Search

The use of Digital Twins in the industry has become a growing trend in recent years, allowing to improve the lifecycle of any process by taking advantage of the relationship between the physical and the virtual world. Existing literature formulates several challenges for building Digital Twins, as well as some proposals for overcoming them. However, in the vast majority of the cases, the architectures and technologies presented are strongly bounded to the domain where the Digital Twins are applied. This article proposes the FIWARE Ecosystem, combining its catalog of components and its Smart Data Models, as a solution for the development of any Digital Twin. We also provide a use case to showcase how to use FIWARE for building Digital Twins through a complete example of a Parking Digital Twin. We conclude that the FIWARE Ecosystem constitutes a real reference option for developing DTs in any domain.

The World Wide Web has become a common platform for interactive software development. Most web applications feature custom user interfaces used by millions of people every day. Information architecture addresses the structural design of information to build quality web applications with improved usability of content, navigation, and findability. One of the most frequently utilized information architecture methods is card sorting—an affordable, user-centered approach for eliciting and evaluating categories and navigable items. Card sorting facilitates decision-making during the development process based on users’ mental models of a given application domain. However, although the qualitative analysis of card sorts has become common practice in information architecture, the quantitative analysis of card sorting is less widely applied. The reason for this gap is that quantitative analysis often requires the use of customized techniques to extract meaningful information for decision-making. To facilitate this process and support the structuring of information, we propose a methodology for the quantitative analysis of card-sorting results in this paper. The suggested approach can be systematically applied to provide clues and support for decisions. These might significantly impact the design and, thus, the final quality of the web application. Therefore, the approach includes proper goodness values that enable comparisons among the results of the methods and techniques used and ensure the suitability of the analyses performed. Two publicly available datasets were used to demonstrate the key issues related to the interpretation of card sorting results and the overall suitability and validity of the proposed methodology, This work was partially supported by the Spanish Government [grant number RTI2018-095255-B-I00]; and the Madrid Research Council [Grant Number P2018/TCS-4314]

As innovative technologies emerge, there is a need to evolve the environments in which these technologies are used. The trend has shifted from considering technology as a support service towards making it the means for transforming all complex systems. Smart cities focus their development on the use of technology to transform every aspect of society and embrace the complexity of these transformations towards something leading to the well-being and safety of people inhabiting these cities. Occupational Health and Safety (OHS) is an essential aspect to be considered in the design of a smart city and its digital ecosystems, however, it remains unconsidered in most smart city's frameworks, despite the need for a specific space for smart OHS. This paper summarizes a 9-month process of generation of a value proposition for evolving the sector of OHS based on a value-map in whose creation several stakeholders have participated. They focused on identifying the products, the methods, the organizational structures and the technologies required to develop an updated, dynamic and robust prevention model focused on workers in smart and complex contexts, and to improve the organizations' capability to guarantee safety even in the most changing, digital and disruptive settings. To assess the relevance and validity of this value-map, a study was carried out to match the set of its elements and its specific and conceptual products discovered, considering also the definition of the past needs and future trends of the sector that a set of renowned stakeholders and key opinion leaders (with mastery in OHS from several companies and industries) have recently defined for the decade of 2020. A prospective analysis of this match is presented, revealing that there is still an existing gap to be covered in the context of smart cities design: the explicit guarantee of safety for workers. This work has been supported by the Madrid Government (Comunidad de Madrid-Spain) under the Multiannual Agreement with UC3M in the line of Excellence of University Professors (EPUC3M17), and in the context of the V PRICIT (Regional Programme of Research and Technological Innovation).

Machine learning (ML) techniques such as classifiers are used in many applications, some of which are related to safety or critical systems. In this case, correct processing is a strict requirement and thus ML algorithms (such as for classification) must be error tolerant. A naive approach to implement error tolerant classifiers is to resort to general protection techniques such as modular redundancy. However, modular redundancy incurs in large overheads in many metrics such as hardware utilization and power consumption that may not be acceptable in applications that run on embedded or battery powered systems. Another option is to exploit the algorithmic properties of the classifier to provide protection and error tolerance at a lower cost. This paper explores this approach for a widely used classifier, the k Nearest Neighbors ( k NNs), and proposes an efficient scheme to protect it against errors. The proposed technique is based on a time-based modular redundancy (TBMR) scheme. The proposed scheme exploits the intrinsic redundancy of k NNs to drastically reduce the number of re-computations needed to detect errors. This is achieved by noting that when voting among the k nearest neighbors has a large majority, an error in one of the voters cannot change the result, hence voting margin (VM). This observation has been refined and extended in the proposed VM scheme to also avoid re-computations in some cases in which the majority vote is tight. The VM scheme has been implemented and evaluated with publicly available data sets that cover a wide range of applications and settings. The results show that by exploiting the intrinsic redundancy of the classifier, the proposed scheme is able to reduce the cost compared to modular redundancy by more than 60 percent in all configurations evaluated. Pedro Reviriego and Josée Alberto Hernández would like to acknowledge the support of the TEXEO project TEC2016-80339-R funded by the Spanish Ministry of Economy and Competitivity and of the Madrid Community research project TAPIR-CM Grant no. P2018/TCS-4496.

The multidimensional classification of multivariate timeseries deals with the assignment of multiple classes to time‐ordered data described by a set of feature variables. Although this challenging task has received almost no attention in the literature, it is present in a wide variety of domains, such as medicine, finance or industry. The complexity of this problem lies in two nontrivial tasks, the learning with multivariate time series in continuous time and the simultaneous classification of multiple class variables that may show dependencies between them. These can be addressed with different strategies, but most of them may involve a difficult preprocessing of the data, high space and classification complexity or ignoring useful interclass dependencies. Additionally, no attention has been given to the development of new multidimensional classifiers of time series based on probabilistic graphical models, even though transparent models can facilitate further understanding of the domain. In this paper, a novel probabilistic graphical model is proposed, which is able to classify a discrete multivariate temporal sequence into multiple class variables while modeling their dependencies. This model extends continuous time Bayesian networks to the multidimensional classification problem, which are able to explicitly represent the behavior of time series that evolve over continuous time. Different methods for the learning of the parameters and structure of the model are presented, and numerical experiments on synthetic and real‐world data show encouraging results in terms of performance and learning time with respect to independent classifiers, the current alternative approach under the continuous time Bayesian network paradigm.

