Computer Engineering Portfolio

Hi, I'm Yeo Kheong Jie

I transform complex problems into elegant solutions through code, creativity, and continuous learning — currently bridging Deep Learning and industrial agricultural applications.

View My Work

B022220074Bachelor of Computer Engineering

UTeM · FTKEKSemester 1, 2025/2026

BERR4723Digital Image Processing

About Me

The person
behind the code

Passionate Computer Engineering Student

My journey is driven by a desire to create meaningful digital experiences. From optimising IoT micro-climates to developing CNN architectures for automated grading, I believe technology should solve real-world challenges.

Currently studying at UTeM (FTKEK), I focus on AI in medical imaging, IoT networks, and Python automation — committed to continuous learning and industrial application.

Technical Skills

Python MATLAB TensorFlow C++ / Java Arduino Git OpenCV VS Code

Philosophy

Passion for Excellence

The values that shape how I approach every engineering challenge.

💡

Problem Solving

I thrive on finding innovative, first-principles solutions to complex technical challenges — breaking problems down and building answers up.

🤝

Collaboration

Diverse perspectives lead to superior, more robust engineering designs. I actively seek out teamwork that challenges and sharpens my thinking.

🚀

Continuous Learning

Committed to staying current with the rapid evolution of technology — from deep learning advances to new embedded systems paradigms.

Research & Projects

Academic Contributions

Published work and ongoing investigations at the intersection of AI and industrial applications.

✓ Published Research

IoT-Based Greenhouse Monitoring

Designed and implemented a smart environmental monitoring system using DHT11 and MQ135 sensors to detect temperature, humidity, and air quality — mitigating the impact of industrial pollution on agricultural micro-climates.

Read Paper →

⏳ Ongoing · PSM1

Deep Learning-Based Oil Palm Ripeness Classification

Designing a CNN-based vision system to replace manual oil palm grading with high-precision, automated classification across four ripeness stages — Unripe, Under-ripe, Ripe, and Over-ripe — to optimise Oil Extraction Rate (OER).

View Proposal PDF →