Showing papers by "University of Extremadura published in 2021"

Guidelines for the use and interpretation of assays for monitoring autophagy (4th edition)

Abstract: In 2008, we published the first set of guidelines for standardizing research in autophagy. Since then, this topic has received increasing attention, and many scientists have entered the field. Our knowledge base and relevant new technologies have also been expanding. Thus, it is important to formulate on a regular basis updated guidelines for monitoring autophagy in different organisms. Despite numerous reviews, there continues to be confusion regarding acceptable methods to evaluate autophagy, especially in multicellular eukaryotes. Here, we present a set of guidelines for investigators to select and interpret methods to examine autophagy and related processes, and for reviewers to provide realistic and reasonable critiques of reports that are focused on these processes. These guidelines are not meant to be a dogmatic set of rules, because the appropriateness of any assay largely depends on the question being asked and the system being used. Moreover, no individual assay is perfect for every situation, calling for the use of multiple techniques to properly monitor autophagy in each experimental setting. Finally, several core components of the autophagy machinery have been implicated in distinct autophagic processes (canonical and noncanonical autophagy), implying that genetic approaches to block autophagy should rely on targeting two or more autophagy-related genes that ideally participate in distinct steps of the pathway. Along similar lines, because multiple proteins involved in autophagy also regulate other cellular pathways including apoptosis, not all of them can be used as a specific marker for bona fide autophagic responses. Here, we critically discuss current methods of assessing autophagy and the information they can, or cannot, provide. Our ultimate goal is to encourage intellectual and technical innovation in the field.

Image Segmentation Using Deep Learning: A Survey.

Abstract: Image segmentation is a key task in computer vision and image processing with important applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among others, and numerous segmentation algorithms are found in the literature. Against this backdrop, the broad success of Deep Learning (DL) has prompted the development of new image segmentation approaches leveraging DL models. We provide a comprehensive review of this recent literature, covering the spectrum of pioneering efforts in semantic and instance segmentation, including convolutional pixel-labeling networks, encoder-decoder architectures, multiscale and pyramid-based approaches, recurrent networks, visual attention models, and generative models in adversarial settings. We investigate the relationships, strengths, and challenges of these DL-based segmentation models, examine the widely used datasets, compare performances, and discuss promising research directions.

Graph Convolutional Networks for Hyperspectral Image Classification

Abstract: Convolutional neural networks (CNNs) have been attracting increasing attention in hyperspectral (HS) image classification due to their ability to capture spatial–spectral feature representations. Nevertheless, their ability in modeling relations between the samples remains limited. Beyond the limitations of grid sampling, graph convolutional networks (GCNs) have been recently proposed and successfully applied in irregular (or nongrid) data representation and analysis. In this article, we thoroughly investigate CNNs and GCNs (qualitatively and quantitatively) in terms of HS image classification. Due to the construction of the adjacency matrix on all the data, traditional GCNs usually suffer from a huge computational cost, particularly in large-scale remote sensing (RS) problems. To this end, we develop a new minibatch GCN (called miniGCN hereinafter), which allows to train large-scale GCNs in a minibatch fashion. More significantly, our miniGCN is capable of inferring out-of-sample data without retraining networks and improving classification performance. Furthermore, as CNNs and GCNs can extract different types of HS features, an intuitive solution to break the performance bottleneck of a single model is to fuse them. Since miniGCNs can perform batchwise network training (enabling the combination of CNNs and GCNs), we explore three fusion strategies: additive fusion, elementwise multiplicative fusion, and concatenation fusion to measure the obtained performance gain. Extensive experiments, conducted on three HS data sets, demonstrate the advantages of miniGCNs over GCNs and the superiority of the tested fusion strategies with regard to the single CNN or GCN models. The codes of this work will be available at https://github.com/danfenghong/IEEE_TGRS_GCN for the sake of reproducibility.