This paper presents a new class of multiple-follower bilevel problems and a heuristic approach to solving them. In this new class of problems, the followers may be nonlinear, do not share constraints or variables, and are at most weakly constrained. This allows the leader variables to be partitioned among the followers. We show that current approaches for solving multiple-follower problems are unsuitable for our new class of problems and instead we propose a novel analytics-based heuristic decomposition approach. This approach uses Monte Carlo simulation and k-medoids clustering to reduce the bilevel problem to a single level, which can then be solved using integer programming techniques. The examples presented show that our approach produces better solutions and scales up better than the other approaches in the literature. Furthermore, for large problems, we combine our approach with the use of self-organising maps in place of k-medoids clustering, which significantly reduces the clustering times. Finally, we apply our approach to a real-life cutting stock problem. Here a forest harvesting problem is reformulated as a multiple-follower bilevel problem and solved using our approach, This publication has emanated from research conducted with the financial support of Science Foundation Ireland (SFI) under Grant Number SFI/12/RC/2289

In many computing applications there is a need to compute the similarity of sets of elements. When the sets have many elements or comparison involves many sets, computing the similarity requires significant computational effort and storage capacity. As in most cases, a reasonably accurate estimate is sufficient, many algorithms for similarity estimation have been proposed during the last decades. Those algorithms compute signatures for the sets and use them to estimate similarity. However, as the number of sets that need to be compared grows, even these similarity estimation algorithms require significant memory with its associated power dissipation. This article for the first time considers the use of approximate memories for similarity estimation. A theoretical analysis and simulation results are provided; initially it is shown that similarity sketches can tolerate large bit error rates and thus, they can benefit from using approximate memories without substantially compromising the accuracy of the similarity estimate. An understanding of the effect of errors in the stored signatures on the similarity estimate is pursued. A scheme to mitigate the impact of errors is presented; the proposed scheme tolerates even larger bit error rates and does not need additional memory. For example, bit error rates of up to 10 4 have less than a 1% impact on the accuracy of the estimate when the memory is unprotected, and larger bit errors rates can be tolerated if the memory is parity protected. These findings can be used for voltage supply scaling and increasing the refresh time in SRAMs and DRAMs. Based on those initial results, an enhanced implementation is further proposed for unprotected memories that further extends the range of tolerated BERs and enables power savings of up to 61.31% for SRAMs. In conclusion, this article shows that the use of approximate memories in sketches for similarity estimation provides significant benefits with a negligible impact on accuracy. This work was supported by ACHILLES project PID2019-104207RB-I00 and Go2Edge network RED2018-102585-T funded by the Spanish Agencia Estatal de Investigación (AEI) 10.13039/501100011033 and by the Madrid Community research project TAPIR-CM under Grant P2018/TCS-4496. The research of S. Liu and F. Lombardi was supported by NSF under Grants CCF-1953961 and 1812467.

Monitoring students in Learning Management Systems (LMS) throughout the teaching– learning process has been shown to be a very effective technique for detecting students at risk. Likewise, the teaching style in the LMS conditions, the type of student behaviours on the platform and the learning outcomes. The main objective of this study was to test the effectiveness of three teaching modalities (all using Online Project-based Learning -OPBL- and Flipped Classroom experiences and differing in the use of virtual laboratories and Intelligent Personal Assistant -IPA-) on Moodle behaviour and student performance taking into account the covariate "collaborative group". Both quantitative and qualitative research methods were used. With regard to the quantitative analysis, differences were found in student behaviour in Moodle and in learning outcomes, with respect to teaching modalities that included virtual laboratories. Similarly, the qualitative study also analysed the behaviour patterns found in each collaborative group in the three teaching modalities studied. The results indicate that the collaborative group homogenises the learning outcomes, but not the behaviour pattern of each member. Future research will address the analysis of collaborative behaviour in LMSs according to different variables (motivation and metacognitive strategies in students, number of members, interactions between students and teacher in the LMS, etc.)., This study is part of the project funded by the Consejería de Educación de la Junta de Castilla y León to the recognised research group DATAHES Grant Number BU032G19., Publicación en abierto financiada por el Consorcio de Bibliotecas Universitarias de Castilla y León (BUCLE), con cargo al Programa Operativo 2014ES16RFOP009 FEDER 2014-2020 DE CASTILLA Y LEÓN, Actuación:20007-CL - Apoyo Consorcio BUCLE

It is important to count on tools to help software professionals to evaluate the software process and how it may be affected by factors related to its deployment. Simulation models are a valuable means to illustrate the behaviour of such a process since scenario generation supports the prediction of potential outcomes and the prevention of undesired scenarios which are harmful to the process and the company in charge of the project to be developed. This work explores the effectiveness of introducing system dynamics (SD) models in the software engineers' process of understanding, from a management perspective, the software process dynamics. The used SD simulation model of the software process emphasises the representation of an iterative process. The COCOMO II model drivers and their main attributes were used, providing a set of reference factors that affect the software process, the estimation of project cost and the effort required. A set of 59 junior software professionals with no previous knowledge about SD participated in a validation study. For simple predictive scenarios, there was no important improvement effect, while for more complex predictive scenarios SD helped them to guess better and provide a rationale for the expected behaviour of the software process performance. This work has beensupportedby the Madrid Government (Comunidad de Madrid‐Spain) under the Multiannual Agree-ment with UC3M in the line of Excellence of University Professors (EPUC3M17) and in the context of the V PRICIT (Regional Programme of Research and Technological Innovation)

© The Author(s) 2021., Novel tools for in silico design of RNA constructs such as riboregulators are required in order to reduce time and cost to production for the development of diagnostic and therapeutic advances. Here, we present MoiRNAiFold, a versatile and user-friendly tool for de novo synthetic RNA design. MoiRNAiFold is based on Constraint Programming and it includes novel variable types, heuristics and restart strategies for Large Neighborhood Search. Moreover, this software can handle dozens of design constraints and quality measures and improves features for RNA regulation control of gene expression, such as Translation Efficiency calculation. We demonstrate that MoiRNAiFold outperforms any previous software in benchmarking structural RNA puzzles from EteRNA. Importantly, with regard to biologically relevant RNA designs, we focus on RNA riboregulators, demonstrating that the designed RNA sequences are functional both in vitro and in vivo. Overall, we have generated a powerful tool for de novo complex RNA design that we make freely available as a web server (https://moiraibiodesign.com/design/, Gerard Minuesa leading to these results has received funding from the European Union’s Horizon 2020 Research and Innovation Programme under the Marie SklodowskaCurie grant agreement No 712949 (TECNIOspring PLUS) and from the Agency for Business and Competitiveness (ACCIO) of the Government of Catalonia. Fund- ´ ing for open access charge: European Union’s Horizon 2020 Research and Innovation Programme under the Marie Sklodowska-Curie grant agreement No 712949 (TECNIOspring PLUS) and from the Agency for Business and Competitiveness (ACCIO) of the Government of Catalonia.

The prediction of multiple numeric outputs at the same time is called multi-target regression (MTR), and it has gained attention during the last decades. This task is a challenging research topic in supervised learning because it poses additional difficulties to traditional single-target regression (STR), and many real-world problems involve the prediction of multiple targets at once. One of the most successful approaches to deal with MTR, although not the only one, consists in transforming the problem in several STR problems, whose outputs will be combined building up the MTR output. In this paper, the Rotation Forest ensemble method, previously proposed for single-label classification and single-target regression, is adapted to MTR tasks and tested with several regressors and data sets. Our proposal rotates the input space in an efficient and novel fashion, avoiding extra rotations forced by MTR problem decomposition. Four approaches for MTR are used: single-target (ST), stacked-single target (SST), Ensembles of Regressor Chains (ERC), and Multi-target Regression via Quantization (MRQ). For assessing the benefits of the proposal, a thorough experimentation with 28 MTR data sets and statistical tests are used, concluding that Rotation Forest, adapted by means of these approaches, outperforms other popular ensembles, such as Bagging and Random Forest., Ministerio de Economía y Competitividad of the Spanish Government under project TIN2015-67534-P (MINECO-FEDER, UE), by the Junta de Castilla y León under project BU085P17 (JCyL/FEDER, UE) (both projects co-financed through European Union FEDER funds), and by the Consejería de Educación of the Junta de Castilla y León and the European Social Fund with the EDU/1100/2017 pre-doctoral grant.

