Algorithm for Generating AI Geo-Fence of Satellite Communication Network Using Multi-Dimensional SVM Model

In this paper, we propose a method for creating an AI-based geo-fence using satellite communication networks to predict the location of terminals in advance and quickly switch between satellite networks in shadow areas of the TN network and TN networks where they exist. To achieve this goal, we used a multi-dimensional support vector machine (SVM) model to create an AI-based geo-fence and confirmed that classification accuracy was secured above a specified level (e.g., 98%).