Search

Since the outbreak of COVID-19, many efforts have been made to utilize the respiratory sounds and coughs collected by smartphones for training Machine Learning models to classify and distinguish COVID-19 sounds from healthy ones. Embedding those models into mobile applications or Internet of things devices can make effective COVID-19 pre-screening tools afforded by anyone anywhere. Most of the previous researchers trained their classifiers with respiratory sounds such as breathing or coughs, and they achieved promising results. We claim that using special voice patterns besides other respiratory sounds can achieve better performance. In this study, we used the Coswara dataset where each user has recorded 9 different types of sounds as cough, breathing, and speech labeled with COVID-19 status. A combination of models trained on different sounds can diagnose COVID-19 more accurately than a single model trained on cough or breathing only. Our results show that using simple binary classifiers can achieve an AUC of 96.4% and an accuracy of 96% by averaging the predictions of multiple models trained and evaluated separately on different sound types. Finally, this study aims to draw attention to the importance of the human voice alongside other respiratory sounds for the sound-based COVID-19 diagnosis.

The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning. To address this problem, recent studies focus on the generation of high-quality missing annotations. In this study, we first specify that it is not enough to generate high-quality annotations using a single model, which looks only once for annotations. Through detailed experimental analyses, we further conclude that hard-label training is conducive for generating high-recall annotations, whereas soft-label training tends to obtain high-precision annotations. Inspired by the aspects mentioned above, we propose a dynamic supervisor framework that updates the annotations multiple times through multiple-updated submodels trained using hard and soft labels. In the final generated annotations, recall and precision improve significantly through the integration of hard-label training with soft-label training. Extensive experiments conducted on various dataset combination settings support our analyses and demonstrate the superior performance of the proposed dynamic supervisor.

In this Perspective, some of the criticisms which have been made concerning the use of oxidation states are addressed, particularly in the context of the teaching of inorganic chemistry. The Oxidation State method and the Covalent Bond Classification method are compared and contrasted, and it is concluded that while each method has its strengths and weaknesses, both are important in teaching and it should be recognized that no single model or method is appropriate in all circumstances.

This paper introduces techniques to restore super-resolution time delay estimation (TDE) of signals in multi-path environments using the Matrix Pencil Method (MPM). To verify the proposed algorithm, estimation errors are evaluated and compared with traditional Multiple Signal Classification (MUSIC) and cross-correlation approaches. TDE uses cross-correlation to produce measurements. Cross-correlation is based on a single model that considers the ideal environment. At the same time, the measurement precision starts to deteriorate as two or more signals are progressively entered at times shorter than the time interval, requiring super-resolution for accurate time delay measurement. The results of the proposed super-resolution MPM algorithm provide better performance over conventional methods by accurately identifying and quantifying all components to their resolution limits and solving closely spaced frequencies.

Traditional root-cause diagnosis methods analyze different faults independently, suffering from repetitive modeling efforts for each fault. Besides, they are disturbed by significant redundancy and...

Drought forecasting can effectively reduce the risk of drought. We proposed a hybrid model based on deep learning methods that integrates an autoregressive integrated moving average (ARIMA) model and a long short-term memory (LSTM) model to improve the accuracy of short-term drought prediction. Taking China as an example, this paper compares and analyzes the prediction accuracy of six drought prediction models, ARIMA, support vector regression (SVR), LSTM, ARIMA-SVR, least square-SVR (LS-SVR) and ARIMA-LSTM, for SPEI. The performance of all the models was compared using measures of persistence, such as the Nash-Sutcliffe efficiency (NSE) and so on. The results show that all three hybrid models (ARIMA-SVR, LS-SVR and ARIMA-LSTM) had higher prediction accuracy than the single model. (ARIMA, SVR and LSTM), for a given lead time, at different scales. the NSEs of the hybrid ARIMA-SVR, LS-SVR and ARIMA-LSTM models for the predicted SPEI1 are 0.043,0.168 and 0.368, respectively, and the NSEs of SPEI24 is 0.781, 0.543 and 0.93, respectively. This finding indicates that when the lead time remains unchanged, the prediction accuracy of the hybrid ARIMA-SVR, LS-SVR and ARIMA-LSTM models for the SPEI at various scales is gradually improved with increasing time scale, and the prediction accuracy of the model with a one-month lead time is higher than that of the model with a two-month lead time. In addition, the ARIMA-LSTM model has the highest prediction accuracy at the 6-, 12-, and 24-month scales, indicating that the model is more suitable for the forecasting of long-term drought in China.