Classification is used in a wide range of applications to determine the class of a new element; for example, it can be used to determine whether an object is a pedestrian based on images captured by the safety sensors of a vehicle. Classifiers are commonly implemented using electronic components and thus, they are subject to errors in memories and combinational logic. In some cases, classifiers are used in safety critical applications and thus, they must operate reliably. Therefore, there is a need to protect classifiers against errors. The k Nearest Neighbors (kNNs) classifier is a simple, yet powerful algorithm that is widely used; its protection against errors in the neighbor computations has been recently studied. This paper considers the protection of kNNs classifiers against errors in the memory that stores the dataset used to select the neighbors. Initially, the effects of errors in the most common memory configurations (unprotected, Parity-Check protected and Single Error Correction-Double Error Detection (SEC-DED) protected) are assessed. The results show that surprisingly, for most datasets, it is better to leave the memory unprotected than to use error detection codes to discard the element affected by an error in terms of tolerance. This observation is then leveraged to develop Less-is-Better Protection (LBP), a technique that does not require any additional parity bits and achieves better error tolerance than Parity-Check for single bit errors (reducing the classification errors by 59% for the Iris dataset) and SEC-DED codes for double bit errors (reducing the classification errors by 42% for the Iris dataset). S. Liu and F. Lombardi would like to acknowledge the support of National Science Foundation, USA grants CCF-1953961 and 1812467, and P. Reviriego would like to acknowledge the support of the ACHILLES project PID2019-104207RB-I00 and the Go2Edge network RED2018-102585-T funded by the Spanish Ministry of Science and Innovation and by the Madrid Community research project TAPIR-CM P2018/TCS-4496.

BayeSuites is the first web framework for learning, visualizing, and interpreting Bayesian networks (BNs) that can scale to tens of thousands of nodes while providing fast and friendly user experience. All the necessary features that enable this are reviewed in this paper; these features include scalability, extensibility, interoperability, ease of use, and interpretability. Scalability is the key factor in learning and processing massive networks within reasonable time; for a maintainable software open to new functionalities, extensibility and interoperability are necessary. Ease of use and interpretability are fundamental aspects of model interpretation, fairly similar to the case of the recent explainable artificial intelligence trend. We present the capabilities of our proposed framework by highlighting a real example of a BN learned from genomic data obtained from Allen Institute for Brain Science. The extensibility properties of the software are also demonstrated with the help of our BN-based probabilistic clustering implementation, together with another genomic-data example.

The dramatic growth of the Web has motivated researchers to extract knowledge from enormous repositories and to exploit the knowledge in myriad applications. In this study, we focus on natural language processing (NLP) and, more concretely, the emerging field of affective computing to explore the automation of understanding human emotions from texts. This paper continues previous efforts to utilize and adapt affective techniques into different areas to gain new insights. This paper proposes two novel feature extraction methods that use the previous sentic computing resources AffectiveSpace and SenticNet. These methods are efficient approaches for extracting affect-aware representations from text. In addition, this paper presents a machine learning framework using an ensemble of different features to improve the overall classification performance. Following the description of this approach, we also study the effects of known feature extraction methods such as TF-IDF and SIMilarity-based sentiment projectiON (SIMON). We perform a thorough evaluation of the proposed features across five different datasets that cover radicalization and hate speech detection tasks. To compare the different approaches fairly, we conducted a statistical test that ranks the studied methods. The obtained results indicate that combining affect-aware features with the studied textual representations effectively improves performance. We also propose a criterion considering both classification performance and computational complexity to select among the different methods.

© ACM 2021. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in ACM Transactions on Software Engineering and Methodology, http://dx.doi.org/10.1145/10.1145/3428076, Models are the central assets in model-driven engineering (MDE), as they are actively used in all phases of software development. Models are built using metamodel-based languages, and so objects in models are typed by a metamodel class. This typing is static, established at creation time, and cannot be changed later. Therefore, objects in MDE are closed and fixed with respect to the class they conform to, the fields they have, and the well-formedness constraints they must comply with. This hampers many MDE activities, like the reuse of model-related artefacts such as transformations, the opportunistic or dynamic combination of metamodels, or the dynamic reconfiguration of models. To alleviate this rigidity, we propose making model objects open so that they can acquire or drop so-called facets. These contribute with a type, fields and constraints to the objects holding them. Facets are defined by regular metamodels, hence being a lightweight extension of standard metamodelling. Facet metamodels may declare usage interfaces, as well as laws that govern the assignment of facets to objects (or classes). This article describes our proposal, reporting on a theory, analysis techniques, and an implementation. The benefits of the approach are validated on the basis of five case studies dealing with annotation models, transformation reuse, multi-view modelling, multi-level modelling, and language product lines, Work partially funded by the R&D programme of the Madrid Region (project FORTE, S2018/TCS-4314) and the Spanish Ministry of Science (project MASSIVE, RTI2018-095255-B-I00)

This article proposes a novel algorithm to detect anomalies during a laser-surface heat-treatment process recorded using a high-speed thermal camera. Our approach detects anomalies by tracking the movement of the laser spot along the surface of a production artifact. No previous knowledge of the anomalies is assumed. The model attempts to learn the behavior of a normal process so that anomalous video frames can be detected when the test data differ significantly from the learned model. The model is trained using real process data provided by a company operating in the automotive sector. First, laser-spot movements are obtained by computing a sequence of their positions. Second, the expected movement of the laser spot is accurately determined from the non anomalous data by using a model based on training multiple kernel density estimation models. Finally, an anomaly score is introduced to classify a workpiece as normal or anomalous using the trained model. Furthermore, our methodology is computationally efficient when compared to other techniques. Additionally, our objective is to perform in-process classification, that is, to perform the classification within a short period after the laser-surface heat-treatment process ends.

Context-sensitive global analysis of large code bases can be expensive, which can make its use impractical during software development. However, there are many situations in which modifications are small and isolated within a few components, and it is desirable to reuse as much as possible previous analysis results. This has been achieved to date through incremental global analysis fixpoint algorithms that achieve cost reductions at fine levels of granularity, such as changes in program lines. However, these fine-grained techniques are not directly applicable to modular programs, nor are they designed to take advantage of modular structures. This paper describes, implements, and evaluates an algorithm that performs efficient context-sensitive analysis incrementally on modular partitions of programs. The experimental results show that the proposed modular algorithm shows significant improvements, in both time and memory consumption, when compared to existing non-modular, fine-grain incremental analysis techniques. Furthermore, thanks to the proposed inter-modular propagation of analysis information, our algorithm also outperforms traditional modular analysis even when analyzing from scratch., Comment: 56 pages, 27 figures. To be published in Theory and Practice of Logic Programming. v3 corresponds to the extended version of the ICLP2018 Technical Communication. v4 is the revised version submitted to Theory and Practice of Logic Programming. v5 (this one) is the final author version to be published in TPLP

The management of educational policies is a complex issue. There are complexities related to the country’s organizational system (competencies delegated by different areas in some cases), and to the limited resources in the educational system. In addition, there are many variables that need to be managed: ICT resources, special educational needs, human resources available, the socioeconomic characteristics of each district, etc. These types of issues are similar to those dealt with by strategic intelligence management. In this field, commonly included within innovation management, methodological frameworks are established that enable collection and consolidation of data from various sources and their subsequent exploitation to enhance decision-making based on previously identified needs. This article presents the details of a pilot plan aimed at implementing a framework for strategic intelligence management in the educational management system of the Community of Madrid (Spain). These intelligence systems are difficult to deploy in educational organizations that have highly fragmented management as in the case described in our pilot plan, although their implementation leads to more correct and agile decision-makings. This paper describes the steps carried out to define the new management platform requirements, its technical implementation issues, and the validation results that demonstrate its functional validity and acceptance by end-users participating in the described pilot project.

