Electrical and Computer Engineering Commons^™

A Novel Method For Determining The Inherent Capabilities Of Computer And Robotic-Assisted Total Knee Arthroplasty Devices, Delaney R.G. Stevens

Electronic Thesis and Dissertation Repository

This thesis presents a method for evaluating and comparing assistive total knee arthroplasty (TKA) devices while controlling surgeon landmarking variability. To achieve consistent landmark selection by surgeons during TKA procedures, the method uses identical 3D-printed knees with indented landmarks. This method was used to compare a robotic and computer-assisted TKA device on three metrics: measurement accuracy, alignment accuracy, and cut-surface uniformity. Although both devices had considerable sagittal plane measurement errors, the robotic device had better measurement and alignment accuracy than the computer-assisted device. Furthermore, the robotic device's measuring error compensated for cutting errors, but the computer-assisted device's compounded them. However, …

Enhancing The Performance Of Nmt Models Using The Data-Based Domain Adaptation Technique For Patent Translation, Maimoonah Ahmed

Electronic Thesis and Dissertation Repository

During today’s age of unparalleled connectivity, language and data have become powerful tools capable of enabling effective communication and cross-cultural collaborations. Neural machine translation (NMT) models are especially capable of leveraging linguistic knowledge and parallel corpora to increase global connectivity and act as a tool for the transmission of knowledge. In this thesis, we apply a data-based domain adaptation technique to fine-tune three pre-existing NMT transformer models with attention mechanisms for the task of patent translation from English to Japanese. Languages, especially in the context of patents, can be very nuanced. A clear understanding of the intended meaning requires comprehensive …

Identifying Sources Of Error In Computer Navigated Total Knee Arthroplasties Using A Metric On Se(3) And Sensitivity Analyses, Nicole E. Martensson

Electronic Thesis and Dissertation Repository

Throughout the procedure of a computer-navigated total knee arthroplasty (TKA), there are many opportunities for sources of error to be introduced. Identifying these errors can improve surgical outcomes. There is also a lack of accessible methods in available literature for clinicians to perform research in this area using engineering analysis techniques. This thesis aims to provide a greater understanding of the sources of error that can occur pre-bone cut. Possible sources of error include the bony landmark selections and the placement of the cut guide. Using artificial bone models and a 3D point capture system concurrently with a computer-navigation system, …

Anomaly Detection On Partial Point Clouds For The Purpose Of Identifying Damage On The Exterior Of Spacecrafts, Kaitlin T. Hutton

Electronic Thesis and Dissertation Repository

The Canadarm3 is going to operate autonomously aboard the Lunar Gateway space station for the purpose of inspections and repairs. To make the repairs, damage to the spacecraft needs to be detected accurately and automatically. This research investigates methods for training Machine Learning models on 3D point clouds to identify anomalous structural damage. The PointNet algorithm was used to train models on point clouds without affecting their structure. The optimal training data style was found by comparing how well the different styles of data performed at classifying the point cloud testing data. Two different methods of anomaly detection were tested …

Efficient Discovery And Utilization Of Radio Information In Ultra-Dense Heterogeneous 3d Wireless Networks, Mattaka Gamage Samantha Sriyananda

Electronic Thesis and Dissertation Repository

Emergence of new applications, industrial automation and the explosive boost of smart concepts have led to an environment with rapidly increasing device densification and service diversification. This revolutionary upward trend has led the upcoming 6th-Generation (6G) and beyond communication systems to be globally available communication, computing and intelligent systems seamlessly connecting devices, services and infrastructure facilities. In this kind of environment, scarcity of radio resources would be upshot to an unimaginably high level compelling them to be very efficiently utilized. In this case, timely action is taken to deviate from approximate site-specific 2-Dimensional (2D) network concepts in radio resource utilization …

Optimized And Automated Machine Learning Techniques Towards Iot Data Analytics And Cybersecurity, Li Yang

