oURspace (Univ. of Regina)
Not a member yet
15455 research outputs found
Sort by
Using machine learning methods to estimate spruce tree crown and DBH from aerial imagery
No full textA Thesis Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the Degree of Master of Applied Science in Industrial Systems Engineering, University of Regina. xi, 87 p.Spruce trees play a vital role in Canada’s forest ecosystems, which is widely used in construction,
paper production, and other industries. However, spruce trees are particularly susceptible to
wildfires, which pose a major risk to both natural landscapes and human settlements. Therefore,
to evaluate the spruce forest biomass volume is an important step to estimate its yield and
combustibility. This paper aims to use Machine Learning (ML) approaches to estimate the biomass
volume of spruce trees from aerial top-view images. Since the aerial images are only show the tree
crown shapes, we set up the relationship between tree crown diameter (TCD) and Diameter of tree
Breast Height (DBH), and this DBH can be further used to estimate the tree biomass volume. Here,
Spruce trees top-view images were taken by a DJI Mavic 3, at an altitude of 50m above ground.
We measured the actual TCD and DBH in the field. 2,155 spruce trees were labelled in our dataset
according to its location in the aerial images. The actual TCD values of 2155 samples were
measured with a Hypsometer device that uses ultrasound at the extremities of the tree branches,
which will be further used to compare and calculate the accuracy of the TCD values that are
measured from top-view images after our model training.
After experimenting with tree detection methods, we conclude that YOLO performed better than
MaskRCNN by 4%. And then we proposed two methods that use YOLOs: First method, a
combination of YOLOv5 bounding box to identify the trees and watershed technique to segment
tree crowns from aerial images. Compared to the second method YOLOv11 that uses instance
segmentation to segment the trees.
A study is conducted to showcase a relationship between TCD and DBH of the field measurements.
This linear relationship can be used to estimate DBH out of TCD and then could futher calculate
tree biomass volume with the estimated DBH.Studentye
Stability studies of a novel amine blend for the capture of CO2 generated from indirect co-combustion of natural gas and biomass
No full textA Thesis Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the Degree of Master of Applied Science in Process Systems Engineering, University of Regina. xvi, 120 p.The excessive release of CO2 from human activities has led to global warming and climate change,
becoming a critical global issue for many years. Data released by the Environment Protection
Agency of United States in 2022 clearly shows that, CO2 is the most emitted gas among other
greenhouse gases. In response, numerous strategies have been developed to address this pressing
problem. One particularly compelling approach is to use an optimal mix of fuels in combination
with post-combustion capture technology to achieve net-zero or even negative CO2 emissions.
Over the past years, solvent absorption in post-combustion capture technology has shown
significant reliability and efficiency in reducing CO2 emissions. Despite this, investors face major
challenges such as the cost of solvents, solvent loss, and the expenses involved in solvent
regeneration.
Monoethanolamine (MEA) is the most extensively studied alkanolamine absorbent and serves as
the benchmark for evaluating other absorbents. MEA is recognized for its high absorption rate,
low cost, and low viscosity. However, MEA is prone to a high degradation rate, which leads to
significant solvent loss. In the field of CO2 capture, degradation refers to the diminished capacity
of the solvent to effectively capture CO2 as expected during the capture process. This degradation
is primarily caused by undesirable side reactions between the absorbent and impurities in the flue
gas, such as oxygen, NOx, SOx, particulate matter, and heavy metals. Degradation is an
endothermic reaction so the process is favoured at high temperature in the presence of these flue
gas impurities.
Solvent degradation is an important parameter to consider during solvent selection for commercial
use in CO2 capture process. It does not only lead to solvent loss but degradation products like
carboxylic acids and heat stable salt (HSS) promotes corrosion. Also, nitrosamines emitted due to
some absorbent reaction with NOx poses threat to human health. There are chances of fouling and
solvent foaming due to degradation. Least to mention is the increase in cost of operation due to
increase in heat duty required for regeneration because of the presence of degradation products.
