College of Agriculture, Engineering and Science

Permanent URI for this communityhttps://hdl.handle.net/10413/6521

Browse

Now showing 1 - 20 of 38

A study on the atmospheric and environmental impacts of aerosol, cloud and precipitation interaction.
(2022) Yakubu, Abdulaziz Tunde.; Chetty, Naven.
Understanding the mechanisms and processes of aerosol-cloud-precipitation interactions (ACPI) is essential in the determination of the specific role of aerosols in modulating extreme weather events and climate change in the long run. Atmospheric aerosols are mainly of various types and are emitted from differing sources. Considering they commonly exist in the heterogeneous forms in most environments, they significantly influence the incoming solar energy and the general perturbation of the clouds depending on their constituents. Thus, a systemic identification and characterisation of these particles are essential for proper representation in climate models. To better understand the process of climate change, this research explores the climate diversity of South Africa to examine aerosol sources and types concerning the atmospheric aerosol suspension over the region and their role in clouds and precipitation formation. The study further provided answers to the cause of extreme precipitation events, including drought and occasional flooding experienced over the region. Also, an insightful explanation of the process of ACPI is provided in the context of climate change. Furthermore, the research found that the effective radiative forcing (RF) over South Africa as monitored in Cape Town and Pretoria is negative (i.e., cooling effect) and provided an analysis of the cause. Similarly, the validation of some satellite datasets from MISR (Multiangle Imaging Spectroradiometer) and MODIS (Moderate Resolution Imaging Spectroradiometer) instruments against AERONET (Aerosol Robotic Network) is conducted over the region. Although a significant level of agreement is observed for the two instruments, intense improvements are needed, especially regarding measurements over water surfaces. Finally, the study demonstrated the proficiency of effective rainfall prediction from satellite instrument cloud datasets using machine learning algorithms.
Analysis of discrete time competing risks data with missing failure causes and cured subjects.
(2023) Ndlovu, Bonginkosi Duncan.; Zewotir, Temesgen Tenaw.; Melesse, Sileshi Fanta.
This thesis is motivated by the limitations of the existing discrete time competing risks models vis-a-vis the treatment of data that comes with missing failure causes or a sizableproportions of cured subjects. The discrete time models that have been suggested to date (Davis and Lawrance, 1989; Tutz and Schmid, 2016; Ambrogi et al., 2009; Lee et al., 2018) are cause-specific-hazard denominated. Clearly, this fact summarily disqualifies these models from consideration if data comes with missing failure causes. It is also a well documented fact that naive application of the cause-specific-hazards to data that has a sizable proportion of cured subjects may produce downward biased estimates for these quantities. The existing models can be considered within the multiple imputation framework (Rubin, 1987) for handling missing failure causes, but the prospects of scaling them up for handling cured subjects are minimal, if not nil. In this thesis we address these issues concerning the treatment of missing failure causes and cured subjects in discrete time settings. Towards that end, we focus on the mixture model (Larson and Dinse, 1985) and the vertical model (Nicolaie et al., 2010) because these models possess certain properties which dovetail with the objectives of this thesis. The mixture model has been upgraded into a model that can handle cured subjects. Nicolaie et al. (2015) have demonstrated that the vertical model can also handle missing failure causes as is. Nicolaie et al. (2018) have also extended the vertical model to deal with cured subjects. Our strategy in this thesis is to exploit both the mixture model and the vertical model as a launching pad to advance discrete time models for handling data that comes with missing failure causes or cured subjects.
Application of ELECTRE algorithms in ontology selection.
(2022) Sooklall, Ameeth.; Fonou-Dombeu, Jean Vincent.
The field of artificial intelligence (AI) is expanding at a rapid pace. Ontology and the field of ontological engineering is an invaluable component of AI, as it provides AI the ability to capture and express complex knowledge and data in a form that encourages computation, inference, reasoning, and dissemination. Accordingly, the research and applications of ontology is becoming increasingly widespread in recent years. However, due to the complexity involved with ontological engineering, it is encouraged that users reuse existing ontologies as opposed to creating ontologies de novo. This in itself has a huge disadvantage as the task of selecting appropriate ontologies for reuse is complex as engineers and users may find it difficult to analyse and comprehend ontologies. It is therefore crucial that techniques and methods be developed in order to reduce the complexity of ontology selection for reuse. Essentially, ontology selection is a Multi-Criteria Decision-Making (MCDM) problem, as there are multiple ontologies to choose from whilst considering multiple criteria. However, there has been little usage of MCDM methods in solving the problem of selecting ontologies for reuse. Therefore, in order to tackle this problem, this study looks to a prominent branch of MCDM, known as the ELimination Et. Choix Traduisant la RÉalite (ELECTRE). ELECTRE is a family of decision-making algorithms that model and provide decision support for complex decisions comprising many alternatives with many characteristics or attributes. The ELECTRE algorithms are extremely powerful and they have been applied successfully in a myriad of domains, however, they have only been studied to a minimal degree with regards to ontology ranking and selection. In this study the ELECTRE algorithms were applied to aid in the selection of ontologies for reuse, particularly, three applications of ELECTRE were studied. The first application focused on ranking ontologies according to their complexity metrics. The ELECTRE I, II, III, and IV models were applied to rank a dataset of 200 ontologies from the BioPortal Repository, with 13 complexity metrics used as attributes. Secondly, the ELECTRE Tri model was applied to classify the 200 ontologies into three classes according to their complexity metrics. A preference-disaggregation approach was taken, and a genetic algorithm was designed to infer the thresholds and parameters for the ELECTRE Tri model. In the third application a novel ELECTRE model was developed, named ZPLTS-ELECTRE II, where the concept of Z-Probabilistic Linguistic Term Set (ZPLTS) was combined with the traditional ELECTRE II algorithm. The ZPLTS-ELECTRE II model enables multiple decision-makers to evaluate ontologies (group decision-making), as well as the ability to use natural language to provide their evaluations. The model was applied to rank 9 ontologies according to five complexity metrics and five qualitative usability metrics. The results of all three applications were analysed, compared, and contrasted, in order to understand the applicability and effectiveness of the ELECTRE algorithms for the task of selecting ontologies for reuse. These results constitute interesting perspectives and insights for the selection and reuse of ontologies.
