Repository logo

ResearchSpace is the institutional repository of the University of KwaZulu-Natal, unlocking knowledge, empowering impact, and preserving UKZN's research legacy.

LinkedIn | YouTube | Twitter X | Facebook | Instagram
UKZN Library


Recent Submissions

Forest image classification based on deep learning and ontologies.
(2024) Kwenda, Clopas.; Gwetu, Mandlenkosi Victor.; Fonou-Dombeu, Jean Vincent.
Forests contribute abundantly to nature’s natural resources and they significantly contribute to a wide range of environmental, socio-cultural, and economic benefits. Classifications of forest vegetation offer a practical method for categorising information about patterns of forest vegetation. This information is required to successfully plan for land use, map landscapes, and preserve natural habitats. Remote sensing technology has provided high spatio-temporal resolution images with many spectral bands that make conducting research in forestry easy. In that regard, artificial intelligence technologies assess forest damage. The field of remote sensing research is constantly adapting to leverage newly developed computational algorithms and increased computing power. Both the theory and the practice of remote sensing have significantly changed as a result of recent technological advancements, such as the creation of new sensors and improvements in data accessibility. Data-driven methods, including supervised classifiers (such as Random Forests) and deep learning classifiers, are gaining much importance in processing big earth observation data due to their accuracy in creating observable images. Though deep learning models produce satisfactory results, researchers find it difficult to understand how they make predictions because they are regarded as black-box in nature, owing to their complicated network structures. However, when inductive inference from data learning is taken into consideration, data-driven methods are less efficient in working with symbolic information. In data-driven techniques, the specialized knowledge that environmental scientists use to evaluate images obtained through remote sensing is typically disregarded. This limitation presents a significant obstacle for end users of Earth Observation applications who are accustomed to working with symbolic information, such as ecologists, agronomists, and other related professionals. This study advocates for the incorporation of ontologies in forest image classification owing to their ability in representing domain expert knowledge. The future of remote sensing science should be supported by knowledge representation techniques such as ontologies. The study presents a methodological framework that integrates deep learning techniques and ontologies with the aim of enhancing domain expert confidence as well as increasing the accuracy of forest image classification. In addressing this challenge, this study followed the following systematic steps (i) A critical review of existing methods for forest image classification (ii) A critical analysis of appropriate methods for forest image classification (iii) Development of the state-of-the-art model for forest image segmentation (iv) Design of a hybrid model of deep learning and machine learning model for forest image classification (v) A state-of-the-art ontological framework for forest image classification. The ontological framework was flexible to capture the expression of the domain expert knowledge. The ontological state-of-the-art model performed well as it achieved a classification accuracy of 96%, with a Root Mean Square Error of 0.532. The model can also be used in the fruit industry and supermarkets to classify fruits into their respective categories. It can also be potentially used to classify trees with respect to their species. As a way of enhancing confidence in deep learning models by domain experts, the study recommended the adoption of explainable artificial intelligence (XAI) methods because they unpack the process by which deep learning models reach their decision. The study also recommended the adoption of high-resolution networks (HRNets) as an alternative to traditional deep learning models, because they can convert low-resolution representation to high-resolution and have efficient block structures developed according to new standards and they are excellent at being used for feature extraction.
Discrete time-to-event construction for multiple recurrent state transitions.
(2023) Batidzirai, Jesca Mercy.; Manda, Samuel O. M.; Mwambi, Henry Godwell.
Recent developments in multi-state models have considered discrete time rather than continuous time in the modeling of transition intensities, whose major drawback lies in the possibility of resulting in biased parameter estimates that arise from issues of handling ties. Discrete-time models have included univariate multilevel models to account for possible dependence among specific pairwise recurrent transitions within the same subject. However, in most cases, there would be several specific pairwise transitions of interest. In such cases, there is a need to model the transitions with the aim of identifying those transitions that are correlated. This provides insight into how the transitions are related to each other. In order to investigate the interdependencies between transitions, the unique contribution of this thesis is to propose a multivariate discrete-time multi-state model with multiple state transitions. In this model, each specific recurrent transition is associated with a random effect to capture possible dependence in the transitions of the same type or different types. The random effects themselves were then modeled by a multivariate normal distribution and model parameters were estimated using maximum likelihood methods with Gaussian quadratures numerical integration. A simulation study was done to evaluate the performance of the proposed model. The model yielded satisfactory results for most fixed effects and random effects estimates. This is noticed by near-zero biases and mean square errors of the average estimates as well as high 95% coverage probabilities of the 95% confidence intervals from 1000 replications. The proposed methodology was applied to marriage formation and dissolution data from KwaZulu-Natal province, South Africa. Five transitions were considered, namely: Never Married to Married, Married to Separated, Married to Widowed, Separated to Married and Widowed to Married. The presence of very small unobserved subject-to subject heterogeneity for each transition and a weak positive correlation between transitions were produced. Statistically, the model produced smaller standard errors compared to those from univariate models, hence it is more precise on estimates. The multivariate modeling of discrete time-to-event models provides a better understanding of the evolution of all transitions simultaneously, thus in addition to covariate effects, giving an assessment of how one transition is associated with the other. Empirical results confirmed well known important socio-demographic predictors of entering and exiting a marriage. Age at sexual debut played a positive critical role in most of the transitions. More educated subjects were associated with a lower likelihood of entering a first marriage, experiencing a marital dissolution as well as remarrying after widowhood. Subjects who had a sexual debut at younger ages were more likely to experience a marital dissolution than those who started late. Age at first marriage had a negative association with marital dissolution. We may, therefore, postulate that existing programs that encourage delay in onset of sexual activity for HIV risk reduction for example, may also have a positive impact on lowering rates of marital dissolution, thus ultimately improving psychological and physical health.
