Browsing by Author "Obada DO"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Ensemble learning prediction of transmittance at different wavenumbers in natural hydroxyapatite
    (2020) Okafor E; Obada DO; Dodoo-Arhin D
    Material engineering-based research has often relied so much on tedious human experiments for generating specific engineering properties with a major draw-back of high time demand that can span between an hour and days. Hence to deviate from the usual paradigm, we provide an alternative approach which employs artificial intelligence (AI) based ensemble learning methods for predicting the degree of transmittance for a range of wavenumbers of infrared radiation through hydroxyapatite (HAp) samples. The effective samples (transmittance and wavenumber) were passed as input to the predictive systems. For this, we trained two ensemble learning methods: Extreme Gradient Boosting (XGBoost) and Random Forest on variants of HAp (density and time variations), while considering a fixed amount of 10,000 base estimators. The results show that Random Forest marginally outperforms the XGBoost in the testing phase but requires a much longer computing time. However, XGBoost is much faster than the Random Forest. Furthermore, the examined ensemble learning models yielded a coefficient of determination (R2 > 0.997): which are in close agreement with experimental data, depicting an excellent generalization capacity. Additionally, the examined ensemble learning models showed a significant ≥ 99.83% decrease in computational complexity relative to the time spent when generating the experimental data. Overall, the use of ensemble learning models is very important for validating material engineering properties.
  • Thumbnail Image
    Item
    Experimental data on the characterization of hydroxyapatite produced from a novel mixture of biowastes
    (2022) Osuchukwu OA; Salihi A; Abdullahi I; Obada DO
    The purpose of this data narrative is to report the morphological structures, functional groups, elemental composition, pH adaptability and mechanical properties of hydroxyapatite (HAp) biomaterials synthesized from a novel mixture of biowastes (bovine and catfish bones) by a simple sol-gel method assisted with sintering at 900 °C. The produced powders were homogenously mixed by the sol-gel approach at different weights (depicted by sample nomenclature) and characterized using scanning electron microscopy (SEM) equipped with electron dispersive X-ray analysis (EDX), X-ray fluorescence (XRF), Fourier Transform Infrared Spectroscopy (FT-IR), immersion in phosphate buffer saline (PBS), and mechanical measurements (hardness and fracture toughness). The SEM micrographs revealed pore interconnections in all samples. The EDX analysis revealed that the as-sintered HAp samples had Ca/P weight ratios of 2.38, 2.51, 2.86, 2.89, and 3.10 for C100, BC 75/25, BC 50/50, BC 25/75, and B100 samples, respectively. The FT-IR spectra was typical of the bands associated with hydroxyapatite (i.e., those associated with the PO43− , CO32- groups and absorbed water). The prepared biomaterials showed pH adaptability and good mechanical strength.