Assessment of antiretroviral drugs uptake by vegetables from contaminated soil and their adsorption by exfoliated graphite in river and wastewater.
(2022) Kunene, Philisiwe Nganaki.; Mahlambi, Precious Nokwethemba.
This study was directed toward vegetable uptake of the commonly used antiretroviral drugs (ARVDs), abacavir, nevirapine, and efavirenz. Antiretroviral drugs are used to treat the human immune-deficiency virus (HIV). South Africa (SA) is one of the countries with a high number of infected people on ARV therapy, therefore, the ARVDs are anticipated to be existing at high concentrations in the South African environment than in other countries worldwide. In recent years, the presence of ARVDs in the environment has drawn attention; hence studies have reported their presence in aquatic environments while very few studies have been conducted on their uptake using vegetables. This work was therefore based on the optimization and application of sensitive, simple, cost-effective, and robust techniques for quantifying ARVDs in vegetables. Based on this information, ultrasonic extraction (UE) and microwave-assisted extraction (MAE) were used to isolate target compounds from vegetable samples to the aqueous phase. Dispersive liquid-liquid microextraction (DLLME) and solid-phase extraction (SPE) were utilized to preconcentration and clean up the extracts from UE and MAE, respectively. A liquid chromatography photodiode array detector (LC-PDA) was utilized to detect and quantify the extracted compounds. The UE with and without DLLME cleanup were compared with each other, also, MAE with and without SPE cleanup were compared with each other. The methods comparison was done in terms of their detection (LOD) and quantification limits (LOQ), extraction efficiencies (%Recovery), relative standard deviations (%RSD), and concentrations of ARVDs found in vegetable samples. In comparison of UE and ultrasonic-assisted dispersive liquid-liquid microextraction (UADLLME), the LOD and LOQ obtained ranged between 0.0081 - 0.015 μg/kg and 0.027 - 0.049 μg/kg for UE and 0.0028 -0.0051 μg/kg and 0.0094 - 0.017 μg/kg for UADLLME respectively. High recoveries ranging from 93 to 113% in UE and 85 to 103% in UADLLME with less than 10% RSD in both procedures were obtained. These results indicated that UADLLME is more sensitive than the UE method, although they are both accurate and precise. The UE can be recommended for routine analysis as UADLLME showed the inability to extract analytes from root vegetables. The optimized UE and UADLLME methods were applied to extract ARVDs from vegetables bought from local fruit and veggie supermarket. Vegetables were categorized as root (carrot, potato, and sweet potatoes), leaf (cabbage and lettuce), and fruit (green paper, butternut, and tomato). The target ARVDs were quantified in most samples with concentrations up to 8.18 μg/kg. The concentrations obtained were slightly high in UADLLME than in UE as a result of its high sensitivity. Efavirenz was the most dominant drug, while the potato was the most contaminated vegetable. In the comparison of MAE and MAESPE, the obtained LOD and LOQ ranged from 0.020 to 0.032 μg/kg and 0.068 to 0.109 μg/kg for MAE and 0.019 to 0.066 μg/L and 0.065 to 0.22 μg/L for MAE-SPE. The obtained recoveries ranged from 85 to 103% for MAE and from 82 to 98 % for MAE-SPE, respectively, and the RSDs were all less than 6%. These results showed that both methods have comparable sensitivity; however, the recoveries values for MAE were slightly higher than those obtained in MAE-SPE, which signals MAE’s high accuracy. The optimized MAE and MAE-SPE methods were applied to remove ARVDs in the root (potatoes, onions, and beetroot), leaf (lettuce, and spinach), and fruit (green paper, cucumber, and eggplant) vegetables bought from local fruit and veggie supermarket. The obtained ARVDs concentration range was 1.48 ± 0.5 - 27.9 ± 1.2 μg/kg. The MAE-SPE resulted in low concentration compared to MAE without cleanup. Beetroot exhibited high concentrations of the target ARVDs, while nevirapine was found to have high concentration and as a dominant compound. The results obtained revealed that the vegetables from the studied area are contaminted with ARVDs, which could indicate their possible irrigation with wastewater effluent or the use of sludge as biosolids in the agricultural areas. This is a concern as it leads to unintentional consumption by consumers which could lead to drug resistance by the human body or have human health effects. The study was then expanded by conducting the phytoremediation approach to investigate the uptake of abacavir, nevirapine, and efavirenz by beetroot, spinach, and tomato from the contaminated soil. The three selected vegetable plants were planted and irrigated with ARVDs spiked (at 2000 and 5000 μg/L) water over a period of three months. The optimized UE and LC-PDA methods were used to extract and quantify the selected ARVDs from the target vegetables and soil. The obtained results showed that the studied vegetables have the potential to take up abacavir, nevirapine, and efavirenz from contaminated soil, be absorbed by the root, and translocate to the aerial part of the plants. Abacavir was found at high concentrations to a maximum of 40.21 μg/kg in the root, 18.43 μg/kg in the stem, and 6.77 μg/kg in the soil, while efavirenz was the highest concentrations, up to 35.44 μg/kg in leaves and 8.86 μg/kg in fruits. Spinach root accumulated more ARVDs than beetroot and tomato. The bio-accumulation factor ranged from 2.0-14 μg/kg in beetroot, 3.6 - 15 μg/kg in spinach, and 6 – 10 μg/kg in tomato. The root concentration factor range was 0.047 – 17.6 μg/kg; 0.34-5.9 μg/kg, and 0.14-2.82 μg/kg in beetroot, spinach, and tomato, respectively. The translocation factor range obtained was 0.40 – 38 μg/kg, 0.08 – 19 μg/kg, and 0.14 – 49 μg/kg in beetroot, spinach, and tomato, respectively. However, the accumulation of ARVDs in all studied plants showed that they could be used in phytoremediation. The results obtained in the phytoremediation approach revealed that the utilization of the contaminated water has an influence on the presence ARVDs in vegetables; hence this work also focused on evaluating the exfoliated graphite adsorption of ARVDs in water. Natural graphite was intercalated with acids and exfoliated with thermal shock to obtain the exfoliated graphite. The scanning electron microscopy images showed that the