关键词： Cerebral aneurysm   morphology   hemodynamics   machine learning  

摘要： Morphological characterization and fluid dynamics simulations were carried out to classify the rupture status of 71 (36 unruptured, 35 ruptured) patient specific cerebral aneurysms using a machine learning approach together with statistical techniques. Eleven morphological and six hemodynamic parameters were evaluated individually and collectively for significance as rupture status predictors. The performance of each parameter was inspected using hypothesis testing, accuracy, confusion matrix, and the area under the receiver operating characteristic curve. Overall, the size ratio exhibited the best performance, followed by the diastolic wall shear stress, and systolic wall shear stress. The prediction capability of all 17 parameters together was evaluated using eight different machine learning algorithms. The logistic regression achieved the highest accuracy (0.75), whereas the random forest had the highest area under curve value among all the classifiers (0.82), surpassing the performance exhibited by the size ratio. Hence, we propose the random forest model as a tool that can help improve the rupture status prediction of cerebral aneurysms.

关键词： LDL   Cholesterol   Triglycerides   Machine learning   Friedewald  

摘要： Background: Accurate determination of low-density lipoprotein cholesterol (LDL) is important for coronary heart disease risk assessment and atherosclerosis. Apart from direct determination of LDL values, models (or equations) are used. A more recent approach is the use of machine learning (ML) algorithms. Methods: ML algorithms were used for LDL determination (regression) from cholesterol, HDL and triglycerides. The methods used were multivariate Linear Regression (LR), Support Vector Machines (SVM), Extreme Gradient Boosting (XGB) and Deep Neural Networks (DNN), in both larger and smaller data sets. Also, LDL values were classified according to both NCEP III and European Society of Cardiology guidelines. Results: The performance of regression was assessed by the Standard Error of the Estimate. ML methods performed better than established equations (Friedewald and Martin). The performance all ML methods was comparable for large data sets and was affected by the divergence of the train and test data sets, as measured by the Jensen-Shannon divergence. Classification accuracy was not satisfactory for any model. Conclusions: Direct determination of LDL is the most preferred route. When not available, ML methods can be a good substitute. Not only deep neural networks but other, less computationally expensive methods can work as well as deep learning.

关键词： LSTM   TEC forecasting   random forest   space weather   ionosphere  

摘要： In this research, we present data-driven forecasting of ionospheric total electron content (TEC) using the Long-Short Term Memory (LSTM) deep recurrent neural network method. The random forest machine learning method was used to perform a regression analysis and estimate the variable importance of the input parameters. The input data are obtained from satellite and ground based measurements characterizing the solar-terrestrial environment. We estimate the relative importance of 34 different parameters, including the solar flux, solar wind density, and speed the three components of interplanetary magnetic field, Lyman-alpha, the Kp, Dst, and Polar Cap (PC) indices. The TEC measurements are taken with 15-s cadence from an equatorial GPS station located at Bogota, Columbia (4.7110 degrees N, 74.0721 degrees W). The 2008-2017 data set, including the top five parameters estimated using the random forest, is used for training the machine learning models, and the 2018 data set is used for independent testing of the LSTM forecasting. The LSTM method as applied to forecast the TEC up to 5 h ahead, with 30-min cadence. The results indicate that very good forecasts with low root mean square (RMS) error (high correlation) can be made in the near future and the RMS errors increase as we forecast further into the future. The data sources are satellite and ground based measurements characterizing the solar-terrestrial environment.

关键词： hyperspectral imaging   machine learning   classification   support vector machine   random forest   convolutional neural network   brain   neurosurgery   tumor  

摘要： Hyperspectral imaging techniques (HSI) do not require contact with patients and are non-ionizing as well as non-invasive. As a consequence, they have been extensively applied in the medical field. HSI is being combined with machine learning (ML) processes to obtain models to assist in diagnosis. In particular, the combination of these techniques has proven to be a reliable aid in the differentiation of healthy and tumor tissue during brain tumor surgery. ML algorithms such as support vector machine (SVM), random forest (RF) and convolutional neural networks (CNN) are used to make predictions and provide in-vivo visualizations that may assist neurosurgeons in being more precise, hence reducing damages to healthy tissue. In this work, thirteen in-vivo hyperspectral images from twelve different patients with high-grade gliomas (grade III and IV) have been selected to train SVM, RF and CNN classifiers. Five different classes have been defined during the experiments: healthy tissue, tumor, venous blood vessel, arterial blood vessel and dura mater. Overall accuracy (OACC) results vary from 60% to 95% depending on the training conditions. Finally, as far as the contribution of each band to the OACC is concerned, the results obtained in this work are 3.81 times greater than those reported in the literature.