Bayesian spatio-temporal and joint modelling of malaria and anaemia among Nigerian children aged under five years, including estimation of the effects of risk factors.
(2023) Ibeji, Jecinta Ugochukwu.; Mwambi, Henry Godwell.; Iddrisu, Abdul-Karim.
Childhood mortality and morbidity in Nigeria have been linked to malaria and anaemia. This thesis focused on exploring the risk factors and the complexity of the relationship between malaria and anaemia in under 5 Nigerian children. Data from the 2010 and 2015 Nigeria Malaria Indicator Survey conducted by Demographic Health Survey were used. In 2010, the prevalence of malaria and anaemia was 48% and 72%, respectively, while in 2015, 27% and 68% were the respective prevalences of malaria and anaemia diseases. Machine learning-based exploratory classification methods were used to explain the relationship and patterns between the independent variables and the two dependent variables, namely malaria and anaemia. Decisions made by the public health body are centered on the administrative units (i.e., states) within the country. Therefore, the development of disease mapping and a brief overview of limiting assumptions and ways of tackling them was explained. Consequently, malaria and anaemia spatial variation for 2010 and 2015 was analyzed with the inclusion of their respective risk factors. A separate multivariate hierarchical Bayesian logistic model for each disease was adopted to investigate the spatial pattern of malaria and anaemia and adjust for the risk factors associated with each disease. Furthermore, a multilevel model analysis was applied to independently investigate the spatio-temporal distribution of malaria and anaemia. A joint model was further adopted to check for the relationship between malaria and anaemia and their common risk factors and relax the nonlinearity assumption. In the 2010 data, type of place of residence, mother’s highest educational level, source of drinking water, type of toilet facility, child’s sex, main floor material, and households that have electricity, radio, television, and water were significantly associated with malaria and anaemia. While in the 2015 data, the type of place of residence, source of drinking water, type of toilet facility, households with radio, main roof material, wealth index, child’s sex, and mother’s highest educational level had a significant relationship with malaria and anaemia. The results from this study can guide policymakers to tailor-make effective interventions to reduce or prevent malaria and anaemia diseases. This will help adequately distribute limited state health system resources, such as personnel, funds and facilities within the country.
Derivatised phenanthroline transition metal chelates : targeted chemotherapeutic agents.
(2024) Hunter, Leigh André.; Akerman, Matthew Piers.
The derivatisation of 1,10-phenanthroline at the 2-position afforded two classes of compounds with two different bridging groups in this study. The first group comprised two amide-bridged tetradentate N4-donor ligands and were chelated to copper(II), nickel(II) and palladium(II). The ligand chelation occurred with concomitant deprotonation of the amide N-H, resulting in a monoanionic ligand and monocationic complexes when coordinated to the divalent metal ions. The ligands N-(quinolin-8-yl)-1,10-phenanthroline-2-carboxamide, HL1, and N-(pyridin-2-ylmethyl)-1,10-phenanthroline-2-carboxamide, HL2, were characterised by NMR, IR and UV/vis spectroscopy as well as mass spectrometry. The second class of compounds were imine-bridged copper(II) chelates. These chelates were synthesised via a templating condensation reaction between various salicylaldehyde derivates and 1,10-phenanthrolin-2-ylmethanaminium chloride, yielding eight additional copper(II) chelates. The metal chelates were characterised by IR, UV/vis and EPR spectroscopy, and mass spectrometry. HL1, [Cu(L4)(NO3)] and [Cu(L7)](NO3) were further studied by X-ray diffraction. The copper(II) chelates exhibit two different solid-state structures with the nitrate counter ion coordinated to the metal centre in [Cu(L4)(NO3)], but in the outer coordination sphere for [Cu(L7)](NO3). The paramagnetic copper(II) chelates were studied with EPR spectroscopy, which confirmed the square planar coordination geometries of these chelates in solution. The metal chelates were designed to be chemotherapeutic agents, exerting their cytotoxicity through DNA intercalation and, for the copper(II) chelates, DNA cleavage through the catalytic production of ROS. The ability of the copper(II) chelates to catalyse the production of hydroxyl radical in situ in the presence of ascorbic acid and hydrogen peroxide was studied via a hydroxyl radical assay using Rhodamine B as an analogue for the aromatic DNA