title: "fire, forestry, frogs, and physiology: the effects of disturbance on amphibian microhabitats"
supervisory committee:
dr. adam algar (supervisor)
dr. carissa brown
dr. stephen mayor
all are welcome to attend. please contact biology@lakeheadu.ca for the meeting id and password.
speaker: dr. oswald schmitz, yale university school of the environment
title: “why animals matter: movement ecology and the zoogeochemistry of ecosystems and landscapes”
host: dr. douglas morris
location: cb 3013 thunder bay, or connect via zoom
all are welcome. please contact biology@lakeheadu.ca for the meeting id and password.
join campus rec for free lunchtime cycle classes during try it week!
register at luathletics.lakeheadu.ca with the promo code fitnesstryit2024.
please join the faculty of natural resource management for vianney cupiche's phd dissertation defense on 'effect of boreal forest disturbance due to logging at different spatial scales on migratory songbirds'.
the presentation will be via zoom.
https://lakeheadu.zoom.us/j/98059883362?pwd=z2jqqmnucg5rulc0zgzwufy1tkvhdz09
zotero is a free and convenient tool that can be used to help you manage information for your research, insert citations into your writing, and easily create bibliographies. this session will provide an overview of how zotero can support your work throughout the research process, with hands-on opportunities to practice using the tool.
after attending this workshop, you will have learned how to use zotero to:
this session will be held online via zoom.
for anyone new to researching with primary sources (original documents or objects, including in digital formats). we’ll explore the nature of archival and primary source collections, share tips on locating sources online and in the physical world, and how to read and evaluate historical documents. this session is for anyone interested in doing historical research, regardless of your program.
by attending this workshop you will:
come visit a furry friend for some much needed relaxation in the sas multi use access lounge. every thursday from 2 to 3 pm in the tunnels, sc 0004. all are welcome!
art with impact presents movies for mental health 2023-2024: connecting with ourselves and others through short films about mental health. climate change focus.
tuesday, january 23, 2024
6 to 8 pm
uc1017
please join the computer science department for the upcoming thesis defense:
presenter: liam dingle
thesis title: a comparison of explainable clinical decision making using white box and black box models
abstract: explainability is a crucial element of machine learning based decision making in high stake scenarios. the area of icu outcome prediction is one such area. there currently exists a performance tradeoff between low-complexity machine learning models capable of making predictions that are inherently interpretable (white box) to a human, and cutting-edge high complexity (black box) models that fit better to non-linear decision boundariesare not readily interpretable . this document aims to assess the reliability of the predictions made by black-box models by comparing the decisions made by white box models and their black box counterparts by contrasting explainable model feature coefficients/importances to feature importance values generated by a post-hoc shap values. the comparison between explainable models and non-explainable models show that both series of models prioritize clinically relevant variables when making outcome predictions. then in another study, we test the reliability of the generated explanations made by both shap and explainable model importances by assessing the performance impact of training models on different subsets of features generated. this is performed by ranking features based on each type of feature importance. to introduce further rigor, two other binary classification tasks are performed on two different clinical datasets . this analysis shows that there is a tangible performance impact between decisions that can be correctly made on important compared to unimportant data. overall, we can conclude that the implementation of black box models in high-stakes decision making can offer tangible benefits in performance while also providing reliable, transparent predictions if proper explainability mechanisms are in place.
committee members:
dr. yimin yang (supervisor, committee chair), dr. ruizhong wei (co-supervisor), dr. amin safaei, dr. thangarajah akilan (software engineering)
please contact grad.compsci@lakeheadu.ca for the zoom link. everyone is welcome.
the chemistry and materials science phd candidate, vira grynko will present her research, "the medical applications of hyperpolarized xe and non-proton magnetic resonance imaging".
the field of medical diagnostics continually demands advancements in imaging modalities to ensure precise diagnostics. magnetic resonance imaging (mri) has an indispensable role in diagnosing numerous diseases owing to its exceptional soft-tissue contrast and superior spatial resolution. nevertheless, there are limitations to mri, particularly in the fields of functional imaging and pulmonary imaging. this is where hyperpolarized 129xe mri becomes crucial, offering the ability to furnish vital insights into the lungs and brain functions and physiology, as well as enabling molecular imaging.
despite its potential, hyperpolarized 129xe mri lacks certain essential elements for further progress. in my research, i addressed three pivotal questions related to hyperpolarized mri. firstly, i investigated the impact of glucose on hyperpolarized xe dissolved in the blood. secondly, i explored the feasibility of conducting multi-slice brain imaging to achieve precise spatial signal localization. lastly, i successfully enhanced the efficiency of molecular imaging using hyperpolarized xe.
committee members: dr. mitchell albert (supervisor), dr. michael campbell, dr. robert mawhinney, dr. alla reznik and dr. boguslaw tomanek (external)
everyone is welcome.
for more information contact brenda magajna at phd.ses@lakeheadu.ca.
