Skip to content
View FyreHyer's full-sized avatar

Highlights

  • Pro

Block or report FyreHyer

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
FyreHyer/README.md

Wan Muhammad Afif

Computer Engineering graduate at UTeM building at the intersection of embedded systems, computer vision, and applied AI.
Currently open to graduate roles starting August 2026.

  • 🎓 Thesis: PCB defect detection using YOLOv12 with CLAHE + bilateral filtering preprocessing
  • 💼 Internship: ROHM Electronics Malaysia — IT infrastructure support & AI chatbot development
  • 📍 Based in Petaling Jaya, Selangor — open to relocation

Reach me: Email · LinkedIn · Portfolio


Projects

Benchmarked YOLOv8n, YOLOv11n, and YOLOv12n for automated PCB defect detection, with an optimized CLAHE + bilateral filtering preprocessing pipeline.
Improved performance by +4.94% mAP@50 over the published YOLOv12n baseline.
Python Ultralytics YOLO OpenCV

Built a fully offline retrieval-augmented chatbot using local embeddings + vector search + open-weight LLM for privacy-first Q&A.
LangChain LlamaIndex ChromaDB Mistral

Developed a real-time air-quality monitoring system and used a Random Forest model to classify pollution levels from live sensor data.
ESP32 Raspberry Pi Arduino scikit-learn


Skills

Category Tools
Programming Python, C/C++
AI / ML Ultralytics YOLO, scikit-learn, LangChain, LlamaIndex, ChromaDB, Mistral
Embedded & IoT Raspberry Pi, Arduino, ESP32
Networking & IT Infrastructure PC hardware, network device setup, server maintenance

Currently Focused On

  • Improving model robustness for real-world computer vision deployment
  • Building practical AI systems that run efficiently on limited hardware
  • Expanding portfolio projects with better documentation and demos

Pinned Loading

  1. pcb-defect-detection-yolov12 pcb-defect-detection-yolov12 Public

    Automated PCB defect detection using YOLOv12, with CLAHE and bilateral filtering preprocessing for improved detection of small, low-contrast defects. Achieves +2.43% mAP@50 over the YOLOv12n baseline.

  2. RemaBot RemaBot Public

    This is where you can try the chatbot

    HTML