关键词： Evaporative condenser   Machine learning   Artificial neural networks   Support vector regression   Decision tree   Random forest  

摘要： Evaporative condensers are regarded as highly-efficient and eco-friendly heat exchangers in refrigeration systems. Data-driven methods can play a key role in performance prediction of evaporative condensers, conducted without the complexity of theoretical analysis. In this study, four machine learning models including multi-layer perceptron artificial neural network (ANNMLP), support vector regression (SVR), decision tree (DT), and random forest (RF) models have been employed to predict heat transfer rate and overall heat transfer coefficient of a small-scale evaporative condenser functioning under a wide range of working conditions. A set of experimental tests were conducted, where inlet air dry/wet-bulb temperatures, spraying water and condenser saturation temperatures, refrigerant, and air flow rates were considered as main influencing parameters. The results show that the ANNMLP followed by SVR, and RF models possess the best generalization capability. Further, the dataset size analysis indicates that SVR is the best model to predict heat transfer rate for small dataset sizes. Additionally, feature importance analysis by the RF model reveals that refrigerant flow rate is the most influencing parameter. (c) 2021 Elsevier Ltd and IIR. All rights reserved.

关键词： MODIS   air temperature estimation   remote sensing   land surface temperature   nighttime LST  

摘要： Air temperature (Ta) is a required input in a wide range of applications, e.g., agriculture. Land Surface Temperature (LST) products from Moderate Resolution Imaging Spectroradiometer (MODIS) are widely used to estimate Ta. Previous studies of these products in Ta estimation, however, were generally applied in small areas and with a small number of meteorological stations. This study designed both temporal and spatial experiments to estimate 8-day and daily maximum and minimum Ta (Tmax and Tmin) on three spatial scales: climate zone, continental and global scales from 2009 to 2018, using the Random Forest (RF) method based on MODIS LST products and other auxiliary data. Factors contributing to the relation between LST and Ta were determined based on physical models and equations. Temporal and spatial experiments were defined by the rules of dividing the training and validation datasets for the RF method, in which the stations selected in the training dataset were all included or not in the validation dataset. The RF model was first trained and validated on each spatial scale, respectively. On a global scale, model accuracy with a determination coefficient (R-2) > 0.96 and root mean square error (RMSE) < 1.96 degrees C and R-2 > 0.95 and RMSE < 2.55 degrees C was achieved for 8-day and daily Ta estimations, respectively, in both temporal and spatial experiments. Then the model was trained and cross-validated on each spatial scale. The results showed that the data size and station distribution of the study area were the main factors influencing the model performance at different spatial scales. Finally, the spatial patterns of the model performance and variable importance were analyzed. Both daytime and nighttime LST had a significant contribution in the 8-day Tmax estimation on all the three spatial scales;while their contribution in daily Tmax estimation varied over different continents or climate zones. This study was expected to improve our understanding of Ta est

关键词： Mitochondrial fusion and fission   QSAR   Machine learning   Structural alerts  

摘要： Mitochondrial fusion and fission are processes to maintain mitochondrial function when cells respond to environment stresses. Disruption of mitochondrial fusion and fission influences cell health and can cause adverse events such as neurodegenerative disorders. It is critical to identify environmental chemicals that can disrupt mitochondrial fusion and fission. However, experimentally testing all the chemicals is not practical because experimental methods are time-consuming and costly. Quantitative structure-activity relationship (QSAR) modeling is an attractive approach for evaluation of chemicals disrupting potential on mitochondrial fusion and fission. In this study, QSAR models were developed for differentiating chemicals capable of inhibition of mitochondrial fusion and fission using machine learning algorithms (i.e. random forest, logistic regression, Bernoulli naive Bayes, and deep neural network). One hundred iterations of five-fold cross validations and external validations showed that the best model on mitochondrial fusion had area under the receiver operating characteristic curve (AUC) of 82.8% and 78.1%, respectively;and the best model for mitochondrial fission yielded AUC of 84.3% and 97.5%, respectively. Furthermore, 45 and 56 structural alerts were identified for inhibition of mitochondrial fusion and fission, respectively. The results demonstrated that the models and the structural alerts could be useful for screening chemicals that inhibit mitochondrial fusion and fission. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： scanning parameters   machine learning   random measurement error  

