I am part of a dynamic team developing a full-stack application that enhances the Peer Learning Facilitator (PLF) program experience. Our collaborative effort is centered around leveraging ASP.NET Core and Entity Framework to build a comprehensive platform. We focus on streamlining roster signing and shift logging processes and maintaining data integrity with SQL Server. Through Bitbucket, we foster a seamless collaborative environment, contributing to a tool that has significantly improved efficiency and engagement for students involved in the PLF program.

• Applied in-depth knowledge of curriculum materials for CAB201 – Programming Principles to facilitate student learning. • Reviewed and graded assignments, providing support and guidance as needed.

Assisted and provided valuable STEM supports for students in areas of IT and Mathematics.

Handed out tickets to guests for physics and chemistry tours during QUT Open Day, ensuring adherence to safety standards by maintaining the lab's maximum capacity of 40 people.

Research topic: Deep learning for Enhanced Medical Image AnalysisSupervisor: Professor YuanTong Gu & Dr Laith Alzubaidi & Yubo Chen• Fine-tuned state-of-the-art deep learning models (VGG16, ResNet50, DenseNet121, InceptionNet, EfficientNet, Vision Transformer, Data-Efficient Image Transformer) specifically for image classification tasks in detecting bone fractures. • Integrated Gradient-weighted Class Activation Mapping (Grad-CAM) and Grad-CAM++ within PyTorch to enhance interpretability by providing visual explanations for model decisions, highlighting critical regions in input images.• Applied classical pre-processing techniques (CLAHE) and feature extraction methods (HOG, LBP), combined with dimensionality reduction techniques (Auto-Encoder), to enhance traditional machine learning models (SVM, KNN, Random Forest) and evaluate their precision and efficiency in medical image analysis for fracture detection.• Conducted a comprehensive comparative analysis of deep learning models versus classical machine learning techniques (SVM, KNN, Random Forest) in the context of medical image classification.• Outcome: Received the Best Abstract & Poster Award for the research.

• Taught mathematics, with a focus on number theory topic, to students to prepare them for national competitions.• Prepared mock tests and marked students' exams, assessing and providing feedback on their performance.• Collaborated with former students and teachers to write and publish a book compiling a collection of past exams with solutions, professionally typeset in LaTeX.