The aim of this paper is to develop a system for drug–target interaction prediction using artificial intelligence which involves development of both machine learning and deep learning-based systems. In this paper, we use a convolutional neural network (CNN) model, to classify drug–target interactions between drug pairs. Applied to the DDI-Corpus dataset, the single CNN model achieve performance with an F1-score of 0.82 ± 0.012 for the single model and 0.81 ± 0.015 for the ensemble model using deep learning-based CNN with an approved accuracy of 96.72% which is an extra-ordinary achievement. This work has also been performed using the machine learning-based classifiers support vector machine (SVM). For machine learning-based implementation, drug-bank dataset was used for the training and testing. The main challenge when using machine learning for this purpose is the availability of negative DTI to train on. Training machine learning model, the SVM achieved an area under the ROC curve (AUC) of 0.753 ± 0.006, which taking the difference in computational resources into consideration compares well to the AUC of 0.886 ± 0.010 network-based state-of-the-art approach. We achieved and best accuracy of 93.76% using SVM after testing several times.

This work has been supported by the Marsden Fund grant VUW0813 (Royal Society of New Zealand to C.J.N.W.), a James Cook Fellowship (Royal Society of New Zealand) to C.J.N.W., and the ECLIPSE Programme, funded by the N.Z. Ministry of Business, Innovation and Employment. G.F.C. is supported by a NERC Standard Grant (NE/T000317/1), M.L.M. is supported by an NSF CAREER grant (EAR 2042662) and S.J.B. acknowledges Marsden Fund grant VUW1627.

Desde finales del siglo XIX, pero, sobre todo, desde el final de la Gran Guerra, el régimen parlamentario liberal sufrió, en la mayoría de las sociedades europeas, una profunda crisis de legitimidad. En esos momentos, las sociedades europeas experimentaron un proceso de «corporativización» que puso en cuestión la concepción liberal de la sociedad. Como alternativa al sistema todavía vigente, se propuso la alternativa corporativa, basada en la concepción orgánica de la sociedad y en la representación de intereses. Sin embargo, no puede hablarse de un único modelo de régimen corporativo; existen diversas variantes: la tradicionalista, la social católica, la liberal-organicista y la fascista. En ese sentido, puede distinguirse entre «corporativismo social» y «corporativismo de Estado». Como en el resto de Europa, España experimentó este proceso político-social de manera traumática.

In 2010, the European Parliament and the European Union adopted a directive on the protection of animals used for scientific purposes. The directive aims to protect animals in scientific research, with the final goal of complete replacement of procedures on live animals for scientific and educational purposes as soon as it is scientifically viable. Furthermore, the directive announces the implementation of the 3Rs principle: "When choosing methods, the principles of replacement, reduction and refinement should be implemented through a strict hierarchy of the requirement to use alternative methods." The visibility, accessibility, and the rapid growth of the chorioallantoic membrane (CAM) offers a clear advantage for various manipulations and for the simulation of different Bio-Barriers according to the 3R principle. The extensive vascularisation on the CAM provides an excellent substrate for the cultivation of tumour cells or tumour xenografts which could be used for the therapeutic evaluation of nanoscale drug delivery systems. The tumour can be targeted either by topical application, intratumoural injection or i.v. injection. Different application sites and biological barriers can be examined within a single model.

Current works on super-resolution have obtained satisfactory results since the advance of the convolution neural network. Nevertheless, most previous works use one network for one integer scale factor so ignore the super-resolution of the arbitrary scale factor. In this work, we propose a novel approach called Global Enhanced Upscale Network (GEUN) to tackle super-resolution with a single model adapting the arbitrary scale factor. In our GEUN, we propose the Global Enhanced Upscale module to replace the conventional upscale module. Our GEUN can upscale low-resolution images with an arbitrary scale factor through only one model. Extensive experimental results demonstrate the superiority of our GEUN.

