Brock University Digital Repository
Brock University's Digital Repository is an online archive showcasing and preserving the Brock community's scholarly output as well as items from the Library's Archives & Special Collections. Researchers can disseminate their work by depositing it in this Open Access repository, which provides free, immediate access to users while also allowing Brock scholars to track downloads and views of their scholarship. The Digital Repository is also the home of the Brock University E-Thesis Portal.
For more information, see the repository's policies and procedures.
Communities in Brock University Digital Repository
Select a community to browse its collections.
Recent Submissions
Community Connected Experiential Learning: Change in the K-12 Classroom
(Brock University) Pirosko, Jennifer; Kitchen, Julian; Department of Graduate and Undergraduate Studies in Education
Emerging from lived experience in education and student success administration, the researcher offers a critique of experiential learning in Ontario and moves to identify universal problems in policy and system implementation of community connected experiential learning. A qualitative study with K–12 educators from a school board in Ontario and grounded theory methodology is used to analyze, code, and identify several theoretical cornerstones. The prominent themes of teacher pedagogy and community connections emerge and offer implications for theory and practice. The resulting implementation framework—viewed from the school/district/state tri level lens—will guide teachers, administrators, and policy makers on the integration of community connected experiential learning with traditional learning methods and curriculum to provide K–12 students with rich, authentic, and engaging learning opportunities.
Performance Assessment of Bayesian Networks for Soil Moisture Prediction in Agricultural Water Management
(Brock University) Asgari, Kamran; Ramazi, Pouria; Department of Mathematics
Estimating soil moisture using easily measurable parameters can significantly improve irrigation management efficiency while reducing time and cost. This study evaluated the performance of LASSO, Decision Tree, and Random Forest models for predicting soil moisture. In addition, Bayesian networks were used to model the complex interactions between soil, weather, and topographical factors at the Schäfertal site in Germany. To achieve this, seven structure learning algorithms, including PC, Grow-Shrink, Incremental Association, Fast Incremental Association, Hill Climbing, Max-Min Hill-Climbing, and Tabu Search, were used. Subsequently, soil moisture was predicted using all these algorithms to determine the best performance among them. The results showed that Bayesian networks had the best
performance for prediction, while LASSO, Decision Tree and Random Forest did not perform as well, likely due to the complex relationships between variables. Bayesian networks, however, effectively identified key factors like soil texture, depth, and evapotranspiration using measured variables across all search algorithms. Bayesian networks showed better performance than the other three models. More importantly, they predicted soil moisture using only a subset of variables, with performance close to that achieved using the full set of variables. This result demonstrates improvements in predictions and handling missing data in practical applications such as precision agriculture and water management
The Press, Volume 24, Issue 13, December 2, 1987
(1987-12-02) Pavelka, Rita (Editor); Kelly, Brian (News); Nesbitt, Mark (Arts); Gerber, Matt (Sports); Pellow, John (Photos); Woodward, Paula (Ad Manager); Wilson, Taylor (Circulation Manager); Arnold, Moira (Production Manager); Shaw, John K. (Illustrator)
The Press, Volume 24, Issue 13 includes: Professors argue about the best use of Brock computer system; major accessibility problems; Brock’s architecture is crumbling; SWAP work abroad program in Australia feature; Brock student takes pilgrimage to Israel story; BUSU members’ pet peeves.
Leveraging the Latent Space for Model Understanding and Optimization
(Brock University) Park, Brendan; Li, Yifeng; Department of Computer Science
In recent years, the field of machine learning has seen massive growth in both the size
and quality of models and performance on tasks such as classification or image generation.
However, these models are typically limited by two key factors. First, models such as those
used in tasks of text-to-image generation lack interpretation. Second, models that leverage
the latent space to represent data struggle to capture high-level details. This often results in
reconstructions which do not accurately represent the original data. First, to address the issue
of interpretability in text-to-image models, we introduce WINOVIS, a novel dataset designed
to probe models in their ability to interpret textual prompts. This approach reframes the task
of pronoun disambiguation from a single mode of natural language to a multi-model problem
involving both visual and textual understanding. Second, we turn our focus to models in
image generation such as the VQ-VAE which often struggle to reconstruct images capturing
the finer details of the original input image. By introducing lightweight and straightforward
modifications to the VQ-VAE’s loss function and dictionary selection process, we enable the
reconstruction of images that retain high-level details often absent from the reconstructions
produced by the traditional VQ-VAE.
The Press, Volume 24, Issue 12, November 25, 1987
(1987-11-25) Pavelka, Rita (Editor); Kelly, Brian (News); Nesbitt, Mark (Arts); Gerber, Matt (Sports); Pellow, John (Photos); Woodward, Paula (Ad Manager); Wilson, Taylor (Circulation Manager); Arnold, Moira (Production Manager); Shaw, John K. (Illustrator); Haun, Richard (Typesetter); Carr, Sonja (Typesetter); Richter, Dan (Writer)
The Press, Volume 24, Issue 12 includes: BUSU Prez Vedova attacks the Press for a “misinformation’ campaign regarding the student centre: “There has been nothing but negative coverage of what we’re trying to do.”; The Press responds to accusations of censorship in editorial; Brock President and nominee Earp and White respond to BUSU proposal of the student centre; BUSU candidates showcase.