Universidad de Jaén

In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.

This paper challenges the prevalent notion that family-owned firms are more risk averse than publicly owned firms. Using behavioral theory, we argue that for family firms, the primary reference point is the loss of their socioemotional wealth, and to avoid those losses, family firms are willing to accept a significant risk to their performance; yet at the same time, they avoid risky business decisions that might aggravate that risk. Thus, we propose that the predictions of behavioral theory differ depending on family ownership. We confirm our hypotheses using a population of 1,237 family-owned olive oil mills in Southern Spain who faced the choice during a 54-year period of becoming a member of a cooperative, a decision associated with loss of family control but lower business risk, or remaining independent, which preserves the family's socioemotional wealth but greatly increases its performance hazard. As shown in this study, family firms may be risk willing and risk averse at the same time.

Classifier learning with data-sets that suffer from imbalanced class distributions is a challenging problem in data mining community. This issue occurs when the number of examples that represent one class is much lower than the ones of the other classes. Its presence in many real-world applications has brought along a growth of attention from researchers. In machine learning, the ensemble of classifiers are known to increase the accuracy of single classifiers by combining several of them, but neither of these learning techniques alone solve the class imbalance problem, to deal with this issue the ensemble learning algorithms have to be designed specifically. In this paper, our aim is to review the state of the art on ensemble techniques in the framework of imbalanced data-sets, with focus on two-class problems. We propose a taxonomy for ensemble-based methods to address the class imbalance where each proposal can be categorized depending on the inner ensemble methodology in which it is based. In addition, we develop a thorough empirical comparison by the consideration of the most significant published approaches, within the families of the taxonomy proposed, to show whether any of them makes a difference. This comparison has shown the good behavior of the simplest approaches which combine random undersampling techniques with bagging or boosting ensembles. In addition, the positive synergy between sampling techniques and bagging has stood out. Furthermore, our results show empirically that ensemble-based algorithms are worthwhile since they outperform the mere use of preprocessing techniques before learning the classifier, therefore justifying the increase of complexity by means of a significant enhancement of the results.

The fuzzy linguistic approach has been applied successfully to many problems. However, there is a limitation of this approach imposed by its information representation model and the computation methods used when fusion processes are performed on linguistic values. This limitation is the loss of information; this loss of information implies a lack of precision in the final results from the fusion of linguistic information. In this paper, we present tools for overcoming this limitation. The linguistic information is expressed by means of 2-tuples, which are composed of a linguistic term and a numeric value assessed in (-0.5, 0.5). This model allows a continuous representation of the linguistic information on its domain, therefore, it can represent any counting of information obtained in a aggregation process. We then develop a computational technique for computing with words without any loss of information. Finally, different classical aggregation operators are extended to deal with the 2-tuple linguistic model.

(Knowledge Extraction based onEvolutionary Learning) tool, an open source software that supports datamanagement and a designer of experiments. KEEL pays special attentionto the implementation of evolutionary learning and soft computing basedtechniques for Data Mining problems including regression, classification,clustering, pattern mining and so on.The aim of this paper is to present three new aspects of KEEL: KEEL-dataset, a data set repository which includes the data set partitions in theKEELformatandshowssomeresultsofalgorithmsinthesedatasets; someguidelines for including new algorithms in KEEL, helping the researcherstomaketheirmethodseasilyaccessibletootherauthorsandtocomparetheresults of many approaches already included within the KEEL software;and a module of statistical procedures developed in order to provide to theresearcher a suitable tool to contrast the results obtained in any experimen-talstudy.Acaseofstudyisgiventoillustrateacompletecaseofapplicationwithin this experimental analysis framework.