Autonomous navigation relies upon an accurate understanding of the elements in the surroundings. Among the different on-board perception tasks, 3D object detection allows the identification of dynamic objects that cannot be registered by maps, being key for safe navigation. Thus, it often requires the use of LiDAR data, which is able to faithfully represent the scene geometry. However, although raw laser point clouds contain rich features to perform object detection, more compact representations such as the bird's eye view (BEV) projection are usually preferred in order to meet the time requirements of the control loop. This paper presents an end-to-end object detection network based on the well-known Faster R-CNN architecture that uses BEV images as input to produce the final 3D boxes. Our regression branches can infer not only the axis-aligned bounding boxes but also the rotation angle, height, and elevation of the objects in the scene. The proposed network provides state-of-the-art results for car, pedestrian, and cyclist detection with a single forward pass when evaluated on the KITTI 3D Object Detection Benchmark, with an accuracy that exceeds 64% mAP 3D for the Moderate difficulty. Further experiments on the challenging nuScenes dataset show the generalizability of both the method and the proposed BEV representation against different LiDAR devices and across a wider set of object categories by being able to reach more than 30% mAP with a single LiDAR sweep and almost 40% mAP with the usual 10-sweep accumulation. This work was supported in part by the Government of Madrid (Comunidad de Madrid) under the Multiannual Agreement with the University Carlos III of Madrid (UC3M) in the line of "Fostering Young Doctors Research"(PEAVAUTO-CM-UC3M), and in part by the Context of the V Regional Programme of Research and Technological Innovation (PRICIT).

Recently, two technologies have emerged to provide advanced programmability in Software-Defined Networking (SDN) environments, namely P4 and XDP. At the same time, the Internet of Things (IoT) represents a pillar of future 6G networks, which will be also sustained by SDN. In this regard, there is a need to analyze the suitability of P4 and XDP for IoT. In this article, we aim to compare both technologies to help future research efforts in the field. To this purpose, we evaluate both technologies by implementing diverse use cases, assessing their performance and providing a quick qualitative overview. All tests and designed scenarios are publicly available in GitHub to guarantee replication and serve as initial steps for researchers that want to initiate in the field. Results illustrate that currently XDP is the best option for constrained IoT devices, showing lower latency times, half of CPU usage, and reduced memory in comparison with P4. However, development of P4 programs is more straightforward and the amount of code lines is more similar regardless of the scenario. Additionally, P4 has a lot of potential in IoT if a special effort is made to improve the most common software target, BMv2., Comunidad de Madrid, Junta de Comunidades de Castilla-La Mancha, Universidad de Alcalá

We propose and demonstrate the use of a model-assisted generative adversarial network (GAN) to produce fake images that accurately match true images through the variation of the parameters of the model that describes the features of the images. The generator learns the model parameter values that produce fake images that best match the true images. Two case studies show excellent agreement between the generated best match parameters and the true parameters. The best match model parameter values can be used to retune the default simulation to minimize any bias when applying image recognition techniques to fake and true images. In the case of a real-world experiment, the true images are experimental data with unknown true model parameter values, and the fake images are produced by a simulation that takes the model parameters as input. The model-assisted GAN uses a convolutional neural network to emulate the simulation for all parameter values that, when trained, can be used as a conditional generator for fast fake-image production.

Recently, the recognition of emotions with electroencephalographic (EEG) signals has received increasing attention. Furthermore, the nonstationarity of brain has intensified the application of nonlinear methods. Nonetheless, metrics like quadratic sample entropy (QSE), amplitude-aware permutation entropy (AAPE) and permutation min-entropy (PME) have never been applied to discern between more than two emotions. Therefore, this study computes for the first time QSE, AAPE and PME for recognition of four groups of emotions. After preprocessing the EEG recordings, the three entropy metrics were computed. Then, a tenfold classification approach based on a sequential forward selection scheme and a support vector machine classifier was implemented. This procedure was applied in a multi-class scheme including the four groups of study simultaneously, and in a binary-class approach for discerning emotions two by two, regarding their levels of arousal and valence. For both schemes, QSE+AAPE and QSE+PME were combined. In both multi-class and binary-class schemes, the best results were obtained in frontal and parietal brain areas. Furthermore, in most of the cases channels from QSE and AAPE/PME were selected in the classification models, thus highlighting the complementarity between those different types of entropy indices and achieving global accuracy results higher than 90% in multi-class and binary-class schemes. The combination of regularity- and predictability-based entropy indices denoted a high degree of complementarity between those nonlinear methods. Finally, the relevance of frontal and parietal areas for recognition of emotions has revealed the essential role of those brain regions in emotional processes., Facultad de Ingeniería, Centro de Investigaciones Ópticas

Phytoliths can be an important source of information related to environmental and climatic change, as well as to ancient plant use by humans, particularly within the disciplines of paleoecology and archaeology. Currently, phytolith identification and categorization is performed manually by researchers, a time-consuming task liable to misclassifications. The automated classification of phytoliths would allow the standardization of identification processes, avoiding possible biases related to the classification capability of researchers. This paper presents a comparative analysis of six classification methods, using digitized microscopic images to examine the efficacy of different quantitative approaches for characterizing phytoliths. A comprehensive experiment performed on images of 429 phytoliths demonstrated that the automatic phytolith classification is a promising area of research that will help researchers to invest time more efficiently and improve their recognition accuracy rate., This work was supported by the project TIN2015- 67534-P (MINECO/FEDER, UE) of the Ministerio de Economía y Competitividad of the Spanish Government, by the project BU085P17 (JCyL/FEDER, UE) of the Junta de Castilla y León (both projects co-financed through European Union FEDER funds) and by Grups de Recerca de Qualitat CaSEs – Culture and Socio-Ecological Dynamics (2017 SGR 212), AGAUR-Generalitat de Catalunya. The authors gratefully acknowledge the support of NVIDIA Corporation and its donation of the TITAN Xp GPUs used in this research.

© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works, While being one of the first and most elegant tools for dimensionality reduction, Fisher linear discriminant analysis (FLDA) is not currently considered among the top methods for feature extraction or classification. In this paper, we will review two recent approaches to FLDA, namely, least squares Fisher discriminant analysis (LSFDA) and regularized kernel FDA (RKFDA) and propose deep FDA (DFDA), a straightforward nonlinear extension of LSFDA that takes advantage of the recent advances on deep neural networks. We will compare the performance of RKFDA and DFDA on a large number of two-class and multiclass problems, many of them involving class-imbalanced data sets and some having quite large sample sizes; we will use, for this, the areas under the receiver operating characteristics (ROCs) curve of the classifiers considered. As we shall see, the classification performance of both methods is often very similar and particularly good on imbalanced problems, but building DFDA models is considerably much faster than doing so for RKFDA, particularly in problems with quite large sample sizes

The resolution of multiclass classification problems has been usually addressed by using a "divide and conquer" strategy that splits the original problem into several binary subproblems. This approach is mandatory when the learning algorithm has been designed to solve binary problems and a multiclass version cannot be devised. Artificial Neural Networks, ANN, are binary learning models whose extension to multiclass problems is rather straightforward by using the standard 1-out-of N codification of the classes. However, the use of a single ANN can be inefficient in terms of accuracy and computational complexity when the data set is large, or the number of classes is high. In this work, we exhaustively describe CCE, a new classifier ensemble based on ANN. Each member of this new ensemble is a couple of multiclass ANN's. Each ANN is trained using different subsets of the dataset ensuring these subsets to be disjoint. This new approach allows to combine the benefits of the divide and conquer methodology, with the use of multiclass ANNs and with the combination of individual classification modules that give a complete answer to the addressed problem. The combination of these elements results in a classifier ensemble in which the diversity of the base classifiers provides high accuracy values. Moreover, the use of couples of ANN proves to be tolerant to labeling noise and computationally efficient. The performance of CCE has been tested on various datasets and the results show the higher performance of this approach with respect to other used classification systems. This research was supported by the Spanish MINECO under projects TRA2016-78886-C3-1-R and RTI2018-096036-B-C22.