bases. Competitive binding studies determined the affinity of the metal chelates towards ct-DNA, [Cu(L1)](PF6) has the highest binding constant: 5.91 × 106 M-1. DFT calculations were performed on the ligands and metal chelates to determine the geometry-optimised structures, vibrational frequencies, 1H and 13C NMR chemical shifts and electronic transitions. The B3LYP/6-311G (d,p) level of theory was used for the ligands, copper(II) and nickel(II) chelates and the B3LYP/LanL2DZ level of theory for the palladium(II) chelates. The TD-DFT method was used for the energy calculations. The experimental and calculated results were compared where possible, and a reasonable correlation was found. The cytotoxicity of five amide-based chelates was evaluated against four human cancer cell lines, namely A549, TK-10, HT29 and U251, using an MTT assay. The screened chelates exhibited favourable anticancer activity with the mean IC50 values against the four cancer cell lines ranging from ca. 12 to 35 μM. Importantly, it was found that the combination of the copper(II) ion and the ligand was essential for enhanced cytotoxicity. The complex [Cu(L1)](PF6) was identified as the lead drug candidate based on the high DNA affinity and cytotoxicity. This compound was most cytotoxic towards the glioblastoma cell line U251 with an IC50 value of 7.59 μM. The imine-based chelates were screened against three human cancer cell lines: MDA-MB, HELA, and SHSY5Y, and a healthy human cell line, HEK293. The selectivity index of these chelates for neoplastic versus the healthy cell line was calculated. The imine-based chelates showed a high selectivity towards the triple-negative breast cancer MDA-MB, an order of magnitude more toxic to the tumour cell than the healthy one. This selectivity index is significantly improved over that of cisplatin. A gel mobility shift assay investigated the interactions between the copper(II) chelates and plasmid DNA. The in vivo biodistribution of [Cu(L1)](PF6) was determined using the copper-64 radiolabelled analogue of [Cu(L1)]Cl and microPET-CT scanning. The initial biodistribution studies suggested that the complex has good serum stability and showed that there was no significant accumulation in any organs. The subsequent study involved a xenograft model using the A549 cell line and showed significant uptake and retention of the complex in the tumour. The cytotoxicity of the chelate when synthesised with the non-radioactive isotopes of copper and the uptake of the radiolabelled equivalent in a tumour model suggest that this complex could have application as a “theranostic agent”.
Metallophthalocyanine-based electrochemical sensors for accurate qualitative and quantitative analysis of emerging pollutants in water resources.
(2024) Shoba, Siyabonga Blessing.; Booysen, Irvin Noel.; Mambanda, Allen.
Water is a precious resource and safeguarding it from pollution is paramount to ensure the well-being of both the environment and human health. Emerging contaminants such as pharmaceuticals and heavy metals pose significant threats, necessitating vigilant monitoring and appropriate action. Traditional laboratory-based analytical techniques like Gas Chromatography, ICP-OES and HPLC have been instrumental in quantifying pollutants. However, their high operational costs, maintenance requirements and the need for specialized personnel limit their widespread use, especially in resource-constrained countries. Electrochemical sensors have emerged as a promising solution. They provide real-time, portable and cost-effective options for on-site detection of pollutants in water. Current advancements in electrochemical sensors are centred around achieving selective detection using chemical modifiers, all while maintaining electrocatalytic sensitivity and reproducibility. These sensors can be tailored to target specific contaminants, making them highly efficient tools for monitoring water quality and ensuring the sustainability of this invaluable resource. In the first experimental chapter, a glassy carbon electrode (GCE) was modified by an asymmetric metallophthalocyanine (MPc) complex, A3B-CoPc-flav (where A = flavonyloxy substituent and B = an alkynyloxy substituent/molecular mast). The modification of an electrode was achieved via electrochemical grafting followed by clicked chemistry between the diazonium-functionalized GCE and the a-CoPc-flav3 to afford the GCE|clicked-a-CoPc-flav3. The chemically modified electrodes (CME) were utilized as electrocatalytic detectors for dopamine (DA) under optimized conditions. The response of the GCE|clicked-a-CoPc-flav3 was linear in the concentration range of 2 μM to 14 μM, attaining limits of detection and quantification of 0.311 and 0.942 μM, respectively, and high reproducibility (%RSD of 2.25%, N = 