Electric Vehicle Charging Infrastructure: From Grid to Battery

Abstract: Electrification has been a key component of technological progress and economic development since the industrial revolution It has improved living conditions, spurred innovation, and increased efficiency across all sectors of our economy and all aspects of our lives During the coming decades, electrification is expected to reach further and deeper into the transportation, building, and industry sectors, mainly motivated by the energy transition to a zero-carbonemission-based economy to mitigate climate change

Recent smell loss is the best predictor of COVID-19 among individuals with recent respiratory symptoms.

Abstract: In a preregistered, cross-sectional study, we investigated whether olfactory loss is a reliable predictor of COVID-19 using a crowdsourced questionnaire in 23 languages to assess symptoms in individuals self-reporting recent respiratory illness. We quantified changes in chemosensory abilities during the course of the respiratory illness using 0-100 visual analog scales (VAS) for participants reporting a positive (C19+; n = 4148) or negative (C19-; n = 546) COVID-19 laboratory test outcome. Logistic regression models identified univariate and multivariate predictors of COVID-19 status and post-COVID-19 olfactory recovery. Both C19+ and C19- groups exhibited smell loss, but it was significantly larger in C19+ participants (mean ± SD, C19+: -82.5 ± 27.2 points; C19-: -59.8 ± 37.7). Smell loss during illness was the best predictor of COVID-19 in both univariate and multivariate models (ROC AUC = 0.72). Additional variables provide negligible model improvement. VAS ratings of smell loss were more predictive than binary chemosensory yes/no-questions or other cardinal symptoms (e.g., fever). Olfactory recovery within 40 days of respiratory symptom onset was reported for ~50% of participants and was best predicted by time since respiratory symptom onset. We find that quantified smell loss is the best predictor of COVID-19 amongst those with symptoms of respiratory illness. To aid clinicians and contact tracers in identifying individuals with a high likelihood of having COVID-19, we propose a novel 0-10 scale to screen for recent olfactory loss, the ODoR-19. We find that numeric ratings ≤2 indicate high odds of symptomatic COVID-19 (4 < OR < 10). Once independently validated, this tool could be deployed when viral lab tests are impractical or unavailable.

Dynamic capabilities and SME performance: The moderating effect of market orientation

Abstract: We investigate how the four dimensions of the dynamic capabilities (DC) construct (sensing, learning, integrating, and coordinating) individually affect firm performance and the moderating role of ...

Impact of COVID-19 Confinement on Physical Activity and Sedentary Behaviour in Spanish University Students: Role of Gender.

Abstract: During the COVID-19 pandemic, entire populations were instructed to live in home-confinement to prevent the expansion of the disease. Spain was one of the countries with the strictest conditions, as outdoor physical activity was banned for nearly two months. This study aimed to analyse the changes in physical activity and sedentary behaviours in Spanish university students before and during the confinement by COVID-19 with special focus on gender. We also analysed enjoyment, the tools used and motivation and impediments for doing physical activity. An online questionnaire, which included the International Physical Activity Questionnaire Short Form and certain "ad hoc" questions, was designed. Students were recruited by distributing an invitation through the administrative channels of 16 universities and a total of 13,754 valid surveys were collected. Overall, university students reduced moderate (-29.5%) and vigorous (-18.3%) physical activity during the confinement and increased sedentary time (+52.7%). However, they spent more time on high intensity interval training (HIIT) (+18.2%) and mind-body activities (e.g., yoga) (+80.0%). Adaptation to the confinement, in terms of physical activity, was handled better by women than by men. These results will help design strategies for each gender to promote physical activity and reduce sedentary behaviour during confinement periods.

The origins and spread of domestic horses from the Western Eurasian steppes.

