Review on Using Artificial Intelligence Related Deep Learning Techniques in Gaming and Recent Networks

Abstract

Artificial intelligence (AI) is an effective and efficient solution to manage and analyze many data flows in any network. The Internet of Things (IoT) has quickly attracted significant global attention as an innovative, progressively growing technology. It has shown a rapid and successful involvement in many fields. Thus, IoT applications are evolving exorbitantly and producing vast amounts of data required for intelligent data processing. The overall number of IoT devices connected to Internet is expected to be 41.6 billion by 2025, generating 79.4 zettabytes (ZB) of data. As the number of devices increases, the size of data produced by them is also growing. It creates hurdles for the end-user to evaluate and analyze the collected information effectively. Online gaming concept is growing on with the help of AI algorithm. Strategies used in the past, could program using AI to ensure that AI can learn and develop from the past experiences to enhance gaming experience. Consequently, IoT networks utilize robust and effective AI techniques such as machine learning (ML) and deep learning (DL) to examine large amounts of data and generate meaningful information. Such approaches may allow users to interpret better and evaluate the gathered data and link them to meaningful patterns. ML is the method of self-learning without any external interference or re-programming from interactions and behavior. DL is another effective method for predicting potential behavior, using past data to increase data reading ability, and improving productivity by forecasting future events in different industries such as agriculture, transportation, online gaming, eHealth, etc. This paper has discussed the Deep leaning techniques used in IoT networks, components, applications, protocols, gaming, and increasing expectations for the incoming 5G networks. Furthermore, we have discussed the various DL algorithms and their concepts to enhance recent networks' productivity and efficiency in gaming and IoT networks. In the last part, we have discussed the future trend and challenges arise in the current networks.