Electronic Thesis and Dissertation Repository

The Internet-of-Things (IoT) systems have emerged as a prevalent technology in our daily lives. With the wide spread of sensors and smart devices in recent years, the data generation volume and speed of IoT systems have increased dramatically. In most IoT systems, massive volumes of data must be processed, transformed, and analyzed on a frequent basis to enable various IoT services and functionalities. Machine Learning (ML) approaches have shown their capacity for IoT data analytics. However, applying ML models to IoT data analytics tasks still faces many difficulties and challenges. The first challenge is to process large amounts of dynamic …

Data Preprocessing For Machine Learning Modules, Rawan El Moghrabi

Undergraduate Student Research Internships Conference

Data preprocessing is an essential step when building machine learning solutions. It significantly impacts the success of machine learning modules and the output of these algorithms. Typically, data preprocessing is made-up of data sanitization, feature engineering, normalization, and transformation. This paper outlines the data preprocessing methodology implemented for a data-driven predictive maintenance solution. The above-mentioned project entails acquiring historical electrical data from industrial assets and creating a health index indicating each asset's remaining useful life. This solution is built using machine learning algorithms and requires several data processing steps to increase the solution's accuracy and efficiency. In this project, the …

Machine Learning With Big Data For Electrical Load Forecasting, Alexandra L'Heureux

Electronic Thesis and Dissertation Repository

Today, the amount of data collected is exploding at an unprecedented rate due to developments in Web technologies, social media, mobile and sensing devices and the internet of things (IoT). Data is gathered in every aspect of our lives: from financial information to smart home devices and everything in between. The driving force behind these extensive data collections is the promise of increased knowledge. Therefore, the potential of Big Data relies on our ability to extract value from these massive data sets. Machine learning is central to this quest because of its ability to learn from data and provide data-driven …

Smart Chatbot For User Authentication, Peter Voege

Electronic Thesis and Dissertation Repository

The field of authentication has a lot of room to develop in the age of big data and machine learning. Conventional high-accessibility authentication mechanisms including passwords or security questions struggle with critical vulnerabilities, creating a need for alternative authentication mechanisms able to cover said weaknesses.

We sought to create an authentication mechanism that creates dynamic, ever-changing security questions only the user can answer while remaining intuitive to use and as accessible as typical security questions by creating an authentication chatbot that leverages big data and natural language processing to pose dynamic authentication challenges.

We tested the components of our design …

Web Application – Utilizing A Pose Estimation And Augmented Reality Api For Hand Telerehabilitation, Herbert Shin

Undergraduate Student Research Internships Conference

No abstract provided.

Deep Learning For High-Impedance Fault Detection And Classification, Khushwant Rai

Electronic Thesis and Dissertation Repository

High-Impedance Faults (HIFs) are a hazard to public safety but are difficult to detect because of their low current amplitude and diverse characteristics. Supervised machine learning techniques have shown great success in HIF detection; however, these approaches rely on resource-intensive signal processing techniques and fail in presence of non-HIF disturbances and even for scenarios not included in training data. This thesis leverages unsupervised learning and proposes a Convolutional Autoencoder framework for HIF Detection (CAE-HIFD). In CAE-HIFD, Convolutional Autoencoder learns only from HIF signals by employing cross-correlation; consequently, eliminating the need for diverse non-HIF scenarios in training. Furthermore, this thesis proposes …

Protecting Health Data In A Pandemic: A Systematic Adversarial Threat Analysis Of Contact Tracing Apps, Leah Krehling

Electronic Thesis and Dissertation Repository

In this thesis centralized, decentralized, Bluetooth, and GPS based applications of digital contact tracing were reviewed and assessed. Using privacy principles created by a contingent of security and privacy experts from across Canada, a metric of assessing an application’s privacy was created. An attack tree was built to assess the security of the contact tracing applications. Eighteen attacks were theorized against contact tracing applications currently in use. An application’s vulnerability to the attacks was measured using a scoring system developed for this purpose. The results of the security scores were used to create a metric for assessing the security of …

Longitudinal Partitioning Waveform Relaxation Methods For The Analysis Of Transmission Line Circuits, Tarik Menkad

Electronic Thesis and Dissertation Repository

Three research projects are presented in this manuscript. Projects one and two describe two waveform relaxation algorithms (WR) with longitudinal partitioning for the time-domain analysis of transmission line circuits. Project three presents theoretical results about the convergence of WR for chains of general circuits.