Designing augmented and tangible experiences that intertwine human practices and expectations, interaction spaces and complex digital artifacts is a complex and multifaceted task that relies upon iterative and multidisciplinary ideation processes. Design thinking techniques have been traditionally used in ideation of such digital artifacts. In this paper, we posit that integrating some software engineering practices can improve ideation by providing a structure to the process and helping to build a shared and permanently documented design rationale. It is not a matter of software engineering versus design thinking but a question of developing a holistic understanding of technological development where discipline and creativity, rationality and emotions and quality centered and people centered coexist. Based on this assumption, we conceived a software tool called CoDICE that offers a virtual co-design space where augmented digital experiences are documented and analyzed in a shared and distributed way. The paper discusses how CoDICE contributes to alleviate some problems of co-design events including the need to support multiple co-design spaces, make explicit the co-design process and its goals, support documentation, justify design decisions, explore multiple ideas and generate a shared representation of the outcomes. Two scenarios are used to illustrate the tool utility: short-term co-design workshops in which the tool enabled multidisciplinary teams of novice designers to explore and structure their ideas and a long-term co-design project where the tool facilitated traceability, documentation, the reuse of design components and the shared elaboration of the design rationale and evolution of the deployed technologies.

In this paper, we present a statistical model for spoken dialog segmentation that decides the current phase of the dialog by means of an automatic classification process. We have applied our proposal to three practical conversational systems acting in different domains. The results of the evaluation show that is possible to attain high accuracy rates in dialog segmentation when using different sources of information to represent the user input. Our results indicate how the module proposed can also improve dialog management by selecting better system answers. The statistical model developed with human-machine dialog corpora has been applied in one of our experiments to human-human conversations and provides a good baseline as well as insights in the model limitation.

Software pipelines enable organizations to chain applications for adding value to contents (e.g., confidentially, reliability, and integrity) before either sharing them with partners or sending them to the cloud. However, the pipeline components add overhead when processing large volumes of data, which can become critical in real-world scenarios. This paper presents a gearbox model for processing large volumes of data by using pipeline systems encapsulated into virtual containers. In this model, the gears represent applications, whereas gearboxes represent software pipelines. This model was implemented as a collaborative system that automatically performs Gear up (by using parallel patterns) and/or Gear down (by using in-memory storage) until all gears produce uniform data processing velocities. This model reduces delays and bottlenecks produced by the heterogeneous performance of applications included in software pipelines. The new container tool has been designed to encapsulate both the collaborative system and the software pipelines into a virtual container and deploy it on IT infrastructures. We conducted case studies to evaluate the performance of when processing medical images and PDF repositories. The incorporation of a capsule to a cloud storage service for pre-processing medical imagery was also studied. The experimental evaluation revealed the feasibility of applying the gearbox model to the deployment of software pipelines in real-world scenarios as it can significantly improve the end-user service experience when pre-processing large-scale data in comparison with state-of-the-art solutions such as Sacbe and Parsl. This work has been partially supported by the “Spanish Ministerio de Economia y Competitividad ” under the project grant TIN2016-79637-P “Towards Unification of HPC and Big Data paradigms”.

It is already common to compute quantitative metrics of requirements to assess their quality. However, the risk is to build assessment methods and tools that are both arbitrary and rigid in the parameterization and combination of metrics. Specifically, we show that a linear combination of metrics is insufficient to adequately compute a global measure of quality. In this work, we propose to develop a flexible method to assess and improve the quality of requirements that can be adapted to different contexts, projects, organizations, and quality standards, with a high degree of automation. The domain experts contribute with an initial set of requirements that they have classified according to their quality, and we extract their quality metrics. We then use machine learning techniques to emulate the implicit expert’s quality function. We provide also a procedure to suggest improvements in bad requirements. We compare the obtained rule-based classifiers with different machine learning algorithms, obtaining measurements of effectiveness around 85%. We show as well the appearance of the generated rules and how to interpret them. The method is tailorable to different contexts, different styles to write requirements, and different demands in quality. The whole process of inferring and applying the quality rules adapted to each organization is highly automated This research has received funding from the CRYSTAL project–Critical System Engineering Acceleration (European Union’s Seventh Framework Program FP7/2007-2013, ARTEMIS Joint Undertaking grant agreement no 332830); and from the AMASS project–Architecture-driven, Multi-concern and Seamless Assurance and Certification of Cyber-Physical Systems (H2020-ECSEL grant agreement no 692474; Spain’s MINECO ref. PCIN-2015-262).

Underwater cooperative robotics offers the possibility to perform challenging intervention applications, such as recovering archeological objects as within the context of the MERBOTS research project, or grasping, transporting and assembly of big objects, using more than one mobile manipulator, as faced by the TWINBOT project. In order to enhance safety during the intervention, it is reasonable to avoid the umbilical, also giving more mobility to the robots, and enabling a broader set of cooperative movements. Several solutions, based on acoustic, radiofrequency (RF) or Visual Light Communication (VLC) have been proposed for underwater communications in the literature. This paper presents the architecture of an underwater wireless communication framework for the control of multiple semi-autonomous robots in cooperative interventions. The proposed framework is composed of several modules as the virtual reality interface using UWSim, the Underwater Multi-robot Cooperative Intervention Remote Control Protocol (UMCI-RCP) and a Generic Link Layer (GLL). UMCI-RCP allows the control of an underwater robot over limited communication links. UMCI-RCP integrates a progressive compression algorithm that provides visual feedback at a constant rate and ensures image reception even in channels with loses. The Time Division Multiple Access (TDMA) medium access strategy minimizes the jitter of transmitted packets. The GLL has been designed in order to provide support for multimodal transmission (i.e. acoustic, RF and VLC) and also to interface with the UWSim-NET simulator so that facilitates the experimentation either with a real or with a simulated modem. The possibility of exchange real and simulated devices in the proposed framework are demonstrated by means of a teleoperation experiment with a BlueROV equipped with the S100 RF modems. Hardware-In-the-Loop (HIL) capabilities are demonstrated repeating the experiment with the real modems and modeling the BlueROV, and also modeling both the modems and the BlueROV.

