ABSTRACT
Cloud infrastructure enables individuals, organizations, and enterprises to offer scalable and elastic resources to support business operations remotely. The demand for digital transformation encourages communities and technical professionals to adopt cloud computing and automation platforms for facilitating their resource capacity, including operating systems, networks, and applications. Of cloud-based applications for social good, virtual education platforms play an important role to re-duce the cost and effort for trainees and trainers during practical courses, especially in the context of pandemics such as Covid-19. Nonetheless, the task of setting up practical environments with virtual machines, network elements, and software programs is the burden of the system that hosts many training courses with numerous trainees or resources. Hence, this research provides the mechanism for defining and automatically implementing the hands-on laboratory environments for information technology (IT) training. Specifically, we design and implement a concurrent scheme and local repository for deploying multiple environments with high performance in large virtual classrooms. The total time to finish environmental settings for learners is kept stable to meet the satisfaction of users in case of the remarkable growth in the number of environments and trainees. © 2022 IEEE.
ABSTRACT
The COVID-19 pandemic has caused changes in terms of traditional teaching globally. In Kosovo context, the Universities have found the transition from teaching in class to online classes quite challenging. This study investigates the transformation process from in-campus classes to online classes from the technical perspective within five Higher Education Institutions (HEI) in Kosovo. The data was collected using the qualitative methods and its analysis followed the 3C Litchman approach. The results show that each of the Universities followed a different approach by using either their limited premises infrastructure or using additional cloud infrastructure. © 2021 IEEE.
ABSTRACT
Currently, the most effective way to counteract COVID-19 is to slow its spread through personal distancing, hand washing and the use of personal protective equipment. Vaccination processes of citizens are becoming widespread. At the same time, information technology will be able to help slow down the spread of COVID-19 by early detection, prediction and monitoring of new cases. This paper provides an overview of current research on the selection and processing of COVID-19 data. The role and location of IoT devices, communication networks and cloud infrastructure for the selection and processing of COVID-19 data are described. Based on the analysis of IoT-platforms for detection and monitoring of COVID-19, the structure of the information technology platform was formed. There are included data collection tools, primary networks, Internet, cloud infrastructure, data presentation tools. The architecture of the information technology platform for the selection and processing of COVID-19 data is proposed. A description of the process of collecting and analytical processing of COVID-19 information using machine learning algorithms is given. The model of the information technology platform classes structure for the selection and processing of COVID-19 data is considered. That contains more than 50 classes to describe more than 120 characteristics of information entities. The processes of selection and aggregation of COVID-19 data and integration of analytical processing tools based on machine learning algorithms into the information technology platform are described. © 2021 IEEE.
ABSTRACT
As the world responded to the Coronavirus Disease 2019 (COVID-19) pandemic in 2020, digital operations became more important, and people started to depend on new initiatives such as the cloud and mobile infrastructure. Consequently, the number of cyberattacks such as phishing has increased. Phishing websites can be detected using machine learning by classifying the websites into legitimate or illegitimate websites. The purpose of the study is to conduct a mini-review of the existing techniques and implement experiments to detect whether a website is malicious or not. The dataset consists of 11,055 observations and 32 variables. Three supervised learning models are implemented in this study: Decision Tree, K-Nearest Neighbour (KNN), and Random Forest. The three algorithms are chosen because it provides a better understanding and more suitable for the dataset. Based on the experiments undertaken, the result shows Decision Tree has an accuracy of 91.16% which is the lowest compared to the other models, 97.6% for the KNN model which is the highest among all the models and 94.44% accuracy for the Random Forest model. Through comparisons between the three models, KNN was the prime candidate for the best model considering that it has the highest accuracy. However, Random Forest is deemed more suitable for the dataset even though the accuracy is lesser because of the lowest false-negative value than the other models. The experiments can be further investigated with different datasets and models for comparative analysis. © 2021 IEEE.