Abstract: Domestication of horses fundamentally transformed long-range mobility and warfare1. However, modern domesticated breeds do not descend from the earliest domestic horse lineage associated with archaeological evidence of bridling, milking and corralling2–4 at Botai, Central Asia around 3500 bc3. Other longstanding candidate regions for horse domestication, such as Iberia5 and Anatolia6, have also recently been challenged. Thus, the genetic, geographic and temporal origins of modern domestic horses have remained unknown. Here we pinpoint the Western Eurasian steppes, especially the lower Volga-Don region, as the homeland of modern domestic horses. Furthermore, we map the population changes accompanying domestication from 273 ancient horse genomes. This reveals that modern domestic horses ultimately replaced almost all other local populations as they expanded rapidly across Eurasia from about 2000 bc, synchronously with equestrian material culture, including Sintashta spoke-wheeled chariots. We find that equestrianism involved strong selection for critical locomotor and behavioural adaptations at the GSDMC and ZFPM1 genes. Our results reject the commonly held association7 between horseback riding and the massive expansion of Yamnaya steppe pastoralists into Europe around 3000 bc8,9 driving the spread of Indo-European languages10. This contrasts with the scenario in Asia where Indo-Iranian languages, chariots and horses spread together, following the early second millennium bc Sintashta culture11,12. Analysis of 273 ancient horse genomes reveals that modern domestic horses originated in the Western Eurasian steppes, especially the lower Volga-Don region.

Effect of COVID-19 on Health-Related Quality of Life in Adolescents and Children: A Systematic Review.

Abstract: The aim of the present systematic review was to assess and provide an up-to-date analysis of the impact of coronavirus disease 2019 (COVID-19) pandemic on the health-related quality of life (HRQoL) of children and adolescents. Thus, an electronic search of the literature, in two well-known databases (PubMed and Web of Science), was performed until February 2021 (without date restriction). PRISMA guideline methodology was employed and data regarding the HRQoL were extracted from eligible studies. Articles were included if they met the following inclusion criteria: (a) children and/or adolescent population (4 to 19 years old); (b) HRQoL as a main assessment; (c) German, Spanish, Portuguese, French, and English language; and (d) pre-pandemic and during pandemic HRQoL data. Following the initial search, 241 possible related articles were identified. A total of 79 articles were identified as duplicates. Moreover, 129 articles were removed after reading the title and abstract. Of the remaining 33 articles, 27 were removed since they were not focused on children or adolescents (n = 19), articles did not report pre- and post- pandemic HRQoL values (n = 6), articles were not focused on HRQoL (n = 6), and one article was an editorial. Finally, six studies fulfilled the inclusion criteria and, therefore, were included in the systematic review. A total of 3177 children and/or adolescents during COVID-19 were included in this systematic review. Three articles showed that COVID-19 pandemic significantly impacted the HRQoL of children and adolescents, and another did not report comparison between pre- and during COVID-19 pandemic, although a reduction in the HRQoL can be observed. Nevertheless, two articles did not find significant changes and another one did not report p-values. Regarding sex differences, only two studies analyzed this topic, observing no differences between girls and boys in the impact of COVID-19 pandemic on HRQoL. Taking into account these results, this systematic review might confirm that COVID-19 has a negative impact on the HRQoL of children and/or adolescents.

Deep Unsupervised Embedding for Remotely Sensed Images Based on Spatially Augmented Momentum Contrast

Abstract: Convolutional neural networks (CNNs) have achieved great success when characterizing remote sensing (RS) images. However, the lack of sufficient annotated data (together with the high complexity of the RS image domain) often makes supervised and transfer learning schemes limited from an operational perspective. Despite the fact that unsupervised methods can potentially relieve these limitations, they are frequently unable to effectively exploit relevant prior knowledge about the RS domain, which may eventually constrain their final performance. In order to address these challenges, this article presents a new unsupervised deep metric learning model, called spatially augmented momentum contrast (SauMoCo), which has been specially designed to characterize unlabeled RS scenes. Based on the first law of geography, the proposed approach defines spatial augmentation criteria to uncover semantic relationships among land cover tiles. Then, a queue of deep embeddings is constructed to enhance the semantic variety of RS tiles within the considered contrastive learning process, where an auxiliary CNN model serves as an updating mechanism. Our experimental comparison, including different state-of-the-art techniques and benchmark RS image archives, reveals that the proposed approach obtains remarkable performance gains when characterizing unlabeled scenes since it is able to substantially enhance the discrimination ability among complex land cover categories. The source codes of this article will be made available to the RS community for reproducible research.

