关键词： Cardiovascular diseases   Deep learning   Genetic algorithm   Multi-modal   Electrocardiogram   Phonocardiogram  

摘要： Electrocardiogram (ECG) and phonocardiogram (PCG) play important roles in early prevention and diagnosis of cardiovascular diseases (CVDs). As the development of machine learning techniques, detection of CVDs by them from ECG and PCG has attracted much attention. However, current available methods are mostly based on single source data. It is desirable to develop efficient multi-modal machine learning methods to predict and diagnose CVDs. In this study, we propose a novel multi-modal method for predicting CVDs based both on ECG and PCG features. By building up conventional neural networks, we extract ECG and PCG deep-coding features respectively. The genetic algorithm is used to screen the combined features and obtain the best feature subset. Then we employ a support vector machine to implement classifications. Experimental results demonstrate the performance of our method is superior to those of single modal methods and alternatives. Our method reaches an AUC value of 0.936 when we use multi-modal features of ECG and PCG.

关键词： Machine learning   Assessment   Predictive learning analytics   Concept inventories   Course- vs. institution-specific data sources   Introductory biology  

摘要： High levels of attrition characterize undergraduate science courses in the USA. Predictive analytics research seeks to build models that identify at-risk students and suggest interventions that enhance student success. This study examines whether incorporating a novel assessment type (concept inventories [CI]) and using machine learning (ML) methods (1) improves prediction quality, (2) reduces the time point of successful prediction, and (3) suggests more actionable course-level interventions. A corpus of university and course-level assessment and non-assessment variables (53 variables in total) from 3225 students (over six semesters) was gathered. Five ML methods were employed (two individuals, three ensembles) at three time points (pre-course, week 3, week 6) to quantify predictive efficacy. Inclusion of course-specific CI data along with university-specific corpora significantly improved prediction performance. Ensemble ML methods, in particular the generalized linear model with elastic net (GLMNET), yielded significantly higher area under the curve (AUC) values compared with non-ensemble techniques. Logistic regression achieved the poorest prediction performance and consistently underperformed. Surprisingly, increasing corpus size (i.e., amount of historical data) did not meaningfully impact prediction success. We discuss the roles that novel assessment types and ML techniques may play in advancing predictive learning analytics and addressing attrition in undergraduate science education.

关键词： hyperspectral classification   blood   SVM   genetic algorithm   machine learning  

摘要： This study is focused on applying genetic algorithms (GAs) to model and band selection in hyperspectral image classification. We use a forensic-inspired data set of seven hyperspectral images with blood and five visually similar substances to test GA-optimised classifiers in two scenarios: when the training and test data come from the same image and when they come from different images, which is a more challenging task due to significant spectral differences. In our experiments, we compare GA with a classic model optimisation through a grid search. Our results show that GA-based model optimisation can reduce the number of bands and create an accurate classifier that outperforms the GS-based reference models, provided that, during model optimisation, it has access to examples similar to test data. We illustrate this with experiments highlighting the importance of a validation set.

关键词： artificial intelligence   echocardiography   fluid responsiveness   haemodynamic   machine learning   sepsis   ultrasonography  

摘要： Background: Passive leg raising (PLR) predicts fluid responsiveness in critical illness, although restrictions in mobilising patients often preclude this haemodynamic challenge being used. We investigated whether machine learning applied on transthoracic echocardiography (TTE) data might be used as a tool for predicting fluid responsiveness in critically ill patients. Methods: We studied, 100 critically ill patients (mean age: 62 yr [standard deviation: 14]) with severe sepsis or septic shock prospectively over 24 months. Transthoracic echocardiography measurements were performed at baseline, after PLR, and before and after a standardised fluid challenge in learning and test populations (n=50 patients each). A 15% increase in stroke volume defined fluid responsiveness. The machine learning methods used were classification and regression tree (CART), partial least-squares regression (PLS), neural network (NNET), and linear discriminant analysis (LDA). Each method was applied offline to determine whether fluid responsiveness may be predicted from left and right cardiac ventricular physiological changes detected by cardiac ultrasound. Predictive values for fluid responsiveness were compared by receiver operating characteristics (area under the curve [AUC];mean [95% confidence intervals]). Results: In the learning sample, the AUC values were PLR 0.76 (0.62-0.89), CART 0.83 (0.73-0.94), PLS 0.97 (0.93-1), NNET 0.93 (0.85-1), and LDA 0.90 (0.81-0.98). In the test sample, the AUC values were PLR 0.77 (0.64-0.91), CART 0.68 (0.54-0.81), PLS 0.83 (0.71-0.96), NNET 0.83 (0.71-0.94), and LDA 0.85 (0.74-0.96) respectively. The PLS model identified inferior vena cava collapsibility, velocityetime integral, S-wave, E/Ea ratio, and E-wave as key echocardiographic parameters. Conclusions: Machine learning generated several models for predicting fluid responsiveness that were comparable with the haemodynamic response to PLR.