This work demonstrates the stability of 4M AMP:1-(2 HE) PRLD. The novel amine blend was
subjected to some conditions mimicking CO2 capture for flue gas generated from indirect cocombustion
of natural gas and biomass. When it was compared with a known amine blend, thus,
5M MEA:DMAE under same conditions, 4M AMP:1-(2 HE) PRLD, proved to be inherently more
stable. It had a 33% increase in its rate in degradation as against 80% increment when the oxygen
partial pressure was doubled keeping all other conditions constant. This implies the novel amine
blend is stable and can be used commercially for the capture of CO2 from pretreated flue gas. The
results highlight its resilience and potential for long-term application in environments where
oxygen levels may fluctuate without succumbing easily to the degradation processes that typically
affect similar compounds. A kinetic model was generated for the rate of degradation and it is of
the form:
r( hr M )=6.8222×10 9 e(− 8.314×T 50314.08 )[O₂] 1.3Studentye
Historical accuracy in two video games: a study on reception theory and historical representation in Assassin's Creed
No full textA Thesis Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the Degree of Master of Arts in History, University of Regina. viii, 72 p.Historical video games are a class of video games set in the past, and these games are
considered authentic representations of the past by players. An examination of female nonplayable
characters (NPCs) in Assassin’s Creed: Origins and Assassin’s Creed: Odyssey using
reception as a theoretical framework gauges the historical accuracy of the representations. While
some aspects of the depictions were accurate, the accurate aspects were often supplemented with
invented and inaccurate details, and other aspects were entirely ahistorical. Historical
representations in video games have an impact on players’ understanding of the past, and because
video games see regular graphical and story improvements, the representations will have a
greater impact in future.Studentye
Kiannet: An attention-based CNN-RNN model for violence detection
No full textA Thesis Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy in Software Systems Engineering, University of Regina. xv, 160 p.Violent behaviour poses a significant risk to societal stability and public safety. As
part of proactive strategies to counteract this threat, many organizations and institutions
have implemented surveillance systems to monitor and identify potential violent
instances. Nevertheless, manual review and analysis of vast surveillance footage can
be a daunting and error-prone task for human operators, necessitating the advent of
automated systems for efficient and precise violence detection.
This study introduces a novel approach for violence detection composed of a CNNRNN
structure based on an attention mechanism for binary and multi-class classification
of abnormal behaviours. We called our proposed model KianNet because Kian
is the name of an intelligent innocent murdered in a violent incident, and we chose
his name as a representative of all people who suffered from violent behaviours. In
this technique, a CNN-RNN structure is applied to an input video to extract features
from a sequence of frames and by adding a combination of Multi-Head Self-Attention
(MHSA) and ConvLSTM layers, it can detect the violent event and determine the
type of the observed anomaly.
The key to KianNet’s performance is implementing the MHSA layer, which allows
the model to focus on specific spatiotemporal regions of relevance, improving its capacity
to differentiate between normal and violent events. Consequently, the MHSA
layer boosts KianNet’s discriminatory power, enabling it to discern violent incidents
from regular activities better. Through empirical evaluations, KianNet has proven its
superior performance in violence detection tasks. Our findings reveal that KianNet
outperforms its closest competitors’ accuracy by roughly 10 percent. This substantial
performance margin substantiates the robustness and reliability of KianNet, cementing
its potential as an effective tool in automated surveillance systems for violence
detection.Studentye
Application of data-driven and physics-driven models in predicting vibratory responses of nonlinear dynamic systems
No full textA Thesis Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy in Industrial Systems Engineering, University of Regina. xvi, 187 p.The investigation of chaotic vibrations is essential for understanding the vibro-responses of engineering structures subjected to external excitations. This understanding is crucial for developing advanced strategies to control chaotic structural instability and sensitivity. Traditional methods for investigating chaotic vibration behavior rely on physics-based model establishment, where physical models are mathematically analyzed through complex calculations of differential equations. Although the development of analytical and numerical theories is relatively mature, the costly human labor required for feature engineering and high demands for expert knowledge in mathematical and physical domains limit its application in engineering fields to a certain extent. Therefore, this research aims to establish an innovative approach for predicting the chaotic responses of nonlinear models in the engineering field by proposing data-driven models to accomplish supervised learning regression tasks. The application of these proposed data-driven models in predicting chaotic responses of various nonlinear system models is conducted in a completely data-driven and non-intrusive manner.
