Beyond certain depth there is no light, supposing the main obstacle in the use of optical systems beneath the water. Therefore, the underwater vision system developed is composed of a set of underwater lights which allow the system to work properly and the cameras. These are integrated with the navigation system through the Robot Operating System (ROS) framework, which handles the acquisition and processing of information to be used as support for the navigation and which is also essential for its use in reconnaissance missions. Full article

In this paper, we address the problem of how to bootstrap a cognitive architecture to opportunistically start learning skills in domains where multiple skills can be learned at the same time. To this end, taking inspiration from a series of computational models of the use of motivations in infants, we propose an approach that leverages two types of cognitive motivations: exploratory and proficiency based, the latter modulated by the concept of interestingness as an implementation of attentional mechanisms. This approach is tested in an illustrative experiment with a real robot. Full article

This work explores the potential of the use of interactive and immersive technologies to create impactful experiences that generate emotions, contributing to the process of activation or somatic excitation that triggers links that strengthen cognitive functions. It is intended to demonstrate to what extent the use of immersive environments, by generating a strong emotional load, contribute in a more effective way to the empathy construct about Schizophrenia. Full article

Nowadays, the Internet of things (IoT) network, as system of interrelated computing devices with the ability to transfer data over a network, is present in many scenarios of everyday life. Understanding how traffic behaves can be done more easily if the real environment is replicated to a virtualized environment. In this paper, we propose a methodology to develop a systematic approach to dataset analysis for detecting traffic anomalies in an IoT network. The reader will become familiar with the specific techniques and tools that are used. The methodology will have five stages: definition of the scenario, injection of anomalous packages, dataset analysis, implementation of classification algorithms for anomaly detection and conclusions. Full article

In order to characterize the spatial and temporal variability of the rainfall, we have developed an observation system to monitor the precipitation over the metropolitan area of A Coruña. The observation system (called TREBOADA) consists of a network of rain gauges, comprising gauges operated by the regional weather agency and rain gauges deployed specifically for TREBOADA. The latter ones are built using low cost technology, which significantly reduces the cost of each gauge. Data from the rain gauges are combined with rain observations from the meteorological radar to produce high resolution rain products. Full article

At present, the term Internet of Things (IoT) is a key aspect in determining the sustainability, safety, quality and efficiency of the majority of the most important business sectors in society. The capacity to track processes that are undertaken, facilitates the recording of data of the professionals and clients involved. Identification technologies such as RFID (Radio-Frequency Identification) when integrated into sectorial activities, can generate multiple benefits. Full article

This work focus on the study of solutions that using video 360 and virtual reality that allow children’s and older people that are away of their family environments for various reasons to be able to feel they are participating at family or school events. The solutions proposed should deliver a strong sense of presence to the users and the interface must be friendly. The validation will be made by user observation and inquiries. Full article

In this paper we explain the structure and development of a trajectory management system on board a UAV capable to achieve complex trajectories and versatile to adapt disturbances during flight. This system is built in Python and runs in a companion computer on board the UAV while maintains communication with a ground station over a radio link. Full article

The most widespread analog video encoding systems in the literature are based on the use of the 2D and 3D DCT. These systems use both transformations indistinctly without assessing their suitability. In this paper, we present procedures to compress video using 2D and 3D-DCT and we evaluate the video quality for different compression levels. Full article

This pilot study was carried out with a sample of six older persons in a residential center in A Coruña. It is a “quasi-experimental” study, directed to assess the effect of an intervention on a given population, performing “pre” and “post” intervention measurements, but without comparison with a control group. The multifactorial intervention had a duration of 3 months, which includes the use of technological devices, like a wristband of physical activity and sleep. Full article

This study aimed to examine the feasibility of promoting reminiscences with people with dementia, using 360° videos presented with virtual reality headsets. Four individual sessions were conducted with nine people with dementia. Average duration of the exposure was approximately ten minutes. The experience appeared to be pleasant for most of the participants (with the exception of one of the participants who reported visual limitations). Most participants shared positive memories while viewing the recordings. None of the participants experienced any significant increase in symptoms associated with nausea and disorientation. Full article

