ABSTRACT
Background: One of the negative effects of the COVID-19 illness, which has affected people all across the world, is Alzheimer's disease. Oblivion after COVID-19 has created a variety of issues for many people. Predicting this issue in COVID-19 patients can considerably lessen the severity of the problem. Methods: Alzheimer's disease was predicted in Iranian persons with COVID-19 in using three algorithms: Nave Bayes, Random Forest, and KNN. Data collected by private questioner from hospitals of Tehran Province, Iran, during Oct 2020 to Sep 2021. For ML models, performance is quantified using measures such as Precision, Recall, Accuracy, and F1-score. Results: The Nave Bayes, Random Forest algorithm has a prediction accuracy of higher than 80%. The predicted accuracy of the random forest algorithm was higher than the other two algorithms. Conclusion: The Random Forest algorithm outperformed the other two algorithms in predicting Alzheimer's disease in persons using COVID-19. The findings of this study could help persons with COVID-19 avoid Alzheimer's problems.
ABSTRACT
Along with the advancement of online platforms and significant growth in Internet usage, various threats and cyber-attacks have been emerging and become more complicated and perilous in a day-by-day base. Anomaly-based intrusion detection systems (AIDSs) are lucrative techniques for dealing with cybercrimes. As a relief, AIDS can be equipped with artificial intelligence techniques to validate traffic contents and tackle diverse illicit activities. A variety of methods have been proposed in the literature in recent years. Nevertheless, several important challenges like high false alarm rates, antiquated datasets, imbalanced data, insufficient preprocessing, lack of optimal feature subset, and low detection accuracy in different types of attacks have still remained to be solved. In order to alleviate these shortcomings, in this research a novel intrusion detection system that efficiently detects various types of attacks is proposed. In preprocessing, Smote-Tomek link algorithm is utilized to create balanced classes and produce a standard CICIDS dataset. The proposed system is based on gray wolf and Hunger Games Search (HGS) meta-heuristic algorithms to select feature subsets and detect different attacks such as distributed denial of services, Brute force, Infiltration, Botnet, and Port Scan. Also, to improve exploration and exploitation and boost the convergence speed, genetic algorithm operators are combined with standard algorithms. Using the proposed feature selection technique, more than 80 percent of irrelevant features are removed from the dataset. The behavior of the network is modeled using nonlinear quadratic regression and optimized utilizing the proposed hybrid HGS algorithm. The results show the superior performance of the hybrid algorithm of HGS compared to the baseline algorithms and the well-known research. As shown in the analogy, the proposed model obtained an average test accuracy rate of 99.17%, which has better performance than the baseline algorithm with 94.61% average accuracy.
ABSTRACT
The COVID-19 pandemic brought about many critical issues in all aspects such as economy, environment, health, and lifestyle, but people always try to find some response to crisis in different conditions. E-learning is defined as an elaborate response aiming at continuing education during the COVID-19 pandemic. It seems that developed countries have established and adjusted their technological infrastructures for the transition from a face-to-face education to a digital one. In contrast, developing countries were not completely prepared for this transition. Improper and deficient technological and practical fundamentals have been causing problems for all students, instructors, and other involved individuals. Therefore, we reviewed the challenges that have arisen from e-learning during the COVID-19 outbreak in different parts of tertiary education focusing on underprivileged countries.
