Diabetic Retinopathy (DR) is an eye condition that mainly affects individuals who have diabetes and is one of the important causes of blindness in adults. As the infection progresses, it may lead to permanent loss of vision. Diagnosing diabetic retinopathy manually with the help of an ophthalmologist has been a tedious and a very laborious procedure. This paper not only focuses on diabetic retinopathy detection but also on the analysis of different DR stages, which is performed with the help of Deep Learning (DL) and transfer learning algorithms. CNN, hybrid CNN with ResNet, hybrid CNN with DenseNet are used on a huge dataset with around 3662 train images to automatically detect which stage DR has progressed. Five DR stages, which are 0 (No DR), 1 (Mild DR), 2 (Moderate), 3 (Severe) and 4 (Proliferative DR) are processed in the proposed work. The patient’s eye images are fed as input to the model. The proposed deep learning architectures like CNN, hybrid CNN with ResNet, hybrid CNN with DenseNet 2.1 are used to extract the features of the eye for effective classification. The models achieved an accuracy of 96.22%, 93.18% and 75.61% respectively. The paper concludes with a comparative study of the CNN, hybrid CNN with ResNet, hybrid CNN with DenseNet architectures that highlights hybrid CNN with DenseNet as the perfect deep learning classification model for automated DR detection.

This paper provides a performance comparison of different pathfinding Algorithms used in video games. The Algorithms have been classified into three categories: informed, uninformed, and metaheuristic. Both a practical and a theoretical approach have been adopted in this paper. The practical approach involved the implementation of specific Algorithms such as Dijkstra’s, A-star, Breadth First Search, and Greedy Best First. The comparison of these Algorithms is based on different criteria including execution time, total number of iterations, shortest path length, and grid size. For the theoretical approach, information was collected from various papers to compare other Algorithms with the implemented ones. The Unity game engine was used in implementing the Algorithms. The environment used was a two-dimensional grid system.

In healthcare, the decision-making process is crucial, including COVID-19 prevention methods should include fast diagnostic methods. Computed tomography (CT) is used to diagnose COVID patients’ conditions. There is inherent variation in the texture of a CT image of COVID, much like the texture of a CT image of pneumonia. The process of diagnosing COVID images manually is difficult and challenging. Using low-resolution images and a small COVID dataset, the extraction of discriminant characteristics and fine-tuning of hyperparameters in classifiers provide challenges for computer-assisted diagnosis. In radiomics, quantitative image analysis is frequently used to evaluate the prognosis and diagnose diseases. This research tests an ML model built on GLCM features collected from chest CT images to screen for COVID-19. In this study, Support Vector Machines, K-nearest neighbors, Random Forest, and XGBoost classifiers are used together with LBGM. Tuning tests were used to regulate the hyperparameters of the model. With cross-validation, tenfold results were obtained. Random Forest and SVM were the best classification methods for GLCM features with an overall accuracy of 99.94%. The network’s performance was assessed in terms of sensitivity, accuracy, and specificity.