A complex and important task in the cloud resource management is the efficient allocation of virtual machines (VMs), or containers, in physical machines (PMs). The evaluation of VM placement techniques in real-world clouds can be tedious, complex and time-consuming. This situation has motivated an increasing use of cloud simulators that facilitate this type of evaluations. However, most of the reported VM placement techniques based on simulations have been evaluated taking into account one specific cloud resource (e.g., CPU), whereas values often unrealistic are assumed for other resources (e.g., RAM, awaiting times, application workloads, etc.). This situation generates uncertainty, discouraging their implementations in real-world clouds. This paper introduces CloudBench, a methodology to facilitate the evaluation and deployment of VM placement strategies in private clouds. CloudBench considers the integration of a cloud simulator with a real-world private cloud. Two main tools were developed to support this methodology, a specialized multi-resource cloud simulator (CloudBalanSim), which is in charge of evaluating VM placement techniques, and a distributed resource manager (Balancer), which deploys and tests in a real-world private cloud the best VM placement configurations that satisfied user requirements defined in the simulator. Both tools generate feedback information, from the evaluation scenarios and their obtained results, which is used as a learning asset to carry out intelligent and faster evaluations. The experiments implemented with the CloudBench methodology showed encouraging results as a new strategy to evaluate and deploy VM placement algorithms in the cloud. This work was partially funded by the Spanish Ministry of Economy, Industry and Competitiveness under the Grant TIN2016-79637-P “Towards Unifcation of HPC and Big Data Paradigms” and by the Mexican Council of Science and Technology (CONACYT) through a Ph.D. Grant (No. 212677).

This article describes the design, development and implementation of a set of microservices based on an architecture that enables detection and assisted clinical diagnosis within the field of infectious diseases of elderly patients, via a telemonitoring system. The proposed system is designed to continuously update a medical database fed with vital signs from biosensor kits applied by nurses to elderly people on a daily basis. The database is hosted in the cloud and is managed by a flexible microservices software architecture. The computational paradigms of the edge and the cloud were used in the implementation of a hybrid cloud architecture in order to support versatile high-performance applications under the microservices pattern for the pre-diagnosis of infectious diseases in elderly patients. The results of an analysis of the usability of the equipment, the performance of the architecture and the service concept show that the proposed e-health system is feasible and innovative. The system components are also selected to give a cost-effective implementation for people living in disadvantaged areas. The proposed e-health system is also suitable for distributed computing, big data and NoSQL structures, thus allowing the immediate application of machine learning and AI algorithms to discover knowledge patterns from the overall population., European Commission

Ultrasound transducer arrays are capable of producing tactile sensations on the hand, promising hands-free haptic interaction for virtual environments. However, controlling such an array with respect to reproducing a desired perceived interaction remains a challenging problem. In this work we approach this problem as a dynamic mapping of virtual interactions to existing control metaphors of ultrasound devices, namely, the modulation of focal point positions and intensities over time, a method known as Spatiotemporal Modulation (STM). In particular, we propose an optimization approach that takes into account known perceptual parameters and limitations of the STM method. This results in a set of focal point paths optimized to best reconstruct an arbitrary target pressure field.

In the analysis of real-world data, it is useful to learn a latent variable model that represents the data generation process. In this setting, latent tree models are useful because they are able to capture complex relationships while being easily interpretable. In this paper, we propose two incremental algorithms for learning forests of latent trees. Unlike current methods, the proposed algorithms are based on the variational Bayesian framework, which allows them to introduce uncertainty into the learning process and work with mixed data. The first algorithm, incremental learner , determines the forest structure and the cardinality of its latent variables in an iterative search process. The second algorithm, constrained incremental learner , modifies the previous method by considering only a subset of the most prominent structures in each step of the search. Although restricting each iteration to a fixed number of candidate models limits the search space, we demonstrate that the second algorithm returns almost identical results for a small fraction of the computational cost. We compare our algorithms with existing methods by conducting a comparative study using both discrete and continuous real-world data. In addition, we demonstrate the effectiveness of the proposed algorithms by applying them to data from the 2018 Spanish Living Conditions Survey. All code, data, and results are available at https://github.com/ferjorosa/incremental-latent-forests .

This paper studies the effects that combinations of balancing and feature selection techniques have on wide data (many more attributes than instances) when different classifiers are used. For this, an extensive study is done using 14 datasets, 3 balancing strategies, and 7 feature selection algorithms. The evaluation is carried out using 5 classification algorithms, analyzing the results for different percentages of selected features, and establishing the statistical significance using Bayesian tests. Some general conclusions of the study are that it is better to use RUS before the feature selection, while ROS and SMOTE offer better results when applied afterwards. Additionally, specific results are also obtained depending on the classifier used, for example, for Gaussian SVM the best performance is obtained when the feature selection is done with SVM-RFE before balancing the data with RUS., “La Caixa” Foundation, under agreement LCF/PR/PR18/51130007. This work was also supported by the Junta de Castilla León under project BU055P20 (JCyL/FEDER, UE) and by the Ministry of Science and Innovation under project PID2020-119894GB-I00, co-financed through European Union FEDER funds .

Tagged language resources are an essential requirement for developing machine-learning text-based classifiers. However, manual tagging is extremely time consuming and the resulting datasets are rather small, containing only a few thousand samples. Basic emotion datasets are particularly difficult to classify manually because categorization is prone to subjectivity, and thus, redundant classification is required to validate the assigned tag. Even though, in recent years, the amount of emotion-tagged text datasets in Spanish has been growing, it cannot be compared with the number, size, and quality of the datasets in English. Quality is a particularly concerning issue, as not many datasets in Spanish included a validation step in the construction process. In this article, a dataset of social media comments in Spanish is compiled, selected, filtered, and presented. A sample of the dataset is reclassified by a group of psychologists and validated using the Fleiss Kappa interrater agreement measure. Error analysis is performed by using the Sentic Computing tool BabelSenticNet. Results indicate that the agreement between the human raters and the automatically acquired tag is moderate, similar to other manually tagged datasets, with the advantages that the presented dataset contains several hundreds of thousands of tagged comments and it does not require extensive manual tagging. The agreement measured between human raters is very similar to the one between human raters and the original tag. Every measure presented is in the moderate agreement zone and, as such, suitable for training classification algorithms in sentiment analysis field., Instituto de Investigación en Informática

[EN] Autonomous capabilities are required in AmI environments in order to adapt systems to new environmental conditions and situations. However, keeping the human in the loop and in control of such systems is still necessary because of the diversity of systems, domains, environments, context situations, and social and legal constraints, which makes full autonomy a utopia within the short or medium term. Human-system integration introduces an important number of challenges and problems that have to be solved. On the one hand, humans should interact with systems even in those situations where their attentional, cognitive, and physical resources are limited in order to perform the interaction. On the other hand, systems must avoid overwhelming the user with unnecessary actions. Therefore, appropriate user-centered methods for AmI development should be used to help designers analyze and design human-in-the-loop interactions in AmI environments. This paper presents a user-centered design method that defines a process with a set of tools and techniques that supports the process steps in order to systematically design, prototype, and validate human-in-the-loop (HiL) solutions. The process starts with the definition of the HiL design, which defines how the system cooperates with the human. This HiL design is built using a conceptual framework that focuses on achieving human-system interactions that get human attention and avoid obtrusiveness. Then, we provide a software infrastructure to generate a prototype based on the HiL design and validate it by having end-users use a web simulator. The feedback data generated during the prototype user validation is gathered and used by a machine learning tool that infers the user's needs and preferences. Finally, these inferences are used to automatically enhance the human-in-the-loop designs and prototypes. We have validated the proposed method through a twofold perspective: an experiment to analyze the perception of interaction designers regarding their acceptance of the design method and another experiment to evaluate the usefulness of the "smart" prototyping technique. The results obtained point out the acceptability of the proposed method by designers and the useful adaptations provided by the "smart" prototyping technique to achieve a HiL design that adapts well to users' preferences and needs., This work has been developed with the financial support of the Spanish State Research Agency and the Generalitat Valenciana under the projects TIN2017-84094-R and AICO/2019/009 and co-financed with ERDF.