Recent advances in directional statistics

Abstract: Mainstream statistical methodology is generally applicable to data observed in Euclidean space. There are, however, numerous contexts of considerable scientific interest in which the natural supports for the data under consideration are Riemannian manifolds like the unit circle, torus, sphere, and their extensions. Typically, such data can be represented using one or more directions, and directional statistics is the branch of statistics that deals with their analysis. In this paper, we provide a review of the many recent developments in the field since the publication of Mardia and Jupp (Wiley 1999), still the most comprehensive text on directional statistics. Many of those developments have been stimulated by interesting applications in fields as diverse as astronomy, medicine, genetics, neurology, space situational awareness, acoustics, image analysis, text mining, environmetrics, and machine learning. We begin by considering developments for the exploratory analysis of directional data before progressing to distributional models, general approaches to inference, hypothesis testing, regression, nonparametric curve estimation, methods for dimension reduction, classification and clustering, and the modelling of time series, spatial and spatio-temporal data. An overview of currently available software for analysing directional data is also provided, and potential future developments are discussed.

Ghostnet for Hyperspectral Image Classification

Abstract: Hyperspectral imaging (HSI) is a competitive remote sensing technique in several fields, from Earth observation to health, robotic vision, and quality control. Each HSI scene contains hundreds of (narrow) contiguous spectral bands. The amount of data generated by HSI devices is often both a solution and a problem for a given application. Extracting information from HSI data cubes is a complex and computationally demanding problem. To tackle this challenge, convolutional neural networks (CNNs) have been widely applied to HSI classification. Despite their success, CNNs are computationally demanding algorithms with high memory requirements due to their large number of internal parameters. The recent interest in using HSI devices in mobile and embedded systems for air and spaceborne platforms turned the attention to computationally lightweight CNN architectures with good classification accuracy. In this article, we present a contribution in that direction. The proposed method combines the ghost-module architecture with a CNN-based HSI classifier to reduce the computational cost and, simultaneously, achieves an efficient classification method with high performance. Our new method is evaluated against nine standard HSI classifiers, and five improved deep-CNN architectures, over five commonly used HSI data sets for algorithm benchmarking. Conducted experiments show that the proposed method exhibits similar or better performance than the other classifiers, achieving top values in the considered performance metrics--even for very limited training sets--and, most importantly, with a fraction of the computational cost. Our novel approach for HSI classification is a strong candidate for implementation on systems with limited computational resources.

Tourism and Sustainability in Times of COVID-19: The Case of Spain.

Abstract: The aim of this paper is to study the effects of the spread of the COVID-19 virus in different regions and its impact on the economy and regional tourist flows. To this end, the researchers have been guided by a set of propositions which they have tried to demonstrate with the results obtained. This research shows that the impact of the pandemic is still being evaluated. The analysis of the relationship between the tourism sector and the pandemic outbreak in Spain provides an instructive case study to assist tourism in its recovery process. The paper delves into the impacts on the main Spanish touristic regions during the pandemic and providing implications for tourism recovery. In Spain, the tourism sector is of major economic importance, becoming one of the most vulnerable countries when crisis affects this industry. The negative image of the country due to the high infection rates has had a negative impact on travel and tourism. The Balearic Islands have been the most affected region with an 87% decrease in tourist visitors. The trips made by Spanish residents inside the Spanish territory shows the first increase found in the series analyzed. Domestic tourism not only represents an opportunity for all regions in this critical situation, but the types of accommodation also play a key role.

Micromechanics of Machining and Wear in Hard and Brittle Materials.

