5G Coverage Prediction Identification of Dominant Feature Parameters and Prediction Accuracy

The rapid evolution of mobile network technologies, from 2G to 5G, has significantly enhanced communication systems worldwide. However, predicting network coverage and generation remains a challenging task due to the complex interplay of signal strength, environmental conditions, and technical parameters. This project aims to address this challenge by developing a machine learning-based system to predict the generation of wireless technology (2G, 3G, 4G, or 5G) using India’s mobile network coverage dataset. Key parameters, including signal strength, network speed, latency, tower type, weather conditions, and area type, were used as input features for classification. A comparative analysis was conducted using various existing machine learning algorithms, such as Logistic Regression, Random Forest, and Support Vector Machines, alongside proposed techniques like Stacking Classifier, Voting Classifier, and Convolutional Neural Networks (CNN). The performance of these models was evaluated based on metrics such as accuracy, precision, recall, and F1-score.

  Keywords: mobile network, 2G, 3G, 4G, 5G.