Aiming at the problem that the single model of the traditional recommendation system cannot accurately capture user preferences, this paper proposes a hybrid movie recommendation system and optimization method based on weighted classification and user collaborative filtering algorithm. The sparse linear model is used as the basic recommendation model, and the local recommendation model is trained based on user clustering, and the top-N personalized recommendation of movies is realized by fusion with the weighted classification model. According to the item category preference, the scoring matrix is converted into a low-dimensional, dense item category preference matrix, multiple cluster centers are obtained, the distance between the target user and each cluster center is calculated, and the target user is classified into the closest cluster. Finally, the collaborative filtering algorithm is used to predict the scores for the unrated items of the target user to form a recommendation list. The items are clustered through the item category preference, and the high-dimensional rating matrix is converted into a low-dimensional item category preference matrix, which further reduces the sparsity of the data. Experiments based on the Douban movie dataset verify that the recommendation algorithm proposed in this article solves the shortcomings of a single algorithm model to a certain extent and improves the recommendation effect.

Background: Evaluating the quality of life patients with subacromial impingement syndrome is important for further treatments Aim: The aim of the study was to evaluate simultaneously the quality of life with subacromial impingement syndrome using different parameters in a single model. Material and Methods: Ninety patients diagnosed subacromial impingement syndrome were included in the study. Mental component score and physical component score were measured using SF-36 in the assesment of the quality of life and different scores were evaluated. The indirect and direct effects of these tests on the quality of life were examined in a single model using the structural equation modelling. Results: The most total effect on physical component score was Shoulder Disability Questionnaire and the Quick Disabilities of the Arm, Shoulder and Hand Score, Visual Analog Score had the least total effect on physical component score. Considering the results of mental component score, the total most effect was VAS had the the minimum total effect. Conclusion: The quality of life of the patients with subacromial impingement syndrom give more detailed informations when analysing the scores dependently. Evaluating the quality of life of subacromial impingement syndrome, using different measures of patients dependently will provide a more detailed research opportunity. If the patient quality of life evaluation is done in detail, it will facilitate the selection of appropriate treatment.

This text was produced as part of the theoretical basis of the research Technologies and childhoods: relationship, interaction and perception of children in group 5 in the context of the day care center, within the scope of the LabTEPI Project of the ForTEC Research Group. The purpose of this article is to understand the concept of childhood, making a theoretical and legal discussion around childhood and early childhood education. In this way, the text addresses the change in the concept of childhoods, since in the fields of Human Sciences we cannot affirm that there is a single model of childhood throughout human history, as the human being evolves along with its social context. We will also bring the history of Early Childhood Education in Brazil and the documents that guide and legitimize this segment of basic education as the first stage of education. For these reasons, it is prudent to know the contemporary learning contexts.

Standardized catch per unit effort (CPUE) is frequently used to represent annual fish-stock abundance trends. In multispecies fisheries, the catchability coefficient differs depending on the target strategy. Consideration of the target strategy in CPUE standardization is therefore crucial in improving the accuracy and precision of annual CPUE estimates. This study focuses on the potential of a finite mixture model (FMM), where target species and their annual trends are estimated simultaneously in a single model. The eight candidates of CPUE standardization methods—including the FMM—were used to evaluate the methodological performance as to whether they could identify the target strategy. A numerical simulation was undertaken using simplified data that mimic a Japanese longline fishery considering the target change over years, area effect, and multispecies abundance trends. Our simulation study indicated that the FMM outperformed other methods in the various scenarios, and therefore it is concluded that the FMM is an effective and robust methodology for clarifying the target strategy in the modeling of CPUE standardization.

Abordamos nesse artigo as transposições de modelos teóricos sobre os conhecimentos especializados que os professores têm para ensinar as disciplinas de Biologia, de Física e de Química que foram fundamentadas no modelo do Conhecimento Especializado do Professor de Matemática, o MTSK. Para tanto, traçamos a trajetória da construção dos modelos especializados e, em seguida, trazemos as diversificações teóricas entre os modelos da Biologia, da Física e da Química, comparando-os entre si, revelando os aspetos que os distinguem e/ou aproximam e que amparam a negativa para a transposição de um único modelo das Ciências embasada nas particularidades identificadas, tanto no âmbito do domínio do conteúdo, quanto no domínio pedagógico.

