by Rushit Dave, Naeem Seliya, Nyle Siddiqui and Su Mao
Review Article
Recent advancements in technology now allow for the generation of massive quantities of data. There is a growing need to transmit this data faster and more securely such that it cannot be accessed by malicious individuals. Edge computing has emerged in previous research as a method capable of improving data transmission times and security before the data ends up in the cloud. Edge computing has an impressive transmission speed based on fifth generation (5G) communication which transmits data with low latency and high bandwidth. While edge computing is sufficient to extract important features from the raw data to prevent large amounts of data requiring excessive bandwidth to be transmitted, cloud computing is used for the computational processes required for developing algorithms and modeling the data. Edge computing also improves the quality of the user experience by saving time and integrating quality of life (QoL) features. QoL features are important for the healthcare sector by helping to provide real-time feedback of data produced by healthcare devices back to patients for a faster recovery. Edge computing has better energy efficiency, can reduce the electricity cost, and in turn help people reduce their living expenses. This paper will take a detailed look into edge computing applications around Internet of Things (IoT) devices, smart city infrastructure, and benefits to healthcare.
Journal of Computer Sciences and Applications. 2021, 9(1), 23-34. DOI: 10.12691/jcsa-9-1-3
Pub. Date: October 28, 2021
3525 Views12 Downloads
by Sam Strecker, Rushit Dave, Nyle Siddiqui and Naeem Seliya
Original Research
Modern scientific advancements often contribute to the introduction and refinement of never-before-seen technologies. This can be quite the task for humans to maintain and monitor and as a result, our society has become reliant on machine learning to assist in this task. With new technology comes new methods and thus new ways to circumvent existing cyber security measures. This study examines the effectiveness of three distinct Internet of Things cyber security algorithms currently used in industry today for malware and intrusion detection: Random Forest (RF), Support-Vector Machine (SVM), and K-Nearest Neighbor (KNN). Each algorithm was trained and tested on the Aposemat IoT-23 dataset which was published in January 2020 with the earliest of captures from 2018 and latest from 2019. The RF, SVM, and KNN reached peak accuracies of 92.96%, 86.23%, and 91.48%, respectively, in intrusion detection and 92.27%, 83.52%, and 89.80% in malware detection. It was found all three algorithms are capable of being effectively utilized for the current landscape of IoT cyber security in 2021.
Journal of Computer Sciences and Applications. 2021, 9(1), 16-22. DOI: 10.12691/jcsa-9-1-2
Pub. Date: October 18, 2021
2703 Views10 Downloads
by Thomas Mageto
Original Research
The education sector in the recent past has had changes in policy as a result of high transition rate target, innovation, infrastructure technology advancement and COVID-19 pandemic challenges. In keeping phase with this great achievement and challenges, there is need to incorporate innovations in Information and Communication Technologies in providing library services in education sector in order to have efficient, secure and quality services. In this research project we have investigated the problems with the past and current library systems, then analysed, designed and developed a prototype that would greatly contribute in improving the provision of the library services. The prototype would manage tasks that include appointments, lending, reserving, returning, processing payments, storage of book records, provide information and processing invoices for orders. In reducing the unauthorized access of book records from unauthorized persons, we have described the encryption and accessing of pages security plan for the emerging threats. The system would be accessed in local and unlimited networks but in the areas where there are challenges of connectivity, high internet costs and poor infrastructure we intend to use offline web services and connect only when the service is required and necessary. The development methodology adapted in the development process phases of the electronic library system is the spiral development methodology.
Journal of Computer Sciences and Applications. 2021, 9(1), 1-15. DOI: 10.12691/jcsa-9-1-1
Pub. Date: January 15, 2021
7622 Views19 Downloads