The current study sought to determine the association of sleep with HRQOL and physical function among older nursing home residents. Participants were 37 older adults attending or residing in a semi-urban nursing-home facility in Galicia, Spain (70.3% cognitively normal, 29.7% cognitively impaired, aged 84.1±8.0, 81.1% women) who completed the Pittsburgh Sleep Quality Index (PSQI), the 5-level EuroQol-5D, a measure of HRQOL, and the International Classification of Functioning, Disability and Health (ICF) Core Sets for Sleep, a measure of physical functional. After adjustment for age, poor (PSQI score ≤ 14) and/or worse sleep quality (continuous PSQI score) was associated with several indices of lower HRQOL, including greater immobility (b = 0.19, p = 0.012) difficulty completing self-care (b = 0.23, p < 0.001) and daily activities (b = 0.18, p = 0.004), more severe anxiety/depression (b = 0.10, p = 0.042), and a lower overall health index (b = 0.06, p = 0.001). Further, poor/worse sleep quality was associated with several indices of functional impairment, including greater difficulty maintaining body position (b = 0.32, p = 0.004), walking (b = 0.17, p = 0.001), and moving around (b = 0.45, p = 0.009). Full article

The research intends to gather on a IoT Platform, a set of data existing in the ecosystem - in the universe of things, from sources and types of diverse origin coming from messages, devices, sensors, etc. These structured and related data allow us to generate indicators of anxiety about which we intend to act, either preventively or proactively, through information for an individual's awareness and self-regulation. Full article

A new sparse semiparametric functional model is proposed, which tries to incorporate the influence of two functional variables in a scalar response in a quite simple and interpretable way. One of the functional variables is included trough a single-index structure and the other one linearly, but trough the high-dimensional vector of its discretized observations. For this model, a new algorithm for impact point selection in the linear part and for the model estimation is proposed. This procedure is based on the functional origin of the linear covariates. Some asymptotic results will ensure the good performance of the method. The computational efficiency of the algorithm, without loss of predictive power, will be showed trough a simulation study and a real data application, by comparing its results with those obtained trough the standard PLS method. Full article

The prediction of metabolic activities in silico form is crucial to be able to address all research possibilities without exceeding the experimental costs. In particular, for cancer research, the prediction of certain activities can be of great help in the discovery of different treatments. In this work it has been proposed to predict, through Machine Learning, the anti-angiogenic activity of peptides is currently being used in cancer treatment and is giving hopeful results. From a list of peptide sequences, three types of molecular descriptors were obtained (AAC, DC and TC) that offered the possibility of training different ML algorithms. After a Feature Selection process, different models were obtained with a predictive value that surpassed the current state of the art. These results shown that ML is useful for the classification and prediction of the activity of new peptides, making experimental screening cheaper and faster. Full article

This paper presents a complete system for the automatic identification of pathological Diabetic Macular Edema (DME) cases using Optical Coherence Tomography (OCT) images as source of information. To do so, the system extracts a set of deep features using a transfer learning-based approach from different fully-connected layers and different pre-trained Convolutional Neural Network (CNN) models. Next, the most relevant subset of deep features is identified using representative feature selection methods. Finally, a machine learning strategy is applied to train and test the potential of the identified deep features in the pathological classification process. Satisfactory results were obtained, demonstrating the suitability of the presented system to filter those pathological DME cases, helping the specialist to optimize their diagnostic procedures. Full article

Photoresponse Non-Uniformity (PRNU) is becoming particularly relevant within digital media forensics, as a means to effectively determine the source camera of a given image. Most of the practical applications in digital media forensics involve dealing with highly sensitive data whose content must be protected. In this context, several secure frameworks have been proposed to perform PRNU-based camera attribution while preserving the privacy of both the testing images and the PRNU fingerprint. The two most recent and relevant ones, independently proposed in 2018, are (a) Mohanty et al.’s, who combine the use of a trusted environment (ARM TrustZone) to compute the PRNU fingerprint, with the Boneh-Goh-Nissim (BGN) cryptosystem to perform the matching, and (b) Pedrouzo-Ulloa et al.’s, who propose a more flexible solution which can be fully implemented on a general purpose architecture and does not require access to a trusted environment. In this work, we revisit the existing frameworks and propose a general formulation for PRNU matching based on lattice cryptosystems which improves on the BGN-based solution in terms of efficiency, flexibility and privacy. Full article