Wind serves as natural resources as the solution to minimize global warming and has been commonly used to produce electricity. Because of their uncontrollable wind characteristics, wind speed forecasting is considered one of the best challenges in developing power generation. The Autoregressive Integrated Moving Average (ARIMA), Simple Exponential Smoothing (SES) and a hybrid model combination of ARIMA and SES will be used in this study to predict the wind speed. The mean absolute percentage error (MAPE) and the root mean square error (RMSE) are used as measurement of efficiency. The hybrid model provides a positive outcome for predicting wind speed compare to the single model of ARIMA and SES.

Preclinical testing platforms have been instrumental in the research and development of thrombectomy devices. However, there is no single model which fully captures the complexity of cerebrovascular anatomy, physiology, and the dynamic artery-clot-device interaction. This article provides a critical review of phantoms, in-vivo animal, and human cadaveric models used for thrombectomy testing and provides insights into the strengths and limitations of each platform. Articles published in the past 10 years that reported thrombectomy testing platforms were identified. Characteristics of each test platform, such as intracranial anatomy, artery tortuosity, vessel friction, flow conditions, device-vessel interaction, and visualization, were captured and benchmarked against human cerebral vessels involved in large-vessel occlusion stroke. Thrombectomy phantoms have been constructed from silicone, direct 3D-printed polymers, and glass. These phantoms represent oversimplified patient-specific cerebrovascular geometry but enable adequate visualization of devices and clots under appropriate flow conditions. They do not realistically mimic the artery-clot interaction. For the animal models, arteries from swine, canines, and rabbits have been reported. These models can reasonably replicate the artery-clot-device interaction and have the unique value of evaluating the safety of thrombectomy devices. However, the vasculature geometries are substantially less complex and flow conditions are different from human cerebral arteries. Cadaveric models are the most accurate vascular representations but with limited access and challenges in reproducibility of testing conditions. Multiple test platforms should be likely used for comprehensive evaluation of thrombectomy devices. Interpretation of the testing results should take into consideration platform-specific limitations.

The purpose of this research is to determine the optimal portfolio formation in Islamic stocks on the Jakarta Islamic Index (JII) which is listed on the Indonesia Stock Exchange with a single model. Then measure the risk value that may occur and be accepted by investors using the Value at Risk (VaR) method with the Exponentially Weighted Moving Average (EWMA) approach. By using the Single Index Model, 5 stocks are selected and form an optimal portfolio, namely ASII, ICBP, TLKM, UNTR and UNVR.

The processes by which agonist binding promotes biological activity is a key issue in G protein-coupled receptor (GPCR) pharmacology, with much of our understanding governed by the application of mathematical models to experimental data. Models are built upon decades of fundamental principles, providing key concepts and measurable parameters which quantify agonism. Whilst numerous general receptor activation models exist, such as the operational model of agonism, there is no single model capable of describing all functional effects. Instead, there are a variety of models, each employed to understand specific experimental observations. In this review, we summarise recent GPCR models which incorporate: multiple signalling pathways simultaneously, constitutive receptor activity, or receptor dynamics, whilst providing parameters to quantify agonist bias. We also describe how model parameterisation requires model organisms and advanced experimental techniques, both proving invaluable for the construction of more complex, mechanistic models.

Regional scale debris flow susceptibility is widely evaluated by statistical methods. However, the initiation mechanism of debris flow is not considered, which leads to the neglect of the microtopographic characteristics. To address this problem, we established three novel combined models by introducing the physical model into statistical methods. The integrating models consists of two parts, the statistical models and the TRIGRS model. The eventual results obtained with the integrating model consider both the prediction result of the statistical method for debris flow susceptibility and the mechanism of debris flow initiation. To test the feasibility of the integrating model, three representative statistical models, the analytic hierarchy process (AHP), Shannon entropy (Entropy) and support vector machine (SVM) were selected to evaluate debris flow susceptibility in Yongji County of Jilin Province, China. The results demonstrate that the performance of the integrated models is significantly better than that of the single statistical model, especially in the local areas. The integrating models (AHP-TR, Entropy-TR, SVM-TR) can generate higher quality debris flow susceptibility maps (DFSMs) than the single model, which clearly reflect the scope and boundaries of the areas which are most prone to debris flow and identify the flat land and valleys between adjacent high-prone areas. It also reduces the overprediction generated by the physical model. In general, combining the statistical methods with the TRIGRS model can maximize the strengths of these models and avoid their weaknesses and obtain the effect of 1 + 1 > 2.

