UWSpace
UWSpace is the University of Waterloo’s institutional repository for the free, secure, and long-term home of research produced by faculty, students, and staff.
Depositing Theses/Dissertations or Research to UWSpace
Are you a Graduate Student depositing your thesis to UWSpace? See our Thesis Deposit Help and UWSpace Thesis FAQ pages to learn more.
Are you a Faculty or Staff member depositing research to UWSpace? See our Waterloo Research Deposit Help and Self-Archiving pages to learn more.
Communities in UWSpace
Select a community to browse its collections.
- The University of Waterloo institution-wide UWSpace community.
Recent Submissions
Revisiting Benchmarks for Privacy-Preserving Image Classification
(University of Waterloo, 2024-09-17) Mokhtari, Sabrina
Differential privacy (DP) is a standard method for preserving the privacy of individual data points. DP prevents models from memorizing training data, thus reducing the risk of data leakage. While DP has been effective in machine learning (ML), there are growing concerns about some common practices in differentially private machine learning (DP ML), particularly the reliance on non-private ML benchmarks to measure progress. Popular datasets like CIFAR-10, while extensively used in non-private settings, may not accurately capture the complexities of privacy-sensitive areas like medical data. Additionally, pre-training on publicly available datasets may not yield the same benefits when the private data differs significantly and is not well represented in the public domain. This thesis addresses these concerns by evaluating DP methods using various privacy-sensitive datasets and training scenarios. We focus on medical datasets, where privacy is crucial, and study a thorough set of techniques. These techniques cover a wide range of settings, including those with public data pre-training, cases without public data, full-layer and last-layer fine-tuning, and different privacy levels.
Automatic Whale Detection using Deep learning
(University of Waterloo, 2024-09-17) Patel, Muhammed
Accurate monitoring of whale populations is essential for conservation efforts, yet traditional surveying methods are often time-consuming, expensive, and limited in coverage. This thesis investigates the automation of whale detection using state-of-the-art (SOTA) deep learning techniques applied to high-resolution aerial imagery. By leveraging advancements in computer vision, specifically object detection models, this research aims to develop a robust and efficient system for identifying and counting whales from aerial surveys.
The study formulates whale detection as a small object detection problem and evaluates the performance of various SOTA models, including Faster R-CNN, YOLOv8, and Deformable DETR, paired with modern backbone architectures such as ConvNext-T, Swin-T, and ResNet-50. The influence of input image size and context on model performance is systematically explored by testing patch sizes ranging from 256 to 4096 pixels, marking this study as the first to investigate the efficacy of such large patch sizes in the remote sensing domain.
Results indicate that the Faster R-CNN model with a ConvNext-T backbone achieves the highest detection accuracy, with an average precision of 0.878 at an IoU threshold of 0.1, particularly when trained on larger patch sizes. The study also addresses the challenge of domain adaptation by implementing an active learning framework, designed to enhance model performance on new survey data with varying environmental conditions. A novel portfolio-based acquisition function, leveraging the social behavior of whales, is introduced to optimize the annotation process.
This research significantly contributes to the field of automated whale monitoring, offering a scalable and adaptable solution that reduces annotation costs and improves the accuracy of population estimates. The developed system holds promise for enhancing conservation strategies and providing valuable insights into whale movements and behaviors.
Mycelium Wall Systems: Harnessing Adaptive Fabrication with Biocomposites in Buildings
(University of Waterloo, 2024-09-17) Garboushian, Razmig
Wall assembly prototyping is a strategy that allows for technical performance analysis of construction materials to investigate the function of a building façade and its integrated components. Departing from the complexity of a given building, façades must constantly mediate evolving human needs for comfort and environmental performance. However, traditional construction strategies to address these complex, changing needs, such as multiple wall layers with fluid-wall and fluid-solid interfaces are practically and environmentally inefficient. Mycelium biocomposites can combine effective performance properties for wall systems with reduced layers while being biodegradable. This thesis introduces a novel mycelium biocomposite assembly integrated in a naturally prefabricated wall panel with reduced material layers compared to a typical system. Construction prototyping is employed through nine digitally modelled iterations, supported by three physical experiments and thermal simulations. The key impact of this research is in introducing a new framework for utilizing construction prototyping to efficiently accommodate the growth and performance requirements of mycelium biocomposites within a prefabricated wall assembly while applying hands-on procedures in façade engineering and design.
Robust Recursive Query Parallelization in Graph Database Management Systems
(University of Waterloo, 2024-09-17) Chakraborty, Anurag
Recursive joins such as shortest path and variable length path queries are a core feature set of modern graph database management systems (GDBMS). Since these queries tend to be computationally expensive and may suffer from high execution time, they require efficient parallel processing using multiple cores to achieve good performance. Existing work on parallel query processing includes the morsel driven parallelism approach that distributes a unit of work (denoted as “morsel”) to threads for parallel execution. We revisit this technique in the context of parallelization of recursive joins in GDBMS and discuss how the traditional approach of morsel driven query execution is inadequate to tackle recursive join queries. We show how this approach can be modified to better accommodate scalable parallelization of recursive joins. We further describe how this modified parallel query execution approach has been integrated into Kuzu, an embedded disk based columnar GDBMS. Compared to vanilla morsel driven parallelism, our modified parallel query execution approach can be orders of magnitude faster and scales well on multiple cores.
Novel Wide Bandgap Polymer Donors Containing Benzodithiophene and Substituted-Thiophene as Donating and Accepting Units for High Performance Non-Fullerene Acceptor Based Organic Solar Cells
(University of Waterloo, 2024-09-17) Yuan, Yi
Organic solar cells (OSCs), or organic photovoltaics (OPVs), have attracted widespread attention as a promising technology for converting solar energy to electricity owing to their advantages of good mechanical flexibility, lightweight, low-cost and large-area fabrication durability. Over the decades, OSCs have improved rapidly since Heeger’s group reported the first bulk heterojunction (BHJ) OSC which is composed of a blend active layer containing a p-type conjugated polymer as a donor and an n-type small molecule organic semiconductor as an acceptor. Recently, significant progress has been achieved with the highest power conversion efficiency (PCE) over 19%, ascribed to the rational design and matching of the conjugated polymer donors with the novel non-fullerene acceptors (NFAs). By reviewing the remarkable progress achieved for OSCs in the past three decades, it is noteworthy that the benzodithiophene (BDT) and thiophene units showed much potential for constructing polymer donors which showed great photovoltaic performance. However, several challenges remained with further development of OSCs including cost-efficiency. It is important to develop new wide bandgap (WBG) conjugated polymer donor materials to balance material cost and device efficiency for high performance NFA-based solar cell towards commercialization.