Browsing by Subject "Advanced Analytics"

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    Open Access
    Automated quantification of plant water transport network failure using deep learning
    (2021) Naidoo, Tristan; Britz, Stefan; Moncrieff, Glenn
    Droughts, exacerbated by anthropogenic climate change, threaten plants through hydraulic failure. This hydraulic failure is caused by the formation of embolisms which block water flow in a plant's xylem conduits. By tracking these failures over time, vulnerability curves (VCs) can be created. The creation of these curves is laborious and time consuming. This study seeks to automate the creation of these curves. In particular, it seeks to automate the optical vulnerability (OV) method of determining hydraulic failure. To do this, embolisms need to be segmented across a sequence of images. Three fully convolutional models were considered for this task, namely U-Net, U-Net (ResNet34), and W-Net. The sample consisted of four unique leaves, each with its own sequence of images. Using these leaves, three experiments were conducted. They considered whether a leaf could generalise across samples from the same leaf, across different leaves of the same species, and across different species. The results were assessed on two levels; the first considered the results of the segmentation, and the second considered how well VCs could be constructed. Across the three experiments, the highest test precision-recall AUCs achieved were 81%, 45%, and 40%. W-Net performed the worst across the models, while U-Net and U-Net (ResNet-34) performed similarly to one another. VC reconstruction was assessed using two metrics. The first is Normalised Root Mean Square Error. The second is the difference in Ψ50 values between the true VC and the predicted VC, where Ψ50 is a physiological value of interest. This study found that the shape of the VCs could be reconstructed well if the model was able to recall a portion of embolisms across all images which had embolisms. Moreover, it found that some images may be more important than others due to a non-linear mapping between time and water potential. VC reconstruction was satisfactory, except for the third experiment. This study demonstrates that, in certain scenarios, automation of the OV method is attainable. To support the ubiquitous use and development of the work done in this study, a website was created to document the code base. In addition, this website contains instructions on how to interact with the code base. For more information please visit: https://plant-network-segmentation.readthedocs.io/.
  • Thumbnail Image
    Item
    Open Access
    Computational Psychiatry - Neuropsychological Bayesian reinforcement learning
    (2022) Wolpe, Zach; Shock, Jonathan; Cowley, Benjamin; Clark, Allan
    Cognitive science draws inspiration from a myriad of disciplines, and has become increasingly reliant on computational methods. In particular, theories of learning, operant conditioning and decision making have shown a natural synergy with statistical learning algorithms. This offers a unique opportunity to derive novel insight into the conditioning process by leveraging computational ideas. Specifically, ideas from Bayesian Inference and Reinforcement Learning. In this thesis, we examine the statistical properties of associative learning under uncertainty. We conducted a neuropsychological experiment on over 100 human subjects to measure a suite of executive functions. The primary experimental task (Card Sorting) gauges one's ability to learn, via inference, the structure of some latent pattern that drives the decision making process. We were able to successfully predict the subjects' behaviour in this task by fitting a Bayesian Reinforcement Learning model, alluding to the mechanics of the latent biological decision generating process and executive functions. Primarily, we detail the relationship between working memory capacity and associative learning.
  • Thumbnail Image
    Item
    Open Access
    Estimating Poverty from Aerial Images Using Convolutional Neural Networks Coupled with Statistical Regression Modelling
    (2019) Maluleke, Vongani; Er, Sebnem; Williams, Quentin
    Policy makers and the government rely heavily on survey data when making policyrelated decisions. Survey data is labour intensive, costly and time consuming, hence it cannot be frequently or extensively collected. The main aim of this research is to demonstrate how Convolutional Neural Network (CNN) coupled with statistical regression modelling can be used to estimate poverty from aerial images supplemented with national household survey data. This provides a more frequent and automated method for updating data that can be used for policy making. This aerial poverty estimation approach is executed in two phases; aerial classification and detection phase and poverty modelling phase. The aerial classification and detection phase use CNN to perform settlement typology classification of the aerial images into three broad geotype classes namely; urban, rural and farm. This is then followed by object detection to detect three broad dwelling type classes in the aerial images namely; brick house, traditional house, and informal settlement. Mask Region-based Convolutional Neural Network (Mask R-CNN) model with a resnet101 CNN backbone model is used to perform this task. The second phase, poverty modelling phase, involves using NIDS data to compute the poverty measure Sen-Shorrocks-Thon (SST) index. This is followed by using regression models to model the poverty measure using aggregated results from the aerial classification and detection phase. The study area for this research is Kwa-Zulu Natal (KZN), South Africa. However, this approach can be extended to other provinces in South Africa, by retraining the models on data associated with the location in question.