关键词： Mixing   Electrical resistance tomography   pH   Machine learning   Reaction  

摘要： The development of smart sensors capable to analyse data gathered on the process line and to give a real time feedback has been undergoing extensive research in the last years due to its potential benefits on the process optimisation and products improvement. In this paper, a novel approach to detect and monitor pH and conductivity using 2D electrical resistance tomography (ERT) is proposed for the first time in a reacting system. As a study case, the reaction between phosphoric acid and potassium hydroxide in mediums of both water and sodium carboxymethylcellulose (CMC) aqueous solution was assessed. The information gathered using the ERT have been used to determine local and overall mixing time for a sequence of injections of base and acid to understand the overall performance of the system. In addition, the same information have been used to extrapolate live data about the variation of the pH coupling the ERT data and machine learning techniques. Three different approaches have been investigated to achieve the aforementioned objective all integrating ML to the data processing. The first two approaches did not provide satisfying results showing the limitation of a completely blind approach (pure statistical approaches). However, the last approach, which combined ML technique and physical/chemical knowledge, showed very successful results for the real time monitoring of the pH in a reacting system. (c) 2021 Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.

关键词： snow depth datasets   data fusion   machine learning algorithms   the Northern Hemisphere  

摘要： In this study, a machine learning algorithm was introduced to fuse gridded snow depth datasets. The input variables of the machine learning method included geolocation (latitude and longitude), topographic data (elevation), gridded snow depth datasets and in situ observations. A total of 29,565 in situ observations were used to train and optimize the machine learning algorithm. A total of five gridded snow depth datasets-Advanced Microwave Scanning Radiometer for the Earth Observing System (AMSR-E) snow depth, Global Snow Monitoring for Climate Research (GlobSnow) snow depth, Long time series of daily snow depth over the Northern Hemisphere (NHSD) snow depth, ERA-Interim snow depth and Modern-Era Retrospective Analysis for Research and Applications, version 2 (MERRA-2) snow depth-were used as input variables. The first three snow depth datasets are retrieved from passive microwave brightness temperature or assimilation with in situ observations, while the last two are snow depth datasets obtained from meteorological reanalysis data with a land surface model and data assimilation system. Then, three machine learning methods, i.e., Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Random Forest Regression (RFR), were used to produce a fused snow depth dataset from 2002 to 2004. The RFR model performed best and was thus used to produce a new snow depth product from the fusion of the five snow depth datasets and auxiliary data over the Northern Hemisphere from 2002 to 2011. The fused snow-depth product was verified at five well-known snow observation sites. The R-2 of Sodankyla, Old Aspen, and Reynolds Mountains East were 0.88, 0.69, and 0.63, respectively. At the Swamp Angel Study Plot and Weissfluhjoch observation sites, which have an average snow depth exceeding 200 cm, the fused snow depth did not perform well. The spatial patterns of the average snow depth were analyzed seasonally, and the average snow depths of autumn, winter, and spring were

关键词： auto ML   ChEMBL   classification   deep learning   machine learning   QSAR  

摘要： Machine learning (ML) method performances, including deep learning (DL) on a diverse set with or without feature selection (FS), were evaluated. The superior performance of DL on small sets has not been approved previously. On the other hand, the available sets for the newly identified targets usually are limited in terms of size. It was explored whether the FS, hyperparameters search, and using ensemble model are able to improve the ML and DL performance on the small sets. The QSAR classifier models were developed using K-nearest (KN) neighbors, DL, random forest (RF), naive Bayesian (NB) classification, support vector machine (SVM), and logistic regression (LR). Generally, the best individual performers were DL and SVM. The LR had a similar performance to the DL and SVM on the small subsets. The nested cross-validation method was able to include different feature vectors in combination with different ML methods to generate an ensemble model for the datasets with similar performance to the best performers. The general performance for the baseline NB model was Matthews correlation coefficient = 0.356, and it was improved to around 0.66 and 0.63 by NB assisted FS with subsequent SVM/DL classification and an ensemble model, respectively.