Dealing with uncertainty is always a challenging problem, and different tools have been proposed to deal with it. Recently, a new model that is based on hesitant fuzzy sets has been presented to manage situations in which experts hesitate between several values to assess an indicator, alternative, variable, etc. Hesitant fuzzy sets suit the modeling of quantitative settings; however, similar situations may occur in qualitative settings so that experts think of several possible linguistic values or richer expressions than a single term for an indicator, alternative, variable, etc. In this paper, the concept of a hesitant fuzzy linguistic term set is introduced to provide a linguistic and computational basis to increase the richness of linguistic elicitation based on the fuzzy linguistic approach and the use of context-free grammars by using comparative terms. Then, a multicriteria linguistic decision-making model is presented in which experts provide their assessments by eliciting linguistic expressions. This decision model manages such linguistic expressions by means of its representation using hesitant fuzzy linguistic term sets.

Plant traits-the morphological, anatomical, physiological, biochemical and phenological characteristics of plants-determine how plants respond to environmental factors, affect other trophic levels, and influence ecosystem properties and their benefits and detriments to people. Plant trait data thus represent the basis for a vast area of research spanning from evolutionary biology, community and functional ecology, to biodiversity conservation, ecosystem and landscape management, restoration, biogeography and earth system modelling. Since its foundation in 2007, the TRY database of plant traits has grown continuously. It now provides unprecedented data coverage under an open access data policy and is the main plant trait database used by the research community worldwide. Increasingly, the TRY database also supports new frontiers of trait-based plant research, including the identification of data gaps and the subsequent mobilization or measurement of new data. To support this development, in this article we evaluate the extent of the trait data compiled in TRY and analyse emerging patterns of data coverage and representativeness. Best species coverage is achieved for categorical traits-almost complete coverage for 'plant growth form'. However, most traits relevant for ecology and vegetation modelling are characterized by continuous intraspecific variation and trait-environmental relationships. These traits have to be measured on individual plants in their respective environment. Despite unprecedented data coverage, we observe a humbling lack of completeness and representativeness of these continuous traits in many aspects. We, therefore, conclude that reducing data gaps and biases in the TRY database remains a key challenge and requires a coordinated approach to data mobilization and trait measurements. This can only be achieved in collaboration with other initiatives.

Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Ion Androutsopoulos, Suresh Manandhar, Mohammad AL-Smadi, Mahmoud Al-Ayyoub, Yanyan Zhao, Bing Qin, Orphée De Clercq, Véronique Hoste, Marianna Apidianaki, Xavier Tannier, Natalia Loukachevitch, Evgeniy Kotelnikov, Nuria Bel, Salud María Jiménez-Zafra, Gülşen Eryiğit. Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016). 2016.

The concept of bias is the lack of internal validity or incorrect assessment of the association between an exposure and an effect in the target population in which the statistic estimated has an expectation that does not equal the true value. Biases can be classified by the research stage in which they occur or by the direction of change in a estimate. The most important biases are those produced in the definition and selection of the study population, data collection, and the association between different determinants of an effect in the population. A definition of the most common biases occurring in these stages is given.

BACKGROUND: Bone morphogenic proteins (BMPs) are known to promote osteogenesis, and clinical trials are currently underway to evaluate the ability of certain BMPs to promote fracture-healing and spinal fusion. The optimal BMPs to be used in different clinical applications have not been elucidated, and a comprehensive evaluation of the relative osteogenic activity of different BMPs is lacking. METHODS: To identify the BMPs that may possess the most osteoinductive activity, we analyzed the osteogenic activity of BMPs in mesenchymal progenitor and osteoblastic cells. Recombinant adenoviruses expressing fourteen human BMPs (BMP-2 to BMP-15) were constructed to infect pluripotent mesenchymal progenitor C3H10T1/2 cells, preosteoblastic C2C12 cells, and osteoblastic TE-85 cells. Osteogenic activity was determined by measuring the induction of alkaline phosphatase, osteocalcin, and matrix mineralization upon BMP stimulation. RESULTS: BMP-2, 6, and 9 significantly induced alkaline phosphatase activity in pluripotential C3H10T1/2 cells, while BMP-2, 4, 6, 7, and 9 significantly induced alkaline phosphatase activity in preosteoblastic C2C12 cells. In TE-85 osteoblastic cells, most BMPs (except BMP-3 and 12) were able to induce alkaline phosphatase activity. The results of alkaline phosphatase histochemical staining assays were consistent with those of alkaline phosphatase colorimetric assays. Furthermore, BMP-2, 6, and 9 (as well as BMP-4 and, to a lesser extent, BMP-7) significantly induced osteocalcin expression in C3H10T1/2 cells. In C2C12 cells, osteocalcin expression was strongly induced by BMP-2, 4, 6, 7, and 9. Mineralized nodules were readily detected in C3H10T1/2 cells infected with BMP-2, 6, and 9 (and, to a lesser extent, those infected with BMP-4 and 7). CONCLUSIONS: A comprehensive analysis of the osteogenic activity of fourteen types of BMPs in osteoblastic progenitor cells was conducted. Our results suggest an osteogenic hierarchical model in which BMP-2, 6, and 9 may play an important role in inducing osteoblast differentiation of mesenchymal stem cells. In contrast, most BMPs are able to stimulate osteogenesis in mature osteoblasts.