  • Thumbnail Image
    Item
    Open Access
    Modelling non-linearity in 3D shapes: A comparative study of Gaussian process morphable models and variational autoencoders for 3D shape data
    (2021) Fehr, Fabio; Clark, Allan; Mutsvangwa, Tinashe
    The presence of non-linear shape variation in 3D data is known to influence the reliability of linear statistical shape models (SSM). This problem is regularly acknowledged, but disregarded, as it is assumed that linear models are able to adequately approximate such non-linearities. Model reliability is crucial for medical imaging and computer vision tasks; however, prior to modelling, the non-linearity in the data is not often considered. The study provides a framework to identify the presence of non-linearity in using principal component analysis (PCA) and autoencoders (AE) shape modelling methods. The data identified to have linear and non-linear shape variations is used to compare two sophisticated techniques: linear Gaussian process morphable models (GPMM) and non-linear variational autoencoders (VAE). Their model performance is measured using generalisation, specificity and computational efficiency in training. The research showed that, given limited computational power, GPMMs managed to achieve improved relative generalisation performance compared to VAEs, in the presence of non-linear shape variation by at least a factor of six. However, the non-linear VAEs, despite the simplistic training scheme, presented improved specificity generative performance of at least 18% for both datasets.
  • Thumbnail Image
    Item
    Open Access
    Toward a sustainable energy future: Peak load shaving in commercial properties to reduce cost of energy
    (2022) Woodley, Tiffany Deanne; Nyirenda, Juwa
    Transitioning from fossil fuel-based energy systems to renewable sources is a is a global environmental imperative. South Africa has a coal-based energy sector, and consumers could be incentivised to pursue renewable energy alternatives if these solutions were financially advantageous. In South Africa, commercial properties are billed per kWh and can incur an additional demand charge that often accounts for a substantial portion of the energy bill, depending on the load factor. This thesis investigates peak load shaving as a solution for commercial properties to reduce their cost of electricity while supporting the transition to a greener energy future. Of the methods proposed for peak load shaving, reinforcement learning holds the greatest promise. However, its application in practice has been limited due to the “curse of dimensionality”. To make reinforcement learning a feasible option for peak load shaving, this thesis introduces a novel approach that employs clustering the energy demand profile shapes and training separate learning agents to target specific demand shapes, thereby reducing the complexity of the problem presented to the individual agents. The reinforcement learning model was trained on historical data from a commercial shopping centre in Cape Town using a hypothetical battery. Two scenarios were considered; the first assumed the absence of solar in the energy system while the second assumed its presence. Once trained, the learning agents were tested on unfamiliar energy data from the same shopping centre, and they achieved practical peak load shaving results. In Scenario 1 when using only a battery, monthly demand was reduced by 91 kW on average. Introducing a solar system in Scenario 2 increases uncertainty in the problem. The results, only demonstrated on one cluster, show the battery most often achieved a 50 kW reduction per day. In both scenarios, a learning agent trained on particular clusters of demand profiles was able to reduce peak energy demand for all unfamiliar days. Furthermore, in Scenario 2, the agent's learning progression indicated that the agent was learning to increase the battery output during the predominant peak. This suggests that our method's efficacy would improve with increased training time. If implemented, this approach could provide a practical peak shaving solution for the commercial shopping centre in Cape Town, effectively lowering their energy demand charges. This thesis has shown that clustering techniques used in conjunction with reinforcement learning is a promising approach when considering the peak shaving problem.