Enhancing Cybersecurity through Cloud Computing Solutions in the United States  

作　　者：Omolola F. Hassan Folorunsho O. Fatai Oluwadare Aderibigbe Abdullah Oladoyin Akinde Tolulope Onasanya Mariam Adetoun Sanusi Oduwunmi Odukoya Omolola F. Hassan;Folorunsho O. Fatai;Oluwadare Aderibigbe;Abdullah Oladoyin Akinde;Tolulope Onasanya;Mariam Adetoun Sanusi;Oduwunmi Odukoya(Department of Computer Science, Austin Peay State University, Clarksville, USA;Department of Computer Science, North Carolina Agricultural and Technical State University, Greensboro, USA;Department of Cybersecurity, University of Texas, Dallas, USA;Department of Information Systems, East Tennessee State University, Johnson City, USA)

机构地区：[1]Department of Computer Science, Austin Peay State University, Clarksville, USA [2]Department of Computer Science, North Carolina Agricultural and Technical State University, Greensboro, USA [3]Department of Cybersecurity, University of Texas, Dallas, USA [4]Department of Information Systems, East Tennessee State University, Johnson City, USA

出　　处：《Intelligent Information Management》2024年第4期176-193,共18页智能信息管理（英文）

摘　　要：This study investigates how cybersecurity can be enhanced through cloud computing solutions in the United States. The motive for this study is due to the rampant loss of data, breaches, and unauthorized access of internet criminals in the United States. The study adopted a survey research design, collecting data from 890 cloud professionals with relevant knowledge of cybersecurity and cloud computing. A machine learning approach was adopted, specifically a random forest classifier, an ensemble, and a decision tree model. Out of the features in the data, ten important features were selected using random forest feature importance, which helps to achieve the objective of the study. The study’s purpose is to enable organizations to develop suitable techniques to prevent cybercrime using random forest predictions as they relate to cloud services in the United States. The effectiveness of the models used is evaluated by utilizing validation matrices that include recall values, accuracy, and precision, in addition to F1 scores and confusion matrices. Based on evaluation scores (accuracy, precision, recall, and F1 scores) of 81.9%, 82.6%, and 82.1%, the results demonstrated the effectiveness of the random forest model. It showed the importance of machine learning algorithms in preventing cybercrime and boosting security in the cloud environment. It recommends that other machine learning models be adopted to see how to improve cybersecurity through cloud computing.This study investigates how cybersecurity can be enhanced through cloud computing solutions in the United States. The motive for this study is due to the rampant loss of data, breaches, and unauthorized access of internet criminals in the United States. The study adopted a survey research design, collecting data from 890 cloud professionals with relevant knowledge of cybersecurity and cloud computing. A machine learning approach was adopted, specifically a random forest classifier, an ensemble, and a decision tree model. Out of the features in the data, ten important features were selected using random forest feature importance, which helps to achieve the objective of the study. The study’s purpose is to enable organizations to develop suitable techniques to prevent cybercrime using random forest predictions as they relate to cloud services in the United States. The effectiveness of the models used is evaluated by utilizing validation matrices that include recall values, accuracy, and precision, in addition to F1 scores and confusion matrices. Based on evaluation scores (accuracy, precision, recall, and F1 scores) of 81.9%, 82.6%, and 82.1%, the results demonstrated the effectiveness of the random forest model. It showed the importance of machine learning algorithms in preventing cybercrime and boosting security in the cloud environment. It recommends that other machine learning models be adopted to see how to improve cybersecurity through cloud computing.

关 键 词：CYBERSECURITY Cloud Computing Cloud Solutions Machine Learning Algorithm 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]