exfoliated graphite had increased c-axis distance between the layers with accordion-like structure which were confirmed by the lower density of exfoliated graphite material (0.0068 gmL-1) compared to the natural graphite (0.54 g mL-1). Fourier Transformed Infrared Spectroscopy results showed the C=C in natural and exfoliated graphite at 1635 cm-1 stretching. The phenolic, alcoholic, and carboxylic groups were observed from 1000 to 1700 cm-1 for the intercalated and exfoliated graphite. The Energy-dispersive X-ray results further confirmed these results, which showed carbon and oxygen peaks in the intercalated and exfoliated graphite spectrum, whereas natural graphite showed only a carbon peak. Raman spectroscopy results showed that the material’s crystallinity was not affected by the intercalation and exfoliation processes as observed from the ratios of the G and D peaks and the G' and D'. Natural, intercalated and exfoliated graphite contained the D, G, D', and G' peaks at about 1350 cm-1, 1570 cm-1, 2440 cm-1, and 2720 cm-1, respectively. The exfoliated graphite material showed the characteristic of a hexagonal phase graphitic structure by (002) and (110) reflections in the X-ray diffraction results. The exfoliated graphite adsorption method was optimized based on the pH of a solution, adsorbent dosage, and adsorption time prior to application to water samples. The optimum pH solution, adsorbent dosage, and adsorption time were 7, 30 mg, 0.01 μg/L, and 30 minutes respectively. The kinetics and isotherm studies were conducted to assess the model that best fit and explain the experimental data obtained. The kinetic model and adsorption isotherm studies showed that the experimental data fit well pseudo-second-order kinetics and is well explained by Freundlich’s adsorption isotherm. The maximum adsorption capacity of the exfoliated graphite (EG) for ARVDs ranges between 1.660-197.0, 1.660-232.5, and 1.650-237.7 mg/g for abacavir, nevirapine, and efavirenz, respectively. These results showed that under proper operating conditions, the EG adsorbent could potentially be applied as a water purifying tool for the removal of ARVDs pollutants.
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.
Comparison of extraction methods efficiency for the extraction of polycyclic aromatic hydrocarbons and phenolics in water matrices, sludge and sediment: sources of origin and ecological risk assessment.
(2023) Ndwabu, Sinayo.; Mahlambi, Precious Nokwethemba.; Malungana, Mncedisi.
Polycyclic aromatic hydrocarbons (PAHs) and phenolic compounds (PCs) are persistent and environmentally toxic compounds. This study therefore aimed to determine the levels of both PAHs and PCs in river water, wastewater, sludge and sediment samples. The evaluation of their origin source and ecological risk was also determined. The status of both these contaminants in South African environment is still not fully investigated, which is a gap this study intended to fill together with previous studies that have been carried-out. The PAHs and PCs were extracted using different extraction methods which include a solid phase extraction (SPE) and dispersive liquid-liquid micro-extraction (DLLME) in water matrices. The microwave assisted extraction (MAE) and Ultrasonication (UE) coupled with either filtering (F) or F + SPE as a clean-up technique was used for extraction of solid samples. The analytes extracted form water or sediment were determined using GC-MS. The PAH %recoveries obtained under optimum conditions in liquid samples were determined to be 72.1 - 118% for SPE and 70.7 – 88.4% for DLLME while the LOD and LOQ were 5.00 – 18.0 ng/L and 10.0 – 44.0 ng/L for SPE while they were 6.00 – 20.0 ng/L and 11.0 – 63.0 ng/L for DLLME. The recovery test for PAHs in solid samples gave a range of 93.7% - 121% for UE and 79.6% - 122% for MAE while the LOD and LOQ ranged from 0.0250 μg/kg to 1.21 μg/kg & 0.0800 μg/kg to 3.54 μg/kg for MAE and from 0.0840 μg/kg to 0.215 μg/kg & 0.0190 μg/kg to 0.642 μg/kg for UE respectively. The LOD and LOQs for PCs in both water and solid matrices were 0.01 – 2.00 μg/L and 0.02 – 6.07 μg/L for SPE, 0.05 – 1.20 μg/kg and 0.17 – 3.17 μg/kg for MAE and 0.09 – 1.33 μg/kg and 0.26 - 3.54 μg/kg for UE correspondingly, their %recovery test gave ranges of 75.2 – 112% (SPE), 80.9 – 110% (MAE) and 79.3 – 119% (UE).The optimization and validation of these methods indicated that they can be used for the extraction of PAHs or PCs in liquid samples, however, SPE when compared to DLLME showed to be more accurate and sensitive. Moreover, in solid samples the clean-up method was a deciding factor, with F + SPE cleaned samples giving higher concentrations of both PCs and PAHs than the filtered ones in both MAE and UE. The concentrations of PAHs ranged from nd (not detected) to 1046 ng/L in river water and nd to 778 ng/L in wastewater samples with naphthalene showing dominance over all other PAHs in both water matrices. The PC concentrations at 4.12 to 1134 μg/L for wastewater and nd to 98.0 μg/L for river water were high but still within the maximum allowable limit except for 2.4-DCP (2.4 dichlorophenol) at Wdv4. The concentrations obtained from F + SPE cleaned samples were higher for both PAHs and PCs with a range from 95.96 to 926.0 μg/kg and 1.30 to 310 μg/kg compared to concentrations from filtered only samples at 21.61 to 380.6 μg/kg and 0.90 to 266 μg/kg respectively. Pyrene showed dominance over all other PAHs in both sludge and sediments while 2.4-DCP and PCP dominated the sludge and sediment samples respectively. PAHs were determined to be of petrogenic (water matrices) and pyrolytic (solid samples) origin and on average posed low (water matrices) and a medium to high (solid matrices) ecological risk. The ILCRderm values at 4.98 x 10-1 and 2.62 x 10-1 (DahA) and 5.92 x 10-2 and 5.34 x 10-2 (PCP) were highfor adults compared to that of children at 1.92 x 10-1 and 1.01 x 10-1 (DahA) and 1.39 x 10-2 and 1.26 x 10-2 (PCP) for both sediment and sludge samples respectively. The low values of ILCRderm for children indicates that the have a high risk exposure even at low concentrations of the contaminants. The findings of this study showed that both areas (uMsunduzi river and Darvill wastewater works (WWW) of interest are polluted with PAHs and PCs therefore, more regulations such as the National Environmental Management: Waste Act (NEMWA) are needed to ensure environmental, human and animal safety.
