关键词： Ethanol  

摘要： Permutationally invariant polynomial (PIP) regression has been used to obtain machine-learned potential energy surfaces, including analytical gradients, for many molecules and chemical reactions. Recently, the approach has been extended to moderate size molecules with up to 15 atoms. The algorithm, including "purification of the basis, " is computationally efficient for energies;however, we found that the recent extension to obtain analytical gradients, despite being a remarkable advance over previous methods, could be further improved. Here, we report developments to further compact a purified basis and, more significantly, to use the reverse differentiation approach to greatly speed up gradient evaluation. We demonstrate this for our recent four-body water interaction potential. Comparisons of training and testing precision on the MD17 database of energies and gradients (forces) for ethanol against numerous machine-learning methods, which were recently assessed by Dral and co-workers, are given. The PIP fits are as precise as those using these methods, but the PIP computation time for energy and force evaluation is shown to be 10-1000 times faster. Finally, a new PIP potential energy surface (PES) is reported for ethanol based on a more extensive dataset of energies and gradients than in the MD17 database. Diffusion Monte Carlo calculations that fail on MD17-based PESs are successful using the new PES.

关键词： Wind turbine wake   Analytical model   SCADA data   Machine learning   Actual wind farm  

摘要： To reduce the wake effect by means of layout optimization or cooperative control, it is significant to modeling wind turbine wakes in an accurate and efficient way. However, existing analytical wake models still have large errors in actual wind farms due to the inadequate consideration of various inflow factors and local environmental characteristics. To satisfy this accuracy requirement, a data-driven analytical wake model is proposed in this paper. In the model, the local inflow information and wake expansion feature are extracted from measured data of wind farms, and a machine learning model is trained to establish the relationship between the two. In this way, the model can be well adapted to the local environment and inflow conditions. Verifications in two actual wind farm cases illustrate that there is a good agreement with the measured velocity and power data. Compared with traditional analytical models, the wake prediction performance of the new model has improved more than 20%. Therefore, the proposed model can serve as a reliable tool for wind farm control and optimization.

关键词： Osteoclast differentiation   IRF8   NFATc1   Target prediction   Machine learning  

摘要： Background Interferon regulatory factor-8 (IRF8) and nuclear factor-activated T cells c1 (NFATc1) are two transcription factors that have an important role in osteoclast differentiation. Thanks to ChIP-seq technology, scientists can now estimate potential genome-wide target genes of IRF8 and NFATc1. However, finding target genes that are consistently up-regulated or down-regulated across different studies is hard because it requires analysis of a large number of high-throughput expression studies from a comparable context. Method We have developed a machine learning based method, called, Cohort-based TF target prediction system (cTAP) to overcome this problem. This method assumes that the pathway involving the transcription factors of interest is featured with multiple "functional groups" of marker genes pertaining to the concerned biological process. It uses two notions, Gene-Present Sufficiently (GP) and Gene-Absent Insufficiently (GA), in addition to log2 fold changes of differentially expressed genes for the prediction. Target prediction is made by applying multiple machine-learning models, which learn the patterns of GP and GA from log2 fold changes and four types of Z scores from the normalized cohort's gene expression data. The learned patterns are then associated with the putative transcription factor targets to identify genes that consistently exhibit Up/Down gene regulation patterns within the cohort. We applied this method to 11 publicly available GEO data sets related to osteoclastgenesis. Result Our experiment identified a small number of Up/Down IRF8 and NFATc1 target genes as relevant to osteoclast differentiation. The machine learning models using GP and GA produced NFATc1 and IRF8 target genes different than simply using a log2 fold change alone. Our literature survey revealed that all predicted target genes have known roles in bone remodeling, specifically related to the immune system and osteoclast formation and functions, suggesting confidence an

关键词： triboinformatics   tribology   COF   Al   Gr composites   machine learning   artificial neural network   dry friction   friction   tribological systems   wear   wear mechanisms  

摘要： Data-driven analysis and machine learning (ML) algorithms can offer novel insights into tribological phenomena by establishing correlations between material and tribological properties. We developed ML algorithms using tribological data available in the literature for predicting the coefficient of friction (COF) and wear-rate of self-lubricating aluminum graphite (Al/Gr) composites. We collected data on effects of material variables (graphite content, hardness, ductility, yield strength, silicon carbide content, and tensile strength), processing procedure, heat treatment and tribological test variables (normal load, sliding speed, and sliding distance) on tribological properties and established two-parameter relationships. These data are analyzed using several ML algorithms: artificial neural network (ANN), K nearest neighbor (KNN), support vector machine (SVM), gradient boosting machine (GBM), and random forest (RF). The trained ML models can predict the tribological behavior from material variables and test conditions, beyond what is possible from two-parameter correlations. GBM outperformed other ML algorithms in predicting friction behavior, while RF had the best prediction of the wear behavior. ML analysis identified graphite content and hardness and as the most significant variables in predicting the COF, while graphite content and sliding speed were the most dominant variables for wear-rates.