Over 390 million people worldwide are infected with dengue fever each year. In the absence of an effective vaccine for general use, national control programs must rely on hospital readiness and targeted vector control to prepare for epidemics, so accurate forecasting remains an important goal. Many dengue forecasting approaches have used environmental data linked to mosquito ecology to predict when epidemics will occur, but these have had mixed results. Conversely, human mobility, an important driver in the spatial spread of infection, is often ignored. Here we compare time-series forecasts of dengue fever in Thailand, integrating epidemiological data with mobility models generated from mobile phone data. We show that geographically-distant provinces strongly connected by human travel have more highly correlated dengue incidence than weakly connected provinces of the same distance, and that incorporating mobility data improves traditional time-series forecasting approaches. Notably, no single model or class of model always outperformed others. We propose an adaptive, mosaic forecasting approach for early warning systems.

In the article we present a single-run approach to recognizing nested named entities using neural networks with transformers. The main advantage of this approach is that a single model is trained to recognize all entity types. The model can identify all entities in a single pass. Our main contribution is the simplified representation of nested named entities on the token level, and evaluation of the presented approach on three languages — Polish (PolEval 2018 dataset), German (GermEval 2014 dataset), and Czech (CNEC 2.0 dataset). For each dataset we obtained state-of-the-art results. For Polish and German we obtained a significant improvement — 1.4 pp and 3.0 pp respectively. For Czech we obtained an improvement of 0.5 pp.

In artificial intelligence (AI), knowledge is the information required by an intelligent system to accomplish tasks. While traditional knowledge bases use discrete, symbolic representations, detecting knowledge encoded in the continuous representations learned from data has received increasing attention recently. In this work, we propose a method for building a continuous knowledge base (CKB) that can store knowledge imported from multiple, diverse neural networks. The key idea of our approach is to define an interface for each neural network and cast knowledge transferring as a function simulation problem. Experiments on text classification show promising results: the CKB imports knowledge from a single model and then exports the knowledge to a new model, achieving comparable performance with the original model. More interesting, we import the knowledge from multiple models to the knowledge base, from which the fused knowledge is exported back to a single model, achieving a higher accuracy than the original model. With the CKB, it is also easy to achieve knowledge distillation and transfer learning. Our work opens the door to building a universal continuous knowledge base to collect, store, and organize all continuous knowledge encoded in various neural networks trained for different AI tasks.

Objective: This paper aims to investigate and assess the UAE’s overall entrepreneurship performance (ecosystem) by applying the Global Entrepreneurship Index (GEI). Research Design & Methods: This paper assesses the United Arab Emirates’ entrepreneurial ecosystem and compares it with Qatar and Saudi Arabia by using the Global Entrepreneurship Index (GEI) data collected between 2011 and 2016. The GEI approach is applied to measure the entrepreneurship ecosystem at the country level, and it constitutes an appropriate method to encourage a higher level of entrepreneurship by considering its quality aspects. Findings: Outcomes show an entrepreneurial ecosystem with a GEI index of 44.6. Technology absorption is a critical bottleneck that suppresses entrepreneurial goals. Despite the low score of this pillar, the UAE has one of the highest GDP per capita among all participating countries. As a result, the GEI score of the United Arab Emirates and its sub-indices are above the global average trend and count to the most innovation-driven economies worldwide. However, the UAE is not performing well compared to other average performers in its category. Implications & Recommendations: Crucial policy interferences are required for the improvement of technology absorption. UAE calls for 4% additional resources to expand the GEI score by 10%. Contribution & Value Added: Using a novel approach incorporating individual and institutional variables into a single model, this paper identifies the weak aspects of UAE’s entrepreneurial performance. Also, the utilisation of (PFB) is used to identify which entrepreneurial factors should be tackled.

