Wireless Sensor Networks (WSNs) are being deployed in very diverse application scenarios, including rural and forest environments. In these particular contexts, specimen protection and conservation is a challenge, especially in natural reserves, dangerous locations or hot spots of these reserves (i.e., roads, railways, and other civil infrastructures). This paper proposes and studies a WSN based system for generic target (animal) tracking in the surrounding area of wildlife passages built to establish safe ways for animals to cross transportation infrastructures. In addition, it allows target identification through the use of video sensors connected to strategically deployed nodes. This deployment is designed on the basis of the IEEE 802.15.4 standard, but it increases the lifetime of the nodes through an appropriate scheduling. The system has been evaluated for the particular scenario of wildlife monitoring in passages across roads. For this purpose, different schemes have been simulated in order to find the most appropriate network operational parameters. Moreover, a novel prototype, provided with motion detector sensors, has also been developed and its design feasibility demonstrated. Original software modules providing new functionalities have been implemented and included in this prototype. Finally, main performance evaluation results of the whole system are presented and discussed in depth.

Indoor navigation is a challenging task for visually impaired people. Although there are guidance systems available for such purposes, they have some drawbacks that hamper their direct application in real-life situations. These systems are either too complex, inaccurate, or require very special conditions (i.e., rare in everyday life) to operate. In this regard, Ultra-Wideband (UWB) technology has been shown to be effective for indoor positioning, providing a high level of accuracy and low installation complexity. This paper presents SUGAR, an indoor navigation system for visually impaired people which uses UWB for positioning, a spatial database of the environment for pathfinding through the application of the A* algorithm, and a guidance module. The interaction with the user takes place using acoustic signals and voice commands played through headphones. The suitability of the system for indoor navigation has been verified by means of a functional and usable prototype through a field test with a blind person. In addition, other tests have been conducted in order to show the accuracy of different relevant parts of the system.

In order to perform sensing tasks, most current Intelligent Transportation Systems (ITS) rely on expensive sensors, which offer only limited functionality. A more recent trend consists of using Wireless Sensor Networks (WSN) for such purpose, which reduces the required investment and enables the development of new collaborative and intelligent applications that further contribute to improve both driving safety and traffic efficiency. This paper surveys the application of WSNs to such ITS scenarios, tackling the main issues that may arise when developing these systems. The paper is divided into sections which address different matters including vehicle detection and classification as well as the selection of appropriate communication protocols, network architecture, topology and some important design parameters. In addition, in line with the multiplicity of different technologies that take part in ITS, it does not consider WSNs just as stand-alone systems, but also as key components of heterogeneous systems cooperating along with other technologies employed in vehicular scenarios.

Network slicing is a key feature of 5G and beyond networks, allowing the deployment of separate logical networks (network slices), sharing a common underlying physical infrastructure, and characterized by distinct descriptors and behaviors. The dynamic allocation of physical network resources among coexisting slices should address a challenging trade-off: to use resources efficiently while assigning each slice sufficient resources to meet its service level agreement (SLA). We consider the allocation of time-frequency resources from a new perspective: to design a control algorithm capable of learning over the operating network, while keeping the SLA violation rate under an acceptable level during the learning process. For this purpose, traditional model-free reinforcement learning (RL) methods present several drawbacks: low sample efficiency, extensive exploration of the policy space, and inability to discriminate between conflicting objectives, causing inefficient use of the resources and/or frequent SLA violations during the learning process. To overcome these limitations, we propose a model-based RL approach built upon a novel modeling strategy that comprises a kernel-based classifier and a self-assessment mechanism. In numerical experiments, our proposal, referred to as kernel-based RL, clearly outperforms state-of-the-art RL algorithms in terms of SLA fulfillment, resource efficiency, and computational overhead.

In this paper, an augmented reality mirror application using vision-based human pose detection based on vision-based pose detection called ExerCam is presented. ExerCam does not need any special controllers or sensors for its operation, as it works with a simple RGB camera (webcam type), which makes the application totally accessible and low cost. This application also has a system for managing patients, tasks and games via the web, with which a therapist can manage their patients in a ubiquitous and totally remote way. As a final conclusion of the article, it can be inferred that the application developed is viable as a telerehabilitation tool, as it has the resource of a task mode for the calculation of the range of motion (ROM) and, on the other hand, a game mode to encourage patients to improve their performance during the therapy, with positive results obtained in this aspect.