Due to the widespread proliferation of multimedia traffic resulting from Internet of Things (IoT) applications and the increased use of remote multimedia-based applications, as a consequence of COVID-19, there is an urgent need to develop intelligent adaptive techniques that improve the Quality of Service (QoS) perceived by end-users. In this work, we investigate the integration of deep learning techniques with Software-Defined Network (SDN) architecture to support delay-sensitive applications in IoT environments. Weapon detection in real-time video surveillance applications is deployed as our case study upon which multiple deep learning-based models are trained and evaluated for detection using precision, recall, and mean absolute precision. The deep learning model with the highest performance is then deployed within a proposed artificial intelligence model at the edge to extract the first detected video frames containing weapons for quick transmission to authorities, thus helping in the early detection and prevention of different kinds of crimes, and at the same time decreasing the bandwidth requirements by offloading the communication network from massive traffic transmission. Performance improvement is achieved in terms of delay, throughput, and bandwidth requirements by dynamically programming the network to provide different QoS based on the type of offered traffic and current traffic load, and based on the destination of the traffic. Performance evaluation of the proposed model was carried out using the mininet emulator, which revealed improvement of up to 75.0% in terms of average throughput, up to 14.7% in terms of mean jitter, and up to 32.5% in terms of packet loss.
Keywords: Internet of Things (IoT); Software-Defined IoT; Software-Defined Network (SDN); YOLOv5n; deep-learning; fog/edge computing; video surveillance; weapon detection.