Department of Applied Mathematics

Permanent URI for this community

https://scholar.sun.ac.za/handle/10019.1/96341

Browse

Browsing Department of Applied Mathematics by browse.metadata.advisor "Bah, Bubacarr"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Analysing retinal fundus images with deep learning models
    (Stellenbosch : Stellenbosch University, 2023-12) Ofosu Mensah, Samuel; Bah, Bubacarr; Brink, Willie; Stellenbosch University. Faculty of Science. Dept. of Mathematical Sciences. Applied Mathematics Division.
    ENGLISH ABSTRACT: Convolutional neural networks (CNNs) have successfully been used to classify diabetic retinopathy but they do not provide immediate explanations for their decisions. Explainability is relevant, especially for clinicians. To make results explainable, we use a post-attention technique called gradient-weighted class activation mapping (Grad- CAM) on the penultimate layer of deep learning models to produce localisation maps on retinal fundus images after using them to classify diabetic retinopathy. Moreover, the models were initialised using pre-trained weights obtained from training models on the ImageNet dataset. The results of this are fewer training epochs and improved performance. Next, we predict cardiovascular risk factors (CVFs) using retinal fundus images. In detail, we use a multi-task learning (MTL) model since there are several CVFs. The impact of using an MTL model is the advantage of simultaneously training for and predicting several CVFs rather than doing so individually. Also, we investigate the performance of the fundus cameras used to capture the retinal fundus images. We notice a superior performance of the desktop fundus cameras to the handheld fundus camera. Finally, we propose a hybrid model that fuses convolutions and Transformer encoders. This is done to harness the benefits of convolutions and Transformer encoders. We compare the performance of the proposed model with other attention-based models and observe on-par performance.
  • Thumbnail Image
    Item
    Fruit detection in an orchard using deep learning approaches
    (Stellenbosch : Stellenbosch University, 2022-04) Koech, Kiprono Elijah; Bah, Bubacarr; Stellenbosch University. Faculty of Science. Dept. of Mathematical Sciences (Applied Mathematics)
    ENGLISH ABSTRACT: Over the last few years, we have witnessed rapid advancement in technology in different fields: communication, transport security, finance, and medicine. Agriculture is no exception. Today, agriculture is practised with sophisticated technologies such as satellite imaging, soil and water sensors, weather tracking, and robots. Fruit detection is a critical process in robot harvesting and yield estimation. With the rise in deep learning, state-of-the-art object detectors have been developed. In this paper, we deploy two state-of-the-art model detectors; namely, Mask Region-based CNN (Mask R-CNN), and You Only Look Once (YOLOv5), in the context of fruit detection. The training data are orchard images of apples and mangoes taken under natural outdoor conditions. The images are taken under varied illumination conditions to ensure that the models learn rich features allowing them to generalize well in a new dataset. Ablation studies are presented to understand how the two models compare in terms of accuracy and speed at inference time. We also investigated the significance of transfer learning in such an application. In particular, we considered weight initialization using ImageNet, COCO, and weights from models trained on a di erent orchard dataset. As a post-processing step, we implemented ensemble techniques on the detection results of the two models. Mask R-CNN and YOLOv5 attained an F1 score of 93% on mangoes datasets and 88% on apple images, and ensembling led to an up to 3% increase in F1 score.
  • Thumbnail Image
    Item
    The Impact of peptide flanking residues on predicting peptide-MHC-II binding interactions using convolutional Neural Networks
    (Stellenbosch : Stellenbosch University, 2022-04) Daumas, Tshenolo Thato Eustacia; Bah, Bubacarr; Degoot, Abdoelnaser M.; Ndifon, Wilfred; Stellenbosch University. Faculty of Science. Dept. of Mathematical Sciences (Applied Mathematics)
    ENGLISH ABSTRACT: Major histocompatibility complex class II (MHC-II) is one of three classes of MHC molecules and is located on the surface of professional antigen presenting cells. MHC-II molecules present antigenic peptides derived from pathogens that cause infection, for recognition by CD4+ T lymphocytes. MHC-II molecules are critical components of the chain of intercellular interactions required for the adaptive im- mune response to be launched successfully, as this chain is thought to begin with the binding of antigenic peptides by MHC-II molecules. While considerable progress in computational efforts have been made towards un- derstanding peptide-MHC interactions for classes I and II, the case for peptide- MHC-II remains challenging due to MHC-II molecules being highly polymorphic and having open-ended binding grooves. Consequently, MHC-II molecules interact with peptides of varying lengths; therefore, the role that peptide flanking residues (PFRs) play in peptide-MHC-II binding interactions must be considered. We pro- pose an allele-specific convolutional neural network model that simulates binding interactions between peptides and MHC-II molecules that also incorporates PFR information in the input. Deep learning models for peptide-MHC-II interactions that have been published, such as the allele-specific model, NetMHCII and the transallelic model NetMHCI- Ipan have demonstrated encouraging predictive performance. When compared, our proposed CNN model outperformed the latest version of the model, NetMHCII-2.3 across all MHC-II alleles considered with mean AUC value of 0.951 as compared with 0.822 for NetMHCII-3.2. Furthermore, we analysed the impact that PFRs have on modelling peptide-MHC-II binding interactions and laid the foundations of de- veloping a transallelic model based on the CNN model.
  • Thumbnail Image
    Item
    Intelligent control for processing solar photovoltaic energy
    (Stellenbosch : Stellenbosch University, 2023-12) Wacira, Joseph Muthui; Bah, Bubacarr; Vargas, Alessandro; Stellenbosch University. Faculty of Science. Dept. of Applied Mathematics.
    ENGLISH ABSTRACT: Maximum Power Point Tracking (MPPT) techniques play a pivotal role in optimizing the performance of photovoltaic systems within renewable energy. Traditional MPPT methods, often reliant on Proportional Integral and Derivative (PID) controllers, face challenges when applied to nonlinear systems with dynamic operating conditions, typical in photovoltaic systems where temperature and irradiance continually fluctuate. The inherent static nature of the PID parameters leads to power losses, thereby reducing their efficiency. Additionally, they rely on trial-and-error approaches to determine the actual Maximum Power Point (MPP). This study introduces two novel MPPT approaches: the Gradient Descent Approach and the Deep Q-Network (DQN) approach. These methods share a common feature: they require knowledge of the maximum power point (MPP). An ANN was employed to predict the MPP under current operating conditions. Once the MPP is known, the Gradient Descent Approach aims to minimize the mean squared error by adjusting the duty cycle, whereas the DQN Approach employs a state-action-reward system that penalizes deviations from the MPP and large actions. To evaluate the effectiveness o f t hese a pproaches, s imulations were conducted under uniform operating conditions using MATLAB/Simulink, with data sourced from the NSRBD website for Brazil. The results were compared with those of the conventional Perturb and Observe algorithm with a PI controller tuned using the Ziegler-Nichols method under Standard Test Conditions. Simulations revealed that the proposed methodologies exhibited significantly higher efficiency than the benchmark algorithm. Furthermore, they demonstrate fast response times and minimal steady-state errors. Although these findings underscore the promise of the proposed approaches, further validation in real-world environments is necessary to confirm their superiority and practical applicability.