Fertigation is a widely used crop growing method that consists on the precise injection of a nutrient solution that commonly consists on a mixture of three basis components (nitrogen, phosphorus and potassium) diluted in water. This nutritive suspension is delivered to the plants with a frequency and relative basis contents that depends on the plant’s type, its vegetative state and actual environmental conditions. This production process is becoming increasingly popular due to several advantages over more traditional approaches such as more control on the plant fertilisers and an increasing reduction of irrigation water. This is achieved by an increase complexity on the crop growing process management which requires a technological layer responsible for mixing the nutrients and monitoring the local environmental conditions. Despite this technical component, the short and long term management decisions depend almost exclusively on the grower’s experience and intuition. This type of human-on-the-loop control can lead to a suboptimal use of resources wish can translate into reduction of economic profit and an can lead to waste of water and fertilisers. In this context, decision support mechanisms based on artificial intelligence and machine learning algorithms can be of extreme relevance in order to steer the grower decisions and increase the overall production process efficiency. The performance of those types of approaches strongly relies on the availability of data which can be both local and global. This work deals with the architecture of a sensor network which will be responsible to gather local information on the actual growing conditions. Those conditions are usually not homogeneous within the complete production plant and must be taken into consideration. In particular, the current architecture vision will consider those clusters, where the environmental conditions are similar, as cyberphysical devices. These devices will consist on vegetative production area, sensor networks and local control of irrigation state. Full article

With the cheapening of mass sequencing techniques and the rise of computer technologies, capable of analyzing a huge amount of data, it is necessary nowadays that both branches mutually benefit. Transcriptomics, in this case, is a branch of biology focused on the study of mRNA molecules, among others. The quantification of these molecules gives us information about the expression that a gene is having at a given moment. Having information on the expression of the approximately 20,000 genes harbored by human beings is a really useful source of information for the study of certain conditions and/or pathologies. In this work, patient expression -omic data data have been used to offer a new analysis methodology through Machine Learning. The results of this methodology were compared with a conventional methodology to observe how they differed and how they resembled each other. These techniques, therefore, offer a new mechanism for the search of genetic signatures involved, in this case, with cancer. Full article

PRIN is a neural based recommendation method that allows the incorporation of item prior information into the recommendation process. In this work we study how the system behaves in terms of novelty and diversity under different configurations of item prior probability estimations. Our results show the versatility of the framework and how its behavior can be adapted to the desired properties, whether accuracy is preferred or diversity and novelty are the desired properties, or how a balance can be achieved with the proper selection of prior estimations. Full article

We introduce a hybrid approach that can track an individual football player in a video sequence. This solution achieves a good balance between speed and accuracy, combining traditional object tracking techniques with Deep Neural Networks (DNN). While traditional techniques lack accuracy, the main shortcoming of DNN is performance. Both types of techniques complement to each other to provide an accurate and fast object tracking approach that does not require human intervention. The accuracy of our solution has been validated using the SoccerNet Dataset against hand annotated video sequences. For the tracking of 4 different players of 2 different teams our approach has achieved an Area Under Curve (AUC) of 0.66, in terms of accuracy, and a frame rate of 91.75 FPS, in terms of performance, running on a Nvidia GTX 1080Ti GPU. Full article

When it comes to the writing of a new logic program or theory, it is of great importance to obtain a concise and minimal representation, for simplicity and ease of interpretation reasons. There are already a few methods and many tools, such as Karnaugh Maps or the Quine-McCluskey method, as well as their numerous software implementations, that solve this minimization problem in Boolean logic. This is not the case for Here-and-There logic, also called three-valued logic. Even though there are theoretical minimization methods for logic theories and programs, there aren’t any published tools that are able to obtain a minimal equivalent logic program. In this paper we present the first version of a tool called that is able to efficiently obtain minimal and equivalent representations for any logic program in Here-and-There. The described tool uses an hybrid method both leveraging a modified version of the Quine-McCluskey algorithm and Answer Set Programming techniques to minimize fairly complex logic programs in a reduced time. Full article

