Diabetes affects 40–45% of Diabetic Retinopathy (DR) patients in the US. Early detection of DR may prevent or postpone vision deterioration, but it is difficult since the disorder often manifests with few symptoms until it is too late to treat. Clinically, DR is routinely treated using fundus images, with an estimated 200 million cases worldwide and over 400,000 deaths each year. A great deal of progress has been made by applying machine learning algorithms to the fundus images. As a result, image classification and detection have become reliable techniques for detecting the severity of diabetic retinopathy. Convolutional Neural Networks (CNNs) play a crucial role in the image classification and detection process by capturing various images' details, enabling a fast and efficient method for detecting diabetic retinopathy. CNN pre-trained models such as ResNet50, Inception V3,and EfficientNetB7 have substantially improved their performance in the ImageNet Large-Scale Visual Recognition Competition. In addition, these pre-trained models are more precise and inexpensive to train because of the shorter connections between their input and output layers. This work proposes an approach for image classification that ensembles three pre-trained models, namely: EfficientNetB7, ResNet50V2, and Inception V3,to perform the classification of the diabetic retinopathy subtypes. Our proposed method achieves 97.43 % accuracy by adjusting the weights of the pre-trained models in detecting D R using the EyePacs Dataset.

Fault localization is one of the most important activities in software debugging.Among various fault localization techniques, mutation-based fault localization (MBFL) has been commonly studied with its promising performance.However, MBFL should be improved further by incorporating more useful program information.In this paper, we propose MuCatFL, a novel and lightweight technique for better MBFL via mutant categorization.In details, after executing the original test suite against all generated mutants, we categorize the mutants into two groups, positive mutants and negative mutants, to rank the tied program elements.We evaluate MuCatFL by performing an extensive study on 395 real software faults from the widely used benchmark Defects4J.The experimental results show that MuCatFL can significantly outperform MBFL techniques (e.g., localizing 138 faults within the Top-1 position on method-level, 43.75% more than traditional Metallaxis technique).We also investigate that only positive mutants can contribute to the effectiveness of MBFL.Our findings can also provide guidance for the strategies to reduce the execution cost of MBFL.