摘要： Measurements of technical objects can be done with contact and non-contact approaches. Contact methods are accurate but slow. On the other hand, non-contact methods deliver rapid point acquisition and are increasingly being used as their precision mounts. However, multiple scanning parameters such as the incident angle, object colour and scanning distance influence the measurement error and uncertainty when capturing the geometry of the object. With the aim of creating a generalised model that considers the influence of the aforementioned scanning parameters with satisfactory accuracy, a model for predicting the random measurement error based on machine learning (ML) is proposed in this study. Data acquired from measurements with varying scanning distances, incident angles and surface colours were used to train ML models. The tested ML methods included linear regression, support vector machine, neural network, k-nearest neighbour, AdaBoost and random forest. The best-performing trained model was the random forest, with a standard deviation of relative differences of 1.46% for the case of red surfaces, and 5.2% for the case of an arbitrarily coloured surface, which is comparable to results achieved with model-based methods. The trained models and the data are available online.

关键词： causal inference   covariate adjustment   double robustness   real‐   world evidence   semiparametric theory   super learner  

摘要： The use of real-world data for medical treatment evaluation frequently requires adjusting for population differences. We consider this problem in the context of estimating mean outcomes and treatment differences in a well-defined target population, using clinical data from a study population that overlaps with but differs from the target population in terms of patient characteristics. The current literature on this subject includes a variety of statistical methods, which generally require correct specification of at least one parametric regression model. In this article, we propose to use machine learning methods to estimate nuisance functions and incorporate the machine learning estimates into existing doubly robust estimators. This leads to nonparametric estimators that are n-consistent, asymptotically normal and asymptotically efficient under general conditions. Simulation results demonstrate that the proposed methods perform reasonably well in realistic settings. The methods are illustrated with a cardiology example concerning aortic stenosis.

关键词： Machine learning method   Neurology   Electroencephalography   Status epilepticus   Seizure burden  

摘要： Introduction Current electroencephalography (EEG) practice relies on interpretation by expert neurologists, which introduces diagnostic and therapeutic delays that can impact patients' clinical outcomes. As EEG practice expands, these experts are becoming increasingly limited resources. A highly sensitive and specific automated seizure detection system would streamline practice and expedite appropriate management for patients with possible nonconvulsive seizures. We aimed to test the performance of a recently FDA-cleared machine learning method (Clarit gamma, Ceribell Inc.) that measures the burden of seizure activity in real time and generates bedside alerts for possible status epilepticus (SE). Methods We retrospectively identified adult patients (n = 353) who underwent evaluation of possible seizures with Rapid Response EEG system (Rapid-EEG, Ceribell Inc.). Automated detection of seizure activity and seizure burden throughout a recording (calculated as the percentage of ten-second epochs with seizure activity in any 5-min EEG segment) was performed with Clarit gamma, and various thresholds of seizure burden were tested (>= 10% indicating >= 30 s of seizure activity in the last 5 min, >= 50% indicating >= 2.5 min of seizure activity, and >= 90% indicating >= 4.5 min of seizure activity and triggering a SE alert). The sensitivity and specificity of Clarit gamma's real-time seizure burden measurements and SE alerts were compared to the majority consensus of at least two expert neurologists. Results Majority consensus of neurologists labeled the 353 EEGs as normal or slow activity (n = 249), highly epileptiform patterns (HEP,n = 87), or seizures [n = 17, nine longer than 5 min (e.g., SE), and eight shorter than 5 min]. The algorithm generated a SE alert (>= 90% seizure burden) with 100% sensitivity and 93% specificity. The sensitivity and specificity of various thresholds for seizure burden during EEG recordings for detecting patients with seizures were 100% and 82%

关键词： Ligands   Chemical structure   Power   Software   Receptors  

摘要： In recent years, machine-learning-based scoring functions have significantly improved the scoring power. However, many of these methods do not perform well in distinguishing the native structure from docked decoy poses due to the lack of decoy structural information in their training data. Here, we developed a machine-learning model, named DeepBSP, that can directly predict the root mean square deviation (rmsd) of a ligand docking pose with reference to its native binding pose. Unlike the binding affinity, the rmsd between the docking poses with reference to their native structures can be straightforwardly determined. By training on a generated data set with 11,925 native complexes and more than 165,000 docked poses, our model shows excellent docking power on our test set and also on the CASF-2016 docking decoy set compared to other major scoring functions. Thus, by combining molecular dockings that generate many poses with the application of DeepBSP, one can more accurately predict the best binding pose that is closest to the native complex structure. This DeepBSP model shall be very useful in picking out poses close to their natives from many poses generated from a dock application.