In this paper, we discuss how SDN can contribute to enhance future cellular networks. We first present SDN and describe its characteristics. Then, we explore how SDN can be used to improve current cellular networks, analyzing the advantages and disadvantages, while highlighting some use cases. Finally, we conclude this work exposing some challenges that still require further research to take full advantage of SDN in cellular networks. Full article

Spectral precoding is a popular approach to reduce out-of-band radiation (OBR) in multicarrier systems in order to avoid adjacent channel interference. However, it introduces distortion in the data, appropriate decoding is required at the receiver side. Thus, trading off between implementation complexity, OBR reduction and error rate is important. We present a novel linear precoder design with flexibility to trade off OBR reduction, precoding/decoding complexity, and error rate at the receiver. Moreover, the constraint can be imposed on each subcarrier individually to provide more flexibility. The precoding matrices have low rank, which translates into significant computational savings. In this way, the requirements of different systems can be satisfied with varying complexity levels. Full article

Gene regulatory networks are graphical representations of molecular regulators that interact with each other and with other substances in the cell to govern the gene expression. There are different computational approaches for the reverse engineering of these networks. Most of them require all gene-gene evaluations using different mathematical methods such as Pearson/Spearman correlation, Mutual Information or topology patterns, among others. The Algorithm for the Reconstruction of Accurate Cellular Networks (ARACNe) is one of the most effective and widely used tools to reconstruct gene regulatory networks. However, the high computational cost of ARACNe prevents its use over large biologic datasets. In this work, we present a hybrid MPI/OpenMP parallel implementation of ARACNe to accelerate its execution on multi-core clusters, obtaining a speedup of 430.46 using as input a dataset with 41,100 genes and 108 samples and 32 nodes (each of them with 24 cores). Full article

Spatial Modulation (SM) is a candidate modulation scheme for beyond 5G communications systems due to its reduced hardware complexity and good trade-off between energy and spectral efficiency. This paper proposes two Machine Learning based solutions for easing the implementation of adaptive SM systems. On the one hand, a shallow neural network is shown to be an accurate and simple method for obtaining the capacity of SM. On the other hand, a deep neural network is proposed to select the coding rate in practical adaptive SM systems. Full article

Non-parametric regression with a circular response variable and a unidimensional linear regressor is a topic which was discussed in the literature. In this work, we extend the results to the case of multivariate linear explanatory variables. Nonparametric procedures to estimate the circular regression function are formulated. A simulation study is carried out to study the sample performance of the proposed estimators. Full article

Automatic detection of Alzheimer’s disease is a very active area of research. This is due to its usefulness in starting the protocol to stop the inevitable progression of this neurodegenerative disease. This paper proposes a system for the detection of the disease by means of Deep Learning techniques in magnetic resonance imaging (MRI). As a solution, a model of neuronal networks (ANN) and two sets of reference data for training are proposed. Finally, the goodness of this system is verified within the domain of the application. Full article

Nowadays, a wide variety of computer systems use authentication protocols based on several factors in order to enhance security. In this work, the viability of a second-phase authentication scheme based on users’ mouse behavior is analyzed by means of classical Artificial Intelligence techniques, such as the Support Vector Machines or Multi-Layer Perceptrons. Such methods were found to perform particularly well, demonstrating the feasibility of mouse behavior analytics as a second-phase authentication mechanism. In addition, in the current stage of the experiments, the classification techniques were found to be very stable for the extracted features. Full article

This adaptation consists of the translation from Spanish into Portuguese of the different contents offered by the ClepiTO web platform to be able to carry out a pilot test with a larger population in Portugal and thus be able to compare the results obtained among the Spanish and Portuguese population Full article

One of the most relevant issue in the prediction and classification of the aesthetic value of an image is the sample set used to train and validate the computational system. In this document the limitations found in different datasets used to classificate and predict aesthetic values are exposed, and a new dataset is proposed with images from the DPChallenge.com portal, with evaluations of three different populations. Full article