Abstract: Hard and brittle solids with covalent/ionic bonding are used in a wide range of modern‐day manufacturing technologies. Optimization of a shaping process can shorten manufacturing time and cost of component production, and at the same time extend component longevity. The same process can contribute to wear and fatigue degradation in service. Educated development of advanced finishing protocols for this class of solids requires a comprehensive understanding of damage mechanisms at small‐scale contacts from a materials perspective. The basic science of attendant deformation and removal modes in contact events is here analyzed and discussed in the context of brittle and ductile machining and severe and mild wear. Essentials of brittle–ductile transitions in micro‐ and nano‐indentation fields are outlined, with distinctions between blunt and sharp contacts and axial and sliding loading. The central role of microstructure in material removal modes is highlighted. Pathways to future research—experimental, analytical, and computational—are indicated.

Training During the COVID-19 Lockdown: Knowledge, Beliefs, and Practices of 12,526 Athletes from 142 Countries and Six Continents

Abstract: Our objective was to explore the training-related knowledge, beliefs, and practices of athletes and the influence of lockdowns in response to the coronavirus disease 2019 (COVID-19) pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Athletes (n = 12,526, comprising 13% world class, 21% international, 36% national, 24% state, and 6% recreational) completed an online survey that was available from 17 May to 5 July 2020 and explored their training behaviors (training knowledge, beliefs/attitudes, and practices), including specific questions on their training intensity, frequency, and session duration before and during lockdown (March–June 2020). Overall, 85% of athletes wanted to “maintain training,” and 79% disagreed with the statement that it is “okay to not train during lockdown,” with a greater prevalence for both in higher-level athletes. In total, 60% of athletes considered “coaching by correspondence (remote coaching)” to be sufficient (highest amongst world-class athletes). During lockdown, < 40% were able to maintain sport-specific training (e.g., long endurance [39%], interval training [35%], weightlifting [33%], plyometric exercise [30%]) at pre-lockdown levels (higher among world-class, international, and national athletes), with most (83%) training for “general fitness and health maintenance” during lockdown. Athletes trained alone (80%) and focused on bodyweight (65%) and cardiovascular (59%) exercise/training during lockdown. Compared with before lockdown, most athletes reported reduced training frequency (from between five and seven sessions per week to four or fewer), shorter training sessions (from ≥ 60 to < 60 min), and lower sport-specific intensity (~ 38% reduction), irrespective of athlete classification. COVID-19-related lockdowns saw marked reductions in athletic training specificity, intensity, frequency, and duration, with notable within-sample differences (by athlete classification). Higher classification athletes had the strongest desire to “maintain” training and the greatest opposition to “not training” during lockdowns. These higher classification athletes retained training specificity to a greater degree than others, probably because of preferential access to limited training resources. More higher classification athletes considered “coaching by correspondence” as sufficient than did lower classification athletes. These lockdown-mediated changes in training were not conducive to maintenance or progression of athletes’ physical capacities and were also likely detrimental to athletes’ mental health. These data can be used by policy makers, athletes, and their multidisciplinary teams to modulate their practice, with a degree of individualization, in the current and continued pandemic-related scenario. Furthermore, the data may drive training-related educational resources for athletes and their multidisciplinary teams. Such upskilling would provide athletes with evidence to inform their training modifications in response to germane situations (e.g., COVID related, injury, and illness).

Graph Relation Network: Modeling Relations Between Scenes for Multilabel Remote-Sensing Image Classification and Retrieval

Abstract: Due to the proliferation of large-scale remote-sensing (RS) archives with multiple annotations, multilabel RS scene classification and retrieval are becoming increasingly popular. Although some recent deep learning-based methods are able to achieve promising results in this context, the lack of research on how to learn embedding spaces under the multilabel assumption often makes these models unable to preserve complex semantic relations pervading aerial scenes, which is an important limitation in RS applications. To fill this gap, we propose a new graph relation network (GRN) for multilabel RS scene categorization. Our GRN is able to model the relations between samples (or scenes) by making use of a graph structure which is fed into network learning. For this purpose, we define a new loss function called scalable neighbor discriminative loss with binary cross entropy (SNDL-BCE) that is able to embed the graph structures through the networks more effectively. The proposed approach can guide deep learning techniques (such as convolutional neural networks) to a more discriminative metric space, where semantically similar RS scenes are closely embedded and dissimilar images are separated from a novel multilabel viewpoint. To achieve this goal, our GRN jointly maximizes a weighted leave-one-out $K$ -nearest neighbors ( $K$ NN) score in the training set, where the weight matrix describes the contributions of the nearest neighbors associated with each RS image on its class decision, and the likelihood of the class discrimination in the multilabel scenario. An extensive experimental comparison, conducted on three multilabel RS scene data archives, validates the effectiveness of the proposed GRN in terms of $K$ NN classification and image retrieval. The codes of this article will be made publicly available for reproducible research in the community.