Recently, Generative Adversarial Network (GAN) based approaches are applied in facial attribute translation. However, many tasks, i.e. multi facial attributes translation and background invariance, are not well handled in the literature. In this paper, we propose a novel GAN-based method that aims to get the target image that performs better within modifying one or more facial attributes in a single model. The model generator learns multi-points by inputting a re-coded transfer vector, ensuring the single model could learn multiple attributes simultaneously. It also optimizes the cycle loss to enhance the efficiency of transferring multi attributes. Moreover, the method uses the adaptive parameter to improve the calculation method of the loss function of the residual image. The results are also compared with the StarGAN v2, which is the current state-of-the-art model to prove the effectiveness and advancedness. Experiments show that our method has a satisfactory performance in multi facial attributes translation.

In this paper we demonstrate that $\textit{context free grammar (CFG) based methods for grammar induction benefit from modeling lexical dependencies}$. This contrasts to the most popular current methods for grammar induction, which focus on discovering $\textit{either}$ constituents $\textit{or}$ dependencies. Previous approaches to marry these two disparate syntactic formalisms (e.g. lexicalized PCFGs) have been plagued by sparsity, making them unsuitable for unsupervised grammar induction. However, in this work, we present novel neural models of lexicalized PCFGs which allow us to overcome sparsity problems and effectively induce both constituents and dependencies within a single model. Experiments demonstrate that this unified framework results in stronger results on both representations than achieved when modeling either formalism alone. Code is available at https://github.com/neulab/neural-lpcfg., Accepted at TACL 2020

Accurate prediction of bus delays improves transit service delivery and can potentially increase passenger use and satisfaction. To date, models developed for predicting bus delays have been restricted to single routes because of their poor performance on a wide network, due to reliance on simplistic model architectures and limited sources of data. This paper proposes a deep learning-based framework for predicting bus delays at the network level. The framework is fueled by large, heterogenous bus transit data (GTFS) and vehicle probe data. We utilize entity embeddings to enable the framework to simultaneously fit functions and learn patterns from both categorical and continuous data streams. The framework results in a single model that is able to characterize the factors influencing delays on multiple routes, for multiple stations at a time, at different times of the day, and during different seasons. A case study was conducted in Saint Louis, Missouri, with data collected over a 1-month period. The results indicate that the developed modeling framework is high performing, predicting delays for multiple stops at a mean absolute percentage error (MAPE) of about 6%. For different routes and trips, the observed prediction errors were stable across days of week, bus stops, holidays, and time of day. Although peak hour factors and the distance to bus stop influenced the model’s prediction errors for some routes, the observed differences were not significant. Compared to previous research, the ability to simultaneously model continuous and categorical data with deep learning and the use of heterogenous data contributed to such high performance on multiple routes.

This study examines methods of calibrating projections of future regional climate for the next 40–50 years using large single-model ensembles (the Community Earth System Model (CESM) Large Ensemble and Max Planck Institute (MPI) Grand Ensemble), applied over Europe. The three calibration methods tested here are more commonly used for initialised forecasts from weeks up to seasonal timescales. The calibration techniques are applied to ensemble climate projections, fitting seasonal ensemble data to observations over a reference period (1920–2016). The calibration methods were tested and verified using an “imperfect model” approach using the historical/representative concentration pathway 8.5 (RCP8.5) simulations from the Coupled Model Intercomparison Project 5 (CMIP5) archive. All the calibration methods exhibit a similar performance, generally improving the out-of-sample projections in comparison to the uncalibrated (bias-corrected) ensemble. The calibration methods give results that are largely indistinguishable from one another, so the simplest of these methods, namely homogeneous Gaussian regression (HGR), is used for the subsequent analysis. As an extension to the HGR calibration method it is applied to dynamically decomposed data, in which the underlying data are separated into dynamical and residual components (HGR-decomp). Based on the verification results obtained using the imperfect model approach, the HGR-decomp method is found to produce more reliable and accurate projections than the uncalibrated ensemble for future climate over Europe. The calibrated projections for temperature demonstrate a particular improvement, whereas the projections for changes in precipitation generally remain fairly unreliable. When the two large ensembles are calibrated using observational data, the climate projections for Europe are far more consistent between the two ensembles, with both projecting a reduction in warming but a general increase in the uncertainty of the projected changes.

