INTELLIGENT ANOMALY DETECTION SYSTEM FOR AMBIENT INTELLIGENCE

Abstract

Ambient Intelligence is immensely a descriptive term for a vision that instantiates a responsive, adaptive, personalized, context-aware environment. This technology has relied extensively on the advanced technologies of the Internet of Things (IoT), where everything should be connected to the Internet. Although this has become a hot topic for research, some gaps need to be bridged. Since IoT devices create and trade critical information, security has turned into a major worry because of the creation of zero-day cyberattacks. In addition, the much-required effective overcome for IoT network security can be provided by a Network-based Intrusion Detection System (NIDS). Several new studies about identifying the anomalies in NIDS resulted in attaining a high rate of false alarms. This work proposes an effective intelligent intrusion detection system based on the k-Nearest Neighbor (k-NN) classifier for the IoT network architecture. The proposed model was evaluated by using the available IoT-23 dataset. The experimental results show that the proposed model's accuracy rate is 89.96%.