This article evaluates the suitability of low frequency (LF) heart rate variability (HRV) as an index of sympathetic cardiac control and the LF/high frequency (HF) ratio as an index of autonomic balance. It includes a comprehensive literature review and a reanalysis of some previous studies on autonomic cardiovascular regulation. The following sources of evidence are addressed: effects of manipulations affecting sympathetic and vagal activity on HRV, predictions of group differences in cardiac autonomic regulation from HRV, relationships between HRV and other cardiac parameters, and the theoretical and mathematical bases of the concept of autonomic balance. Available data challenge the interpretation of the LF and LF/HF ratio as indices of sympathetic cardiac control and autonomic balance, respectively, and suggest that the HRV power spectrum, including its LF component, is mainly determined by the parasympathetic system.

Summary The effects of the present biodiversity crisis have been largely focused on the loss of species. However, a missed component of biodiversity loss that often accompanies or even precedes species disappearance is the extinction of ecological interactions. Here, we propose a novel model that (i) relates the diversity of both species and interactions along a gradient of environmental deterioration and (ii) explores how the rate of loss of ecological functions, and consequently of ecosystem services, can be accelerated or restrained depending on how the rate of species loss covaries with the rate of interactions loss. We find that the loss of species and interactions are decoupled, such that ecological interactions are often lost at a higher rate. This implies that the loss of ecological interactions may occur well before species disappearance, affecting species functionality and ecosystems services at a faster rate than species extinctions. We provide a number of empirical case studies illustrating these points. Our approach emphasizes the importance of focusing on species interactions as the major biodiversity component from which the ‘health’ of ecosystems depends.

In those problems that deal with multiple sources of linguistic information we can find problems defined in contexts where the linguistic assessments are assessed in linguistic term sets with different granularity of uncertainty and/or semantics (multigranular linguistic contexts). Different approaches have been developed to manage this type of contexts, that unify the multigranular linguistic information in an unique linguistic term set for an easy management of the information. This normalization process can produce a loss of information and hence a lack of precision in the final results. In this paper, we shall present a type of multigranular linguistic contexts we shall call linguistic hierarchies term sets, such that, when we deal with multigranular linguistic information assessed in these structures we can unify the information assessed in them without loss of information. To do so, we shall use the 2-tuple linguistic representation model. Afterwards we shall develop a linguistic decision model dealing with multigranular linguistic contexts and apply it to a multi-expert decision-making problem.

