In this research, we proposed a novel deep residual convolutional neural network with 197 layers (ResNet197) for the detection of various plant leaf diseases. Six blocks of layers were used to develop ResNet197. ResNet197 was trained and tested using a combined plant leaf disease image dataset. Scaling, cropping, flipping, padding, rotation, affine transformation, saturation, and hue transformation techniques were used to create the augmentation data of the plant leaf disease image dataset. The dataset consisted of 103 diseased and healthy image classes of 22 plants and 154,500 images of healthy and diseased plant leaves. The evolutionary search technique was used to optimise the layers and hyperparameter values of ResNet197. ResNet197 was trained on the combined plant leaf disease image dataset using a graphics processing unit (GPU) environment for 1000 epochs. It produced a 99.58 percentage average classification accuracy on the test dataset. The experimental results were superior to existing ResNet architectures and recent transfer learning techniques.

Diabetic retinopathy (DR) and adult vitelliform macular dystrophy (AVMD) may cause significant vision impairment or blindness. Prompt diagnosis is essential for patient health. Photographic ophthalmoscopy checks retinal health quickly, painlessly, and easily. It is a frequent eye test. Ophthalmoscopy images of these two illnesses are challenging to analyse since early indications are typically absent. We propose a deep learning strategy called ActiveLearn to address these concerns. This approach relies heavily on the ActiveLearn Transformer as its central structure. Furthermore, transfer learning strategies that are able to strengthen the low-level features of the model and data augmentation strategies to balance the data are incorporated owing to the peculiarities of medical pictures, such as their limited quantity and generally rigid structure. On the benchmark dataset, the suggested technique is shown to perform better than state-of-the-art methods in both binary and multiclass accuracy classification tasks with scores of 97.9% and 97.1%, respectively.

This study thoroughly examines Advanced Persistent Threats APTs by investigating defensive strategies, detection mechanisms, and response tactics against these evolving cyber threats. As organizations confront increasingly sophisticated adversaries, understanding and strengthening defenses against APTs become crucial. The analysis begins with a breakdown of key defensive strategies, such as network segmentation and endpoint protection, and explores advanced detection mechanisms like anomaly detection and machine learning algorithms. Effective response tactics, including incident response frameworks and threat hunting methodologies, are also scrutinized. Challenges in countering APTs, such as attribution difficulties and the dynamic nature of their tactics, are addressed. The study investigates emerging trends, such as artificial intelligence integration and threat hunting automation, as potential avenues for enhanced defensive capabilities. By providing comprehensive insights and identifying research opportunities, this study aims to empower cybersecurity practitioners, researchers, and policymakers in developing resilient strategies against APTs.

Large-scale distributed systems have the advantages of high processing speeds and large communication bandwidths over the network. The processing of huge real-world data within a time constraint becomes tricky, due to the complexity of data parallel task scheduling in a time constrained environment. This paper proposes data parallel task scheduling in cloud to address the minimization of cost and time constraints. By running concurrent executions of tasks on multi-core cloud resources, the number of parallel executions could be increased correspondingly, thereby, finishing the task within the deadline is possible. A mathematical model is developed here to minimize the operational cost of data parallel tasks by feasibly assigning a load to each virtual machine in the cloud data center. This work experiments with a machine learning model that is replicated on the multi-core cloud heterogeneous resources to execute different input data concurrently to accomplish distributive learning. The outcome of concurrent execution of data-intensive tasks on different parts of the input dataset gives better solutions in terms of processing the task by the deadline at optimized cost.