This thesis implements prediction tasks for chaotic vibrations of different types of nonlinear dynamic systems based on both physics-driven and data-driven models. These nonlinear systems serve as fundamental reference models and are widely applied in various engineering fields. Specifically, the physics-based investigations in this work focus on comparing the advantages of the developed P-T method over the 4th-order Runge-Kutta method in terms of accuracy and reliability.
Additionally, studies on chaotic vibration prediction based on data-driven models are also carried out in this thesis. Three hybrid neural networks are proposed, and their architectures are thoroughly explained. The effectiveness and robustness of these models are sequentially enhanced. Specifically, their ability to handle chaotic sequences has evolved from considering temporal correlations to considering spatiotemporal correlations, and their capability to manage the length of inputs and outputs has progressed from fixed to variable. Besides the inherent advantages of data-driven investigation compared to physics-driven methods, the superior performance of the proposed data-driven models over conventional benchmarks in terms of training time and testing loss is quantitatively demonstrated.
The continuous development of measuring equipment has facilitated easier access to substantial high-quality data. Thus, the findings of this research provide new insights into the investigation of chaotic responses and are valuable for analyzing and understanding chaotic vibrations with greater efficiency. The optimized results obtained in this research are expected to offer practically sound guidance for optimizing engineering structural design and enhancing performance when considering chaotic or nonlinear vibrations.Studentye
Exploring the Perspectives of Older Adults Living With HIV on Virtual Care: Qualitative Study
No full textBackground
As the population of individuals with HIV ages rapidly due to advancements in antiretroviral therapy, virtual care has become an increasingly vital component in managing their complex health needs. However, little is known about perceptions of care among older adults living with HIV.
Objective
This study aimed to understand the perceptions of older adults living with HIV regarding care.
Methods
Using an interpretive, qualitative, descriptive methodology, semistructured interviews were conducted with 14 diverse older adults living with HIV. The participants lived in Ontario, Canada, self-identified as HIV-positive, and were aged 50 years or older. Efforts were made to recruit individuals with varying experience with health care. Reflexive thematic analysis was conducted with the interview transcripts to identify prevalent themes.
Results
The identified themes included (1) the importance of relationships in virtual care for older adults living with HIV; (2) privacy and confidentiality in virtual care; and (3) challenges and solutions related to access and technological barriers in virtual care. These themes highlight the perceptions of diverse older adults living with HIV concerning care, emphasizing the fundamental role of trust, privacy, and technology access.
Conclusions
By embracing the unique perspectives and experiences of this population, we can work toward building more inclusive and responsive health care systems that meet the needs of all individuals, regardless of age, HIV status, or other intersecting identities
How old do you feel? Associations with self-reported health, physical activity, fruit/vegetable consumption and sleep among adults
No full textMaking (in)visible: Marginality, neurodiversity and COVID-19 in urban Saskatchewan
No full textA Thesis Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the Degree of Master of Arts in Women's and Gender Studies, University of Regina. viii, 127 p.People with disabilities have been coined invisible citizens during the COVID-19 pandemic. This research responds to the ways people with disabilities and other intersecting marginalities were made invisible during COVID-19 in urban Saskatchewan. Using arts-based participatory this research asks, “what are the practices that worked to invisibilize people with disabilities and intersecting marginalities during the COVID-19 pandemic?” To explore this question the project worked with three community-based organizations and individuals with disabilities in Regina Saskatchewan to unpack stories and truths while co-designing a creative outcome focused on lived experiences of COVID-19. Analysis explores the broader contexts in which people with disabilities were made invisible but includes particular emphasis on four focus areas: housing precarity, mental health, food insecurity and substance use. In doing so, the research is grounded in theoretical underpinnings from queer theory and disability justice. Both of which offer frameworks to examine the systems of compulsory able-bodiedness and heterosexuality that codify ideas surrounding normativity and influence pandemic responses. By telling the often-overlooked stories of people with disabilities, participants asserted that these stories are of importance and are fundamental to a collective understanding of how things happened during COVID-19. In such, the paper discusses how stories and artistic contributions from participants require the development of a radical imagination for post-pandemic futures.