Deep learning for brain tumor segmentation and survival prediction.
(2024) Magadza, Tirivangani Batanai Hendrix Takura.; Viriri, Serestina.
A brain tumor is an abnormal growth of cells in the brain that multiplies uncontrolled. The death of people due to brain tumors has increased over the past few decades. Early diagnosis of brain tumors is essential in improving treatment possibilities and increasing the survival rate of patients. The life expectancy of patients with glioblastoma multiforme (GBM), the most malignant glioma, using the current standard of care is, on average, 14 months after diagnosis despite aggressive surgery, radiation, and chemotherapies. Despite considerable efforts in brain tumor segmentation research, patient diagnosis remains poor. Accurate segmentation of pathological regions may significantly impact treatment decisions, planning, and outcome monitoring. However, the large spatial and structural variability among brain tumors makes automatic segmentation a challenging problem, leaving brain tumor segmentation an open challenge that warrants further research endeavors. While several methods automatically segment brain tumors, deep learning methods are becoming widespread in medical imaging due to their resounding performance. However, the boost in performance comes at the cost of high computational complexity. Therefore, to improve the adoption rate of computer-assisted diagnosis in clinical setups, especially in developing countries, there is a need for more computational and memoryefficient models. In this research, using a few computational resources, we explore various techniques to develop deep learning models accurately for segmenting the different glioma sub-regions, namely the enhancing tumor, the tumor core, and the whole tumor. We quantitatively evaluate the performance of our proposed models against the state-of-the-art methods using magnetic resolution imaging (MRI) datasets provided by the Brain Tumor Segmentation (BraTS) Challenge. Lastly, we use segmentation labels produced by the segmentation task and MRI multimodal data to extract appropriate imaging/radiomic features to train a deep learning model for overall patient survival prediction.
Deep learning framework for speech emotion classification.
(2024) Akinpelu, Samson Adebisi.; Viriri, Serestina.
A robust deep learning-based approach for the recognition and classification of speech emotion is proposed in this research work. Emotion recognition and classification occupy a conspicuous position in human-computer interaction (HCI) and by extension, determine the reasons and justification for human action. Emotion plays a critical role in decision-making as well. Distinguishing among various emotions (angry, sad, happy, neutral, disgust, fear, and surprise) that exist from speech signals has however been a long-term challenge. There have been some limitations associated with existing deep learning techniques as a result of the complexity of features from human speech (sequential data) which consists of insufficient label datasets, Noise and Environmental Factors, Cross-cultural and Linguistic Differences, Speakers’ Variability and Temporal Dynamics. There is also a heavy reliance on huge parameter tunning, especially for millions of parameters before the model can learn the expected emotional features necessary for classification emotion, which often results in computational complexity, over-fitting, and poor generalization. This thesis presents an innovative deep learning framework-based approach for the recognition and classification of speech emotions. The deep learning techniques currently in use for speech-emotion classification are exhaustively and analytically reviewed in this thesis. This research models various approaches and architectures based on deep learning to build a framework that is dependable and efficient for classifying emotions from speech signals. This research proposes a deep transfer learning model that addresses the shortcomings of inadequate training datasets for the classification of speech emotions. The research also models advanced deep transfer learning in conjunction with a feature selection algorithm to obtain more accurate results regarding the classification of speech emotion. Speech emotion classification is further enhanced by combining the regularized feature selection (RFS) techniques and attention-based networks for the classification of speech emotion with a significant improvement in the emotion recognition results. The problem of misclassification of emotion is alleviated through the selection of salient features that are relevant to emotion classification from speech signals. By combining regularized feature selection with attention-based mechanisms, the model can better understand emotional complexities and outperform conventional ML model emotion detection algorithms. The proposed approach is very resilient to background noise and cultural differences, which makes it suitable for real-world applications. Having investigated the reasons behind the enormous computing resources required for many deep learning based methods, the research proposed a lightweight deep learning approach that can be deployed on low-memory devices for speech emotion classification. A redesigned VGGNet with an overall model size of 7.94MB is utilized, combined with the best-performing classifier (Random Forest). Extensive experiments and comparisons with other deep learning models (DenseNet, MobileNet, InceptionNet, and ResNet) over three publicly available speech emotion datasets show that the proposed lightweight model improves the performance of emotion classification with minimal parameter size. The research further devises a new method that minimizes computational complexity using a vision transformer (ViT) network for speech emotion classification. The ViT model’s capabilities allow the mel-spectrogram input to be fed into the model, allowing for the capturing of spatial dependencies and high-level features from speech signals that are suitable indicators of emotional states. Finally, the research proposes a novel transformer model that is based on shift-window for efficient classification of speech emotion on bi-lingual datasets. Because this method promotes feature reuse, it needs fewer parameters and works well with smaller datasets. The proposed model was evaluated using over 3000 speech emotion samples from the publicly available TESS, EMODB, EMOVO, and bilingual TESS-EMOVO datasets. The results showed 98.0%, 98.7%, and 97.0% accuracy, F1-Score, and precision, respectively, across the 7 classes of emotion.