OBJECTIVES: To assess the association between gender and suicide attempt/death and identify gender-specific risk/protective factors in adolescents/young adults. METHODS: Systematic review (5 databases until January 2017). Population-based longitudinal studies considering non-clinical populations, aged 12-26 years, assessing associations between gender and suicide attempts/death, or evaluating their gender risk/protective factors, were included. Random effect meta-analyses were performed. RESULTS: Sixty-seven studies were included. Females presented higher risk of suicide attempt (OR 1.96, 95% CI 1.54-2.50), and males for suicide death (HR 2.50, 95% CI 1.8-3.6). Common risk factors of suicidal behaviors for both genders are previous mental or substance abuse disorder and exposure to interpersonal violence. Female-specific risk factors for suicide attempts are eating disorder, posttraumatic stress disorder, bipolar disorder, being victim of dating violence, depressive symptoms, interpersonal problems and previous abortion. Male-specific risk factors for suicide attempt are disruptive behavior/conduct problems, hopelessness, parental separation/divorce, friend's suicidal behavior, and access to means. Male-specific risk factors for suicide death are drug abuse, externalizing disorders, and access to means. For females, no risk factors for suicide death were studied. CONCLUSIONS: More evidence about female-specific risk/protective factors of suicide death, for adolescent/young adults, is needed.

The Likert-type format is one of the most widely used in all types of scales in the field of social sciences. Nevertheless, there is no definitive agreement on the number of response categories that optimizes the psychometric properties of the scales. The aim of the present work is to determine in a systematic fashion the number of response alternatives that maximizes the fundamental psychometric properties of a scale: reliability and validity. The study is carried out with data simulated using the Monte Carlo method. We simulate responses to 30 items with correlations between them ranging from 0.2 to 0.9. We also manipulate sample size, analyzing four different sizes: 50, 100, 200, and 500 cases. The number of response options employed ranges from two to nine. The results show that as the number of response alternatives increases, both reliability and validity improve. The optimum number of alternatives is between four and seven. With fewer than four alternatives the reliability and validity decrease, and from seven alternatives onwards psychometric properties of the scale scarcely increase further. Some applied implications of the results are discussed.

Covering: up to June 2020Ribosomally-synthesized and post-translationally modified peptides (RiPPs) are a large group of natural products. A community-driven review in 2013 described the emerging commonalities in the biosynthesis of RiPPs and the opportunities they offered for bioengineering and genome mining. Since then, the field has seen tremendous advances in understanding of the mechanisms by which nature assembles these compounds, in engineering their biosynthetic machinery for a wide range of applications, and in the discovery of entirely new RiPP families using bioinformatic tools developed specifically for this compound class. The First International Conference on RiPPs was held in 2019, and the meeting participants assembled the current review describing new developments since 2013. The review discusses the new classes of RiPPs that have been discovered, the advances in our understanding of the installation of both primary and secondary post-translational modifications, and the mechanisms by which the enzymes recognize the leader peptides in their substrates. In addition, genome mining tools used for RiPP discovery are discussed as well as various strategies for RiPP engineering. An outlook section presents directions for future research.

Abstract Data scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate data to train DL frameworks. Usually, manual labeling is needed to provide labeled data, which typically involves human annotators with a vast background of knowledge. This annotation process is costly, time-consuming, and error-prone. Usually, every DL framework is fed by a significant amount of labeled data to automatically learn representations. Ultimately, a larger amount of data would generate a better DL model and its performance is also application dependent. This issue is the main barrier for many applications dismissing the use of DL. Having sufficient data is the first step toward any successful and trustworthy DL application. This paper presents a holistic survey on state-of-the-art techniques to deal with training DL models to overcome three challenges including small, imbalanced datasets, and lack of generalization. This survey starts by listing the learning techniques. Next, the types of DL architectures are introduced. After that, state-of-the-art solutions to address the issue of lack of training data are listed, such as Transfer Learning (TL), Self-Supervised Learning (SSL), Generative Adversarial Networks (GANs), Model Architecture (MA), Physics-Informed Neural Network (PINN), and Deep Synthetic Minority Oversampling Technique (DeepSMOTE). Then, these solutions were followed by some related tips about data acquisition needed prior to training purposes, as well as recommendations for ensuring the trustworthiness of the training dataset. The survey ends with a list of applications that suffer from data scarcity, several alternatives are proposed in order to generate more data in each application including Electromagnetic Imaging (EMI), Civil Structural Health Monitoring, Medical imaging, Meteorology, Wireless Communications, Fluid Mechanics, Microelectromechanical system, and Cybersecurity. To the best of the authors’ knowledge, this is the first review that offers a comprehensive overview on strategies to tackle data scarcity in DL.

