Developing a simple and efficient attack detection system for ensuring the security of cloud systems against cyberthreats is a crucial and demanding process in the present time. In traditional work, various machine-learning-based detection methodologies have been developed for securing the cloud network. However, those methodologies face the complications of overfitting, complex system design, difficulty understanding, and higher time consumption. Hence, the proposed work contributes to the design and development of an effective security model for detecting cyberthreats from cloud systems. The proposed framework encompasses the modules of preprocessing and normalization, feature extraction, optimization, and prediction. An improved principal component analysis (IPCA) model is used to extract the relevant features from the normalized dataset. Then, a hybrid grasshopper–crow search optimization (GSCSO) is employed to choose the relevant features for training and testing operations. Finally, an isolated heuristic neural network (IHNN) algorithm is used to predict whether the data flow is normal or intrusive. Popular and publicly available datasets such as NSL-KDD, BoT-IoT, KDD Cup’99, and CICIDS 2017 are used for implementing the detection system. For validation, the different performance indicators, such as detection accuracy (AC) and F1-score, are measured and compared with the proposed GSCSO-IHNN system. On average, the GSCO-IHNN system achieved 99.5% ACC and 0.999 F1 scores on these datasets. The results of the performance study show that the GSCSO-IHNN method outperforms the other security models. Ultimately, this research strives to contribute to the ongoing efforts to fortify the security of cloud systems, making them resilient against cyber threats more simply and efficiently.

Cloud organizations now face a challenge in managing the enormous volume of data and various resources in the cloud due to the rapid growth of the virtualized environment with many service users, ranging from small business owners to large corporations. The performance of cloud computing may suffer from ineffective resource management. As a result, resources must be distributed fairly among various stakeholders without sacrificing the organization’s profitability or the satisfaction of its customers. A customer’s request cannot be put on hold indefinitely just because the necessary resources are not available on the board. Therefore, a novel cloud resource allocation model incorporating security management is developed in this paper. Here, the Deep Linear Transition Network (DLTN) mechanism is developed for effectively allocating resources to cloud systems. Then, an Adaptive Mongoose Optimization Algorithm (AMOA) is deployed to compute the beamforming solution for reward prediction, which supports the process of resource allocation. Moreover, the Logic Overhead Security Protocol (LOSP) is implemented to ensure secured resource management in the cloud system, where Burrows–Abadi–Needham (BAN) logic is used to predict the agreement logic. During the results analysis, the performance of the proposed DLTN-LOSP model is validated and compared using different metrics such as makespan, processing time, and utilization rate. For system validation and testing, 100 to 500 resources are used in this study, and the results achieved a make-up of 2.3% and a utilization rate of 13 percent. Moreover, the obtained results confirm the superiority of the proposed framework, with better performance outcomes.

Agriculture is crucial in determining land availability and economic productivity in developing countries, where most of the population relies on this sector. Even though plant diseases are common, they are primarily identified in agriculture. Automated disease detection technology is necessary for the timely identification of plant diseases. Detecting plant diseases is crucial in avoiding loss of production and enhancing agricultural produce quality. Lack of proper attention in this area can cause severe damage to plants, resulting in loss of product quality, quantity, or productivity. Diagnosing plant diseases can be a complex process that requires specialized knowledge and hands-on attention. The previous methods didn't find accurate disease in the plant leaves. To combat this problem, this paper presents deep learning (DL) based Assessment-based Convolutional Neural Network (A-CNN) method to detect healthy and unhealthy plant leaves. We first collect the plant image dataset from a Kaggle repository. To enhance the quality of plant images and achieve a smoother appearance, an Optimized Gaussian Wiener Filter (OGWF) can be utilized for image pre-processing. Additionally, the edges of plant leaves can be detected by implementing Sobel and Canny operators. Then we use Otsu's Threshold Fragment (OTF) algorithm to segment the disease-affected region. Additionally, the Spatial Grey-Level Dependence Matrix (SGLDM) algorithm is utilized to identify the most suitable feature of the impacted leaf. The A-CNN method is employed to detect healthy and unhealthy plant leaves accurately. The proposed simulation results have shown higher accuracy, sensitivity, and specificity in predicting plant diseases than other methods.