Engineering Science - Theses, Dissertations, and other Required Graduate Degree Essays

Receive updates for this collection

Towards the Development of an Adaptive Compression System

Author: 
Date created: 
2016-11-16
Abstract: 

Regarded as the mainstay for treatment of venous insufficiency and the associated complications, compression therapy aims at assisting with venous return through the exertion of external pressure on the limbs. Compression is achieved by medical bandages and stockings, which hold promise only during supine and walking conditions, or mechanical pumps, which are usually bulky and limited to non-ambulatory use. Hence, the purpose of this study was to develop an improved compression system that eliminates the flaws of the existing products. To attain this goal, a motorized compression bandage was designed that takes advantage of force-sensing resistors (FSRs®) to exert reproducible, controlled pressure on the lower extremities. The performance of the device in enhancing venous return was explored in a pilot experiment, wherein graded lower body negative pressure (LBNP) was employed as a surrogate of standing erect. The results revealed a significant reduction in the mean cardiovascular changes to LBNP.

Document type: 
Thesis
File(s): 
Senior supervisor: 
Carlo Menon
Department: 
Applied Sciences: School of Engineering Science
Thesis type: 
(Thesis) M.A.Sc.

Clustering and identification of body extremities for pose recognition through a network of calibrated depth sensors

Author: 
Date created: 
2019-08-06
Abstract: 

This thesis presents a framework of a marker-less human pose recognition system by identifying key body extremity parts through a network of calibrated depth sensors. The depth sensors can overcome challenges related to low illuminations which usually compromises the information from the RGB cameras. The thesis proposed a novel approach for calibrating multiple depth sensors using retro-reflective (RR) marked spheres. The calibrated parameters are then used to align the point cloud data of the human body associated with multiple depth sensors with respect to a common coordinate frame. This fusion of point clouds facilitates in overcoming the self-occlusion problems from body parts without incurring disjointedness in the fused point cloud data. The second part of the thesis introduces a novel algorithm for the identification of key body extremities such as head, hands, and feet of a human subject. A geodesic mapping is applied on the fused point cloud to produce a set of distinct topological clusters of 3D points. From these clusters, a hierarchical skeleton tree graph is generated and used for key extremities classification which finally leads to pose recognition. The thesis presents the assessment of each proposed part and its comparison with other available techniques in a succession of experimental configurations.

Document type: 
Thesis
File(s): 
Senior supervisor: 
Shahram Payandeh
Department: 
Applied Sciences: School of Engineering Science
Thesis type: 
(Thesis) M.A.Sc.

Evaluation of Support Vector Machine kernels for detecting network anomalies

Author: 
Date created: 
2019-04-18
Abstract: 

Border Gateway Protocol (BGP) is used to exchange routing information across the Internet. BGP anomalies severely affect network performance and, hence, algorithms for anomaly detection are important for improving BGP convergence. Efficient and effective anomaly detection mechanisms rely on employing machine learning techniques. Support Vector Machine (SVM) is a widely used machine learning algorithm. It employs a set of mathematical functions called kernels that transform the input data into a higher dimensional space before classifying the data points into distinct clusters. In this Thesis, we evaluate the performance of linear, polynomial, quadratic, cubic, Gaussian radial basis function, and sigmoid SVM kernels used for classifying power outage such as Moscow Power Blackout, BGP mis-configuration, and BGP anomalies such as Slammer, Nimda and Code Red I. The SVM kernels are compared based on accuracy and the F-Score when detecting anomalous events in the Internet traffic traces. Simulation results indicate that the performance heavily depends on the selected features and their combinations.

Document type: 
Thesis
File(s): 
Senior supervisor: 
Ljiljana Trajkovic
Department: 
Applied Sciences: School of Engineering Science
Thesis type: 
(Thesis) M.A.Sc.

Deep learning-based computer-aided diagnosis for brain and retinal diseases

Author: 
Date created: 
2019-08-15
Abstract: 

Deep neural network has achieved excellent performance for many recognition tasks. Despite its recent wide application on medical imaging tasks, the requirement of large amount of manually labeled samples limits its performance on medical image recognition tasks. Comparing with natural images, medical image is difficult and expensive to acquire and requires specialized training for its labeling. However, the data samples for a specific clinical task shares much less heterogeneity comparing with most image recognition tasks. Exploring advanced network architecture and incorporate it with a-priori, domain-specific knowledge has a great potential to deliver superior recognition performance and better computer-aided diagnosis system. In this thesis, we presented the development of four novel deep learning based frameworks regarding four medical image recognition tasks, early diagnosis of Alzheimer's disease, differential diagnosis of multiclass dementia, OCT retinal fluid segmentation and OCT retinal layer segmentation. Comprehensive experiments proved that the proposed frameworks out-performed state-of-the-art methods in each individual task.

