It has become important to develop different standards for vehicle-to-everything (V2X) communications concept with the increase in studies on intelligent transportation systems in recent years. In this direction, organizations such as 3GPP, which leads 5th Generation (5G) communications, and IEEE, which leads Wi-Fi communications, have developed different V2X standards. There are various studies showing that these two critical standards may have advantages over each other in different scenarios. With the proposed method, which of 3GPP and IEEE standards will be more advantageous under different conditions is determined by artificial learning techniques and appropriate V2X standard is selected automatically. In this context, it is assumed that there is related equipment for each of the two standards in the vehicle and its environmental systems. For this purpose, a new artificial dataset was created, and various artificial learning models were trained using K-nearest neighbor, decision tree, artificial neural network and TabNet classifiers. In addition, hyperparameter optimization was performed with cross validation. With the TabNet classifier, the accuracy value and the weighted F1 score were obtained as 0.88. When all these studies are considered together, it has been seen that a significant contribution to the literature has been made by conducting a novel study on V2X communications. It is thought that the developed artificial learning based V2X standard selection method can be integrated into vehicles under intelligent transportation systems.