No abstract

No abstract

The Internet-of-things (IoT) plays a significant role in healthcare monitoring, where the IoT Cloud integration introduces many new opportunities for real-time remote monitoring of the patient. Task scheduling is one of the major challenges in cloud environment. Solving that problem reduces delay, missed tasks, and failure rate, and increases the guarantee ratio. This paper proposes a new task scheduling and allocation technique: Prioritized Sorted Task-Based Allocation (PSTBA) for healthcare monitoring implemented in IoT cloud-based architecture. The proposed technique selects the best virtual machine to execute the health task considering multiple factors such as; the wait time of the VM and the Expected processing time (EPT) of the task as well as its criticality. An extensive simulation study is conducted using the CloudSim simulator to evaluate the performance of the proposed technique. The proposed technique is compared to the Sorted Task-Based Allocation (STBA) and FCFS techniques and it reduces the delay by 13.7% and 80.2%, the failure rate by 21% and 37.5%, and increases the guarantee ratio by 2.2% and 4.5% compared to STBA and FCFS, respectively. In analyzing the critical health tasks, the proposed PSTBA has also reduced the critical health tasks missed ratio by 15.7% and 50.9% compared to STBA and FCFS, respectively. The simulation results demonstrate that PSTBA is more effective than the STBA and FCFS techniques in terms of delay, missed critical tasks, guarantee ratio, and failure rate.

Flight delay has been the fiendish problem to the world's aviation industry, so there is very important significance to research for computer system predicting flight delay propagation. Extraction of hidden information from large datasets of raw data could be one of the ways for building predictive model. This paper describes the application of classification techniques for analysing the Flight delay pattern in Egypt Airline's Flight dataset. In this work, four decision tree classifiers were evaluated and results show that the REPTree have the best accuracy 80.3% with respect to Forest, Stump and J48. However, four rules based classifiers were compared and results show that PART provides best accuracy among studied rule-based classifiers with accuracy of 83.1%. By analysing running time for all classifiers, the current work concluded that REPtree is the most efficient classifier with respect to accuracy and running time. Also, the current work is extended to apply of Apriori association technique to extract some important information about flight delay. Association rules are presented and association technique is evaluated.

Computer modelling and simulation methods are very important and play a critical role in the mitigation and response to the ongoing COVID-19 pandemic. In this study, we propose a computational modeling technique based on Cellular Automata (CA) with realistic proposed rules. The rules are designed to simulate the propagation of COVID-19 disease through a bounded area. Our proposed CA rules are novel in many respects. For on, the classification of neighbors to nearest neighbors and range of neighbors based on cellular layers is explained. Moreover, the concepts of time generation and access time are deployed for the first time to model the propagation of the disease over time in this work. Further details of the proposed model including the topology of the defined area, the initial states of the cells and four-layer transfer mechanism are explained as well. This work may be considered a criterion of spreading for COVID-19 from point source in a defined population area. The results of the proposed algorithm represent the percentage of the population whose infectious status is described by different cellular state objects after a defined generation time. The results are compared under different circumstances and analyzed equanimity.