Document type: 
Thesis
File(s): 
Senior supervisor: 
Mirza Faisal Beg
Department: 
Applied Sciences: School of Engineering Science
Thesis type: 
(Thesis) Ph.D.

Aberration correction with sensorless adaptive optics for imaging the mouse retina

Author: 
Date created: 
2019-05-02
Abstract: 

Small animals, such as mice, are commonly used in biomedical research as models for studying human diseases. Imaging the retina in a living animal can provide valuable insights into the causes and mechanisms of vision loss. However, often imaging in vivo results in low resolution due to optical aberrations that can be caused by the biological tissue in front of the retina. Imaging systems that could non-invasively image the mouse retina with cellular-level resolution would be beneficial to many vision scientists. Adaptive optics (AO) is a technology that was originally developed for astronomers to image through the turbulent atmosphere. AO technology has been extended for microscopy and ophthalmoscopy to restore imaging performance lost due to optical aberrations from biological samples. Often, AO systems employ a wavefront sensor for direct measurement of the aberrations. Alternatively, Sensorless AO (SAO) has been implemented for imaging into tissue with multiple scattering layers, which can confound the optical wavefront measurements from a single imaging plane.In this thesis, I present several imaging systems for imaging the mouse retina with cellular-level resolution by using custom and novel SAO methods. The imaging modalities include Scanning Laser Ophthalmoscopy with fluorescence detection, Optical Coherence Tomography, and Two-Photon Excited Fluorescence imaging. The simple and robust optical designs in this thesis feature wide imaging field of views for navigation and a compactable system layout. Using SAO enables depth-resolved aberration correction in the different layers of the mouse retina. My results demonstrate detailed non-invasive cellular imaging capabilities in the living mouse eye of GFP labelled cells, nerve fibers bundles, volumetric imaging of vasculature, as well as the RPE mosaic of the outer retina.

Document type: 
Thesis
File(s): 
Senior supervisor: 
Marinko Sarunic
Department: 
Applied Sciences: School of Engineering Science
Thesis type: 
(Thesis) Ph.D.

A stand-alone adaptive corrosion protection system (ACPS) in various corrosive environments

Author: 
Date created: 
2019-07-26
Abstract: 

A novel approach to corrosion monitoring and protection is investigated in different corrosive environments. The standalone Adaptive Corrosion Protection System (ACPS) works in a feedback loop to monitor the corrosion status and protect the target metal. Experiments in different corrosive mediums are carried out using a new stand-alone ACPS unit. A comparative study of the ACPS with the standard Impressed Current Cathodic Protection (ICCP) is done in corrosive mediums at different temperatures and pH. Furthermore, a miniature transmission tower grillage structure buried in the soil is protected using the ACPS. The variations of the electrochemical parameters in different environments are studied and correlated with the macro-environment data. Dynamic ACPS can optimize power consumption by updating the protection parameters at a user-defined interval. Unlike the standard ICCP, the adaptive corrosion protection mechanism is a current-sourced system that effectively monitors and optimally protects the target structure.

Document type: 
Thesis
File(s): 
Senior supervisor: 
Bozena Kaminska
Department: 
Applied Sciences: School of Engineering Science
Thesis type: 
(Thesis) M.A.Sc.

Applications of fireworks-based evolutionary algorithms for computationally challenging network problems

Author: 
Date created: 
2019-06-04
Abstract: 

This thesis covers two types of contributions: formulation of network optimization problems and algorithms to solve these optimization problems. We propose resource assignment problem in Internet of Things network (IoTN) with three nodes: IoT, core cluster node (CCN) and base station (BS). The assignment of resources, such as CPU and memory, from IoTs to CCNs, and CCNs to BSs is a challenging task. The objective of the problem is to minimize the weighted sum of computational power at CCNs and transmission power between IoTs-CCNs and CCNs-BSs radio connections. We also propose a broadband wireless network (BWN) wherein the planning of BSs, relay stations (RSs), and their connections to subscribers minimizes the overall (i.e., weighted sum of the hardware and operational) cost of the network and reformulate a virtual machine (VM) placement to minimize power consumption in a datacenter. The (re)formulated problems are integer programming problem and finding optimal solutions for these problems by using exhaustive search is not practical due to demand of high computing resources. The practical approach is to minimize power in IoT network and VM placement, and plan broadband wireless network using population-based heuristic algorithms. We propose swarm intelligence-based algorithms, that is, two versions of the discrete fireworks algorithm (DFWA) and its variants. The performance of these new algorithms is compared against the low-complexity Biogeography-based Optimization (LC-BBO) algorithm, the Discrete Artificial Bee Colony (DABC) algorithm, and the Genetic Algorithm (GA). Our simulation results and statistical test demonstrate that the proposed algorithm can comparatively find good-quality solutions with moderate computing resources.