Impact of contextual variables on the representative external load profile of Spanish professional soccer match-play: A full season study

Abstract: The aims of this study were to: (1) identify the representative external load profile of match-play in Spanish professional soccer players by principal components analysis (PCA), and (2) analyse th...

Gamification and active learning in higher education: is it possible to match digital society, academia and students' interests?

Abstract: This study aims to examine whether it is possible to match digital society, academia and students interests in higher education by testing to what extent the introduction of gamification into active learning setups affects the skills development demanded by the workplace of the digital society of the twenty-first century, the academic achievement standards claimed by the academia, and the satisfaction with the learning process required by the students. Our results provide statistically significant empirical evidence, concluding that the generation of a co-creative and empowered gameful experience that supports students' overall value creation yields to satisfactory active learning setups without any loss of academic achievement, and allowing to develop a series of skills especially relevant for twenty-first century professionals.

Generative Adversarial Minority Oversampling for Spectral-Spatial Hyperspectral Image Classification

Abstract: Recently, convolutional neural networks (CNNs) have exhibited commendable performance for hyperspectral image (HSI) classification. Generally, an important number of samples are needed for each class to properly train CNNs. However, existing HSI data sets suffer from a significant class imbalance problem, where many classes do not have enough samples to characterize the spectral information. The performance of existing CNN models is biased toward the majority classes, which possess more samples for the training. This article addresses this issue of imbalanced data in HSI classification. In particular, a new 3D-HyperGAMO model is proposed, which uses generative adversarial minority oversampling. The proposed 3D-HyperGAMO automatically generates more samples for minority classes at training time, using the existing samples of that class. The samples are generated in the form of a 3-D hyperspectral patch. A different classifier from the generator and the discriminator is used in the 3D-HyperGAMO model, which is trained using both original and generated samples to determine the classes of newly generated samples to which they actually belong. The generated data are combined classwise with the original training data set to learn the network parameters of the class. Finally, the trained 3-D classifier network validates the performance of the model using the test set. Four benchmark HSI data sets, namely, Indian Pines (IP), Kennedy Space Center (KSC), University of Pavia (UP), and Botswana (BW), have been considered in our experiments. The proposed model shows outstanding data generation ability during the training, which significantly improves the classification performance over the considered data sets. The source code is available publicly at https://github.com/mhaut/3D-HyperGAMO.