In the context of neurorehabilitation, sound is being increasingly applied for facilitating sensorimotor learning. In this study, we aimed to test the potential value of auditory stimulation for improving gait in chronic stroke patients by inducing alterations of the frequency spectra of walking sounds via a sound system that selectively amplifies and equalizes the signal in order to produce distorted auditory feedback. Twenty‐two patients with lower extremity paresis were exposed to real‐time alterations of their footstep sounds while walking. Changes in body perception, emotion, and gait were quantified. Our results suggest that by altering footsteps sounds, several gait parameters can be modified in terms of left–right foot asymmetry. We observed that augmenting low‐frequency bands or amplifying the natural walking sounds led to a reduction in the asymmetry index of stance and stride times, whereas it inverted the asymmetry pattern in heel–ground exerted force. By contrast, augmenting high‐frequency bands led to opposite results. These gait changes might be related to updating of internal forward models, signaling the need for adjustment of the motor system to reduce the perceived discrepancies between predicted–actual sensory feedbacks. Our findings may have the potential to enhance gait awareness in stroke patients and other clinical conditions, supporting gait rehabilitation. This study was supported by the Spanish Government with an MINECO grant (PSI2015‐69178‐P) awarded to A.R.F., two MINECO grants (RYC‐2014–15421 and PSI2016‐79004‐R, AEI/FEDER, UE) awarded to A.T.‐J., and a predoctoral FPI grant (BES‐2016‐078889) awarded to A.G.‐A.

With the widespread adoption of data mining models to solve real-world problems, the scientific community is facing the need of increasing their interpretability and comprehensibility. This is especially relevant in the case of black box models, in which inputs and outputs are usually connected by highly complex and nonlinear functions; in applications requiring an interaction between the user and the model; and when the machine’s solution disagrees with the human experience. In this contribution we present a new methodology that allows to simplify the process of understanding the rules behind a classification model, even in the case of black box ones. It is based on the perturbation of the features describing one instance, and on finding the minimal variation required to change the forecasted class. It thus yields simplified rules describing under which circumstances would the solution have been different, and allows to compare these with the human expectation. We show how such methodology is well defined, model-agnostic, easy to implement and modular; and demonstrate its usefulness with several synthetic and real-world data sets.

Tourist traceability is the analysis of the set of actions, procedures, and technical measures that allows us to identify and record the space–time causality of the tourist’s touring, from the beginning to the end of the chain of the tourist product. Besides, the traceability of tourists has implications for infrastructure, transport, products, marketing, the commercial viability of the industry, and the management of the destination’s social, environmental, and cultural impact. To this end, a tourist traceability system requires a knowledge base for processing elements, such as functions, objects, events, and logical connectors among them. A knowledge base provides us with information on the preparation, planning, and implementation or operation stages. In this regard, unifying tourism terminology in a traceability system is a challenge because we need a central repository that promotes standards for tourists and suppliers in forming a formal body of knowledge representation. Some studies are related to the construction of ontologies in tourism, but none focus on tourist traceability systems. For the above, we propose OntoTouTra, an ontology that uses formal specifications to represent knowledge of tourist traceability systems. This paper outlines the development of the OntoTouTra ontology and how we gathered and processed data from ubiquitous computing using Big Data analysis techniques This research was financially supported by the Ministry of Science, Technology, and Innovation of Colombia (733-2015) and by the Universidad Santo Tomás Seccional Tunja.

In this paper we investigate the benefits of applying a multi-objective approach for solving a symbolic regression problem by means of Grammatical Evolution. In particular, we extend previous work, obtaining mathematical expressions to model glucose levels in the blood of diabetic patients. Here we use a multi-objective Grammatical Evolution approach based on the NSGA-II algorithm, considering the root-mean-square error and an ad-hoc fitness function as objectives. This ad-hoc function is based on the Clarke Error Grid analysis, which is useful for showing the potential danger of mispredictions in diabetic patients. In this work, we use two datasets to analyse two different scenarios: What-if and Agnostic, the most common in daily clinical practice. In the What-if scenario, where future events are evaluated, results show that the multi-objective approach improves previous results in terms of Clarke Error Grid analysis by reducing the number of dangerous mispredictions. In the Agnostic situation, with no available information about future events, results suggest that we can obtain good predictions with only information from the previous hour for both Grammatical Evolution and Multi-Objective Grammatical Evolution.

The use of games as learning tools have proven to be a valuable way to help pupils learn while having fun. By using BetterGeo, which is a modification created by the Swedish Geological Survey (SGU) on Minecraft (one of the world's most popular games), primary school students can become familiar not only with the importance of raw materials in modern life, but also in how these minerals and rocks become part of everything they use in everyday life, and start learning basic concepts about geology, minerals, mining, mineral processing, and circular economy. Alongside the development of the mod, the BetterGeo Project develops free use teaching materials to help teachers and students in this approach to the raw materials sector. This European project is developed with the support of EIT Raw Materials, one of the eight Knowledge and Innovation Communities (KICs) launched by the EIT (European Institute of Innovation and Technology), and funded by the European Commission, whose mission is to help boost the competitiveness, growth and attractiveness of the European raw materials sector through radical innovation and guided entrepreneurship. The Universidad Politécnica de Madrid (Technical University of Madrid) is one of the partners involved in this pioneering initiative, and this paper describes the idea behind BetterGeo, together with the innovative development of exercises and educational material designed to facilitate primary school students their first contact with raw materials. Learning to make cement from minerals and rocks is an involving and interesting experience for students under this schema developed in BetterGeo by going one step further and showing first-hand the direct applications of minerals and rocks in the manufacturing of building and construction materials. In this case, they go deeper in what is the cement, the main binding element used in construction today and whose composition can accept hundreds of variants including other materials or raw materials. Using a simple script with short and simple instructions, students will be able to differentiate the most commonly used mineral components or ingredients, becoming able to make their own mixtures by adjusting quantities and setting times. They will also learn to differentiate when a cement reaches its maximum strength and will even be able to experiment with the addition of components from recycled materials or other raw materials that are not normally used in its manufacture, but which add new and interesting properties to this building material.

Due to the globalisation of the COVID-19 pandemic, and the expansion of social media as the main source of information for many people, there have been a great variety of different reactions surrounding the topic. The World Health Organization (WHO) announced in December 2020 that they were currently fighting an “infodemic” in the same way as they were fighting the pandemic. An “infodemic” relates to the spread of information that is not controlled or filtered, and can have a negative impact on society. If not managed properly, an aggressive or negative tweet can be very harmful and misleading among its recipients. Therefore, authorities at WHO have called for action and asked the academic and scientific community to develop tools for managing the infodemic by the use of digital technologies and data science. The goal of this study is to develop and apply natural language processing models using deep learning to classify a collection of tweets that refer to the COVID-19 pandemic. Several simpler and widely used models are applied first and serve as a benchmark for deep learning methods, such as Long Short-Term Memory (LSTM) and Bidirectional Encoder Representations from Transformers (BERT). The results of the experiments show that the deep learning models outperform the traditional machine learning algorithms. The best approach is the BERT-based model. This work has been supported by the Madrid Government (Comunidad de Madrid) under the Multiannual Agreement with UC3M in the context of “Fostering Young Doctors Research” (NLP4RARE-CM-UC3M), as well as in the context of “Excellence of University Professors” (EPUC3M17) and in the context of the V PRICIT (Regional Programme of Research and Technological Innovation).