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”.
Design and fabrication of tissue-like phantoms for use in biomedical imaging.
(2022) Ntombela, Lindokuhle Charles.; Chetty, Naven.; Adeleye, Bamise.
The continuous need for tissue-like samples to understand biological systems and the development of new diagnostic and therapeutic applications has led to the adoption of tissue models using potential materials. This work presents a low-cost method for manufacturing PVAslime glue-based phantoms to replicate diseased and healthy biological tissues’ optical, mechanical, and structural properties. The deformable phantoms with complex geometries are vital to model tissues’ anatomic shapes and chemical composition. Absorption and scattering properties were set by adding black India ink and aluminium oxide (Al2O3) particles in varying quantities to obtain slime phantom tissues with optical properties of the brain, malignant brain tumour, lung carcinoma, and post-menopausal uterus. The phantom properties were characterized and validated using a He-Ne laser emitting at 532 nm and 630 nm wavelengths propagated through various thicknesses of the fabricated phantom. The incident and transmitted intensity were measured to determine the absorption coefficient (a) and scattering coefficient (s). Furthermore, the effective attenuation coefficient (eff ) and penetration depth () were deduced from the reduced scattering coefficient (0s) and the anisotropy factor (g) obtained through the scattering phase function and Wolfram Mathematica. The anisotropy factor demonstrated a forward scatter, typical of strongly scattering media as real tissues. Such geometrically and optically realistic phantoms would function as effective tools for developing techniques in diagnostic and therapeutic applications such as laser ablation and PDT cancer treatment.
Determination of neonicotinoid insecticides in water, soil and sediment samples: acute and chronic risk assessment.
(2022) Ngomane, Nkosinathi Chris.; Mahlambi, Precious Nokwethemba.
Neonicotinoids are a type of insecticides pesticides widely used worldwide as a result of their low vertebrates toxicity, relative environmental stabilities, good bioavailability and high level of selectiveness. These insecticides are commonly employed in agricultural activities, in grass management and horticulture as well as in households to control domestic pet flea. Due to neonicotinoids intensive usage, they are continuously introduced to the water bodies where they can adversely affect the aquatic life and accumulate in sediments. Moreover, they can end up in drinking and unintentionally consumed by human beings resulting to health effects. With this regard, this work reports for the first time on the occurrence of neonicotinoids in sediment, soil tap, sludge, wastewater and river water samples from the province of KwaZulu-Natal. Also, the ecological risk of neonicotinoids in water sources was also assessed for the first time in the samples from this province.The liquid chromatography coupled with a photo-diode array detector (LC-PDA) method was modified and applied for the simultaneous detection of neonicotinoids (clothianidin, thiamethoxam and imidacloprid). Ultrasonic extraction (UE), soxhlet extraction (SE) and solid-phase extraction (SPE) methods were developed and applied for the extraction of nitro-guanidine neonicotinoids in water, soil and sediment samples. The SPE, SE, and UE parameters that influence the recoveries of the analytes were first optimized before application to real samples for the analytes recovery improvement. The SPE was used for the extraction of neonicotinoids in sludge and water samples, while SE and UE were both used to extract soil and sediment samples. The extraction conditions optimized for SPE were conditioning solvent and sample volume. While for the UE were extraction time, extraction solvent, and the solvent volume. And for SE method, extraction solvent and the extraction solvent volume were optimized. The LC-PDA method used for detection was also first optimized to improve peak separation, retention times, detection limits and quantification limits. The optimized parameters for the LC-PDA method were the mobile phase, flow rate, and the PDA detection wavelength. Optimum water recoveries of the neonicotinoids ranged from 79 to 112%. The detection and quantification limits of the analytes in water samples were 0.013 - 0.031 μg/L and 0.041 - 0.099 μg/L, respectively. The obtained analytes concentration ranged from 0.061 - 0.10 μg/L, 0.077- 3.76 μg/L and 0.99 - 15 μg/L in tap, river and wastewater, respectively. Analyte recoveries ranged from 85 - 102% in soil and 92 - 103% in sediment for the ultrasonic extraction method. The neonicotinoid recoveries ranged from 83 to 109% in soil and between 84 to 94% in sediment samples for the Soxhlet extraction method. The method’s detection limits and quantification limits in solid samples ranged from 40 - 80 μg/kg and 140 - 270 μg/kg, respectively. The relative standard deviation was less than 4%. The concentration determined in real environmental samples were 47 to 410 μg/kg in soil and 25 to 410 in sediment. The toxicity studies showed that clothianadin pose a high risk towards daphnia species in the river. Imidacloprid, clothianidin and thiamethoxam posed medium risk against algae, daphnia and fish species in the effluent receiving water bodies. These results imply the necessity to continuously monitor these neonicotinoids in the water sources. In South Africa there is limited data concerning the environmental occurrence of neonicotinoids, therefore this work will contribute towards the information available for the analysis of neonicotinoids. This will assist the policy makers to establish the MRL values that are precise for the African continent.