Single model large ensembles are widely used model experiments to estimate internal climate variability. The underlying assumption is that the internal variability (here: inter-annual variability) of the chosen model is a good approximation of the observed natural (inter-annual) variability. In this study, we test this assumption based on three regional climate model large ensembles (16 members of an EC-EARTH-RACMO ensemble, 21 members of a CESM-CCLM ensemble, 50 members of a CanESM-CRCM ensemble) for four European domains (British Isles, France, Mid-Europe, Alps). Simulated inter-annual variability is evaluated against E-OBS and the inter-annunal variability and its future change are compared across the ensembles. To the knowledge of the authors, this is the first comparison of regional large ensembles over Europe. Analysis comprises seasonal temperature and precipitation, as well as indicators for dry periods and heat waves. Results show a large consistency of all three ensembles with E-OBS data for most indicators and regions, validating the abilities of these ensembles to represent natural variability on the annual scale. EC-EARTH-RACMO shows the highest inter-annual variability for winter temperature and precipitation, whereas CESM-CCLM shows the highest variability for summer temperature and precipitation, as well as for heatwaves and dry periods. Despite these model differences, the sign of the future changes in internal variability is largely the same in all models: for summer temperature, summer precipitation and the number of heat waves, the internal variability increases, while it decreases for winter temperature. Changes of winter precipitation and dry periods are a bit unclear, with a tendency to increase for dry periods. The overall consistency across single model large ensembles and observations strengthens the concept of large ensembles, and underlines their great potential for understanding and quantifying the role of internal climate variability.

Many important drugs exhibit substantial variability in pharmacokinetics and pharmacodynamics leading to a loss of the desired clinical outcomes or significant adverse effects. Forecasting drug exposures using pharmacometric models can improve individual target attainment when compared with conventional therapeutic drug monitoring (TDM). However, selecting the "correct" model for this model-informed precision dosing (MIPD) is challenging. We derived and evaluated a model selection algorithm (MSA) and a model averaging algorithm (MAA), which automates model selection and finds the best model or combination of models for each patient using vancomycin as a case study, and implemented both algorithms in the MIPD software "TDMx." The predictive performance (based on accuracy and precision) of the two algorithms was assessed in (i) a simulation study of six distinct populations and (ii) a clinical dataset of 180 patients undergoing TDM during vancomycin treatment and compared with the performance obtained using a single model. Throughout the six virtual populations the MSA and MAA (imprecision: 9.9-24.2%, inaccuracy: less than ± 8.2%) displayed more accurate predictions than the single models (imprecision: 8.9-51.1%; inaccuracy: up to 28.9%). In the clinical dataset, the predictive performance of the single models applying at least one plasma concentration varied substantially (imprecision: 28-62%, inaccuracy: -16 to 25%), whereas the MSA or MAA utilizing these models simultaneously resulted in unbiased and precise predictions (imprecision: 29% and 30%, inaccuracy: -5% and 0%, respectively). MSA and MAA approaches implemented in TDMx might thereby lower the burden of fit-for-purpose validation of individual models and streamline MIPD.

Air quality forecast is an important technical means to ensure timely and proper response to heavy pollution weather. In this study, a hybrid deep air quality predictor (HDAQP) model consisting of one-dimensional convolutional neural network (CNN), long short-term memory (LSTM), and deep neural network (DNN) is proposed to forecast air quality indicators (mainly PM2.5 concentrations). The proposed model can overcome the limitations of the single model and meanwhile make the best of each. CNN model is used to convolve the historical PM2.5 concentration data along with meteorological data to extract shallow features, while LSTM model is used to extract the deep temporal features. Finally, the DNN model is adopted to transfer these deep features into the final forecast results. Compared with the mainstream deep learning models (e.g., RNN, LSTM, and CNN-LSTM models), the HDAQP model exhibits a better performance in short-term PM2.5 concentration forecast. With the increase of prediction time, the long-term prediction performance of the HDAQP model will be degraded, but it is still better than the mainstream deep learning models. Moreover, considering other meteorological factors, with the multi-source data, the HDAQP model can forecast PM2.5 concentrations more accurately.

