Please join us for Victoria Ewen's, PhD Clinical Psychology, Final Doctoral Dissertation Defense on January 16th, 2023 beginning at 2 pm via Zoom.

Dissertation Title: Coping Motives Associated with Affect, Anxiety, and Depression After Cannabis Use in Young Adults: An Ecological Momentary Assessment Study

Supervisor: Dr. Chris Mushquash
Supervisory Committee Member: Dr. Deborah Scharf
Internal Examiner: Dr. Michel Bédard
External Examiner: Dr. Andrea Howard
GSC Rep: Dr. Gordon Hayman

Please email grad.psych@lakeheadu.ca for the Zoom link and passcode.

Please join the Computer Science Department for the upcoming thesis defense:

Presenter: Chandrashekhar Singh

Thesis title: Improving Cataract Surgery Procedure using Machine Learning and Thick Data Analysis

Abstract: Cataract surgery is one of the most frequent and safe Surgical operations are done globally, with approximately 16 million surgeries conducted each year. The entire operation is carried out under microscopical supervision. Even though ophthalmic surgeries are similar in some ways to endoscopic surgeries, the way they are set up is very different. Endoscopic surgery operations were shown on a big screen so that a trainee surgeon could see them. Cataract surgery, on the other hand, was done under a microscope so that only the operating surgeon and one more trainee could see them through additional oculars. Since surgery video is recorded for future reference, the trainee surgeon watches the full video again for learning purposes. My proposed framework could be helpful for trainee surgeons to better understand the cataract surgery workflow. The framework is made up of three assistive parts: figuring out how serious cataract surgery is; if surgery is needed, what phases are needed to be done to perform surgery; and what are the problems that could happen during the surgery. In this framework, three training models has been used with different datasets to answer all these questions. The training models include models that help to learn technical skills as well as thick data heuristics to provide non-technical training skills. For video analysis, big data and deep learning are used in many studies of cataract surgery. Deep learning requires lots of data to train a model, while thick data requires a small amount of data to find a result. We have used thick data and expert heuristics to develop our proposed framework. Thick data analysis reduced the use of lots of data and also allowed us to understand the qualitative nature of data in order to shape a proposed cataract surgery workflow framework.


Committee Members:
Dr. Jinan Fiaidhi (supervisor, committee chair), Dr. Sabah Mohammed, Dr. Carlos Zerpa (Kinesiology)

Please contact grad.compsci@lakeheadu.ca for the Zoom link.
Everyone is welcome.

Please join the Computer Science Department for the upcoming thesis defense:

Presenter: Darien Sawyer

Thesis title: Detecting Crohn’s Disease from High Resolution Endoscopy Videos: The Thick Data Approach

Abstract: Detecting diseases in high resolution endoscopy videos can be done in several ways depending on the methodology for detection. One such method that has been a hot topic in the field of medical technology research is the implementation of machine learning techniques to aid in the diagnosis of networks. While, this has been studied extensively with traditional machine learning methods and more recently neural networks, major issues persist in their implementation in everyday health. Among the largest issues is the size of the training data needed to make accurate prediction, as well as the inability to generalize the networks to several disease. We address these issues with a novel approach to detecting Inflammatory bowel diseases, specifically Crohn’s disease in endoscopy videos. We use thick data analytics to teach a network to detect heuristics of a disease, not to simply make classifications from images. Using heuristic annotations like bounding boxes and segmentation masks, we train a Siamese neural network to detect video frames for ulcers, polyps, erosions, and erythema with accuracies as high as 87.5% for polyps and 77.5% for ulcers. We then implement this network in a protype frontend that physicians can use to upload videos and receive the processed images in an interactive format. We also pontificate as to how our approach and prototype can be expanded to several diseases with learning of more heuristics.


Committee Members:
Dr. Jinan Fiaidhi (supervisor, committee chair), Dr. Sabah Mohammed, Dr. Arnold Kim (NOSM University)

Please contact grad.compsci@lakeheadu.ca for the Zoom link.
Everyone is welcome.

Please join the Computer Science Department for the upcoming thesis defense:

Presenter: Shamisa Kaspour

Thesis title: Investigating the Performance of Federated Learning Framework and Energy Disaggregation Techniques for Residential Energy Management

Abstract: Residential energy use is a significant part of total power usage in developed countries. To reduce overall energy use and save funds, these countries need solutions that help them keep track of how different appliances are used at residences. Non-Intrusive Load Monitoring (NILM) or energy disaggregation is a method for calculating individual appliance power consumption from a single meter tracking the aggregated power of several appliances. To implement any NILM approach in the real world, it is necessary to collect massive amounts of data from individual residences and transfer them to centralized servers, where they will undergo extensive analysis. The centralized fashion of this procedure makes it time-consuming and costly since transferring the data from thousands of residences to the central server takes a lot of time and storage. This thesis proposes utilizing Federated Learning (FL) framework for NILM in order to make the entire system cost-effective and efficient. Rather than collecting data from all clients (residences) and sending it back to the central server, local models are generated on each client’s end and trained on local data in FL. This allows FL to respond more quickly to changes in the environment and handle data locally in a single household, increasing the system’s speed. On top of that, without any data transfer, FL prevents data leakage and preserves the clients’ privacy, leading to a safe and trustworthy system. For the first time, in this work, the performance of deploying FL in NILM was investigated with two different energy disaggregation models: Short Sequence-to-Point (Seq2Point) and Variational Auto-Encoder (VAE). Short Seq2Point with fewer samples as input window for each appliance, tries to simulate the real-time energy disaggregation for the different appliances. Despite having a light-weighted model, Short Seq2Point lacks generalizability and might confront some challenges while disaggregating multi-state appliances. VAE is a generative model with a complex structure, which resolves the mentioned issues in Short Seq2Point. The proposed experiments are examined using two real-life datasets of appliance-level power from the UK: UK-DALE and REFIT. In order to more thoroughly examine the utility of FL in this study, several experiments have been conducted, including the implementation of attention-based aggregation in FL, and the addition of differential privacy noise to the aggregated parameters. The attention-based mechanism in FL, is a novel aggregation approach that applies a scale factor to the parameters of each client based on the importance of the information it carries. The results were then compared with recent cutting-edge studies in the same field. Based on the results, this study presents that FL framework provides comparable performance to its centralized counterparts while enhancing clients’ privacy.


Committee Members:
Dr. Abdulsalam Yassine (supervisor, committee chair), Dr. Thiago E Alves de Oliveira, Dr. Thangarajah Akilan (Software Engineering)

Please contact grad.compsci@lakeheadu.ca for the Zoom link.
Everyone is welcome.