Browsing by Author "Samuel Adewale Aderoju"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A New Lifetime Distribution and its Application to Cancer Data
    (Journal of Biostatistics and Epidemiology, 2023-12-15) Samuel Adewale Aderoju; Nihimat Iyebuhola Aleshinloye; Bako Lukmon Taiwo; Bello Ishola Sanni
    Introduction: Recently, researchers have introduced new generated families of univariate lifetime distributions. These new generators are obtained by adding one or more extra shape parameters to the underlying distribution or compounding two distributions to get more flexibility in fitting data in different areas such as medical sciences, environmental sciences, and engineering. The addition of parameter(s) has been proven useful in exploring tail properties and for improving the goodness-of-fit of the family of the proposed distributions. Methods:A new Three-Parameter Weibull-Generalized Gamma distribution which provides more flexibility in modeling lifetime data is developed using a two-component mixture of Weibull distribution (with parameters θ and λ) and Generalised Gamma distribution (with parameters α=4,θ and λ). Some of its mathematical properties such as the density function, cumulative distribution function, survival function, hazard rate function, moment generating function, Renyi entropy and order statistics are obtained. The maximum likelihood estimation method was used in estimating the parameters of the proposed distribution and a simulation study is performed to examine the performance of the maximum likelihood estimators of the parameters. Results: Real life applications of the proposed distribution to two cancer datasets are presented and its fit was compared with the fit attained by some existing lifetime distributions to show how the Three-Parameter Weibull-Generalized Gamma distribution works in practice. Conclusion: The results suggest that the proposed model performed better than its competitors and it’s a useful alternative to the existing models.
  • Thumbnail Image
    Item
    A novel hybrid dimension reduction technique for efficient selection of bio-marker genes and prediction of heart failure status of patients
    (Scientific African, 2021-05-02) Kazeem Adesina Dauda; Kabir Opeyemi Olorede; Samuel Adewale Aderoju
    This study highlighted and provided a conceptual framework of a hybridized dimension reduction by combining Genetic Algorithms (GA) and Boruta Algorithm (BA) with Deep Neural Network (DNN). Among questions left unanswered sufficiently by both computational and biological scientists are: which genes among thousand of genes are statistically relevant to the prediction of patients’ heart rhythm? and how they are associated with heart rhythm? A plethora of models has been proposed to reliably identify core informative genes. The premise of this present work is to address these limitations. Five distinct micro-array data on heart diseases have been taken into consideration to observe the prominent genes. We form three distinct set two-way hybrids between Boruta Algorithm and Neural Network (BANN); Genetic Algorithm and Deep Neural Network (GADNN) and Boruta Algorithm and Deep Neural Network (BADNN), respectively, to extract highly differentially expressed genes to achieve both better estimation and clearer interpretation of the parameters included in these models. The results of the filtering process were observed to be impressive since the technique removed noisy genes. The proposed BA algorithm was observed to select minimum genes in the wrapper process with about 80% of the five datasets than the proposed GA algorithm with 20%. Moreover, the empirical comparative results revealed that BADNN outperformed other proposed algorithms with prediction ac curacy of 97%, 87%, and 100% respectively. Finally, this study has successfully demonstrated the utility, versatility, and applicability of hybrid dimension reduction algorithms (HDRA) in the realm of deep neural networks.