Pham, H.N.A. and Triantaphyllou, E. (2008) The Impact of Overfitting and Overgeneralisation on the Classification Accuracy in Data Mining. In: Maimon, O. and Rokach, L., Eds., Soft Computing for Knowledge Discovery and Data Mining, Springer, Boston, MA, 391-431.
https://doi.org/10.1007/978-0-387-69935-6_16

has been cited by the following article:

• TITLE: Artificial Intelligence Self-Organising (AI-SON) Frameworks for 5G-Enabled Networks: A Review

  AUTHORS: Delali Kwasi Dake

  KEYWORDS: Self-Organising Networks, Artificial Intelligence, Software-Defined Networks, 5G Networks, Big Data

  JOURNAL NAME: Journal of Computer and Communications, Vol.11 No.4, April 25, 2023

  ABSTRACT: The fifth generation (5G) networks will support the rapid emergence of Internet of Things (IoT) devices operating in a heterogeneous network (HetNet) system. These 5G-enabled IoT devices will result in a surge in data traffic for Mobile Network Operators (MNOs) to handle. At the same time, MNOs are preparing for a paradigm shift to decouple the control and forwarding plane in a Software-Defined Networking (SDN) architecture. Artificial Intelligence powered Self-Organising Networks (AI-SON) can fit into the SDN architecture by providing prediction and recommender systems to minimise costs in supporting the MNO’s infrastructure. This paper presents a review report on AI-SON frameworks in 5G and SDN. The review considers the dynamic deployment and functions of the AI-SON frameworks, especially for SDN support and applications. Each module in the frameworks was discussed to ascertain its relevance based on the context of AI-SON and SDN integration. After examining each framework, the identified gaps are summarised as open issues for future works.