The first WR algorithm uses a assignment-partition procedure that relies on inserting external series combinations of positive and negative resistances into the circuit to control the speed of convergence of the algorithm. The convergence of the subsequent WR method is examined, and fast convergence is cast as a generic optimization problem in the frequency-domain. An automatic …

Material Evaluation And Structural Monitoring Of Early-Age Masonry Structures, Kyle Dunphy

Electronic Thesis and Dissertation Repository

During the initial construction period, “early-age” masonry walls are susceptible to lateral loads induced by wind or earthquake, which may result in damages or catastrophic failures. To mitigate such consequences at construction sites, temporary bracings are adopted to provide lateral support to masonry walls until they are matured enough to serve as the inherent lateral system of the structure. However, current temporary bracing guidelines provide oversimplified design due to the lack of available information on the material properties of early-age masonry. Moreover, there are no existing techniques for monitoring masonry walls to detect cracks due to construction activities. …

Network Resource And Performance Optimization In Autonomous Systems: A Connected Vehicles And Autonomous Networks Perspective, Ibrahim Shaer

Electronic Thesis and Dissertation Repository

This thesis covers two topics that optimize a network-related problem subject to environment-specific constraints; placing vehicular applications and executing network traffic assignment changes. The first topic introduces an optimization model, Resource and Delay-aware V2X service Placement (RDP), and a baseline approach that only considers the resource requirements of vehicular services. Both are responsible for placing vehicular services used by vehicular applications in an edge computing environment. Under different simulation scenarios, the results obtained by RDP satisfy the delay requirements of vehicular applications as opposed to the baseline approach. The second topic examines the efficient execution of inter-domain traffic changes under …

A New Approach For Homomorphic Encryption With Secure Function Evaluation On Genomic Data, Mounika Pratapa

Electronic Thesis and Dissertation Repository

Additively homomorphic encryption is a public-key primitive allowing a sum to be computed on encrypted values. Although limited in functionality, additive schemes have been an essential tool in the private function evaluation toolbox for decades. They are typically faster and more straightforward to implement relative to their fully homomorphic counterparts, and more efficient than garbled circuits in certain applications. This thesis presents a novel method for extending the functionality of additively homomorphic encryption to allow the private evaluation of functions of restricted domain. Provided the encrypted sum falls within the restricted domain, the function can be homomorphically evaluated “for free” …

Optimized Machine Learning Models Towards Intelligent Systems, Mohammadnoor Ahmad Mohammad Injadat

Electronic Thesis and Dissertation Repository

The rapid growth of the Internet and related technologies has led to the collection of large amounts of data by individuals, organizations, and society in general [1]. However, this often leads to information overload which occurs when the amount of input (e.g. data) a human is trying to process exceeds their cognitive capacities [2]. Machine learning (ML) has been proposed as one potential methodology capable of extracting useful information from large sets of data [1]. This thesis focuses on two applications. The first is education, namely e-Learning environments. Within this field, this thesis proposes different optimized ML ensemble models to …

Hyperspectral Image Classification For Remote Sensing, Hadis Madani

Electronic Thesis and Dissertation Repository

This thesis is focused on deep learning-based, pixel-wise classification of hyperspectral images (HSI) in remote sensing. Although presence of many spectral bands in an HSI provides a valuable source of features, dimensionality reduction is often performed in the pre-processing step to reduce the correlation between bands. Most of the deep learning-based classification algorithms use unsupervised dimensionality reduction methods such as principal component analysis (PCA).

