Differences

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

--- 2025-26:fall [2025/08/09 05:13] – mnayebi
+++ 2025-26:fall [2025/09/05 02:45] (current) – grau
@@ Line 15: / Line 15: @@
 ==== Computer Security Projects ====
 ** [added 2025-07-21] **
@@ Line 35: / Line 33: @@
 ----
+==== Analysis of gait data for health applications using machine learning ====
+** [added 2025-09-04] **
+** Course:** {EECS4080 | EECS4088 | EECS4090}
+**Supervisors:** Gerd Grau, Garrett Melenka
+**Supervisor's email address:** grau@yorku.ca, gmelenka@yorku.ca
+**Project Description:**
+//Project Motivation//
+Understanding human gait is crucial for diagnosing and managing conditions such as arthritis, where mobility is often impaired and subtle changes may indicate disease progression. With objective measurement and analysis of walking patterns, clinicians can tailor interventions and monitor the effectiveness of treatments more precisely. This project seeks to uncover relationships between gait data and restriction levels, paving the way for advanced health applications using modern machine learning techniques.
+//Project Overview//
+A comprehensive dataset of human gait has been collected from healthy subjects in various walking scenarios, with restricted braces simulating different levels of disease-related mobility impairment. The primary objective is to extract meaningful insights about gait characteristics and restriction levels from this dataset. The student will employ machine learning methods such as Long Short-Term Memory (LSTM) networks for time-domain analysis and Principal Component Analysis (PCA) for frequency-domain exploration.
+//Key Tasks and Responsibilities//
+• Preprocess and clean gait data collected under controlled walking conditions, including different restriction levels modelled by braces.
+• Apply time-domain and frequency-domain analysis techniques to identify distinctive features and trends related to restriction and gait quality.
+• Develop, train, and validate machine learning models (e.g., LSTM, PCA) to classify restriction levels and extract clinically relevant patterns.
+• Interpret model results and visualize findings to support health-related insights and recommendations for mobility assessment.
+• Document all steps of the analysis to ensure reproducibility and clarity for future research and clinical use.
+**Required skills or prerequisites:**
+•	Excellent programming skills (preferably in Python)
+•	Some knowledge of machine learning concepts and algorithms
+•	Interest in health applications and biomedical data analysis
+**Instructions:**
+Interested students should email Gerd Grau (grau@yorku.ca) and Garrett Melenka (gmelenka@yorku.ca) with:
+- CV
+- Latest transcript
+----
+==== Emotion-Aware Analysis of EECS Course Feedback for Instructional Improvement ====
+** [added 2025-08-08] **
+** Course:**  {EECS4080}
+** Supervisors:**  Pooja Vashith
+** Supervisor's email address: ** vashistp@yorku.ca
+** Project Description: ** This project aims to uncover meaningful insights from EECS course evaluations by applying natural language processing (NLP) techniques to student feedback. While most universities collect large volumes of student comments in course evaluations, these are typically underused, especially when embedded in PDF files. Qualitative feedback is often reviewed manually or averaged superficially, leaving behind rich emotional and experiential data that could inform course improvement.
+The primary goal is to build a processing pipeline that extracts, cleans, and analyzes this feedback using both basic sentiment analysis tools (e.g., VADER) and advanced emotion classification models (e.g., GoEmotions). The emotional tone expressed in the feedback will be mapped to different course components such as the instructor, teaching assistant, assessments, and course content. NB: These are already separated in the evaluation structure.
+By comparing the expressiveness and usefulness of simple versus fine-grained emotional analysis, this research will help determine which approaches are more effective at surfacing actionable insights. These insights will be visualized to highlight recurring patterns of sentiment or emotion across course components, such as whether students consistently express frustration about assessments or admiration for certain instructors.
+This project is educational in nature as it equips the student with skills in text analytics, NLP tools, and data visualization while contributing to a broader understanding of how data-driven analysis can support evidence-based teaching and curriculum refinement in academic institutions.
+** Required skills or prerequisites: **EECS 4412 or EECS4404
+Data Analysis, Report Writing, Python programming, web app development, appetite for research
+** 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  ====