Like other disciplines, Astronomy faces the era of Big Data, where the analyses and discovery of specific objects is a significant and non-trivial matter. The APOGEE survey and Gaia mission are good examples of how these kind of projects have increased the amount of data to be managed. In this context, we have developed an algorithm to search for specific features in the APOGEE database. The main purpose is to seek spectral lines both in absorption or emission, in the whole APOGEE database, in order to find chemically-peculiar stars. We propose an algorithm which has been validated using cerium lines and we have applied it to the search for other chemical compounds. Full article

Information Retrieval is not any more exclusively about document ranking. Continuously new tasks are proposed on this and sibling fields. With this proliferation of tasks, it becomes crucial to have a cheap way of constructing test collections to evaluate the new developments. Building test collections is time and resource consuming: it requires time to obtain the documents, to define the user needs and it requires the assessors to judge a lot of documents. To reduce the latest, pooling strategies aim to decrease the assessment effort by presenting to the assessors a sample of documents in the corpus with the maximum number of relevant documents in it. In this paper, we propose the preliminary design of different techniques to easily and cheapily build high-quality test collections without the need of having participants systems. Full article

Hereby we present a methodology with the objective of detecting retinal fluid accumulations in between the retinal layers. The methodology uses a robust Densely Connected Neural Network to classify thousands of subsamples, extracted from a given Optical Coherence Tomography image. Posteriorly, using the detected regions, it satisfactorily generates a coherent and intuitive confidence map by means of a voting strategy. Full article

Most wireless devices transmit and receive at different spectrum frequency bands. This approach is no longer optimal due to increasing electromagnetic exhaustion. Besides, interference
among all present and future working services should be negligible. A full-duplex scheme using the same band for simultaneous uplink and downlink is a huge step towards solving this issue. However, sharing the same frequency band involves a large interference of transmitted signal over received signal. To fix this problem, we propose the usage of a hybrid multistage cancellation system,
consisting of an analog cancellation setup at RF frequencies and a baseband digital cancellation stage. Full article

The methodology presented in this paper aims to detect pathological regions affected by one or more of the three clinically defined types of Diabetic Macular Edema (DME). Using representative samples extracted from Optical Coherence Tomography (OCT) images, three representative classifiers are trained to analyze new input images and create an intuitive visualization of the detection results. The trained models provided a satisfactory performance for all three defined types of DME, and the visual feedback can effectively assists clinical experts in the diagnosis of this representative and extended disease. Full article

Making natural language processing technologies available for low-resource languages is an important goal to improve the access to technology in their communities of speakers. In this paper, we provide the first annotated corpora for polarity classification for Uzbek language. Our methodology considers collecting a medium-size manually annotated dataset and a larger-size dataset automatically translated from existing resources. Then, we use these datasets to train sentiment analysis models on the Uzbek language, using both traditional machine learning techniques and recent deep learning models. Full article

This paper explains the design and construction of a platform that implements the ESP32 embedded system and connects it to a telephone asterisk plant, to exchange data on both sides, commands sent from a telephone to the esp32 and make calls from an order of sending from a digital input of esp32. It is a low-cost device that can be implemented through the use of Wi-Fi, and as a use in the industry, it has a role in analogue communication in buildings, for example. Full article

Communication network data has been growing in the last decades and with the generalisation of the Internet of Things (IoT) its growth has increased. The number of attacks to this kind of infrastructures have also increased due to the relevance they are gaining. As a result, it is vital to guarantee an adequate level of security and to detect threats as soon as possible. Classical methods emphasise in detection but not taking into account the number of records needed to successfully identify an attack. To achieve this, time-aware techniques both for detection and measure may be used. In this work, well-known machine learning methods will be explored to detect attacks based on public datasets. In order to obtain the performance, classic metrics will be used but also the number of elements processed will be taken into account in order to determine a time-aware performance of the method. Full article

A comparison of two open source electroencephalography devices designed to acquire signals associated to the brain activity is presented in this work. The experiments are developed considering the task of determining the user eye state i.e., open eyes or closed eyes, applying an algorithm based on computing the sliding Fourier Transform of the captured signals. Full article

