Muhammad Ureed Hussain@Ureedhussain

Inefficient network planning and unmanaged traffic congestion hinder public connectivity, especially in underserved areas. Existing methods fail to strategically place infrastructure or classify network traffic for better bandwidth allocation. Our project, "AI Unified Network Optimizer for Public Connectivity," predicts the optimal placement of network towers and infrastructure using geospatial and demographic data. Machine learning models classify network traffic by type, enabling smarter prioritization and paving the way for AI-driven bandwidth optimization in the future. This hybrid solution combines strategic planning and real-time insights, providing a scalable and cost-effective approach to enhance public connectivity.

This project leverages machine learning to optimize TVWS base station locations using datasets on schools, towers, demographics, elevation, and spectrum. The dashboard provides key insights, including predicted interference, failure risks, and AI-driven recommendations to enhance network performance. A dedicated Potential Location page simulates TVWS availability on an interactive map, identifying optimal base station placements based on factors like population density and elevation. Additionally, a Procurement page, currently in progress, will track infrastructure and equipment acquisition for future deployments. By integrating historical data and predictive analytics, this system enables proactive decision-making to improve TVWS coverage and reliability.