DalSpace Institutional Repository
DalSpace is a digital service that collects, preserves, and distributes digital material produced by the Dalhousie community.
- To learn about content guidelines, policies, and how to deposit, view the Help documents.
- Contact us to get started submitting content to DalSpace at dalspace@dal.ca
Communities in DSpace
Select a community to browse its collections.
Recent Submissions
Qualifying and Regulating the Use of Artificial Intelligence in Software Systems for the Canadian Nuclear Sector
(2024-10-29) Dahaweer, Samer; Not Applicable; Master of Science; Department of Engineering Mathematics & Internetworking; Not Applicable; Dr. Kamal El-Sankary; Not Applicable; Dr. Farzaneh Naghibi; Dr. Issam Hammad
This thesis examines the inadequacies in qualifying Artificial Intelligence (AI) software for the Canadian nuclear energy sector. The nuclear energy sector is a high-risk environment with strict regulations to ensure safety. Despite the rising popularity of new technologies like AI, a compliance assessment would be needed against nuclear qualification procedures. First, the thesis analyzes the existing regulatory framework within the Canadian nuclear sector. This analysis reveals potential gaps that traditional software qualification methods fail to address when applied to AI. The risks of AI, primarily linked to the complexity and opacity of decision-making processes, show the need for a new approach to AI regulation in nuclear. Next, a review of the Canadian regulatory framework focusing on the Canadian Standards Association (CSA) N290.14 with case studies of qualifying commercial software is presented to showcase the software qualification lifecycle. Through these detailed case studies, gaps are identified when applying the software qualifications methods to AI software. The thesis also suggests three methodologies for future AI qualification: model interpretability, feature importance, and data variety. These features are investigated in order to improve the transparency, reliability, and safety of AI applications in high-risk contexts such as nuclear power plants. Finally, the thesis proposes incorporating these three methodologies of AI into the software qualification framework to significantly mitigate the risks and support a safe deployment and operations of AI based software in the nuclear sector.
Investigating in-season management strategies for triazine resistant common lambsquarters (Chenopodium album L.) In Atlantic Canadian potato production
(2024-10-28) Anderson, Laura; Not Applicable; Master of Science; Department of Plant, Food and Environmental Sciences; Not Applicable; N/A; Not Applicable; Dr. Sameul Asiedu; Dr. Aaron Mills; Dr. Andrew McKenzie-Gopsill; Dr. Scott White
Potato (Solanum tuberosum L.) producers in Canada’s Atlantic provinces of Prince Edward Island (PE) and New Brunswick (NB) rely on photosystem II (PSII)-inhibiting herbicides to provide season-long weed control. Despite this, a high proportion of common lambsquarters (Chenopodium album L.) populations have been identified as resistant to this class of herbicides. With the absence of new herbicide chemistries, weed science research has regained focus on preventative integrated weed management (IWM) strategies. As such, this project aims to investigate common lambsquarters biology and seedbank dynamics to optimize control tactics that increase mortality, deplete the weed seedbank, and decrease germination and viable seed shed. Crop-topping common lambsquarters post-flowering by mowing or wick-applied glyphosate reduced common lambsquarters harvest index and viable seed production. Soil-incorporation of fast-establishing cover crops reduced the common lambsquarters seedbank as well as populations in subsequent potato crop. Combined, this study demonstrates how alternative integrated weed management strategies can be utilized for seedbank management of herbicide-resistant common lambsquarters in potato production systems.
ENHANCING THE COMPREHENSIBILITY OF MEDICAL PREDICTION MODELS WITH KNOWLEDGE GRAPHS: A NEURO-SYMBOLIC EXPLAINABLE AI APPROACH
(2024-10-31) Rad, Jaber; Not Applicable; Doctor of Philosophy; Faculty of Computer Science; Not Applicable; Dr. Enea Parimbelli; Not Applicable; Dr. Samina Abidi; Dr. Hassan Sajjad; Dr. Syed Sibte Raza Abidi; Dr. Karthik Tennankore
A challenge in using machine learning (ML) for decision support in critical domains such as healthcare is their lack of transparency in making predictions. eXplainable Artificial Intelligence (XAI) aims to explain the underlying decision logic and feature importance of black-box ML models, to build trust in the use of ML models. Despite advance XAI approaches, the comprehensibility of black-box ML model’s explanations remains a challenge. To enhance the comprehensibility of explanations, Neuro-Symbolic (NeSy) explainability approaches incorporate external knowledge sources to provide contextual information beyond just the use of input features in generating explanations.
This thesis proposes a NeSy XAI framework to enhance the comprehensibility of explanations for ML models’ predictions in clinical settings, aiming to bridge the gap between human-comprehensible explanations and those provided by traditional XAI methods. Our approach integrates data-driven and knowledge-driven methodologies to offer conceptually-salient, domain context-rich explanations. The data-driven component of our framework employs model-agnostic surrogate modeling to generate an optimized set of transparent decision paths, based on the metrics of fidelity, coverage, confidence, and compactness, to represent the decision logic of black-box models. The knowledge-driven component of our framework integrates external domain knowledge to the decision paths in terms of a Semantic Explanation Knowledge Graph (SeE-KG) to generate semantically-rich context-sensitive and compressive explanations. We developed a graph-based visualization system that allows users to query the SeE-KG in near-natural language for localized, context-specific insights and to explore dataset-wide trends.
