No abstract

No abstract

Smart cities provide new application based on Internet of Things (IoT) technology. Moreover, Software Defined Networks (SDN) offer the possibility of controlling the network based on applications requirements. One of the main problems that arise when an emergency happens is minimizing the delay time in emergency resource forwarding so as to reduce both human and material damages. In this paper, a new control system based on the integration of SDN and IoT in Smart City environments is proposed. This control system actuates when an emergency happens and modifies dynamically the routes of normal and emergency urban traffic in order to reduce the time that the emergency resources need to get to the emergency area. The architecture is based on a set of IoT networks composed by traffic lights, traffic cameras and an algorithm. The algorithm controls the request of resources and the modification of routes in order to ease the movement of emergency service units. Afterwards, the proposal is tested by emulating a Smart City as a SDNutilizing Mininet. The experiments show that the delay of the emergency traffic improves in a 33% when the algorithm is running. Moreover, the energy consumed by the IoT nodes is modeled and the obtained results display that it increases linearly with the number of nodes, therefore, the proposal is scalable.

No abstract

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 work, 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 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 (SDN) have become a new way to make dynamic topologies. They have great potential in both the creation and development of new network protocols and the inclusion of distributed artificial intelligence in the network. There are few emulators, like Mininet, that allow emulating a SDN in a single personal computer, but there is lack of works showing its performance and how it performs compared with real cases. This paper shows a performance comparison between Mininet and a real network when multimedia streams are being delivered. We are going to compare them in terms of consumed bandwidth (throughput), delay and jitter. Our study shows that there are some important differences when these parameters are compared. We hope that this research will be the basis to show the difference with real deployments when Mininet is used.Keywords: Multimedia delivery; Multimedia streaming; Software Defined Networks (SDNs); Mininet.www.macrothink.org/npa 37 Network Protocols and Algorithms ISSN 1943-3581 2015 IntroductionDue to the substantial improvement in terms of hardware and software for computer networks and also the number of network devices available around the world, the interconnections of devices as well as the network complexity have increased. This fact has also enhanced the way we currently process the information transmitted through the network. Over the past 30 years, the Internet Engineering Task Force (IETF) has developed and built around 5500 Request for Comments (RFC) [1]. Nowadays, Internet and other networks are able to offer huge amount of functionalities suited to the requirements of users.In general, network devices perform two main functions, i.e., the transport function and the control function. On the one hand, the transport function (data plane) that is in charge of sending data through the routes previously calculated. This function is normally performed by specialized circuits known as Application Specific Integrated Circuits (ASICs). The control function (control plane) manages the transport operation thanks to the exchanged information between network devices and the calculation of optimal routes. This allows each device to independently treat the traffic. Network administrators have available few resources to manage and increase the efficiency of the data flows.A professional of networks often finds a big challenge the fact of configuring a network and installing the needed network elements to work properly. Due to the services and the features required by the applications currently require, it is possible to increase the network efficiency if we try to manage jointly the entire network. In this way, there appears the need of developing a new technology to reduce the costs and increase the efficiency by automating policy-based flows.Software-Defined networking (SDN) is a new approach for designing, building, and managing networks that separates the network's control and forwarding planes of a better network optimization [2]. The SDN architecture decouples the netw...

No abstract