However, in this thesis in order to take advantage of class discriminatory information in the dimensionality reduction step as well as power of deep neural network we propose a new method that combines a supervised dimensionality …

Leveraging Cloud-Based Nfv And Sdn Platform Towards Quality-Driven Next-Generation Mobile Networks, Hassan Hawilo

Electronic Thesis and Dissertation Repository

Network virtualization has become a key approach for Network Service Providers (NSPs) to mitigate the challenge of the continually increasing demands for network services. Tightly coupled with their software components, legacy network devices are difficult to upgrade or modify to meet the dynamically changing end-user needs. To virtualize their infrastructure and mitigate those challenges, NSPs have started to adopt Software Defined Networking (SDN) and Network Function Virtualization (NFV). To this end, this thesis addresses the challenges faced on the road of transforming the legacy networking infrastructure to a more dynamic and agile virtualized environment to meet the rapidly increasing demand …

Cluster-Based Chained Transfer Learning For Energy Forecasting With Big Data, Yifang Tian

Electronic Thesis and Dissertation Repository

Smart meter popularity has resulted in the ability to collect big energy data and has created opportunities for large-scale energy forecasting. Machine Learning (ML) techniques commonly used for forecasting, such as neural networks, involve computationally intensive training typically with data from a single building/group to predict future consumption for that same building/group. With hundreds of thousands of smart meters, it becomes impractical or even infeasible to individually train a model for each meter. Consequently, this paper proposes Cluster-Based Chained Transfer Learning (CBCTL), an approach for building neural network-based models for many meters by taking advantage of already trained models through …

Adaptation Of A Deep Learning Algorithm For Traffic Sign Detection, Jose Luis Masache Narvaez

Electronic Thesis and Dissertation Repository

Traffic signs detection is becoming increasingly important as various approaches for automation using computer vision are becoming widely used in the industry. Typical applications include autonomous driving systems, mapping and cataloging traffic signs by municipalities. Convolutional neural networks (CNNs) have shown state of the art performances in classification tasks, and as a result, object detection algorithms based on CNNs have become popular in computer vision tasks. Two-stage detection algorithms like region proposal methods (R-CNN and Faster R-CNN) have better performance in terms of localization and recognition accuracy. However, these methods require high computational power for training and inference that make …

Towards Efficient Intrusion Detection Using Hybrid Data Mining Techniques, Fadi Salo

Electronic Thesis and Dissertation Repository

The enormous development in the connectivity among different type of networks poses significant concerns in terms of privacy and security. As such, the exponential expansion in the deployment of cloud technology has produced a massive amount of data from a variety of applications, resources and platforms. In turn, the rapid rate and volume of data creation in high-dimension has begun to pose significant challenges for data management and security. Handling redundant and irrelevant features in high-dimensional space has caused a long-term challenge for network anomaly detection. Eliminating such features with spectral information not only speeds up the classification process, but …

Augmented Reality Simulation Modules For Evd Placement Training And Planning Aids, Hamza Waleed Ghandorh

Electronic Thesis and Dissertation Repository

When a novice neurosurgeon performs a psychomotor surgical task (e.g., tool navigation into brain structures), a potential risk of damaging healthy tissues and eloquent brain structures is unavoidable. When novices make multiple hits, thus a set of undesirable trajectories is created, and resulting in the potential for surgical complications. Thus, it is important that novices not only aim for a high-level of surgical mastery but also receive deliberate training in common neurosurgical procedures and underlying tasks. Surgical simulators have emerged as an adequate candidate as effective method to teach novices in safe and free-error training environments. The design of neurosurgical …

Secure Integer Comparisons Using The Homomorphic Properties Of Prime Power Subgroups, Rhys A. Carlton

Electronic Thesis and Dissertation Repository

Secure multi party computation allows two or more parties to jointly compute a function under encryption without leaking information about their private inputs. These secure computations are vital in many fields including law enforcement, secure voting and bioinformatics because the privacy of the information is of paramount importance.

