Search

Internet of Drones (IoD) is a decentralized network and management framework which connects drones' access to the limited airspace and offers inter-location navigation services via the Internet of Things (IoT). For effective design of security based solutions for access control in IoD network, intrusion detection scheme (IDS) plays a vital role which determines the presence of intruders or non-intruders in the network. This paper presents an oppositional Aquila Optimizer based feature selection with machine learning enabled intrusion detection system (OAOFS-MLIDS) model in IoD environment. The proposed OAOFS-MLIDS model aims to accomplish secure access control via the detection of the intrusions exist in it. To accomplish this, the proposed OAOFS-MLIDS model initially pre-processes the networking data using min-max normalization. In addition, the OAOFS-MLIDS model involves the design of OAOFS technique to elect a subset of features. Besides, coyote optimization algorithm (COA) with extreme gradient boosting (XGBoost) model is employed for the recognition and classification of intrusions exists in the IoD environment. For ensuring the better performance of the OAOFS-MLIDS model, a wide range of simulations were carried out on benchmark dataset. The comparative study reported the supremacy of the OAOFS-MLIDS model over recent approaches. • Internet of Drones (IOD) connects drones' access to limited airspace and offers inter-location navigation services. • The interlinking of drones in the IoD networks takes place via the Internet of Things (IoT). • Extensive range of benchmark dataset simulation ensures better performance of the OAOFS-MLIDS model. • The comparative study reported the supremacy of the OAOFS-MLIDS model over current approaches. [ABSTRACT FROM AUTHOR]