关键词： Machine learning   Decision making   Decision tree   Random forest   Automated neural network  

摘要： Background Machine learning is a broad term encompassing a number of methods that allow the investigator to learn from the data. These methods may permit large real-world databases to be more rapidly translated to applications to inform patient-provider decision making. Methods This systematic literature review was conducted to identify published observational research of employed machine learning to inform decision making at the patient-provider level. The search strategy was implemented and studies meeting eligibility criteria were evaluated by two independent reviewers. Relevant data related to study design, statistical methods and strengths and limitations were identified;study quality was assessed using a modified version of the Luo checklist. Results A total of 34 publications from January 2014 to September 2020 were identified and evaluated for this review. There were diverse methods, statistical packages and approaches used across identified studies. The most common methods included decision tree and random forest approaches. Most studies applied internal validation but only two conducted external validation. Most studies utilized one algorithm, and only eight studies applied multiple machine learning algorithms to the data. Seven items on the Luo checklist failed to be met by more than 50% of published studies. Conclusions A wide variety of approaches, algorithms, statistical software, and validation strategies were employed in the application of machine learning methods to inform patient-provider decision making. There is a need to ensure that multiple machine learning approaches are used, the model selection strategy is clearly defined, and both internal and external validation are necessary to be sure that decisions for patient care are being made with the highest quality evidence. Future work should routinely employ ensemble methods incorporating multiple machine learning algorithms.

关键词： Digital soil sampling   Machine learning   Semi-supervised learning   Self-training   Predictive mapping  

摘要： Numerous machine learning models have been developed for constructing the relationship between soil classes or properties and its environmental covariates in digital soil mapping (DSM). Most machine learning models are trained with a supervised learning (SL) method based on training samples. However, the collected sample data is often limited in practice due to that field sampling is expensive and time-consuming. The insufficient samples may limit the learning ability of the model to a large extent. Semi-supervised machine learning, a new machine learning paradigm that makes use of both unsampled data and a small amount of sampled data in the learning process, can be a potential effective method for DSM. In this study, we present a self-training semi-supervised learning (SSL) method for DSM. Different with the SL method for machine learning models, the SSL method not only utilizes the sampled locations but also the abundant environmental covariate information at the unvisited locations. Its basic idea is to iteratively enlarge the training data set by adding the unsampled points with high prediction confidence from the unvisited locations until a stopping criterion reached. The proposed SSL method was applied in machine learning models for predicting soil classes in Heshan Farm of Nenjiang County in Heilongjiang Province, China. Three machine learning models, including multinomial logistic regression (MLR), k-nearest neighbor (KNN) and random forest (RF), were selected to evaluate the efficiency of the SSL method. The entropy threshold was an important parameter in the SSL method, and a sensitivity analysis on this parameter was conducted with using a series of entropy thresholds. The SSL method was compared with the SL method for the three machine learning models for soil prediction. A cross-validation was employed to evaluate the accuracy of the predicted soil class maps generated based on each method. The results showed that the prediction accuracies (the proport

关键词： Spatial interpolation   Multiple point statistics   Bayesian compressive sampling   Compressive sensing   Sparse measurement  

摘要： Spatial interpolation has been frequently encountered in earth sciences and engineering.A reasonable appraisal of subsurface heterogeneity plays a significant role in planning,risk assessment and decision making for geotechnical *** is commonly used to interpolate spatially varying properties at un-sampled locations from scatter ***,successful application of classic geostatistical models requires prior characterization of spatial auto-correlation structures,which poses a great challenge for unexperienced engineers,particularly when only limited measurements are ***-driven machine learning methods,such as radial basis function network(RBFN),require minimal human intervention and provide effective alternatives for spatial interpolation of non-stationary and non-Gaussian data,particularly when measurements are *** RBFN,however,is direction independent(***)and cannot quantify prediction uncertainty in spatial *** this study,an ensemble RBFN method is proposed that not only allows geotechnical anisotropy to be properly incorporated,but also quantifies uncertainty in spatial *** proposed method is illustrated using numerical examples of cone penetration test(CPT)data,which involve interpolation of a 2D CPT cross-section from limited continuous 1D CPT soundings in the vertical *** addition,a comparative study is performed to benchmark the proposed ensemble RBFN with two other non-parametric data-driven approaches,namely,Multiple Point Statistics(MPS)and Bayesian Compressive Sensing(BCS).The results reveal that the proposed ensemble RBFN provides a better estimation of spatial patterns and associated prediction uncertainty at un-sampled locations when a reasonable amount of data is available as ***,the prediction accuracy of all the three methods improves as the number of measurements increases,and vice *** is also found that BCS prediction is less se

关键词： Structure-activity relationship (SAR)   quantitative structure-activity relationship (QSAR)   K-Means   tyrosinase inhibitors   machine learning  