The framework’s practical application is demonstrated in the complex task of organ allocation, specifically kidney transplantation. Using a comprehensive dataset of kidney transplants sourced from the Scientific Registry of Transplant Recipients (SRTR), the framework generates explanations for graft survival predictions, highlighting the underlying factors contributing to the outcomes (graft survival or failure) across donor-recipient combinations.
ECOSYSTEM SERVICES TRADE-OFFS OF SALT MARSHES AS COASTAL NUTRIENT FILTERS VERSUS GREENHOUSE GAS SINKS
(2024-10-28) Steele, Jacob; Not Applicable; Master of Applied Science; Department of Civil and Resource Engineering; Not Applicable; Lisa Kellman; Not Applicable; Rob Jamieson; Lauren Somers
Salt marshes are recognized for the ecosystem services they provide as coastal nutrient filters and carbon sinks, but relying on salt marshes to attenuate nutrient pollution comes at the potential cost of enhanced greenhouse gas (GHG) emissions. In this study, we quantify and assess the trade-offs between the nutrient attenuation and carbon sequestration functions of salt marshes in Atlantic Canada. We conducted groundwater monitoring, surface and groundwater sampling, and GHG flux measurements at two salt marshes located adjacent to eutrophic estuaries in Basin Head, PEI and Rushton’s Beach, Nova Scotia. A hydrogeological model was developed to characterize the magnitude and pathways of nitrate transport into, and attenuation by, the Basin Head marsh. Our results indicate that nitrate loading is mainly via tidal flooding from the adjacent eutrophic lagoon and was estimated at 0.06 mmol N m-2 d-1 with 36% of input nitrate retained or converted in the marsh. The net climatic effect of average N2O and CH4 fluxes at Basin Head and Rushton’s Beach results in only a small reduction in the marshes carbon sink (8.3% and 5.0%, respectively).
Microfinance, institution-building and development : an Egyptian case study
(2008-12) Al Abassi, Soulafa; Not Applicable; Master of Development Economics; Department of Economics; Not Applicable; unknown; Not Applicable; Barry Lesser; Ruth Forsdyke; Ian McAllister
The purpose of this thesis is: a) to understand the behaviour of microfinance institutions; b) to capture some of the issues that affect their behaviour and development; and c) to focus on 'healthy' institutionalization processes. Two methodologies were used to achieve this purpose: research and field exposure. From frameworks for analysis to the history and waves of the microfinance revolution; from understanding microfinance within a national context to understanding microfinance within an institutional context; to field cases from Cairo, Egypt (four borrowers and four credit officers)... this thesis has
argued the necessity of evaluating the performance of microfinance institutions from within and without. A microfinance institution has to be 'healthy' from within and without to evolve in a 'healthy' manner; one cannot be achieved without the other. Furthermore, the indicators of 'health' should reflect both financial and non-financial data.
The photosynthetic and respiratory physiology of Palmaria palmata (L.) Stackhouse, as affected by temperature, irradiance, total carbon dioxide, salinity and pH
(1976-12) Robbins, Jonathan V.; Not Applicable; Master of Science; Department of Oceanography; Not Applicable; unknown; Not Applicable; unknown; James Craigie
A chamber of variable volume was designed in which photosynthesis and respiration of the red alga Palmaria palmata could be measured under a variety of environmental conditions. The chamber was equipped with a polarographic oxygen electrode, pH electrode, injection port, and a sample removal tube. Using this apparatus, the effects of temperature, irradiance, total carbon dioxide concentration, salinity, and pH on the photosynthetic and respiratory rates of intact P. palmata plants were measured. The photosynthetic rates of seasonally adapted plants showed relatively little variation and no seasonal changes in respiration were detectable. P. palmata was shown to be a stenothermal plant, with a temperature optimum for photosynthesis of 10 and 15°c . . The photosynthetic rate became light saturated above 212 microEinsteins, with Pmax being temperature dependent. The compensation point for plants in
late winter was found to be approximately 6.6 microEinsteins. Ambient sea water concentrations of inorganic carbon were shown to be insufficient to produce a maximum photosynthetic rate. By raising the concentration of total carbon dioxide to 6.0 - 7.0 mM, it was possible to stimulate photosynthesis by about 2.7 fold over the rate at normal concentrations. Maximum rates for photosynthesis and respiration were observed at a salinity of 32.0°/oo. A pH of 6.5 to 7.5 stimulated photosynthesis when compared to rates at pH 8.1, but below pH 6.5 photosynthesis dropped off sharply. At pH values above 8.0, a nearly linear decrease in the photosynthetic rate was observed.