Browsing by Author "Mbanaso, Uche M."

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Conceptual Framework for the Assessment of the Degree of Dependency of Critical National Infrastructure on ICT in Nigeria
    (Department of Computer Science, Nasarawa State University Keffi, 2019-03-06) Mbanaso, Uche M.; Kulugh, Victor; Musa, Habiba; Aimufua, Gilbert Imuetinyan Osaze
    Critical National Infrastructure (CNI) are assets that provide core functions to modern society, which failure or incapacitation can adversely affect national security, economic prosperity and wellbeing of citizens. In an evolving digital society, CNI rely heavily on Information and Communications Technology (ICT) infrastructure to improve productivity, and effectively deliver critical services in timely and cost-effective fashion. However, the underlying ICT infrastructure that drives CNI amplify cyber risks, threats and vulnerabilities exponentially. Consequently, a failure in ICT infrastructure has the potential to affect CNI in an unexpected manner. The risks associated with the use of ICT are dynamic, raising the need for continuous assessment of degree of ICT dependency. Presently however, there is rarely a framework nor a publicly available tool in Nigeria that can quantitatively gauge the degree of CNI dependency on ICT. The study addresses this gap by the development of a conceptual framework that can facilitate the assessment of the degree of CNI dependency on ICT. In this study, existing relevant documents on critical infrastructure, ICT frameworks and standards and critical process engineering principles were scanned, analysed and synthesised to conceptualise the framework, and the construction of the building blocks, metrics and indicators. The framework was tested using a hypothetical discrete dataset. The outcome further facilitated the framing of ICT Dependency Index (IDI), a predefined quadrant, of which the computation of Dependency must fall within one of the quadrants.
  • Thumbnail Image
    ItemOpen Access
    MACHINE LEARNING APPROACH FOR BREAST CANCER CLASSIFICATION
    (Department of Computer Science, Nasarawa State University Keffi, 2022-06-20) Aimufua, Gilbert Imuetinyan Osaze; Mbanaso, Uche M.; Abdullahi, M.U.
    Breast cancer is the most common cancer among women in Africa. These facts have led researchers to continue studying how to treat and detect breast cancer in women, especially older women, who are at higher risk. Achieving satisfactory cancer classification accuracy with the complete set of genes remains a great challenge (most especially with microarray datasets), due to the high dimensions, small sample size, and presence of noise in gene expression data. Feature reduction is critical and sensitive to the classification task. One of the major drawbacks of cancer studies is recognizing informative genes (features) among the thousands of others in the dataset. A large number of features (genes) against a small sample size and redundancy in expressed data are the main two reasons that lead to poor classification accuracy in machine learning and data mining processes. Therefore, dimensionality reduction is an exciting research area in the fields of pattern recognition, machine learning, data mining, and statistics. The purpose of dimensionality reduction is to improve classification performance through the removal of redundant or irrelevant features. Furthermore, feature selection is typically useful in reducing computation time and memory complexity, which have always been challenges in big data tasks. Besides, the high complexity of the memory space or time as a result of high dimension, noise effect, and outliers but it also has adverse impacts on the performance of the algorithms This paper tends to improve the low general accuracy and minimize memory space and execution time in classification models of machine learning algorithms; hence, the system will employ InfoGain for dimensional reduction and the Random Forest algorithm for classification.
  • Thumbnail Image
    ItemOpen Access
    Quantitative assessment of critical infrastructures degree of dependency on information and communications technology
    (Department of Computer Science, Nasarawa State University Keffi, 2022-04-04) Mbanaso, Uche M.; Kulugh, Victor Emmanuel; Aimufua, Gilbert Imuetinyan Osaze; Dandaura, Emmanuel S.
    This paper presents a computational model for the quantification of critical infrastructure (CI) degree of dependency on ICT. Traditional CIs that support modern society in providing uninterruptable vital services are increasingly ICT dependent. To build the needed bulwark against cyber threats, there is the need to assess their dependency on ICT since ICT infrastructure comes with vulnerabilities that amplify cyber risk. Consequently, the proposed computational model for the quantification of CI degree of dependency on ICT is a function of ICT metrics and indicators based on mathematical constructs. The outcome is ICT dependency index (IDI), and ICT dependency quadrant (IDQ), which compare, rank, and visualise the IDI of sectors and organisations. The findings show that no one sector can be chosen arbitrarily as the most critical ICT dependent. The model is particularly useful for developing countries to uniformly assess CI’s degree of dependency on ICT as opposed to uninformed valuation.