关键词： Forecasting rainfall   Machine learning algorithms   Boosted decision tree regression   Decision forest regression   Neural network regression   Bayesian linear regression  

摘要： Rainfall plays a main role in managing the water level in the reservoir. The unpredictable amount of rainfall due to the climate change can cause either overflow or dry in the reservoir. In this study, several models and methods were applied to predict the rainfall data in Tasik Kenyir, Terengganu. The comparative study was conducted focusing on developing and comparing several Machine Learning (ML) models, evaluating different scenarios and time horizon, and forecasting rainfall using two types of methods. Data involved for this research consist of taking the average rainfall from 10 stations around the study area using Thiessen polygon to weight the station area and projected rainfall. The forecasting model uses four different ML algorithms, which are Bayesian Linear Regression (BLR), Boosted Decision Tree Regression (BDTR), Decision Forest Regression (DFR) and Neural Network Regression (NNR). On the other hand, the rainfall was predicted on different time horizon by using different ML's algorithms which is method 1 (M1): Forecasting Rainfall Using Autocorrelation Function (ACF) and method 2 (M2): Forecasting Rainfall Using Projected Error. In Ml, the best regression developed for ACF is BDTR since it has the highest coefficient of determination, R2, after tuning the hyperparameter. The results show coefficient between 0.5 and 0.9 with the highest of each scenarios for daily (0.9739693), weekly (0.989461), 10days (0.9894429) and monthly (0.9998085). In M2, overall model performances show that normalization using LogNormal is preferably giving a good result of each categories except for 10-days with BDTR and DFR are the most acceptable result than NNR and BLR. It is concluded that, two different methods have been applied with different scenarios and different time horizons, and Ml shows a rather high accuracy than M2 using BDTR modeling. (C) 2020 The Authors. Published by Elsevier B.V. on behalf of Faculty of Engineering, Ain Shams University.

关键词： Outlier detection   Machine learning   Model selection   Imbalanced classification  

摘要： A precision feeding (PF) system is an intelligent computer-controlled feeding system that can be used to feed individual broilers, breeders or layers automatically based on measuring real-time body weight (BW). Vast amounts of real-time BW data can be generated every day when birds visit a PF station. However, anomalous observations occurred in real-time BW observations, which were caused by multiple birds entering the station at the same time, upward or downward variation in scale measurement in the recorded data due to the movement of the bird, or a misread for radio frequency identification tag. Known anomalous data should be removed because they have a negative impact on the interpretation of the data. Manually cleaning the anomalies is accurate, but it is time-consuming and labor-intensive. Statistical methods and unsupervised machine learning methods are effective in detecting anomalies to some extent because they just check data distribution. The current study reported a supervised machine learning method to detect anomalies in real-time BW recorded by the PF system. Real-time BW data of 5 broiler breeders from day 15 to 306 were checked and the anomalies were manually labeled. Variables regarding the statistical distribution of data and features regarding the feeding activity recorded by the PF system in each day were extracted from the dataset. Among the 4 machine learning algorithms including k-nearest neighbor (KNN), random forest classifier (RF), support vector machine (SVM), and artificial neural network (ANN), RF produced the highest F1 score (0.9712) and area under the precisionrecall curve (0.9948). Compared with 4 other common anomaly detection methods including Z-scores, interquartile range (IQR), density-based spatial clustering of applications with noise (DBSCAN), and local outlier factor (LOF), RF had a higher average F1 score (0.9448), which indicated that RF was a more effective anomaly detection algorithm for this type of data.

