https://github.com/sayedgamal99/sayedgamal99

Last synced: 4 months ago
JSON representation

Host: GitHub
URL: https://github.com/sayedgamal99/sayedgamal99
Owner: sayedgamal99
Created: 2025-01-10T19:10:39.000Z (over 1 year ago)
Default Branch: main
Last Pushed: 2025-07-29T06:57:30.000Z (11 months ago)
Last Synced: 2025-09-07T05:39:33.431Z (9 months ago)
Size: 9.77 KB
Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

---

## 🚀 About Me

```yaml
name: Sayed Gamal
location: Cairo, Egypt
current_role: AI Engineer @ Noursoft
education: Computer Engineering - Mansoura University
passion:
[
"Artificial Intelligence",
"Machine Learning",
"Problem Solving",
"Innovation",
]
current_focus:
["LLM Applications", "Computer Vision", "MLOps", "System Architecture"]
fun_fact: "I've solved 450+ coding problems and led teams of 200+ participants!"
```

I'm passionate about creating intelligent systems that make a real difference. With hands-on experience in AI and machine learning, I love turning complex problems into practical solutions. and I always start by understanding the problem deeply before building. This mindset helps me deliver results that truly matter.

---

## Featured Projects

DriveMate: Multi-Agent Voice Assistant
Flare Guard: Real-Time Smoke Fire Detection And Alert System

DriveMate is a multilingual AI assistant with natural dialogue and personality profiling that adapts to user preferences. Designed for ADAS systems, it delivers personalized, context-aware voice interactions and leverages tool integrations to enable hands-free driving. With intelligent long term memory, it enhances user experience and safety by supporting seamless, voice-driven control.

Flare Guard uses real-time computer vision for instant fire and smoke detection with real-time alerts. Trained YOLOv11 on 10,000+ images, it provides fast, reliable early warnings for safety-critical environments via Telegram and WhatsApp.

The Parasiter: Microscopic Image Classification
Customer Churn Prediction Analytics

The Parasiter leverages deep learning for accurate microscopic parasite classification, making expert diagnostics accessible. It classifies 15 parasite species, features a user-friendly interface, Docker deployment, and live Azure hosting.

This project enables banks to predict customer churn using an ensemble of XGBoost, LightGBM, and CatBoost, achieving 0.891 AUC. It includes a full ML pipeline, real-time Flask Web app, and Docker deployment for actionable business insights.