The Impact of the COVID-19 Pandemic on Social, Health, and Economy

Abstract: In late December 2019, a series of acute atypical respiratory disease occurred in Wuhan, China, which rapidly spread to other areas worldwide. It was soon discovered that a novel coronavirus was responsible, named the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2, 2019-nCoV). The impact of the COVID-19 pandemic on the population’s health is unprecedented in recent years and the impact on a social level even more so. The COVID-19 pandemic is the most large-scale pandemic on earth this century, and the impact in all life sectors is devasting and directly affected human activity in the first wave. The impact on the economy, social care systems, and human relationships is causing an unprecedented global crisis. SARS-CoV-2 has a strong direct acute impact on population health, not only at the physiological level but also at the psychological level for those who suffer it, those close to them, and the general population, who suffer from the social consequences of the pandemic. In this line, the economic recession increased, even more, the social imbalance and inequity, hitting the most vulnerable families, and creating a difficult context for public institutions to address. We are facing one of the greatest challenges of social intervention, which requires fast, effective, and well-coordinated responses from public institutions, the private sector, and non-governmental organizations to serve an increasingly hopeless population with increasingly urgent needs. Long-term legislation is necessary to reduce the vulnerability of the less fortunate, as well as to analyze the societal response to improve the social organization management of available resources. Therefore, in this scoping review, a consensus and critical review were performed using both primary sources, such as scientific articles, and secondary ones, such as bibliographic indexes, web pages, and databases. The main search engines were PubMed, SciELO, and Google Scholar. The method was a narrative literature review of the available literature. The aim was to assess the effects of the COVID-19 pandemic on population health, where the possible interventions at the health level are discussed, the impact in economic and social areas, and the government and health systems interventions in the pandemic, and finally, possible economic models for the recovery of the crisis are proposed.

Scheduling-Guided Automatic Processing of Massive Hyperspectral Image Classification on Cloud Computing Architectures

Abstract: The large data volume and high algorithm complexity of hyperspectral image (HSI) problems have posed big challenges for efficient classification of massive HSI data repositories. Recently, cloud computing architectures have become more relevant to address the big computational challenges introduced in the HSI field. This article proposes an acceleration method for HSI classification that relies on scheduling metaheuristics to automatically and optimally distribute the workload of HSI applications across multiple computing resources on a cloud platform. By analyzing the procedure of a representative classification method, we first develop its distributed and parallel implementation based on the MapReduce mechanism on Apache Spark. The subtasks of the processing flow that can be processed in a distributed way are identified as divisible tasks. The optimal execution of this application on Spark is further formulated as a divisible scheduling framework that takes into account both task execution precedences and task divisibility when allocating the divisible and indivisible subtasks onto computing nodes. The formulated scheduling framework is an optimization procedure that searches for optimized task assignments and partition counts for divisible tasks. Two metaheuristic algorithms are developed to solve this divisible scheduling problem. The scheduling results provide an optimized solution to the automatic processing of HSI big data on clouds, improving the computational efficiency of HSI classification by exploring the parallelism during the parallel processing flow. Experimental results demonstrate that our scheduling-guided approach achieves remarkable speedups by facilitating the automatic processing of HSI classification on Spark, and is scalable to the increasing HSI data volume.

Accelerating Convolutional Neural Network-Based Hyperspectral Image Classification by Step Activation Quantization

Abstract: Convolutional neural networks (CNNs) have achieved excellent feature extraction capabilities in remotely sensed hyperspectral image (HSI) classification. This is due to their ability to learn representative spatial and spectral features. However, it is difficult for conventional computers to classify HSIs quickly enough for practical use in many applications, mainly because of the large number of calculations and parameters needed by deep learning-based methods. Although several weight quantization methods achieved remarkable results in network compression, the network acceleration effect is still not significant because a full exploration of the potential of network acceleration brought by network weight quantization is still absent from the literature. In this article, a new step activation quantization method is proposed to constrain the input of the network layer of the CNN so that the data can be represented by low-bit integers. As a result, floating-point operations can be replaced with integer operations to greatly accelerate the forward (inference) step of the network. Specifically, nonlinear uniform quantization is adopted in this work to restrain the input of the CNN in the forward inference of the step activation quantization layer, and two functions (constant and tanh-like) are used in the backpropagation step to avoid gradient vanishing and noise. Our newly proposed step activation quantization acceleration method is applied to a CNN for HSI with two well-known benchmark data sets and the experimental results demonstrate that the proposed method is very effective in terms of both memory savings and computation acceleration, with only a slight decrease in classification accuracy. Specifically, our method reduces memory requirements in 13.6x and obtains around 10x speedup with regard to the original real-valued network version.

