Pablo López-Matencio

Ambient Intelligence Systems for Personalized Sport Training

Several research programs are tackling the use of Wireless Sensor Networks (WSN) at specific fields, such as e-Health, e-Inclusion or e-Sport. This is the case of the project “Ambient Intelligence Systems Support for Athletes with Specific Profiles”, which intends to assist athletes in their training. In this paper, the main developments and outcomes from this project are described. The architecture of the system comprises a WSN deployed in the training area which provides communication with athletes’ mobile equipments, performs location tasks, and harvests environmental data (wind speed, temperature, etc.). Athletes are equipped with a monitoring unit which obtains data from their training (pulse, speed, etc.). Besides, a decision engine combines these real-time data together with static information about the training field, and from the athlete, to direct athletes’ training to fulfill some specific goal. A prototype is presented in this work for a cross country running scenario, where the objective is to maintain the heart rate (HR) of the runner in a target range. For each track, the environmental conditions (temperature of the next track), the current athlete condition (HR), and the intrinsic difficulty of the track (slopes) influence the performance of the athlete. The decision engine, implemented by means of (m, s)-splines interpolation, estimates the future HR and selects the best track in each fork of the circuit. This method achieves a success ratio in the order of 80%. Indeed, results demonstrate that if environmental information is not take into account to derive training orders, the success ratio is reduced notably.

On the optimal random deployment of wireless sensor networks in non-homogeneous scenarios

Random scattering of WSNs is needed in many practical cases due to the large scale of the network required or to the inaccessibility of the terrain. However several important features of deployments of this type have been neglected due to their analytical complexity. Node placement must guarantee correct operation: if nodes are too separated many would be isolated and data would not reach the sinks. Besides, if the nodes are too close, the area covered would be small and little information would be retrieved. Moreover, the target area cannot be considered homogeneous since in real-life situations some zones are more important than others. This paper addresses these constraints by proposing and solving an optimization problem which maximizes network sensing coverage. In our model several clusters of nodes are spread over the target area following Gaussian random distributions, and the goal is to decide the optimal launch point and the dispersion for each cluster. This corresponds to real situations where clusters are dropped in an airborne launch in which dispersion is controlled by the release altitude. The problem is solved by considering iterative steps where single cluster deployments are addressed. Several tests validate our approach and indicate that our method outperforms previous approaches, especially in deployments with a low number of nodes, which are more challenging from the optimization perspective.

Ambient intelligence assistant for running sports based on k-NN classifiers

Outdoor sport practitioners can improve greatly their results if they train at the right intensity. Nevertheless, in common training systems the athletes performance is used for evaluation at the end of the exercises, and the sensed data is incomplete because only human biometrics are analyzed. These systems do not consider environmental conditions, which may have direct influence on athletes performance during training. In this paper, we present the system architecture and implementation of an ambient intelligence assistant for runners. Our system is composed of a Wireless Sensor Network (WSN) deployed over a cross-country running circuit, and by mobile elements carried by the users, which monitor their heart rate (HR). The goal is to select, for a given user, suitable tracks where the heart rate will be in the selected HR range. The decision-taking process is based on k-NN classification and has achieved a success classification ratio of 70%.

Acoustic Sensor Planning for Gunshot Location in National Parks: A Pareto Front Approach

In this paper, we propose a solution for gunshot location in national parks. In Spain there are agencies such as SEPRONA that fight against poaching with considerable success. The DiANa project, which is endorsed by Cabaneros National Park and the SEPRONA service, proposes a system to automatically detect and locate gunshots. This work presents its technical aspects related to network design and planning. The system consists of a network of acoustic sensors that locate gunshots by hyperbolic multi-lateration estimation. The differences in sound time arrivals allow the computation of a low error estimator of gunshot location. The accuracy of this method depends on tight sensor clock synchronization, which an ad-hoc time synchronization protocol provides. On the other hand, since the areas under surveillance are wide, and electric power is scarce, it is necessary to maximize detection coverage and minimize system cost at the same time. Therefore, sensor network planning has two targets, i.e., coverage and cost. We model planning as an unconstrained problem with two objective functions. We determine a set of candidate solutions of interest by combining a derivative-free descent method we have recently proposed with a Pareto front approach. The results are clearly superior to random seeding in a realistic simulation scenario.

