector was fed to the machine learning classifiers. The SVM classifier achieved the highest classification accuracy of 98.85% on a publicly available dataset, i.e., Kaggle EyePACS. Rigorous testing and comparisons with state-of-the-art approaches in the literature indicate the effectiveness of the proposed methodology.
A novel resin-based nanocomposite-coated sand proppant is introduced to address the issue of proppant flowback in post-fracturing fluid flowback treatments and hydrocarbon production. Self-aggregation in the water environment is the most attractive aspect of these developed proppants. In this work, sand was sieve-coated with 0.1% multiwalled carbon nanotubes (MWCNTs) followed by optimized thin and uniform resin (polyurethane) spray coating in the concentration range of 2 to 10%. Quantitative and qualitative evaluations have been carried out to assess the self-aggregation capabilities of the proposed sand proppants where no flowback was witnessed at 4% polyurethane coating containing 0.1% MWCNTs. This applied resin incorporating MWCNT coating was characterized by field emission scanning electron microscopy, and energy-dispersive X-ray spectroscopy depicted the dispersed presence of MWCNTs into polyurethane resin corroborated by the presence of 38% elemental carbon on the sand substrate. Proppant crushing resistance tests were conducted, including proppant pack stress-strain response, compaction, and fines production. It was found that the proposed sand proppant decreased the proppant pack compaction by ∼25% compared to commonly used silica sand with the ability to withstand high closure stress as high as 55 MPa with less than 10 wt % fines production. The surface wettability was determined by the sessile drop method. The application of resin incorporating MWCNT coating layers changed the sand proppant wetting behavior to oil-wet with a contact angle of ∼124°. Thermogravimetric analyses revealed a significant increment in thermal stability, which reached up to 280 °C due to the addition of MWCNTs as reinforcing nanofillers.