ML-ASSURE: Analog Station Service Utilization and Regulatory Enforcement Framework Using AI

Analog television stations play a crucial role in providing diverse content to viewers worldwide. There are many challenges to ensuring compliance in this area. In this research paper, we provide an ML method to identify different services provided by analog-compatible stations for regulatory compliance. Using a data set with different attributes such as route frequencies, call signs, and spatial networks, we use five different machine learning models, which are Random Forest (RF), K-Nearest Neighbors (KNN), Decision Tree (DT), Support Vector Classifier (SVC), Logistic Regression. Between admonitory testing, we look over the performance of this model for accurately predicting a diversity of applications, including local data processing (LD), conditional state processing (CA), transmission processing (TX), and television broadcasting (TV). Furthermore, The performance estimation of regulatory compliance is calculated through different matrices such as accuracy, precision, recall, and confusion matrix. With these metrics, models are also evaluated using receiver operating characteristic (ROC) curves, precision-recall (PR) curves, and confusion matrix to visually examine the model’s performance and confirm its fit. This ML-based method gives authorities an overarching, complete monitoring solution to effectually monitor and control compliance with analog television broadcasting standards to secure the uprightness and reliability of broadcasting services.