关键词： Catalysis  

摘要： Heterogeneous catalysis plays a significant role in the modern chemical industry. Towards the rational design of novel catalysts, understanding reactions over surfaces is the most essential aspect. Typical industrial catalytic processes such as syngas conversion and methane utilisation can generate a large reaction network comprising thousands of intermediates and reaction pairs. This complexity not only arises from the permutation of transformations between species but also from the extra reaction channels offered by distinct surface sites. Despite the success in investigating surface reactions at the atomic scale, the huge computational expense of ab initio methods hinders the exploration of such complicated reaction networks. With the proliferation of catalysis studies, machine learning as an emerging tool can take advantage of the accumulated reaction data to emulate the output of ab initio methods towards swift reaction prediction. Here, we briefly summarise the conventional workflow of reaction prediction, including reaction network generation, ab initio thermodynamics and microkinetic modelling. An overview of the frequently used regression models in machine learning is presented. As a promising alternative to full ab initio calculations, machine learning interatomic potentials are highlighted. Furthermore, we survey applications assisted by these methods for accelerating reaction prediction, exploring reaction networks, and computational catalyst design. Finally, we envisage future directions in computationally investigating reactions and implementing machine learning algorithms in heterogeneous catalysis.

关键词： 土壤转换函数   机器学习   人工神经网络   支持向量机   K-最近邻居法  

摘要： 土壤水分状态及运动过程的准确描述与预测需要精确的土壤水力参数,而使用土壤转换函数的方法可以方便省时省力地获得土壤水力参数。对于不同的建模方法,在模型预测精度、运行效率等方面有所差异。【目的】探究不同机器学习方法建立土壤转换函数模型的优劣。【方法】使用UNSODA全球土壤水力性质数据库,对比分析了人工神经网络(ANN)、支持向量机(SVM)、K-最近邻居法(KNN)对于van Genuchten模型参数的预测精度,并使用土壤样本的含水率-负压实测数据,从土壤质地的角度评价了各模型的预测效果。【结果】SVM模型对样本的预测效果最好,ANN次之,KNN模型受边缘效应影响预测效果稍逊。在训练模型时,ANN模型用时最长,KNN模型用时最短。然而,在预测过程中,ANN模型用时最短,KNN模型用时最长。【结论】本研究推荐在小数据集上建立土壤转换函数模型时使用SVM,而在更大型的数据集上要综合考虑计算成本、预测精度等方面合理选取建模方法。

关键词： NIR光谱   咖啡   蛋白质   SVM   ELM   潜变量技术  

摘要： 采用近红外(NIR)光谱快检技术实现对咖啡蛋白质的定量检测,研究支持向量机(SVM)和极限学习机(ELM)等机器学习方法在建模分析中的实用性。结合潜变量分析技术,建立潜变量SVM(LV-SVM)模型和潜变量ELM(LV-ELM)模型,通过调试潜变量个数和机器学习关键参数的联合优选,实现数据降维和机器学习关键参数的同过程优化。运用定标—验证—测试机制,利用定标集样本建立咖啡蛋白质的NIR分析模型,随参数变动形成三维随动优选结构的建模预测结果,结合验证集样本对模型进行联合优选,然后将优化模型应用于测试集样本进行模型评价。LV-SVM建模优选的验证集预测均方根误差为6.797,对应的测试集预测均方根误差为8.384。LV-ELM建模优选的验证集预测均方根误差为6.118,对应的测试集预测均方根误差为7.837。与常规偏最小二乘(PLS)方法相比较,LV-SVM和LV-ELM方法均取得更好的预测结果,验证了潜变量机器学习方法在近红外定量分析中的应用优势,该方法有望应用于不同类型的咖啡各成分含量检测。