The nearest neighbor classifier is one of the most used and well-known techniques for performing recognition tasks. It has also demonstrated itself to be one of the most useful algorithms in data mining in spite of its simplicity. However, the nearest neighbor classifier suffers from several drawbacks such as high storage requirements, low efficiency in classification response, and low noise tolerance. These weaknesses have been the subject of study for many researchers and many solutions have been proposed. Among them, one of the most promising solutions consists of reducing the data used for establishing a classification rule (training data) by means of selecting relevant prototypes. Many prototype selection methods exist in the literature and the research in this area is still advancing. Different properties could be observed in the definition of them, but no formal categorization has been established yet. This paper provides a survey of the prototype selection methods proposed in the literature from a theoretical and empirical point of view. Considering a theoretical point of view, we propose a taxonomy based on the main characteristics presented in prototype selection and we analyze their advantages and drawbacks. Empirically, we conduct an experimental study involving different sizes of data sets for measuring their performance in terms of accuracy, reduction capabilities, and runtime. The results obtained by all the methods studied have been verified by nonparametric statistical tests. Several remarks, guidelines, and recommendations are made for the use of prototype selection for nearest neighbor classification.

Abstract The Iberian Peninsula precipitation and river flow regimes are characterized by large values of inter‐annual variability, with large disparities between wet and dry years, especially in southern Iberia. This situation is a major problem for water resources management in general, and for the production of hydroelectricity in particular. Hydroelectric production represents, in an average year of precipitation, 20% of the total Spanish electricity production (and 35% for Portuguese production). Its absolute value, however, can vary by a factor of three between wet and dry years. We have assessed the impact of the North Atlantic oscillation (NAO) on winter precipitation and river flow regimes for the three main international Iberian river basins, namely the Douro (north), the Tejo (centre) and the Guadiana (south). Results show that the large inter‐annual variability in the flows of these three rivers is largely modulated by the NAO phenomenon. Throughout most of the 20th century, the January‐to‐March river flow is better correlated with the December to February (DJF) NAO index than is the simultaneous (DJF) river flow. Correlation values for the period 1973–98 are highly significant (−0.76 for Douro, −0.77 for Tejo and −0.79 for Guadiana), being consistently of higher magnitude than those obtained over previous decades. This impact of the NAO on winter river flow was quantified in terms of total Spanish potential hydroelectricity production. The important control exerted by the NAO and the recent positive trend in the NAO index contribute to a significant decrease in the available flow. This reduction represents an important hazard for the two Iberian economies because of its negative impact on water‐dependent resources, such as intensive agriculture and hydroelectric power production. Copyright © 2004 Royal Meteorological Society

The group decision-making framework with linguistic preference relations is studied. In this context, we assume that there exist several experts who may have different background and knowledge to solve a particular problem and, therefore, different linguistic term sets (multigranular linguistic information) could be used to express their opinions. The aim of this paper is to present a model of consensus support system to assist the experts in all phases of the consensus reaching process of group decision-making problems with multigranular linguistic preference relations. This consensus support system model is based on i) a multigranular linguistic methodology, ii) two consensus criteria, consensus degrees and proximity measures, and iii) a guidance advice system. The multigranular linguistic methodology permits the unification of the different linguistic domains to facilitate the calculus of consensus degrees and proximity measures on the basis of experts' opinions. The consensus degrees assess the agreement amongst all the experts' opinions, while the proximity measures are used to find out how far the individual opinions are from the group opinion. The guidance advice system integrated in the consensus support system model acts as a feedback mechanism, and it is based on a set of advice rules to help the experts change their opinions and to find out which direction that change should follow in order to obtain the highest degree of consensus possible. There are two main advantages provided by this model of consensus support system. Firstly, its ability to cope with group decision-making problems with multigranular linguistic preference relations, and, secondly, the figure of the moderator, traditionally presents in the consensus reaching process, is replaced by the guidance advice system, and in such a way, the whole group decision-making process is automated