Browsing by Author "Kazeem Adesina Dauda"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    A New Generalized Gamma-Weibull Distribution with Applications to Time-to-event Data
    (2023-11-18) Kazeem Adesina Dauda; Rasheed Kehinde Lamidi; Adeshola Adediran Dauda; Waheed Babatunde Yahya
    In this research, a new class of probability distributions referred to as Generalized Gamma Weibull (GGW) distributions was introduced within the context of parametric survival analysis. This distribution represents a modification of the gamma Weibull distribution and offers valuable insights, particularly when dealing with highly skewed lifetime data. The study extensively examined the mathematical characteristics of these distributions, encompassing hazard functions, moments, quantile functions, and order statistics. Furthermore, the research delved into parameter estimation methods for these newly proposed distributions, employing the maximum likelihood technique, Fisher Information (FI), and deriving asymptotic confidence intervals for both censored and uncensored scenarios. To illustrate the practical utility of these proposed distributions, the study applied them to analyze two sets of real-life survival data and two sets of real-life data, resulting in a total of four distinct datasets. To gauge the effectiveness of the GGW distributions in comparison to existing methods such as Generalized Weibull and Generalized gamma (G-Weibull and G-Gamma) distributions, the research employed statistical indices including the Akaike Information Criterion (AIC), Corrected Akaike Information Criterion (CAIC), and Bayesian Information Criterion (BIC). The outcomes of this comparative analysis demonstrated the superior performance of the newly introduced GGW distributions (AIC=338.6313, BIC=346.2794, and CAIC=339.5202) when contrasted with the existing methods (G-Weibull: AIC=376.1946, BIC=381.9307, and CAIC=376.5424) across all three criteria, thereby highlighting the enhanced suitability of GGW distributions for modeling and analyzing skewed lifetime data.
  • 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.
  • Thumbnail Image
    Item
    Hydration Status in Nigeria: A Cross-Sectional Study
    (Pakistan Journal of Nutrition, 2014) Yunusa Olufadi; Alfred B. O. Soboyejo; Kabir Opeyemi Olorede; Kazeem Adesina Dauda
    Most literatures on daily water intake are focused on developed countries and to our knowledge; there is limited information on the hydration status of Nigerians. Our objective was to describe daily water intake (DWI) among Nigerian students, develop a model for the prediction of students’ DWI and examine the association between DWI and four predictor variables. Data on DWI for 150 students aged 18-26 years were collected through a survey conducted at Kwara State University in February, 2013 together with information on their age, weight, gender and awareness of dieticians’ recommendation. Our results indicates that students’ DWI varies by gender with male students drinking more than their female counterparts; although, the awareness rate is higher in females than males. We found that nearly half of participants (44%) drank less than 2.7 L of water/day, 25% between 2.7 and 3.7 L/day and 31% reported drinking more than 3.7 L of water/day. Results also revealed that students’ DWI decline with age but increases with weight and one-in-two of the students are unaware of the dangers of poor hydration. Arguably, this study is the first description of DWI among Nigerian students and fills the gap in the literature by developing two models for the prediction of students’ DWI. In light of the significance of the knowledge and awareness of Dieticians’ recommendation on DWI (as evidence in this study) and the low awareness rate existing among the students; nutrition and health promotion program on the benefits of adequate DWI by schools and health organizations is extremely important. This has the potential of improving the health of students.