Retinal diseases impact a significant portion of the global population, yet specialized care is predominantly available in urban areas. We have developed AI-based methods for diagnosing various retinal conditions using fundus images to address this disparity. We aim to create a highly accurate automatic detection system to bridge the gap between patients and the limited number of retinal specialists. Critical challenges in multi-label classification tasks include limited sample sizes per label and imbalanced class distributions. To overcome these issues and enhance data diversity, we created three composite datasets (MRID) by aggregating multiple open source datasets. We developed hybrid models integrating deep Convolutional Neural Networks (CNNs), Transformer encoders, and ensemble architectures to classify retinal fundus images into 21 distinct labels. Our models demonstrated superior performance compared to baseline methods and the existing state-of-the-art model, with significant improvements in evaluation metrics. Performance was further enhanced by incorporating domain knowledge into the patch extraction step of Vision Transformers used in specific hybrid models. To address user trust and model interpretability, we implemented SHAP-based explanations and used these alongside evaluation metrics for comparative analysis of model performance across datasets. This research aims to advance retinal disease diagnosis, offering accessible healthcare solutions in underserved regions while ensuring accurate and comprehensive disease prediction.

Abstract Google app market captures the school of thought of users from every corner of the globe via ratings and text reviews, in a multilinguistic arena. The critique's viewpoint regarding an app is proportional to their satisfaction level. The potential information from the reviews cannot be extracted manually, due to its exponential growth. So, sentiment analysis, by machine learning and deep learning algorithms employing NLP, explicitly uncovers and interprets the emotions. This study performs the sentiment classification of the app reviews and identifies the university students' behavior toward the app market via exploratory analysis. We applied machine learning algorithms using the TP, TF, and TF‐IDF text representation scheme and evaluated its performance on Bagging, an ensemble learning method. We used word embedding, GloVe, on the deep learning paradigms. Our model was trained on Google app reviews and tested on students' app reviews (SAR). The various combinations of these algorithms were compared among each other using F‐score and accuracy and inferences were highlighted graphically. SVM, among other classifiers, gave fruitful accuracy (93.41%), F‐score (0.89) on bi‐gram + TF‐IDF scheme. Bagging enhanced the performance of LR and NB with accuracy 87.88% and 86.69% and F‐score 0.86 and 0.78 respectively. Overall, LSTM on Glove embedding recorded the highest accuracy (95.2%) and F‐score (0.88).

Federated learning (FL) is a distributed learning process where the model (weights and checkpoints) is transferred to the devices that posses data rather than the classical way of transferring and aggregating the data centrally. In this way, sensitive data does not leave the user devices. FL uses the FedAvg algorithm, which is trained in the iterative model averaging way, on the non-iid and unbalanced distributed data, without depending on the data quantity. Some issues with the FL are, 1) no scalability, as the model is iteratively trained over all the devices, which amplifies with device drops; 2) security and privacy trade-off of the learning process still not robust enough and 3) overall communication efficiency and the cost are higher. To mitigate these challenges we present Federated Learning and Privately Scaling (FLaPS) architecture, which improves scalability as well as the security and privacy of the system. The devices are grouped into clusters which further gives better privacy scaled turn around time to finish a round of training. Therefore, even if a device gets dropped in the middle of training, the whole process can be started again after a definite amount of time. The data and model both are communicated using differentially private reports with iterative shuffling which provides a better privacy-utility trade-off. We evaluated FLaPS on MNIST, CIFAR10, and TINY-IMAGENET-200 dataset using various CNN models. Experimental results prove FLaPS to be an improved, time and privacy scaled environment having better and comparable after-learning-parameters with respect to the central and FL models.

Smart Grid addresses the problem of existing power grid's increasing complexity, growing demand and requirement for greater reliability, through two-way communication and automated residential load control among others. These features also makes the Smart Grid a target for a number of cyber attacks. In the paper, we study the problem of rate alteration attack (RAA) through fabrication of price messages which induces changes in load profiles of individual users and eventually causes major alteration in the load profile of the entire network. Combining with cascading failure, it ends up with a highly damaging attack. We prove that the problem is NP-Complete and provide its inapproximability. We devise two approaches for the problem, former deals with maximizing failure of lines with the given resource and then extending the effect with cascading failure while the later takes cascading potential into account while choosing the lines to fail. To get more insight into the impact of RAA, we also extend our algorithms to maximize number of node failures. Empirical results on both IEEE Bus data and real network help us evaluate our approaches under various settings of grid parameters.