关键词： COVID-19   Hybrid deep learning   short-term forecasting   LSTM-CNN   GAN-GRU  

摘要： Within the recent pandemic, scientists and clinicians are engaged in seeking new technology to stop or slow down the COVID-19 pandemic. The benefit of machine learning, as an essential aspect of artificial intelligence, on past epidemics offers a new line to tackle the novel Coronavirus outbreak. Accurate short-term forecasting of COVID-19 spread plays an essential role in improving the management of the overcrowding problem in hospitals and enables appropriate optimization of the available resources (i.e., materials and staff).This paper presents a comparative study of machine learning methods for COVID-19 transmission forecasting. We investigated the performances of deep learning methods, including the hybrid convolutional neural networks-Long short-term memory (LSTM-CNN), the hybrid gated recurrent unit-convolutional neural networks (GAN-GRU), GAN, CNN, LSTM, and Restricted Boltzmann Machine (RBM), as well as baseline machine learning methods, namely logistic regression (LR) and support vector regression (SVR). The employment of hybrid models (i.e., LSTM-CNN and GAN-GRU) is expected to eventually improve the forecasting accuracy of COVID-19 future trends. The performance of the investigated deep learning and machine learning models was tested using confirmed and recovered COVID-19 cases time-series data from seven impacted countries: Brazil, France, India, Mexico, Russia, Saudi Arabia, and the US. The results reveal that hybrid deep learning models can efficiently forecast COVID-19 cases. Also, results confirmed the superior performance of deep learning models compared to the two considered baseline machine learning models. Furthermore, results showed that LSTM-CNN achieved improved performances with an averaged mean absolute percentage error of 3.718%, among others.

关键词： Low-carbon city   Urban blocks carbon emissions   Built environment factors   Machine learning   Prediction  

摘要： Predicting urban blocks carbon emissions (UBCE) accurately based on built environment factors (BEF) is an effective way to reduce UBCE and alleviate urban heat islands (UHI) from the perspective of urban planning. At an urban level, this study collected various sources of data and proposed a machine learning method (Back Propagation Neural Network - BPNN) to predict different functions of UBCE by BEF in Changxing, a representative small city in China. The study found that UBCE can be significantly affected by BEF such as density, function, and morphology. The BPNN has a good prediction performance on different functions of UBCE, and the mean absolute percentage error (MAPE) is stable within 10 %?20 %. The prediction results showed that the average value of different functions of UBCE presented an obvious variation. The carbon emission map showed that the high UBCE are mainly clustered in the middle-east and south of the central city of Changxing. By comparison with other studies, the accuracy of this method was proved. This method could be applied to predict carbon emissions of the urban planning scheme. Optimizing the BEF of urban blocks can play key roles in the reduction of carbon emissions and then alleviation of the UHI.

关键词： Quantitative Structure-Property Relationships (QSPR) models   Marine Natural Products (MNPs)   Terrestrial Natural Products (TNPs)  

摘要： In recent years there has been a growing interest in studying the differences between the chemical and biological space represented by natural products (NPs) of terrestrial and marine origin. In order to learn more about these two chemical spaces, marine natural products (MNPs) and terrestrial natural products (TNPs), a machine learning (ML) approach was developed in the current work to predict three classes, MNPs, TNPs and a third class of NPs that appear in both the terrestrial and marine environments. In total 22,398 NPs were retrieved from the Reaxys (R) database, from those 10,790 molecules are recorded as MNPs, 10,857 as TNPs, and 761 NPs appear registered as both MNPs and TNPs. Several ML algorithms such as Random Forest, Support Vector Machines, and deep learning Multilayer Perceptron networks have been benchmarked. The best performance was achieved with a consensus classification model, which predicted the external test set with an overall predictive accuracy up to 81 %. As far as we know this approach has never been intended and therefore allow to be used to better understand the chemical space defined by MNPs, TNPs or both, but also in virtual screening to define the applicability domain of QSAR models of MNPs and TNPs.

关键词： imbalanced data   burned area   prediction large wildfire   logistic regression   multi-layer perceptron  

摘要： Wildfires are becoming more frequent in different parts of the globe, and the ability to predict when and where they will occur is a complex process. Identifying wildfire events with high probability of becoming a large wildfire is an important task for supporting initial attack planning. Different methods, including those that are physics-based, statistical, and based on machine learning (ML) are used in wildfire analysis. Among the whole, those based on machine learning are relatively novel. In addition, because the number of wildfires is much greater than the number of large wildfires, the dataset to be used in a ML model is imbalanced, resulting in overfitting or underfitting the results. In this manuscript, we propose to generate synthetic data from variables of interest together with ML models for the prediction of large wildfires. Specifically, five synthetic data generation methods have been evaluated, and their results are analyzed with four ML methods. The results yield an improvement in the prediction power when synthetic data are used, offering a new method to be taken into account in Decision Support Systems (DSS) when managing wildfires.