One common reference problem for secure multi party computation is the Millionaires' problem which was first introduced by Turing Award winner Yao in his paper "Protocols for secure computation". The Millionaires' problem considers two millionaires who want to know who is richer without disclosing their actual worth.

There are public-key cryptosystems that …

Collective Contextual Anomaly Detection For Building Energy Consumption, Daniel Berhane Araya

Electronic Thesis and Dissertation Repository

Commercial and residential buildings are responsible for a substantial portion of total global energy consumption and as a result make a significant contribution to global carbon emissions. Hence, energy-saving goals that target buildings can have a major impact in reducing environmental damage. During building operation, a significant amount of energy is wasted due to equipment and human-related faults. To reduce waste, today's smart buildings monitor energy usage with the aim of identifying abnormal consumption behaviour and notifying the building manager to implement appropriate energy-saving procedures. To this end, this research proposes the \textit{ensemble anomaly detection} (EAD) framework. The EAD is …

Hidden Markov Model Based Intrusion Alert Prediction, Udaya Sampath Karunathilaka Perera Miriya Thanthrige

Electronic Thesis and Dissertation Repository

Intrusion detection is only a starting step in securing IT infrastructure. Prediction of intrusions is the next step to provide an active defense against incoming attacks.

Most of the existing intrusion prediction methods mainly focus on prediction of either intrusion type or intrusion category. Also, most of them are built based on domain knowledge and specific scenario knowledge. This thesis proposes an alert prediction framework which provides more detailed information than just the intrusion type or category to initiate possible defensive measures. The proposed algorithm is based on hidden Markov model and it does not depend on specific domain knowledge. …

A Digital Game Maturity Model, Saiqa Aleem

Electronic Thesis and Dissertation Repository

Game development is an interdisciplinary concept that embraces artistic, software engineering, management, and business disciplines. Game development is considered as one of the most complex tasks in software engineering. Hence, for successful development of good-quality games, the game developers must consider and explore all related dimensions as well as discussing them with the stakeholders involved.

This research facilitates a better understanding of important dimensions of digital game development methodology. The increased popularity of digital games, the challenges faced by game development organizations in developing quality games, and severe competition in the digital game industry demand a game development process maturity …

Development Of An Autonomous Robotic Mushroom Harvester, Nikita Alexeevich Kuchinskiy

Electronic Thesis and Dissertation Repository

The process of development of a new robot is one of the modern technological arts. This process involves multiple complex steps and recursive approach. In this project, a solution for automatic harvesting of mushrooms is developed. In order to design an effective solution, it is necessary to explore and take into consideration the limitations of grasping very soft and fragile objects (particularly mushrooms). We will elaborate several strategies of picking and analyze each strategy to formulate the design requirements, develop a solution, and finally, evaluate the efficiency of the proposed solution in actual farm conditions for real mushrooms. The mushroom …

Enhanced Indoor Localization System Based On Inertial Navigation, Rasika Lakmal Hettiarachchige Don

Electronic Thesis and Dissertation Repository

An algorithm for indoor localization of pedestrians using an improved Inertial Navigation system is presented for smartphone based applications. When using standard inertial navigation algorithm, errors in sensors due to random noise and bias result in a large drift from the actual location with time. Novel corrections are introduced for the basic system to increase the accuracy by counteracting the accumulation of this drift error, which are applied using a Kalman filter framework.

A generalized velocity model was applied to correct the walking velocity and the accuracy of the algorithm was investigated with three different velocity models which were derived …

Gamification Framework For Sensor Data Analytics, Alexandra L'Heureux

Electronic Thesis and Dissertation Repository

Data in all of its form is becoming a central part of our existence, it is being captured in every facets of our everyday life: social media, pictures, smartphones, wearable devices, smart building etc. One of the main drivers of this Big Data Revolution is the Internet of Things, which enables inert objects to communicate through a multitude of sensors. The data amassed fuels a thirst for information, the extraction of such knowledge is rendered possible through Data Analytics Techniques.

However, when it comes to sensor data our large-scale ability to perform analytics is highly limited by the difficulties associated …