关键词： 数据挖掘   疾病分类   医疗大数据   决策树算法  

摘要： 伴随着当前医院信息系统在我国的很多大型医院中的普及与应用,医院每天产生患者的临床数据数量庞大,并且伴随着治疗规模的不断提升,这部分具体的数据针对医生诊疗来讲会产生非常有益的价值。信息发生了变化,变得越来越重要。基于医院信息系统(HIS),采用决策树算法对影响疾病诊断的因素进行预测分析,形成有效的诊断分析模型。

关键词： 机器学习   因子选股   Logistic回归  

摘要： 基于机器学习方法与多因子选股模型相结合,构建出新的多因子选股模型,通过机器学习算法对个股进行分类,从而筛选出具有投资价值的股票,进行构造有效的投资组合,并模拟回测证实其有效性。以沪深300成分股为股票池,运用6个因子,选取2010—2020年的数据,并对其进行去值化、标准化、中性化的处理。每个月底根据前一年的数据使用机器学习算法建模,以当月的数据输入预测下个月的综合因子,将综合因子排序,选取前两个分位点的股票分别构建等权重组合进行投资。借助优矿平台进行回测,结果显示,Logistic回归构建的模型比较好,具有较高的实际应用价值。

关键词： Oral drug delivery   Bio-enabling formulations   Food effect   Machine learning  

摘要： Despite countless advances in recent decades across various in vitro, in vivo and in silico tools, anticipation of whether a drug will show a human food effect (FE) remains challenging. One means to predict potential FE involves probing any dependence between FE and drug properties. Accordingly, this study explored the potential for two machine learning (ML) algorithms to predict likely FE. Using a collated database of drugs licensed from 2016-2020, drugs were classified into three groups;positive, negative or no FE. Greater than 250 drug properties were predicted for each drug which were used to train predictive models using Support Vector Machine (SVM) and Artificial Neural Network (ANN) algorithms. When compared, ANN outperformed SVM for FE classification upon training (82%, 72%) and testing (72%, 69%). Both models demonstrated higher FE prediction accuracy than the Biopharmaceutics Classification System (BCS) (46%). This exploratory work provided new insights into the connection between FE and drug properties as the Octanol Water Partition Coefficient (S+logP), Number of Hydrogen Bond Donors (HBD), Topological Polar Surface Area (T_PSA) and Dose (mg) were all significant for prediction. Overall, this study demonstrated the utility of ML to facilitate early anticipation of likely FE in preclinical development using four well-known drug properties.

关键词： intrusion detection systems   Internet of Things   botnet attack detection   feature selection   machine learning   ensemble methods  

摘要： Due to the wide availability and usage of connected devices in Internet of Things (IoT) networks, the number of attacks on these networks is continually increasing. A particularly serious and dangerous type of attack in the IoT environment is the botnet attack, where the attackers can control the IoT systems to generate enormous networks of "bot" devices for generating malicious activities. To detect this type of attack, several Intrusion Detection Systems (IDSs) have been proposed for IoT networks based on machine learning and deep learning methods. As the main characteristics of IoT systems include their limited battery power and processor capacity, maximizing the efficiency of intrusion detection systems for IoT networks is still a research challenge. It is important to provide efficient and effective methods that use lower computational time and have high detection rates. This paper proposes an aggregated mutual information-based feature selection approach with machine learning methods to enhance detection of IoT botnet attacks. In this study, the N-BaIoT benchmark dataset was used to detect botnet attack types using real traffic data gathered from nine commercial IoT devices. The dataset includes binary and multi-class classifications. The feature selection method incorporates Mutual Information (MI) technique, Principal Component Analysis (PCA) and ANOVA f-test at finely-granulated detection level to select the relevant features for improving the performance of IoT Botnet classifiers. In the classification step, several ensemble and individual classifiers were used, including Random Forest (RF), XGBoost (XGB), Gaussian Naive Bayes (GNB), k-Nearest Neighbor (k-NN), Logistic Regression (LR) and Support Vector Machine (SVM). The experimental results showed the efficiency and effectiveness of the proposed approach, which outperformed other techniques using various evaluation metrics.

关键词： glucose sensing   surface-enhanced infrared absorption spectroscopy   sensor calibration   machine learning   regression analysis   artificial neural network   Gaussian process regression  

摘要： The measurement and quantification of glucose concentrations is a field of major interest, whether motivated by potential clinical applications or as a prime example of biosensing in basic research. In recent years, optical sensing methods have emerged as promising glucose measurement techniques in the literature, with surface-enhanced infrared absorption (SEIRA) spectroscopy combining the sensitivity of plasmonic systems and the specificity of standard infrared spectroscopy. The challenge addressed in this paper is to determine the best method to estimate the glucose concentration in aqueous solutions in the presence of fructose from the measured reflectance spectra. This is referred to as the inverse problem of sensing and usually solved via linear regression. Here, instead, several advanced machine learning regression algorithms are proposed and compared, while the sensor data are subject to a pre-processing routine aiming to isolate key patterns from which to extract the relevant information. The most accurate and reliable predictions were finally made by a Gaussian process regression model which improves by more than 60% on previous approaches. Our findings give insight into the applicability of machine learning methods of regression for sensor calibration and explore the limitations of SEIRA glucose sensing.

关键词： Emergencies   Machine learning   Triage  

摘要： Background: In emergency services is important to accurately assess and classify symptoms, which may be improved with the help of technology. One mechanism that could help and improve predictions from health records or patient flow is machine learning (ML). Aim: To analyse the effectiveness of ML systems in triage for making predictions at the emergency department in comparison with other triage scales/scores. Methods: Following the PRISMA recommendations, a systematic review was conducted using CINAHL, Cochrane, Cuiden, Medline and Scopus databases with the search equation "Machine learning AND triage AND emergency". Results: Eleven studies were identified. The studies show that the use of ML methods consistently predict important outcomes like mortality, critical care outcomes and admission, and the need for hospitalization in comparison with scales like Emergency Severity Index or others. Among the ML models considered, XGBoost and Deep Neural Networks obtained the highest levels of prediction accuracy, while Logistic Regression performed obtained the worst values. Conclusions: Machine learning methods can be a good instrument for helping triage process with the prediction of important emergency variables like mortality or the need for critical care or hospitalization.