Diffuse radio emission in ACTPol clusters.
(2021) Sikhosana, Sinenhlanhla Precious.; Moodley, Kavilan.; Knowles, Kenda Leigh.; Hilton, Matthew James.
Low-frequency radio observations of galaxy clusters reveal cluster-scale diffuse emission that is not associated with individual galaxies. Studying the properties of these diffuse radio sources gives insight into astrophysical processes such as cosmic ray transportation in the intracluster medium (ICM). Observations have linked the formation of radio halos and relics with turbulence caused by cluster mergers and the formation of mini-halos to gas sloshing in cool-core clusters. Statistical studies of large galaxy cluster samples have been used to determine how the radio properties of diffuse emission scale with the mass and X-ray luminosity of the host clusters. Such studies are crucial for refining the formation theories of diffuse emission. New generation telescopes with wide bandwidths and high sensitivity such as the upgraded Giant Metrewave Radio Telescope (uGMRT) andMeerKAT are advantageous for the study of faint extended emission in large cluster samples. The main aim of this thesis was to do an in-depth study of the diffuse radio emission using a cluster sample that spans a wider mass and redshift range compared to the currently studied parameter space. We developed data reduction techniques for calibrating data from telescopes such as uGMRT and MeerKAT. The wide bandwidth of these telescopes introduces directional dependent effects (DDEs) that make the calibration process extremely complicated. However, such observations are excellent for studies of the faint diffuse emission and in-band spectral indices of this emission. In the first part of this thesis, we focused on the study of diffuse radio emission in a Sunyaev- Zeldovich (SZ) selected sample of clusters. These clusters were observed by the Atacama Cosmology Telescope’s Polarimetric extension (ACTPol). We used archival and new GMRT observations for the radio analysis of this sample. We reported newly detected diffuse emission in the following clusters: a radio halo and revived fossil plasma in ACT-CL J0137.4 0827, a radio relic in ACT-CL J2128.4+0135, and a candidate relic in ACT-CL J0022.2 0036. The radio analysis of the full sample revealed that the fraction of clusters in the sample hosting diffuse emission is 26.7% excluding candidate emission and 30% when it is included. The detection rate of the diffuse emission over all categories is lower than the detection rates reported in literature. We note that this may be because the sample comprised high redshift (z ¡ 0.5) and low mass clusters (M500c;SZ 5 1014 Md), though future more sensitive observations of these clusters could reveal fainter diffuse emission structures. We compared our results to the most recent radio halo and radio relic scaling relations. The radio halo P1:4GHz M500 scaling relation plot indicates that a few flatter spectrum radio halos are located in the region previously known to be populated by ultrasteep spectrum radio halos (USSRHs). Finally, we presented preliminary results of the uGMRT wideband backend (GWB) data reduction for ACT-CL J0034.4+0225, ACT-CL J0137.4 0827, and ACT-CL J2128.4+0135. We prioritised these clusters because the narrowband data revealed that they host diffuse emission. However, once the data reduction algorithm is improved, we will reduce the remaining clusters with non-detections. Comparing the GWB results to the narrowband GMRT data, we note that the radio halo observed in ACT-CL J0137.4 0827 is more extended in the GWB data. The diffuse emission is detected at a higher signal-to-noise ratio in the GWB images for the three clusters. We note that an improvement in the GWB reduction algorithm might reveal diffuse emission that was not detected in the narrowband data. In the second part of the thesis, we used MeerKAT observations to study diffuse emission in the Bullet Cluster (1E0657 56), RXCJ1314.4 2515, Abell 3562, and Abell 3558. We detected new extended features in the radio halos hosted by the Bullet cluster and Abell 3562. We assume that the decrement feature in the Bullet cluster might be an indication of a second wave of merger activity. The ridge feature in the peripheral region of the radio halo in Abell 3562 overlaps with the edge of the X-ray emission. Hence, we assume that the feature might be related to a shock region. We also reported the detection of a new mini-halo in Abell 3558. MeerKAT’s sensitivity and wide bandwidth enabled us to perform in-band spectral index studies and produce spectral index maps for the Bullet cluster, RXCJ1314.4 2515, and Abell 3562. The spectral index maps of the relics in the Bullet cluster and RXCJ1314.4 2515 indicate a spectral steepening towards the cluster center, while the spectral index map of the radio halo in the Bullet cluster indicates radial spectral steepening. The spectral index map of Abell 3562 indicates that the radio halo and ridge have similar spectral index variations, which suggests that the ridge feature is related to the radio halo.
Discrete time-to-event construction for multiple recurrent state transitions.
(2023) Batidzirai, Jesca Mercy.; Manda, Samuel.; 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.
Exploration of ear biometrics with deep learning.
(2024) Booysens, Aimee Anne.; Viriri, Serestina.
Biometrics is the recognition of a human using biometric characteristics for identification, which may be physiological or behavioural. Numerous models have been proposed to distinguish biometric traits used in multiple applications, such as forensic investigations and security systems. With the COVID-19 pandemic, facial recognition systems failed due to users wearing masks; however, human ear recognition proved more suitable as it is visible. This thesis explores efficient deep learning-based models for accurate ear biometrics recognition. The ears were extracted and identified from 2D profiles and facial images, focusing on both left and right ears. With the numerous datasets used, with particular mention of BEAR, EarVN1.0, IIT, ITWE and AWE databases. Many machine learning techniques were explored, such as Naïve Bayes, Decision Tree, K-Nearest Neighbor, and innovative deep learning techniques: Transformer Network Architecture, Lightweight Deep Learning with Model Compression and EfficientNet. The experimental results showed that the Transformer Network achieved a high accuracy of 92.60% and 92.56% with epochs of 50 and 90, respectively. The proposed ReducedFireNet Model reduces the input size and increases computation time, but it detects more robust ear features. The EfficientNet variant B8 achieved a classification accuracy of 98.45%. The results achieved are more significant than those of other works, with the highest achieved being 98.00%. The overall results showed that deep learning models can improve ear biometrics recognition when both ears are computed.
