Scholarly works in the Department of Computer Science

Permanent URI for this collection

https://repository.fupre.edu.ng/handle/123456789/17

Browse

Browsing Scholarly works in the Department of Computer Science by Title

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Genetic Algorithm Rule-Based Intrusion Detection System (GAIDS)
    (Journal of Emerging Trends in Computing and Information Sciences, 2012-08) Ojugo, Arnold Adimabua; Eboka, A.O.; Okonta, O.E.; Yoro, R.E; Aghware, F.O.
    This study examines the detection of attacks or network intrusion by users referred to as hackers (whose aim is to gain illegal entry as well as access to a network system and resources. Network and data security has become a pertinent issue with the advent of the Internet; though the Internet comes with a lot of merits on its own. Traditional used methods for data security includes the use of passwords, cryptography to mention few. The approach considered here is Intrusion Detection System, which is a software, driver or device used to prevent an unauthorized or illegal access to data in a networked system. Most of the existing IDS are implemented via rule-based systems where new attacks are not detectable. This study thus, presents a genetic algorithm based approach (with its driver implementation), which employs a set of classification rule derived from network audit data and the support-confidence framework, utilized as fitness function to judge the quality of each rule. The software implementation is aimed at improving system security in networked settings allowing for confidentiality, integrity and availability of system resources.
  • No Thumbnail Available
    Item
    Investigating The Unexpected Price Plummet and Volatility Rise In Energy Market: A Comparative Study of Machine Learning Approaches
    (2020) Ojugo, Arnold Adimabua; Otakore, Oghenevwede Debby
    Energy market aims to manage risks associated with prices and volatility of oil asset. It is a capital-intensive market, rippled with chaos and complex interactions among its demand-supply derivatives. Models help users to forecast such interactions and give insight with empirical evidence of price direction to investors. Our study sought to investigate the unexpected plummet in price of the energy market using evolutionary modeling –which seeks to analyze input data and yield an optimal, complete solution that are tractable, robust and low-cost with tolerance of ambiguity, uncertainty and noise. We adopt the Gabillon‟s model to: (a) predict spots/futures prices, (b) investigate why previous predictions failed as to why price plummet, and (c) seek to critically evaluate values reached by both proposed deep learning model and the memetic algorithm by Ojugo and Allenotor (2017).