Engineering Commons^™

Enhancing Strawberry Disease And Quality Detection: Integrating Vision Transformers With Blender-Enhanced Synthetic Data And Swinunet Segmentation Techniques, Kimia Aghamohammadesmaeilketabforoosh

Electronic Thesis and Dissertation Repository

Agricultural productivity in strawberry cultivation was enhanced through the application of machine learning in this study. Traditional methods for detecting diseases and assessing ripeness in strawberries were identified as labor-intensive and error-prone, which limited farming efficiency and reduced crop yields. To address these challenges, it was hypothesized that advanced machine learning models incorporating attention mechanisms could significantly improve these tasks. The objective was to evaluate the effectiveness of various models by optimizing them for specific agricultural applications. Two datasets of strawberry images were augmented, and three pretrained models—Vision Transformer (ViT), MobileNetV2, and ResNet18—were fine-tuned. Data quality was improved through background …

A Secure Lightweight Wireless M-Bus Protocol For Iot: Leveraging The Noise Protocol Framework, Wafaa Anani

Electronic Thesis and Dissertation Repository

The expansion of smart metering within the Internet of Things (IoT) ecosystem underscores the need for robust security protocols that safeguard data transmission while optimizing device efficiency. Wireless Meter-Bus (wM-Bus), a key protocol for remote meter reading in utility systems such as gas, water, and heat meters, faces significant security challenges. This dissertation introduces a method to enhance wM-Bus security by integrating the Noise Protocol Framework (NPF), which secures wM-Bus against vulnerabilities and optimizes for the energy constraints of IoT devices. Initially examining wM-Bus security issues, particularly in battery-operated smart meters, the study explores the NPF’s lightweight, adaptable security solutions. …

Cyber Risks In Ontario Online Elections, James D. Brunet

Electronic Thesis and Dissertation Repository

Online voting is increasingly prevalent in Ontario's municipalities, despite a lack of regulated technological and procedural safeguards. Individual municipalities, lacking deep knowledge of online voting technologies, are responsible for procuring technology from private vendors which make security and privacy claims that are difficult to verify. These reasons, among others, have contributed to an anomalous environment where election technology, security, and procedures diverge greatly from other robust democracies that use electronic voting. This thesis demonstrates this divergence by first presenting a novel security vulnerability in a popular online voting system used in Ontario, as well as the difficulty communicating this risk …

Improving Fused Filament Fabrication Additive Manufacturing Through Computer Vision Analysis And Fabrication Optimization, Aliaksei Petsiuk

Electronic Thesis and Dissertation Repository

Additive manufacturing (AM), also known as 3-D printing, is one of the fundamental elements of Industry 4.0. According to ASTM standards, AM can be classified by production principles, types of raw materials, energy sources, and fabrication volumes. Fused filament fabrication (FFF) is one of the most accessible technologies that offers independent manufacturers great opportunities due to its simplicity, scalability, and low cost.

Modern 3-D printing is moving from single-material prototyping to complex multi-material product creation. It is firmly established in a wide range of applications, significantly expanding manufacturing horizons, providing innovative design capabilities, and improving product quality through the optimal …

Planetary Exploration Via Fully Automatic Topological Structure Extraction Using Adaptive Resonance, Jonathan Kissi

Electronic Thesis and Dissertation Repository

Renewed interest in Solar System exploration, along with ongoing improvements in computing, robotics and instrumentation technologies, have reinforced the case for remote science acquisition systems development in space exploration. Testing systems and procedures that allow for autonomously collected science has been the focus of analogue field deployments and mission planning for some time, with such systems becoming more relevant as missions increase in complexity and ambition. The introduction of lidar and laser scanning-type instruments into the geological and planetary sciences has proven popular, and, just as with the established image and photogrammetric methods, has found widespread use in several research …

The Development And Testing Of A Gyroscope-Based Neck Strengthening Rehabilitation Device, Nicole D. Devos

Electronic Thesis and Dissertation Repository

Neck pain can be debilitating, and is experienced by the majority of people at some point over the course of their life. Resistance training has been shown to have significant improvement in pain or disability for patients. There are few options available for telerehabilitation, and the use of gyroscope stabilizers is proposed for this use. A biomechanics model of a head--neck--gyroscope system was created. In order to also model the dynamics of such a system, this work proposes a blended method using the Denavit--Hartenberg (DH) convention, popular in the field of robotics, with the Lagrangian mechanics approach to analyze an …

Attribution Robustness Of Neural Networks, Sunanda Gamage

Electronic Thesis and Dissertation Repository

While deep neural networks have demonstrated excellent learning capabilities, explainability of model predictions remains a challenge due to their black box nature. Attributions or feature significance methods are tools for explaining model predictions, facilitating model debugging, human-machine collaborative decision making, and establishing trust and compliance in critical applications. Recent work has shown that attributions of neural networks can be distorted by imperceptible adversarial input perturbations, which makes attributions unreliable as an explainability method. This thesis addresses the research problem of attribution robustness of neural networks and introduces novel techniques that enable robust training at scale.

Firstly, a novel generic framework …