We are witnessing an increasing interest in building recommender systems (RSs) for all sorts of Software Engineering activities. Modelling is no exception to this trend, as modelling environments are being enriched with RSs that help building models by providing recommendations based on previous solutions to similar problems in the same domain. However, building a RS from scratch requires considerable effort and specialized knowledge. To alleviate this problem, we propose an automated approach to the generation of RSs for modelling languages. Our approach is model-based, and we provide a domain-specific language called Droid to configure every aspect of the RS (like the type and features of the recommended items, the recommendation method, and the evaluation metrics). The RS so configured can be deployed as a service, and we offer out-of-the-box integration of this service with the EMF tree editor. To assess the usefulness of our proposal, we present a case study on the integration of a generated RS with a modelling chatbot, and report on an offline experiment measuring the precision and completeness of the recommendations, This project has received funding from the EU Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 813884, the Spanish Ministry of Science (RTI2018-095255-B-I00) and the R&D programme of Madrid (P2018/TCS-4314)

How can you measure the percentage of sensory accessibility in the new Subscription Video on Demand (SVOD) platforms? This investigation aims to answer this research question. For this, a qualitative methodology model based on a content analysis of 37 variables is presented, which have been written based on the Spanish technical regulations UNE 153010 of May 2012 of the Subtitling for deaf people and people with hearing disabilities and UNE 153020 of January 2005 of the Audio description for people with visual disabilities. This method is applicable for cinema, series and short films presented at SVOD and is limited to the accessibility of subtitling for deaf people (CC) and the audio description for blind people.

The use of advanced learning technologies (ALT) techniques in learning management systems (LMS) allows teachers to enhance self-regulated learning and to carry out the personalized monitoring of their students throughout the teaching–learning process. However, the application of educational data mining (EDM) techniques, such as supervised and unsupervised machine learning, is required to interpret the results of the tracking logs in LMS. The objectives of this work were (1) to determine which of the ALT resources would be the best predictor and the best classifier of learning outcomes, behaviours in LMS, and student satisfaction with teaching; (2) to determine whether the groupings found in the clusters coincide with the students’ group of origin. We worked with a sample of third-year students completing Health Sciences degrees. The results indicate that the combination of ALT resources used predict 31% of learning outcomes, behaviours in the LMS, and student satisfaction. In addition, student access to automatic feedback was the best classifier. Finally, the degree of relationship between the source group and the found cluster was medium (C = 0.61). It is necessary to include ALT resources and the greater automation of EDM techniques in the LMS to facilitate their use by teachers., This research was funded by the MINISTERIO DE CIENCIA E INNOVACIÓN, grant number PID2020-117111RB-I00.

In this paper, we use an evolutionary swarm intelligence approach to build an automatic electric dispatch controller for an offshore wind power plant (WPP). The optimal power flow (OPF) problem for this WPP is solved by the Canonical Differential Evolutionary Particle Swarm Optimization algorithm (C-DEEPSO). In this paper, C-DEEPSO works as a control system for reactive sources in energy production. The control operation takes place in a daily energy dispatch, scheduled into 15 min intervals and resulting in 96 operating test scenarios. As the nature of the optimization problem is dynamic, a fine-tuning of the initialization parameters of the optimization algorithm is performed at each dispatch interval. Therefore, a version of the C-DEEPSO algorithm has been built to automatically learn the best set of initialization parameters for each scenario. For this, we have coupled C-DEEPSO with the irace tool (an extension of the iterated F-race (I/F-Race)) by using inferential statistic techniques. The experiments carried out showed that the methodology employed here is robust and able to tackle this OPF-like modeling. Moreover, the methodology works as an automatic control system for a dynamic schedule operation., European Commission, Agencia Estatal de Investigación, Comunidad de Madrid

This article belongs to the Special Issue Advanced Computer Vision Techniques for Autonomous Driving. The role of sensors such as cameras or LiDAR (Light Detection and Ranging) is crucial for the environmental awareness of self-driving cars. However, the data collected from these sensors are subject to distortions in extreme weather conditions such as fog, rain, and snow. This issue could lead to many safety problems while operating a self-driving vehicle. The purpose of this study is to analyze the effects of fog on the detection of objects in driving scenes and then to propose methods for improvement. Collecting and processing data in adverse weather conditions is often more difficult than data in good weather conditions. Hence, a synthetic dataset that can simulate bad weather conditions is a good choice to validate a method, as it is simpler and more economical, before working with a real dataset. In this paper, we apply fog synthesis on the public KITTI dataset to generate the Multifog KITTI dataset for both images and point clouds. In terms of processing tasks, we test our previous 3D object detector based on LiDAR and camera, named the Spare LiDAR Stereo Fusion Network (SLS-Fusion), to see how it is affected by foggy weather conditions. We propose to train using both the original dataset and the augmented dataset to improve performance in foggy weather conditions while keeping good performance under normal conditions. We conducted experiments on the KITTI and the proposed Multifog KITTI datasets which show that, before any improvement, performance is reduced by 42.67% in 3D object detection for Moderate objects in foggy weather conditions. By using a specific strategy of training, the results significantly improved by 26.72% and keep performing quite well on the original dataset with a drop only of 8.23%. In summary, fog often causes the failure of 3D detection on driving scenes. By additional training with the augmented dataset, we significantly improve the performance of the proposed 3D object detection algorithm for self-driving cars in foggy weather conditions.

The occupancy and activity estimation are fields that have been severally researched in the past few years. However, the different techniques used include a mixture of atmospheric features such as humidity and temperature, many devices such as cameras and audio sensors, or they are limited to speech recognition. In this work is proposed that the occupancy and activity can be estimated only from the audio information using an automatic approach of audio feature engineering to extract, analyze and select descriptors/variables. This scheme of extraction of audio descriptors is used to determine the occupation and activity in specific smart environments, such that our approach can differentiate between academic, administrative or commercial environments. Our approach from the audio feature engineering is compared to previous similar works on occupancy estimation and/or activity estimation in smart buildings (most of them including other features, such as atmospherics and visuals). In general, the results obtained are very encouraging compared to previous studies., European Commission

The current state of the web, which is dominated by centralized cloud services, raises several concerns regarding different aspects such as governance, privacy, surveillance, and security. A way to address these issues is to decentralize the platforms by adopting new distributed technologies, such as IPFS and Blockchain, which follow a full peer-to-peer model. This work proposes a set of guidelines to design decentralized systems, taking the different trade-offs these technologies face with regard to their consistency requirements into consideration. These guidelines are then illustrated with the design of a decentralized questions and answers system. This system serves to illustrate a framework to create decentralized services and applications that uses IPFS and Blockchain technologies and incorporates the discussion and guidelines of the paper, providing solutions for data access, data provenance, and data discovery. Thus, this work proposes a framework to assist in the design of new decentralized systems, proposing a set of guidelines to choose the appropriate technologies depending on the relevant requirements, e.g., considering if Blockchain technology may be required or IPFS might be sufficient.