Document type: 
Thesis
File(s): 
Senior supervisor: 
Daniel C. Lee
Jiangchuan Liu
Department: 
Applied Sciences: School of Engineering Science
Thesis type: 
(Thesis) Ph.D.

Towards an assistive vestibular stimulation and brain monitoring using a two-channel in-ear EEG system for fine motor enhancement

Author: 
Date created: 
2019-06-03
Abstract: 

The thesis focused on the development of an assistive device employing a galvanic vestibular stimulation (GVS) and brain monitoring platform through in-ear electroencephalography (EEG) system that aims to improve the user’s fine motor skills. The effect of noisy GVS on fine motor skills in healthy subjects was investigated and results showed that simultaneous GVS delivery statistically improved the tracking performance and may be beneficial in improving sensorimotor performance during a fine motor task. A two-channel in-ear EEG system was used for user-state monitoring during performing such a task and results demonstrated the feasibility of using the ear-worn wearable for detecting mental workload induced through a visuomotor task. Future work requires integrating the two components together where electrical stimulation can be reliably delivered and triggered by monitoring user’s mental state through an in-ear EEG system so that the two subsystems work in a closed-loop manner coherently.

Document type: 
Thesis
File(s): 
Senior supervisor: 
Carlo Menon
Department: 
Applied Sciences: School of Engineering Science
Thesis type: 
(Thesis) M.A.Sc.

Biological cell trap arrays with applications to extraordinary optical transmission based immunobiosensing assays

Author: 
Date created: 
2019-05-09
Abstract: 

This thesis’ work is part of a multi-disciplinary project developing a novel immunobiosensing (IBS) platform to monitor antibody (Ab) production by specific cells trapped in a micromachined slide. This platform consists of two subsystems, the micromachined slide featuring the cell traps and the IBS slide integrated with the traps to gauge the affinity with which Ab(s) secreted by specific trapped cells bind an immobilized target antigen (Ag). This thesis’ primary contributions involve the design, fabrication, and experimental testing of multiple cell trap generations—including their integration with co-designed IBS slides. Hydrodynamic flows and sedimentation under gravity are used to trap cells, as they are gentler and require fewer components than other methods. Hydrodynamic flows that guide cells into cup-based traps in enclosed microfluidic channels are investigated. However, their enclosed nature complicates removing extraneous untrapped cells, selectively retrieving trapped cells, and device cleaning between experiments. An open system involving arrays of microwell-(MW)-based traps are used for all subsequent traps. Multiple generations of MW traps and co-designed IBS slides are presented, with each generation refined to further streamline alignment and examination via optical microscopy. Statistical analyses of the observed distribution of trapped cells in the MWs confirm that sedimentation is Poisson distributed, and further suggest that a zero-inflated Poisson (ZIP) function serves as a superior model. This thesis shows that cells can be trapped into an open array of MW traps subsequently aligned with an IBS slide to gauge the affinity with which cell-secreted Ab(s) bind a target Ag. Further refinement to the Extraordinary Optical Transmission (EOT)-based IBS slide used in this thesis is required to achieve Ab-Ag binding detection at the desired single cell/trap level and to improve the IBS slide re-usability. Integration of the traps with a different IBS subsystem is also a possibility. As potential future work, it is proposed that a micropipette needle be used to obtain a revised single cell/trap distribution prior to IBS slide integration and to retrieve the cells of interest selectively.

Document type: 
Thesis
File(s): 
Senior supervisor: 
Bonnie L. Gray
Department: 
Applied Sciences: School of Engineering Science
Thesis type: 
(Thesis) Ph.D.

Simulation of SFU Wi-Fi using Riverbed Modeler

Author: 
Date created: 
2019-04-24
Abstract: 

Pervasive in the workplace, the home, educational institutions, café, airports, and street corners, wireless networks are now one of the most important access network technologies on the Internet today. The IEEE has standardized the 802.11 protocol for wireless local area networks. This project involves the study of the SFU wireless LAN to understand the problem of the slow wireless network (e.g. problems with top hat quizzes, congestion of devices, etc.).The wireless profile in the academic quadrangle area in various classrooms(AQ3181, AQ3182) and hallways will be studied. The Xirrus WiFi inspector and WirelessMon will be used to check the Wi-Fi network and to gather information about the wireless access point(signal strength, data rate, sent rate, etc.). The scenario of the lecture halls with a high-density network will be simulated in the Riverbed modeler to find out the network issues and the solution for the same.

Document type: 
Graduating extended essay / Research project
File(s): 
Senior supervisor: 
Ash M Parameswaran
Department: 
Applied Sciences: School of Engineering Science
Thesis type: 
(Project) M.Eng.