Software defined network (SDN) is one of the most interesting research topic that is currently being investigated. The inclusion of artificial intelligence (AI) can improve the performance of routing protocols. Nowadays the application of AI over routing protocols is only applied to real devices, especially in wireless sensor nodes. In this paper, we present a new proposal to implement an intelligent routing protocol in a SDN topology. The intelligent routing protocol is based on the reinforcement learning process that allows choosing the best data transmission paths according to the best criteria and based on the network status.

Multimedia traffic has drastically grown in the last few years. In addition, some of the last paradigms proposed, like the Internet of Things (IoT), adds new types of traffic and applications. Software-defined networks (SDNs) improve the capability of network management. Combined with SDN, artificial intelligence (AI) can provide solutions to network problems based on classification and estimation techniques. In this paper, we propose an artificial intelligence system for detecting and correcting errors in multimedia transmission in a surveillance IoT environment connected through a SDN. The architecture, algorithm, and messages of the SDN are detailed. The AI system design is described, and the test-bed and the data set are explained. The AI module consists of two different parts. The first one is a classifying part, which detects the type of traffic that is sent through the network. The second part is an estimator that informs the SDN controller on which kind of action should be executed to guarantee the quality of service and quality of experience. Results show that with the actions performed by the network, like jitter can be reduced up to 70% of average and losses can be reduced from 9.07% to nearly 1.16%. Moreover, the presented AI module is able to detect critical traffic with 77% accuracy.

Internet of Things (IoT) can be combined with machine learning in order to provide intelligent applications to the network nodes. Furthermore, IoT expands these advantages and technologies to the industry. In this paper, we propose a modification of one of the most popular algorithms for feature selection, fast-based-correlation feature (FCBF). The key idea is to split the feature space in fragments with the same size. By introducing this division, we can improve the correlation and, therefore, the machine learning applications that are operating on each node. This kind of IoT applications for industry allows us to separate and prioritize the sensor data from the multimedia-related traffic. With this separation, the sensors are able to detect efficiently emergency situations and avoid both material and human damage. The results show the performance of the three FCBF-based algorithms for different problems and different classifiers, confirming the improvements achieved by our approach in terms of model accuracy and execution time.

The COVID-19 pandemic has been a worldwide catastrophe. Its impact, not only economically, but also socially and in terms of human lives, was unexpected. Each of the many mechanisms to fight the contagiousness of the illness has been proven to be extremely important. One of the most important mechanisms is the use of facemasks. However, the wearing the facemasks incorrectly makes this prevention method useless. Artificial Intelligence (AI) and especially facial recognition techniques can be used to detect misuses and reduce virus transmission, especially indoors. In this paper, we present an intelligent method to automatically detect when facemasks are being worn incorrectly in real-time scenarios. Our proposal uses Convolutional Neural Networks (CNN) with transfer learning to detect not only if a mask is used or not, but also other errors that are usually not taken into account but that may contribute to the virus spreading. The main problem that we have detected is that there is currently no training set for this task. It is for this reason that we have requested the participation of citizens by taking different selfies through an app and placing the mask in different positions. Thus, we have been able to solve this problem. The results show that the accuracy achieved with transfer learning slightly improves the accuracy achieved with convolutional neural networks. Finally, we have also developed an Android-app demo that validates the proposal in real scenarios.

Software Defined networks (SDNs) paradigm tries to improve the network performance, facilitating the network management and the scalability basing on open-source software and adding a new entity called controller that manages the entire network. One of the goals of the controller is taking decisions in regards to routing instead of distributing it among the network nodes, as usual. However, this field inside SDN needs more work because it is not clearly defined how the traditional routing protocols will work over a SDN. Thus, in this paper, we analyze how a dynamic routing protocol as Open Shortest Path First (OSPF) works in a SDN. The study analyzes the stability of network through parameters as convergence time and round trip time (RTT) and the quality of service (QoS) when a video is streamed between end devices. The results have been compared with a traditional network in order to evaluate the similarity in terms of stability and performance. Results show that, despite the proposal uses an OSPF implementation that does not have a performance as good as the traditional solution in terms of convergence time, with the SDN proposed we get better performance in terms of Quality of Service.