We propose a sequence of activities to be programmed to improve the learning of Science, Technology, Engineering and Mathematics in Secondary Education. This proposal consists on generate and transform images and figures programming in Octave. This enables the students to use basic and iterative instructions to construct a complex program, understand and structure problems, logic reformulation of problems, design of systematic processes for the resolution, generalization and comparison of solutions. Initial analyses of the implementation of the activities will be presented. Full article

There exist many different methods to choose the bandwidth in kernel regression. If, however, the target is regression based prediction for samples or populations with potentially different distributions, then the existing methods can easily be suboptimal. This situation occurs for example in impact evaluation, data matching, or scenario simulations. We propose a bootstrap method to select a global bandwidth for nonparametric out-of-sample prediction. The asymptotic theory is developed, and simulation studies show the successful operation of our method. The method is used to predict nonparametrically the salary of Spanish women if they were paid along the same wage equation as men, given their own characteristics. Full article

In this work we design a novel and efficient quasi-regression Monte Carlo algorithm in order to approximate the solution of discrete time backward stochastic differential equations (BSDEs), and we analyze the convergence of the proposed method. With the challenge of tackling problems in high dimensions we propose suitable projections of the solution and efficient parallelizations of the algorithm taking advantage of powerful many core processors such as graphics processing units (GPUs). Full article

This work explores the use of paired and unpaired data for training deep neural networks in the multimodal reconstruction of retinal images. Particularly, we focus on the reconstruction of fluorescein angiography from retinography, which are two complementary representations of the eye fundus. The performed experiments allow to compare the paired and unpaired alternatives. Full article

The artificial neural networks used in a multitude of fields are achieving good results. However, these systems are inspired in the vision of classical neuroscience where neurons are the only elements that process information in the brain. Advances in neuroscience have shown that there is a type of glial cell called astrocytes that collaborate with neurons to process information. In this work, a connectionist system formed by neurons and artificial astrocytes is presented. The astrocytes can have different configurations to achieve a biologically more realistic behaviour. This work indicates that the use of different artificial astrocytes behaviours is beneficial. Full article

In a society in which information is a cornerstone the exploding of data is crucial. Thinking of the Internet of Things, we need systems able to learn from massive data and, at the same time, being inexpensive and of reduced size. Moreover, they should operate in a distributed manner making use of edge computing capabilities while preserving local data privacy. The aim of this work is to provide a solution offering all these features by implementing the algorithm LANN-DSVD over a cluster of Raspberry Pi devices. In this system, every node first learns locally a one-layer neural network. Later on, they share the weights of these local networks to combine them into a global net that is finally used at every node. Results demonstrate the benefits of the proposed system. Full article

It is a fact that, non-destructive measurement technologies have gain a lot of attention over the years. Among those technologies, NIR technology is the one which allows the analysis of electromagnetic spectrum looking for carbon-link interactions. This technology analyzes the electromagnetic spectrum in the band between 700 nm and 2500 nm, a band very close to the visible spectrum. Traditionally, the devices used to measure are utterly expensive and enormously bulky. That is why this project was focused on a portable spectrophotometer to make measures. This device is smaller and cheaper than the common spectrophotometer, although at the cost of a lower resolution. In this work, that device in combination with the use of machine learning was used to detect if a beer contains alcohol or it can be labeled as non-alcoholic drink. Full article

Dependency parsing has been built upon the idea of using parsing methods based on shift-reduce or graph-based algorithms in order to identify binary dependency relations between the words in a sentence. In this study we adopt a radically different approach and cast full dependency parsing as a pure sequence tagging task. In particular, we apply a linearization function to the tree that results in an output label for each token that conveys information about the word’s dependency relations. We then follow a supervised strategy and train a bidirectional long short-term memory network to learn to predict such linearized trees. Contrary to the previous studies attempting this, the results show that this approach not only leads to accurate but also fast dependency parsing. Furthermore, we obtain even faster and more accurate parsers by recasting the problem as multitask learning, with a twofold objective: to reduce the output vocabulary and also to exploit hidden patterns coming from a second parsing paradigm (constituent grammars) when used as an auxiliary task. Full article