SAETA: A Smart Coaching Assistant for Professional Volleyball Training

This paper introduces a smart assistant for professional volleyball training based on machine-learning techniques (SAETA). SAETA addresses two main aspects of elite sports coaching: 1) technical-tactical effort control, which aims at controlling exercise effort and fatigue levels and 2) exercise quality training, which complements the former by analyzing the execution of player movements. SAETA relies on a sensing infrastructure that monitors both players and their environment, and produces real-time data that is analyzed by different modules of a decision engine. Technical-tactical effort control is based on a dynamic programming model, which selects the best activity and rest durations in interval training, with the goal of maximizing effort while preventing fatigue. Exercise quality control consists of two stages. In the first stage, movements are detected by means of a k-nearest neighbors classifier and in the second stage, movement intensity is classified according to recent statistical data from the player being analyzed. These analyses are reported to coaches and players in real-time. SAETA has been developed in close collaboration with the Universidad Católica San Antonio de Murcia volleyball team, which competes in the Spanish womens premier league. Data gathered during training sessions has provided a knowledge base for the algorithms developed, and has been used for the validation of results.

A Dynamic Programming Approach for Ambient Intelligence Platforms in Running Sports Based on Markov Decision Processes

Outdoor sport practitioners can improve greatly their performance if they train at the right intensity. Nevertheless, in common training systems, performance is only evaluated at the end of the training session, and sensed data are incomplete because only human biometrics are analyzed. These systems do not consider environmental conditions, which may influence athletes’ performance directly during instruction. In this paper, we introduce a decision making method for a multi-step training scenario based on dynamic program optimization and formulated as a Markov Decision Process, which allow athletes to complete heterogeneous training programs with several levels of exercise intensity. This methodology is applied in a pilot experiment of cross-country running. Environment and athletes are monitored by means of a wireless sensor network deployed over the running circuit, and by mobile elements carried by the users themselves, which monitor their heart rate (HR). The goal is to select, for a given user, a running track that optimizes heart rate according to a predefined training program. Results show that the proposal is of practical interest. It achieves a notable success in heart rate control over non-optimal track selection policies. The importance of environmental data is shown as well, since heart rate control improves when those data are taken into account.

ANT: Agent Stigmergy-Based IoT-Network for Enhanced Tourist Mobility

In this work, we propose ANT, a network of agents which exchange information in a stigmergy-based fashion. In ANT, each system’s actor distributes pheromones as a way of indicating places’ attractiveness, as well as for building a proper routing path to those sites. The goal of ANT is to improve the chances of discovering points of interest, as well as to reduce the time required for doing so. We have applied ANT to a tourist mobility scenario, where both people and things (events, restaurants, performances, etc.) participate. ANT has achieved notable success in this example case. We find that probability of discovering temporary events and dates improves by more than 35%, while the mean time employed to determine static point decreases by more than a third. We also introduce a mobile-based architecture which performs ANT tasks efficiently and easily for the user.

An ACOR-Based Multi-Objective WSN Deployment Example for Lunar Surveying

Wireless sensor networks (WSNs) can gather in situ real data measurements and work unattended for long periods, even in remote, rough places. A critical aspect of WSN design is node placement, as this determines sensing capacities, network connectivity, network lifetime and, in short, the whole operational capabilities of the WSN. This paper proposes and studies a new node placement algorithm that focus on these aspects. As a motivating example, we consider a network designed to describe the distribution of helium-3 (3He), a potential enabling element for fusion reactors, on the Moon. 3He is abundant on the Moon’s surface, and knowledge of its distribution is essential for future harvesting purposes. Previous data are inconclusive, and there is general agreement that on-site measurements, obtained over a long time period, are necessary to better understand the mechanisms involved in the distribution of this element on the Moon. Although a mission of this type is extremely complex, it allows us to illustrate the main challenges involved in a multi-objective WSN placement problem, i.e., selection of optimal observation sites and maximization of the lifetime of the network. To tackle optimization, we use a recent adaptation of the ant colony optimization (ACOR) metaheuristic, extended to continuous domains. Solutions are provided in the form of a Pareto frontier that shows the optimal equilibria. Moreover, we compared our scheme with the four-directional placement (FDP) heuristic, which was outperformed in all cases.

Evaluation of Team-Sport Training Effort Control Systems

This work studies different analytical systems to evaluate and control effort in team-sport training. They analyze real-time training data obtained by means of biometric belts and provide instructions to direct athletes’ training. The decision techniques estimate the ratios of each effort regime, based on three different methodologies: (i) best-fit polynomial approximations, (ii) Kalman filters and (iii) sliding-window distribution estimation. The goal is to predict the future effort regimes and to provide suitable training orders to control that effort. The complete system results in a virtual coach, operating in real time and automatically. This methodology has been piloted in an experiment with the UCAM Volleyball Murcia team, top of the Spanish national women’s volleyball league. Data obtained during training sessions have provided a knowledge base for the algorithms developed and allowed us to validate results.