3). Interference studies were conducted, revealing a marginal shift in the DA peak potential in the presence of interfering substances. Despite this shift, the peak current intensity of DA remained largely unaffected, affirming the selectivity and accuracy of the CME. The analytical capabilities of the CME were further assessed using real water samples. The obtained percentage recoveries of (97.1%) of DA by the GCE|clicked-a-CoPc-flav3 and the well-established HPLC-MS method (113%) are both within the acceptable range of 80-120%. In the second experimental chapter, a platinum electrode (Pt) was modified via the electropolymerization of polypyrrole (PPy) after its co-electrodeposition of tetra-[4-((1H benzotriazole)methoxy)phthalocyaninato]cobalt(II) (CoPc-Bzt). The electrodeposition of CoPc-Bzt was performed in 1:1 DMF/acetonitrile containing 1 M tetrabutylammonium hexafluorophosphate (NBu4PF6) electrolyte over 20 cycles using cyclic voltammetry to afford a Pt|PPy/CoPc-Bzt (Bzt = benzotriazole). The resultant CME was prone to fouling by the analyte of interest, mercury(II). Due to fouling the differential pulse anodic stripping voltammetry (DPASV) was used to detect Hg(II) using the Pt|PPy/CoPc-Bzt within 10 μM to 100 μM linear range. The LOD and LOQ were found to be 3.11 and 10.00 μM, respectively. Interference studies illustrated that the detection capabilities of the CME were not affected by the presence of other heavy metal cations. The analytical performances of Pt|PPy/CoPc-Bzt (97.4%) and Inductively coupled plasma – optical emission spectroscopy (ICP-OES) (112.3%) are both within the acceptable range of 80-120%. In the third experimental chapter, the Pb electrocatalytic sensing capability of a gold electrode modified via the adsorption of electrospun nanofibers (ENFs) and Nafion (Nf) as an annealed conductive top-layer was evaluated. The fabricated ENFs comprised of a core polymeric nanocomposite of tetra-4-(3-oxyflavonephthalocyaninato)cobalt(II) (CoPc-flav), the carboxylic acid functionalized multiwalled carbon nanotubes (f-MWCNTs) and polyaniline (PANI) encapsulated in a polyvinyl acetate (PVA) ENFs. The resultant CME, Au|ENFs-1-Nf was not prone to fouling as was found when using the bare and the other constructed CMEs whose signal stabilities were compromised by background electrolyte currents. The Au|ENFs-1-Nf electrode could detect the Pb(II) cations in a reproducible manner (%RSD of 3.92%, N = 3) ranging from 8 to 125 μM, and limits of detection and quantification of 0.51 and 1.55 μM were obtained, respectively. However, the interference studies illustrated that the detection capabilities of the CME are severely compromised by the presence of other heavy metal cations. The analytical performance of the CME rendered a comparable percentage recovery (103%) with that of the ICP-OES (115%). In the fourth experimental chapter, the nanofabrication and characterization of new conductive materials, PANI-CoPc-fur (1) ((PANI = polyaniline and CoPc-fur = tetra-4-(2-furanmethylthiophthalocyaninato)Co(II)) and PANI-CoPc-fur-f-MWCNTs (2) are reported. Subsequently, an electrospun nanofiber (ENF) composite was fabricated where the core comprised of 2 that was encapsulated with a PVA shell. The resultant nanoconjugate, ENFs-2 was adsorbed on a glassy carbon electrode (GCE) followed by the immobilization of a permeable adhesion top layer of Nafion (Nf) to render the chemically modified electrode, GCE|ENFs-2-Nf. The classical physical properties of the electron-mediating layer for the CME synergistically aided in promoting its electrocatalytic activities. Consequently, the CME showed greater anodic and cathodic cyclic voltammetry (CV) peak currents compared to the bare GCE and other modified electrodes, indicating its higher sensitivity to acetaminophen (APAP), an emerging water pollutant of concern. Limits of detection and quantification (LOD and LOQ) values for APAP attained by squarewave voltammetry (SWV) were lower compared to those acquired using other electrochemical techniques. The detection of APAP at the GCE|ENFs-2-Nf attained by squarewave voltammetry (SWV) was linear from 10 to 200 μM of APAP and was reproducible (%RSD of 3.2%, N = 3). The respective calculated LOD and LOQ values of 0.094 and 0.28 μM were lower compared to those acquired using other electrochemical techniques. Analysis of APAP in the presence of commonly associated interferences metronidazole (MTZ) and dopamine (DA) illustrated a significant separation between the SWV peak potentials of APAP and MTZ, whereas there was some degree of overlap between the SWV current responses of APAP and DA. The analytical performance of the GCE|ENFs-2-Nf rendered a comparable percentage recovery (103.8%) with that of liquid chromatography–mass spectrometry (LC–MS) (106%).