Financial modelling of cryptocurrency: a case study of Bitcoin, Ethereum, and Dogecoin in comparison with JSE stock returns.
(2022) Kaseke, Forbes.; Ramroop, Shaun.; Mwambi, Henry Godwell.
The emergency of cryptocurrency has caused a shift in the financial markets. Although it was created as a currency for exchange, cryptocurrency has been shown to be an asset, with investors seeking to profit from it rather than using it as a medium of exchange. Despite being a financial asset, cryptocurrency has distinct, stylised facts like any other asset. Studying these stylised facts allows the creation of better-suited models to assist investors in making better data-driven decisions. The data used in this thesis was of three leading cryptocurrencies: Bitcoin, Ethereum, and Dogecoin and the Johannesburg Stock Exchange (JSE) data as a guide for comparison. The sample period was from 18 September 2017 to 27 May 2021. The goal was to research the stylised facts of cryptocurrencies and then create models that capture these stylised facts. The study developed risk-quantifying models for cryptocurrencies. The main findings were that cryptocurrency exhibits stylised facts that are well-known in financial data. However, the magnitude and frequency of these stylised facts tend to differ. For example, cryptocurrency is more volatile than stock returns. The volatility also tends to be more persistent than in stocks. The study also finds that cryptocurrency has a reverse leverage effect as opposed to the normal one, where past negative returns increase volatility more than past positive returns. The study also developed a hybrid GARCH model using the extreme value theorem for quantifying cryptocurrency risk. The results showed that the GJR-GARCH with GDP innovations could be used as an alternative model to calculate the VaR. The volatile nature of cryptocurrency was also compared with that of the JSE while accounting for structural breaks and while not accounting for them. The results showed that the cryptocurrencies’ volatility patterns are similar but differ from those of the JSE. The cryptocurrency was also found to be an inefficient market. This finding means that some investors can take advantage of this inefficiency. The study also revealed that structural breaks affect volatility persistence. However, this persistence measure differs depending on the model used. Markov switching GARCH models were used to strengthen the structural break findings. The results showed that two-regime models outperform single-regime models. The VAR and DCC-GARCH models were also used to test the spillovers amongst the assets used. The results showed short-run spillovers from Bitcoin to Ethereum and long-run spillovers based on the DCC-GARCH. Lastly, factors affecting cryptocurrency adoption were discussed. The main reasons affecting mass adoption are the complexity that comes with the use of cryptocurrency and its high volatility. This study was critical as it gives investors an understanding of the nature and behaviour of cryptocurrency so that they know when and how to invest. It also helps policymakers and financial institutions decide how to treat or use cryptocurrency within the economy.
Flexible Bayesian hierarchical spatial modeling in disease mapping.
(2022) Ayalew, Kassahun Abere.; Manda, Samuel.
The Gaussian Intrinsic Conditional Autoregressive (ICAR) spatial model, which usually has two components, namely an ICAR for spatial smoothing and standard random effects for non-spatial heterogeneity, is used to estimate spatial distributions of disease risks. The normality assumption in this model may not always be correct and misspecification of the distribution of random effects could result in biased estimation of the spatial distribution of disease risk, which could lead to misleading conclusions and policy recommendations. Limited research studies have been done where the estimation of the spatial distributions of diseases under the ICAR-normal model were compared to those obtained from fitting ICAR-nonnormal model. The results from these studies indicated that the ICAR-nonnormal models performed better than the ICAR-normal in terms of accuracy, efficiency and predictive capacity. However, these efforts have not fully addressed the effect on the estimation of spatial distributions under flexible specification of ICAR models in disease mapping. The overall aim of this PhD thesis was to develop approaches that relax the normality assumption that is often used in modeling and fitting of ICAR models in the estimation of spatial patterns of diseases. In particular, the thesis considered the skewnormal and skew-Laplace distributions under the univariate, and skew-normal for the multivariate specifications to estimate the spatial distributions of either univariable or multivariable areal data. The thesis also considered non-parametric specification of the multivariate spatial effects in the ICAR model, which is a novel extension of an earlier work. The estimation of the models was done using Bayesian statistical approaches. The performances of our suggested alternatives to the ICAR-normal model were evaluated by simulating studies as well as with practical application to the estimation of district-level distribution of HIV prevalence and treatment coverage using health survey data in South Africa. Results from the simulation studies and analysis of real data demonstrated that our approaches performed better in the prediction of spatial distributions for univariable and multivariable areal data in disease mapping approaches. This PhD has shown the limitations of relying on the ICAR-normal model for the estimations of spatial distributions for all spatial analyses, even when the data could be asymmetric and non-normal. In such scenarios, skewed-ICAR and nonparametric ICAR approaches could provide better and unbiased estimation of the spatial pattern of diseases.
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.
Hybrid genetic optimisation for quantum feature map design.
(2024) Pellow-Jarman, Rowan Martin.; Pillay, Anban Woolaganathan.; Ilya, Sinayskiy.; Petruccione, Francesco.