One of the hottest and most popular methods in applied Machine Learning is Ensemble methods.Ensemble combines predictions from different models to generate a final prediction with better performance than any other single model. The research focused on the implementation of Ensemble method for predicting student academic performance based on their personal characteristics, family background, infrastructural environment in the college and external environment, etc...Our study uses RandomForestClassifier, Logistic Regression, and ExtraTreesClassifier as the Base Learners and AdaBoost Classifier as the Meta Learner. This result helps in predicting the accuracy of students’ academic performance and also in identifying the poor performers, so that early measures prior to final semester examination can be deployed

In this article, we propose novel techniques to predict a user’s movie genre preference and rating behavior from her psycholinguistic attributes obtained from the social media interactions. The motivation of this work comes from various psychological studies that demonstrate that psychological attributes such as personality and values can influence one’s decision or choice in real life. In this work, we integrate user interactions in Twitter and IMDb to derive interesting relations between human psychological attributes and their movie preferences. In particular, we first predict a user’s movie genre preferences from the personality and value scores of the user derived from her tweets. Second, we also develop models to predict user movie rating behavior from her tweets in Twitter and movie genre and storyline preferences from IMDb. We further strengthen the movie rating model by incorporating the user reviews. In the above models, we investigate the role of personality and values independently and combinedly while predicting movie genre preferences and movie rating behaviors. We find that our combined models significantly improve the accuracy than that of a single model that is built by using personality or values independently. We also compare our technique with the traditional movie genre and rating prediction techniques. The experimental results show that our models are effective in recommending movies to users.

Resumo Objetivo Avaliar, por meio de ensaio biomecânico, a carga máxima, a energia, e o deslocamento necessários para a ocorrência de fratura em modelos sintéticos de fêmures após a retirada de parafusos acanulados e a realização de técnica de reforço com polimetilmetacrilato (PMMA) em diferentes posições combinadas. Métodos Foram utilizados 25 ossos sintéticos divididos em 4 grupos: o grupo controle (GC), com 10 modelos sem perfuração, e os grupos teste (A, B e C), com 5 modelos cada. Os grupos de teste foram fixados com parafusos acanulados pela técnica de Asnis, e tiveram a síntese removida e o preenchimento de dois dos orifícios formados por técnica de reforço com PMMA. A análise biomecânica foi realizada simulando queda sobre o grande trocânter utilizando máquina servo-hidráulica. Resultados Todos os corpos de prova do GC e dos grupos A, B e C apresentaram fratura baso-cervical do colo femoral, exceto um modelo do grupo B, que apresentou fratura longitudinal. Foi utilizada uma média de 5,4 mL de PMMA no reforço dos grupos com preenchimento. Segundo a análise de variância (analysis of variance, ANOVA) e o teste de comparações múltiplas de Tukey, no nível de 5%, observou-se que o GC apresentou diferença significativa em relação aos grupos A e C nos seguintes parâmetros: carga máxima, energia até a fratura, e deslocamento. Conclusão Observou-se que os grupos A e C, quando comparados ao GC, apresentaram diferenças significativas na observação do deslocamento, da carga máxima, e da energia até a fratura.

Future hydroclimate projections of global climate models for East-Central Europe diverge to a great extent, thus, constrain adaptation strategies. To reach a more comprehensive understanding of this regional spread in model projections, we make use of the CMIP5 multi-model ensemble and six single-model initial condition large ensemble (SMILE) simulations to separate the effects of model structural differences and internal variability, respectively, on future hydroclimate projection uncertainty. To account for model uncertainty, we rank 32 CMIP5 models based on their predictive skill in reproducing multidecadal past hydroclimate variability. Specifically, we compare historical model simulations to long instrumental and reanalysis surface temperature and precipitation records. The top 3–ranked models—that best reproduce regional past multidecadal temperature and precipitation variability—show reduced spread in their projected future precipitation variability indicating less dry summer and wetter winter conditions in part at odds with previous expectations for Central Europe. Furthermore, not only does the regionally best performing CMIP5 models belong to the previously identified group of models with more realistic land-atmosphere interactions, their future summer precipitation projections also emerge from the range of six SMILEs’ future simulations. This suggests an important role for land-atmosphere coupling in regulating hydroclimate uncertainty on top of internal variability in the upcoming decades. Our results help refine the relative contribution of structural differences between models in affecting future hydroclimate uncertainty in the presence of irreducible internal variability in East-Central Europe.