Differences

This shows you the differences between two versions of the page.

--- 2025-26:fall [2025/08/09 21:01] – sallin
+++ 2025-26:fall [2025/08/20 13:28] (current) – sallin
@@ Line 57: / Line 57: @@
 ** Instructions:** sen a CV, transcript, statement of interest, and skills to the instructor (Pooja).
+----
+==== Deep Learning and AI in Incident Management ====
+** [added 2025-08-20] **
+** Course:**  {EECS4070 | EECS4080 | EECS4090}
+** Supervisors:**  Marios Fokaefs
+** Supervisor's email address: ** fokaefs@yorku.ca
+** Project Description: ** "Large scale complex software systems generate immense amounts of event data. This creates a significant cognitive and work load for reliability engineers and a number of different challenges. First, the detection of problems becomes problematic and delayed due to the sheer amount of data. When problems are finally detected, their analysis and resolution may take even more time, which translates in loss of revenue. After resolution, the whole cycle must be well-documented, otherwise reproducibility is reduced and unnecessary effort may be invested.
+** Required skills or prerequisites: **
+Student must have:
+Excellent programming skills (preferably python)
+Good software design skills (must have at least a B+ in EECS3311 or similar courses)
+Some experience with the use of LLM models as a user and as a developer
+** Instructions:** Interested students must submit to the instructor (Marios):
+- CV
+- A statement of interest
+- Latest transcript
+- Other evidence (e.g., software repositories) as proof of skills
 -----
+==== Beyond the Mask: Reimagining Facial Recognition with Deep Transfer Learning ====
+** [added 2025-08-21] **
+** Course:**  {EECS4480}
+** Supervisors:**  Sunila Akbar
+** Supervisor's email address: ** sunila@yorku.ca
+** Project Description: ** "The project involves adapting a state-of-the-art, pretrained deep learning model for facial recognition to accurately identify individuals wearing masks. The student will utilize publicly available datasets and apply data augmentation techniques to simulate mask-wearing scenarios. Transfer learning will be employed to fine-tune the model for this specific task. The performance of the resulting model will be rigorously evaluated against established benchmarks.
+Application Domain: The proposed solution has relevance in environments where mask-wearing is mandatory, such as healthcare facilities, long-term care homes, food service industries, and chemical or pharmaceutical plants. Accurate masked facial recognition can enhance access control, attendance tracking, and safety compliance in these critical settings."
+** Required skills or prerequisites: **
+Python, PyTorch, NumPy, Scikit-learn, OpenCV
+Knowledge of any deep learning model is a plus
+Hyperparameter tuning and optimization
+Understanding of image processing techniques and object detection evaluation metrics
+General interest in computer vision algorithms and applications
+** Instructions:** Send CV, Transcript to the instructor (Sunila).
+----
 ==== Smart Tools for Smarter Brain Scans: Motion Correction in fMRI  ====