The healthcare industry is facing mounting pressure due to population increase, a higher prevalence of diseases, and an expanding volume of patient data collected by hospitals. While machine learning (ML) has been successfully used to develop data management systems, the enormous volume of sensitive medical data and privacy issues frequently limit its broad use. Furthermore, the absence of accurate and organized clinical data continues to be a key impediment to the efficient application of standard ML models in healthcare. To solve these challenges, Federated Learning (FL), an advanced method within the larger ML field, has emerged as a possible option. FL provides collaborative model training without the requirement to centralize data, ensuring anonymity while managing large datasets from multiple institutions. This paper provides a comprehensive review of recent research on Federated Learning

Efficient task scheduling in GPU-enabled cloud computing environments remains a critical challenge, as optimizing resource utilization, minimizing execution time, and ensuring fair task distribution are essential. This paper proposes a new approach integrating heuristic scheduling algorithms, such as Round Robin (RR) and Shortest Job First (SJF), with deep learning models to enhance scheduling efficiency. The proposed approach is applied to a real-world healthcare application-diabetes detection-where deep learning models trained on medical datasets, demonstrate how efficient task scheduling in GPU-enabled cloud environments improves the performance of predictive healthcare systems. The experimental results showed that the Round Robin (RR) algorithm provides the most balanced scheduling strategy due to its fairness in job distribution, and its integration with deep learning leads to significant

The rapid expansion of Internet of Things (IoT) technologies has introduced significant security issues requiring advanced Intrusion Detection Systems (IDS) to counteract changing threats. Constructing a robust system to prevent such attacks is critical. Prior work primarily relies on traditional feature selection techniques for training models, frequently disregarding the application of hybrid approaches. In this paper, a novel hybrid algorithm is proposed to improve the performance of machine learning (ML) and deep learning (DL) models in detecting attacks within anomaly intrusion detection systems. The hybrid algorithm leverages Fireworks and Grey Wolf optimization algorithms for feature selection, enabling the models to prioritize the most significant features during training, thereby improving predictive accuracy. The results revealed that the random forest outperformed other models achieving a recall of 99.75 …

This paper examines the performance of nine physics-based metaheuristic algorithms—Electromagnetism-Like Algorithm (EMLA), Fluid Search Algorithm (FSA), Gravitational Search Algorithm (GSA), and six hybrids (EMLA + FSA, EMLA + GSA, FSA + ELMA, FSA + GSA, GSA + EMLA, GSA + FSA) for vehicle pathfinding. Performance is evaluated using four metrics: travel distance, time, energy consumption, and number of obstacles encountered, along with a weighted multi-objective cost combining these metrics. Simulation results show that hybrid algorithms generally outperform their individual counterparts. The ranking of algorithms varies with the weighting of the metrics. The hybrids involving EMLA consistently achieve the best overall performance across grid sizes. FSA + EMLA performs best when minimizing distance. EMLA + GSA is most effective when time is the priority. EMLA + GSA also performs best when energy use and obstacle avoidance dominate. It is recommended to use the cases FSA + GSA or FSA + EMLA for energy-efficient and obstacle-aware navigation, GSA or GSA + EMLA for achieving global optimality on complex maps, and EMLA + FSA and FSA + EMLA for dynamic environments requiring high safety.