Keywords: Neurodiversity, COVID-19, Arts-Based Methods, Intersectionality, Invisibilization, Disability JusticeStudentye
An experimental study of police interactions with persons with mental illness using simulation technology
No full textA Thesis Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy in Experimental and Applied Psychology, University of Regina. xiii, 268 p.Mass deinstitutionalization and repeated reports of the use of force during police
responses to person(s) with mental illness (PMI) have resulted in public and political
debates about police mistreatment of PMI and motivated requests for police reform. As
police interactions with PMI continue to increase it is important to understand police
decision making, how officers perceive and interact with PMI, and the role of policing
during mental health crises. Research examining police records or police-civilian
interactions in the field has produced mixed results in the rates of use of force during
interactions with PMI. The current study used a laboratory experiment to control
environmental variances in police interactions to add to the understanding of police useof-
force during interactions with PMI. Study 1 compared perceptions of PMI between law
enforcement students and university undergraduate students. Study 2 compared law
enforcement students’ behaviour during a use-of-force scenario with either a PMI or
healthy civilian, preceded by a dispatch report with or without information of the presence
of mental health issues. Behaviours assessed include use-of-force choices, intervention
response times, risk assessment, and communication tactics. The results of the studies
found no significant differences between law enforcement and civilian students’ attitudes
of mental health and the attitudes of law enforcement students did not influence their
behaviour during the use-of-force scenarios. Use-of-force response times revealed that OC
spray (i.e., pepper spray) use was delayed when interacting with the simulated PMI. While
other intervention methods were rarely used, participants who used their pistol were not
influenced by the mental health manipulations. Participants’ risk assessments and
communication strategies were observed to vary between experimental conditions and in
different contexts. Having prior information of mental health issues or responding to a
PMI resulted in lower ratings of the risk of harm to others and situational factors, and
higher ratings of risk to oneself. These results demonstrate that law enforcement students
were not applying risk assessments equally across contexts as they are taught. These
conditions also resulted in increased attempts to engage in conversation and to offer
assistance. The results of this study demonstrate that law enforcement students had a
tendency to wait longer before deciding to use force and used de-escalating
communication when responding to a mental health crisis, while those who interacted with
the healthy individual made more attempts to gain compliance and control using
commands and earlier force. Overall, the students’ communication focused on police
commands in all conditions and may indicate that more training on de-escalation is still
needed. These results demonstrate a tendency towards de-escalation with PMI, particularly
in use-of-force responses, as well as how law enforcement students are applying their
training and the gaps that may still be present during interactions with PMI.Studentye
Clinical counselling at Joshua Tree Learning Centre: a field practicum experience
No full textA Practicum Report Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the Degree of Master of Social Work, University of Regina. 69 p.This report provides a description of my field practicum experience in a clinical counselling experience with Joshua Tree Learning Centre. The report includes a literature review of the theoretical frameworks and approaches that guided my interactions and the work I did during my practicum. The report then discusses the specific counselling modalities I adopted through the use of an integrative approach, which included narrative therapy, trauma- focused cognitive behaviour therapy, expressive therapy, and equine facilitated psychotherapy, as well as practices in individual counselling and group work. The report also highlights case examples and discusses how my learning goals were achieved throughout my practicum experience. Supervision experiences and self-reflection on the practicum experience will be discussed, followed by a section on challenges, including ethical dilemmas that arose and appropriate boundaries and self-care. My personal and professional values will be reflected throughout the report. To conclude, implications for my future social practice will be discussed, as well as final comments on the benefits of utilizing an integrative therapeutic approach.Studentye