Deep Autoencoders With Multitask Learning for Bilinear Hyperspectral Unmixing

Abstract: Hyperspectral unmixing is an important problem for remotely sensed data interpretation. It amounts at estimating the spectral signatures of the pure spectral constituents in the scene (endmembers) and their corresponding subpixel fractional abundances. Although the unmixing problem is inherently nonlinear (due to multiple scattering), the nonlinear unmixing of hyperspectral data has been a very challenging problem. This is because nonlinear models require detailed knowledge about the physical interactions between the sunlight scattered by multiple materials. In turn, bilinear mixture models (BMMs) can reach good accuracy with a relatively simple model for scattering. In this article, we develop a new BMM and a corresponding unsupervised unmixing approach which consists of two main steps. In the first step, a deep autoencoder is used to linearly estimate the endmember signatures and their associated abundance fractions. The second step refines the initial (linear) estimates using a bilinear model, in which another deep autoencoder (with a low-rank assumption) is adapted to model second-order scattering interactions. It should be noted that in our developed BMM model, the two deep autoencoders are trained in a mutually interdependent manner under the multitask learning framework, and the relative reconstruction error is used as the stopping criterion. The effectiveness of the proposed method is evaluated using both synthetic and real hyperspectral data sets. Our experimental results indicate that the proposed approach can reasonably estimate the nature of nonlinear interactions in real scenarios. Compared with other state-of-the-art unmixing algorithms, the proposed approach demonstrates very competitive performance.

Associations Between Variations in Accumulated Workload and Physiological Variables in Young Male Soccer Players Over the Course of a Season

Abstract: This study sought to analyze the relationship between in-season training workload with changes in aerobic power (VO2m ax ), maximum and resting heart rate (HR max and HR rest ), linear sprint medium (LSM), and short test (LSS), in soccer players younger than 16 years (under-16 soccer players). We additionally aimed to explain changes in fitness levels during the in-season through regression models, considering accumulated load, baseline levels, and peak height velocity (PHV) as predictors. Twenty-three male sub-elite soccer players aged 15.5 ± 0.2 years (PHV: 13.6 ± 0.4 years; body height: 172.7 ± 4.2 cm; body mass: 61.3 ± 5.6 kg; body fat: 13.7% ± 3.9%; VO2m ax : 48.4 ± 2.6 mL⋅kg-1⋅min-1), were tested three times across the season (i.e., early-season (EaS), mid-season (MiS), and end-season (EnS) for VO2m ax , HR max , LSM, and LSS. Aerobic and speed variables gradually improved over the season and had a strong association with PHV. Moreover, the HR max demonstrated improvements from EaS to EnS; however, this was more evident in the intermediate period (from EaS to MiS) and had a strong association with VO2m ax . Regression analysis showed significant predictions for VO2m ax [F ( 2, 20) = 8.18, p ≤ 0.001] with an R 2 of 0.45. In conclusion, the meaningful variation of youth players' fitness levels can be observed across the season, and such changes can be partially explained by the load imposed.

Morphological Convolutional Neural Networks for Hyperspectral Image Classification

Abstract: Convolutional neural networks (CNNs) have become quite popular for solving many different tasks in remote sensing data processing. The convolution is a linear operation, which extracts features from the input data. However, nonlinear operations are able to better characterize the internal relationships and hidden patterns within complex remote sensing data, such as hyperspectral images (HSIs). Morphological operations are powerful nonlinear transformations for feature extraction that preserve the essential characteristics of the image, such as borders, shape, and structural information. In this article, a new end-to-end morphological deep learning framework (called MorphConvHyperNet ) is introduced. The proposed approach efficiently models nonlinear information during the training process of HSI classification. Specifically, our method includes spectral and spatial morphological blocks to extract relevant features from the HSI input data. These morphological blocks consist of two basic 2-D morphological operators (erosion and dilation) in the respective layers, followed by a weighted combination of the feature maps. Both layers can successfully encode the nonlinear information related to shape and size, playing an important role in classification performance. Our experimental results, obtained on five widely used HSIs, reveal that our newly proposed MorphConvHyperNet offers comparable (and even superior) performance when compared to traditional 2-D and 3-D CNNs for HSI classification.