关键词： Channel reservoir modeling   Rule-based fluvial reservoir model conditioning   Machine learning   Geostatistics   Model parameterization   Reservoir characterization  

摘要： Constructing subsurface models that accurately reproduce geological heterogeneity and their associated uncertainty is critical to many geoscience and engineering applications. For hydrocarbon reservoir modeling and forecasting, for example, spatial variability must be consistent with geological processes, geophysical measurements, and time records of fluid production measurements. Generating such subsurface models can be time-consuming;conditioning them to different types of measurements is even more computationally intensive and technically challenging. Using too many free variables can cause overfitting of the data, thereby decreasing the predictive ability of the model;high dimensionality also slows convergence during history matching of fluid production measurements. To contend with these problems, we introduce here a new machine learning approach, referred to as the stochastic pix2pix method, which parameterizes high-dimensional, stochastic reservoir models into low-dimensional Gaussian random variables in latent space. Many of the world's significant hydrocarbon fields originate from fluvial or turbidite deposits, with sedimentary processes and spatial distribution of rock facies significantly influencing their flow behavior. Rule- or object-based methods are commonly used to model geostatistically these types of reservoirs. Here, we introduce a new and efficient machine learning-based reservoir modeling workflow capable of generating 2D fluvial reservoir models that account for the available field data and the geometries of different facies. By constraining subsurface model realizations to available geophysical and petrophysical interpretations, multiphysics inversion can be greatly accelerated, thereby requiring only production history matching. Although our models are 2D, an extension to 3D can be readily implemented through zone-by-zone (i.e., reservoir unit) modeling and conditioning. The proposed method and workflow also partially solve the common proble

关键词： Oceans   Predictive models   Satellite broadcasting   MODIS   Satellites   Machine learning   Spatial resolution   Celebes sea   internal wave (IW)   machine learning   Sulu sea  

摘要： Internal waves (IWs), observed in the world oceans, have significant impacts on ocean engineering and environments. In this study, we collected satellite images from Moderate-Resolution Imaging Spectroradiometer and Visible Infrared Imaging Radiometer Suite sensors in the Sulu-Celebes Sea from 2016 to 2019 to understand the IW generation and propagation. Satellite observations show a coherent IW phase difference in both seas, indicating that the IWs are alternatively generated when the tidal currents oscillate back and forth in the Sulu Archipelago, which separates two seas. A new generation site is found for occasionally observed long IWs in the eastern Sulu Sea. To understand the IW propagation characteristics, we developed a machine-learning-based forecast model. We trained the model with both IW wave crest curves extracted from satellite images and published climatological ocean temperaturesalinity profiles. Since many satellite images contain IW packets generated at two or three tidal cycles, we can validate the model performance by matching the model prediction after one or two tidal cycles with the second or third wave crests in satellite images. Three factors are adopted to evaluate the forecast results: the root-mean-square error (RMSE), the Frchet distance (FD), and the correlation coefficient (CC). The forecast model has an average error with an RMSE of 12.92 km, an FD of 18.73 km, and a CC of 0.98. Analysis shows that a smaller time step is preferred in regions where the water depth changes significantly. Comparison with the Kortewegde Vries equation solutions shows that the developed forecast model is more robust when errors introduced to the model inputs.

关键词： SARS-COV-2   Data Mining   Deep Learning   Extreme Gradient Boosting   Machine Learning  

摘要： Background and Objective: The new type of Coronavirus (2019-nCov) epidemic spread rapidly, causing more than 250 thousand deaths worldwide. The virus, which first appeared as a sign of pneumonia, was later called the SARS-COV-2 with Severe Acute Respiratory Syndrome by the World Health Organization. The SARS-COV-2 virus is triggered by binding to the Angiotensin-Converting Enzyme 2 (ACE 2) inhibitor, which is vital in cardiovascular diseases and the immune system, especially in conditions such as cerebrovascular, hypertension, and diabetes. This study aims to evaluate the prediction performance of death status based on the demographic/clinical factors (including COVID-19 severity) by data mining methods. Methods: The dataset consists of 1603 SARS-COV-2 patients and 13 variables obtained from an open source web address. The current dataset contains age, gender, chronic disease (hypertension, diabetes, renal, cardiovascular, etc.), some enzymes (ACE, angiotensin II receptor blockers), and COVID-19 severity, which are used to predict death status using deep learning and machine learning approaches (random forest, k-nearest neighbor, extreme gradient boosting [XGBoost]). A grid search algorithm tunes hyperparameters of the models, and predictions are assessed through performance metrics. Steps of knowledge discovery in databases are applied to obtain the relevant information. Results: The accuracy rate of deep learning (97.15%) was more successful than the accuracy rate based on classical machine learning (92.15% for RF and 93.4% for k-NN), but the ensemble classifier XGBoost method gave the highest accuracy (99.7%). While COVID-19 severity and age calculated from XGBoost were the two most important factors associated with death status, the most determining variables for death status estimated from deep learning were COVID-19 severity and hypertension. Conclusions: The proposed model (XGBoost) achieved the best prediction of death status based on the factors as compared