ML-Driven Handover Optimization in LTE Networks 📡

This project presents a machine learning-based approach to optimize handover decisions in LTE networks using real-world signal data. It combines Quality Signal Indicator (QSI) classification, supervised learning for handover prediction, and reinforcement learning (Q-Learning) for optimization.

---

🔍 Project Overview

• 📍 Location: Real signal data collected from a drive test in Dhaka using XCAL-M and GPS modules.
• 🧠 Techniques Used:
  • Percentile-based thresholding for QSI labeling
  • PCA for dimensionality reduction
  • K-Means clustering for unsupervised learning
  • Supervised ML classifiers: Logistic Regression, SVM, Random Forest, XGBoost, etc.
  • Reinforcement learning: Q-Learning with hybrid logistic regression strategy
• ⚙️ Tools & Languages:
  • Python (scikit-learn, matplotlib, pandas, numpy)
  • HTML, CSS, JavaScript (for visualization)
  • XCAL-M for drive test
  • Arduino UNO + Neo-7M GPS for mobility tracking

---

🌐 Live URL

🔗 Deployed Website on Netlify

---