Good feature maps are crucial for machine learning kernel methods for effective mapping of non-linearly separable input data into a higher dimension feature space, thus allowing the data to be linearly separable in feature space. Recent works have proposed automating the task of quantum feature map circuit design with methods such as variational ansatz parameter optimization and genetic algorithms. A problem commonly faced by genetic algorithm methods is the high cost of computing the genetic cost function. To mitigate this, this work investigates the suitability of two metrics as alternatives to test set classification accuracy. Accuracy has been applied successfully as a genetic algorithm cost function for quantum feature map design in previous work. The first metric is kernel-target alignment, which has previously been used as a training metric in quantum feature map design by variational ansatz training. Kernel-target alignment is a faster metric to evaluate than test set accuracy and does not require any data points to be reserved from the training set for its evaluation. The second metric is an estimation of kernel-target alignment which further accelerates the genetic fitness evaluation by an adjustable constant factor. The second aim of this work is to address the issue of the limited gate parameter choice available to the genetic algorithm. This is done by training the parameters of the quantum feature map circuits output in the final generation of the genetic algorithm using COBYLA to improve either kernel-target alignment or root mean squared error. This hybrid approach is intended to complement the genetic algorithm structure optimization approach by improving the feature maps without increasing their size. Eight new approaches are compared to the accuracy optimization approach across nine varied binary classification problems from the UCI machine learning repository, demonstrating that kernel-target alignment and its approximation produce feature map circuits enabling comparable accuracy to the original approach, with larger margins on training data that improve further with variational training.
Improved collection of photogenerated current using bi-metal nanoparticles.
(2024) Jili, Ncedo.; Mola, Genene Tessema.
The energy demand has been continuously growing owing to the shortage of sources of traditional energy (such as fossil fuels), due to the growing population of the world, and increased industrialization, which prompted the need for more energy. However renewable energy (such as photovoltaics) has attained attention due to its reliance on the infinite energy source (sun) which provides an hour long energy flow that fulfil the yearly energy of the glob. Not only that, renewable energy sources offer clean energy, that is meant to contribute to decarbonization in the future and reduce environmental changes. Solar cell materials that can effectively capture photons and conduct charges are continuously investigated for the last six decades. Contrarily to silicon based solar cells, organic solar cells are among the most promising solar cells in terms of offering cheap device fabrication, flexibility, high absorption, etc. However, these solar cells still suffer from low efficiency compared to traditional silicon solar cells due to poor absorption, low mobility, and poor stability. Numerous strategies have been employed to improve the efficiency of OSC devices, these include Ternary OScs, Tandem OSCs, and the inclusion of nanoparticles in OSC devices. Nanoparticles remain the best candidate to feature in OSC devices because Tandem OSCs require multi-absorber layers which leads to high device cost, whereas nanoparticles can be produced at a small scale and still offer good results. This study takes advantage of the features offered by the nanoparticles and uses them to investigate the effect of Nickel doped with cobalt bi-metal nanoparticles(Ni/Co BMNPs) in the PEDOT:PSS buffer layers of the P3HT: PCBM-based devices. Solar cells were successfully fabricated with four different concentrations of Ni/Co BMNPs as 0.05 %(0.5 mg), 0.15 %(1.5 mg), and 0.25 %(2.5 mg). Significant improvements were achieved for the 0:05% with the Fill factor of 58:52 %, and current density of 15.31 mA/cm2, and maximum efficiency of 5:05 % which displayed 67:8 % improvement from the undoped device. The investigation was further conducted by simulation program called SCAPS to confirm the contribution of the metal nanoparticles on the device performance. The results were reproduced in SCAPS where the energy band gap of the P3HT:PCBM and the shallow conduction density of electrons of the PEDO:PSS were simultaneously varied. All results are comparable with the experimental results and found to be similar. The device that was made to mimic the 0:05 % device produced a FF of 57:76 %, Jsc of 15.76 mA/cm2, and maximum efficiency of 5:76 % which displayed 88 % improvement from the undoped device. This study further provides factors that contributed to the high/low device performance due to the inclusion of the BMNPs in the OSC device and some of the necessary background and theory are provided to support these findings.
Mathematical modelling of the Ebola virus disease.
(2024) Abdalla, Suliman Jamiel Mohamed.; Govinder, Keshlan Sathasiva.; Chirove, Faraimunashe.
Despite the numerous modelling efforts to advise public health physicians to understand the dynamics of the Ebola virus disease (EVD) and control its spread, the disease continued to spread in Africa. In the current thesis, we systematically review previous EVD models. Further, we develop novel mathematical models to explore two important problems during the 2018-2020 Kivu outbreak: the impact of geographically targeted vaccinations (GTVs) and the interplay between the attacks on Ebola treatment centres (ETCs) and the spread of EVD. In our systematic review, we identify many limitations in the modelling literature and provide brief suggestions for future work. Our modelling findings underscore the importance of considering GTVs in areas with high infections. In particular, we find that implementing GTVs in regions with high infections so that the total vaccinations are increased by 60% decreases the cumulative cases by 15%. On the other hand, we need to increase the vaccinations to more than 1000% to achieve the 15% decrease in EVD cases if we implement GTVs in areas with low infections. On the impact of the attacks on ETCs, we find that due to the attacks on ETCs, the cumulative cases increased by more than 17% during the 2018-2020 Kivu outbreak. We also find that when 10% of the hospitalised individuals flee the attacks on ETCs after spending only three days under treatment, the cumulative cases increased by more than 30% even if these individuals all returned to the ETCs three days later. On the other hand, if only half of these individuals returned to ETCs for treatment, the cumulative cases increase by approximately 50%. Further, when these patients spend one more day in the community, after which they all return to ETCs, the cumulative cases rise by an additional 10%. Global sensitivity analysis also confirmed these findings. To conclude, our literature systematic review is used to identify many critical factors which were overlooked in previous EVD models. Our modelling findings show that the attacks on ETCs can be destructive to the efforts of EVD response teams. Hence, it is important for decision-makers to tackle the reasons for community distrust and address the roots of the hostility towards ETCs. We also find that GTVs can be used to contain the spread of EVD when ring vaccinations, contact tracing and antiviral treatments cannot successfully control the spread of EVD.

Browse

Browsing College of Agriculture, Engineering and Science by SDG "SDG4"