摘要： Tyrosinase is a key rate-limiting enzyme in the process of melanin synthesis, which is closely related to human pigmentation disorders. Tyrosinase inhibitors can down-regulate tyrosinase to effectively reduce melanin synthesis. In this work, we conducted structure-activity relationship (SAR) study on 1097 diverse mushroom tyrosinase inhibitors. We applied five kinds of machine learning methods to develop 15 classification models. Model 5B built by fully connected neural networks and ECFP4 fingerprints achieved the highest prediction accuracy of 91.36% and Matthews correlation coefficient (MCC) of 0.81 on the test set. The applicability domains (AD) of classification models were defined by d(STD-PRO) method. Moreover, we clustered the 1097 inhibitors into eight subsets by K-Means to figure out inhibitors' structural features. In addition, 10 quantitative structure-activity relationship (QSAR) models were constructed by four machine learning methods based on 813 inhibitors. Model 6 J, the best QSAR model, was developed by fully connected neural networks with 50 RDKit descriptors. It resulted in a coefficient of determination (r(2)) of 0.770 and a root mean squared error (RMSE) of 0.482 on the test set. The AD of Model 6 J was visualized by Williams plot. The models built in this study can be obtained from the authors.

关键词： 矿产资源定量预测   地学大数据   数据挖掘   信息融合   机器学习  

摘要： 回顾了国内外在矿产资源定量预测研究领域的发展历程,对近十年来国外相关方向的文献进行了统计对比分析,结果显示机器学习方法已经成为矿产资源定量预测研究领域的热点方向,并主要在如下3个方面发挥了积极的作用:①提取和挖掘复杂数据中隐藏的难以识别的矿化信息;②致矿异常信息关联与转换;③多源地学数据的致矿异常信息融合、预测和发现矿床。对逻辑回归、人工神经网络、随机森林与支持向量机等主要机器学习算法与模型在矿产资源定量预测实践中的应用效果进行了评述,并探讨了在实际应用过程中存在的样本选择、错分代价、不确定性评价以及模型性能评价等主要问题及目前的解决方案。最后提出基于大数据与机器学习的矿产资源定量预测是未来发展的重要趋势。

关键词： BP模型   XGBoost模型   机器学习   暴雨内涝灾情   灾情阈值   上海  

摘要： 本文基于区域灾害系统理论,综合考虑致灾因子、暴露度和脆弱性,提出了一套暴雨内涝灾情预测指标体系;在此基础上利用上海市应急联动中心110接报暴雨内涝灾情数据,构建了暴雨内涝灾情预测BP模型(Back Propagation Model)和XGBoost模型(Extreme Gradient Boosting Model),并对比分析了预测模型效果,实现对上海市暴雨过程内涝灾情数量预测;最后对内涝灾情影响等级进行阈值划分,以期为暴雨内涝影响预报与风险预警业务、服务及灾害管理提供技术支撑。结果表明:1)综合考虑致灾因子、暴露度、脆弱性指标且不经主成分分析降维的指标组合作为暴雨内涝灾情预测指标体系时,BP模型和XGBoost模型的预测精度最优;2)全量样本XGBoost模型总体表现最优,暴雨内涝灾情的右偏分布和内涝灾情的异常高值均对XGBoost模型预测误差有不同程度的贡献;3)综合评价法在历史灾情百分位法和模拟灾情百分位法基础上,结合多年业务实践经验和用户对于110灾情的处置承受力对暴雨内涝灾情进行阈值划分,在实际应用中具有一定参考意义。

关键词： 缺资料小流域   时空变源混合产流模型   参数区域化   机器学习方法  

摘要： 针对山丘区中小流域洪水预报面临的产流机制混合多变和模型参数难以获取的问题,提出了适用于缺资料地区的中小流域时空变源混合产流模型和基于机器学习CART的参数区域化方法。在小流域地貌水文响应单元划分基础上,利用GARTO非饱和下渗计算模型,从超渗/蓄满机制的平面混合、垂向混合和时段混合三个方面构建时空变源混合产流模型,并采用机器学习CART方法进行模型参数区域化研究。选取不同地貌类型区的15个流域和河南省19个小流域实测降雨径流资料分别对模型适用性和参数区域化方法进行了验证。结果表明,通过与国内外8个水文模型的对比验证,时空变源混合产流模型模拟平均纳什系数为0.78,比其他模型提高约20%;利用本模型和CART参数区域化方法在河南省19个流域计算的平均纳什系数为0.70,比参数随机移植结果提高了35%,本模型和参数区域化方法在山丘区中小流域洪水模拟中应用效果较好。

关键词： 处理效应异质性   机器学习   因果随机森林   贝叶斯叠加回归树  

摘要： 处理效应异质性是定量社会科学关注的重点。本文以因果随机森林与贝叶斯叠加回归树为例,指出以算法为导向的新兴分析手段可以克服模型形式和变量选择的限制,并考虑变量间各种交互关系。因果随机森林与贝叶斯叠加回归树分别体现了"匹配"和"模拟"的分析逻辑,以帮助研究者勾勒出异质性处理效应的经验分布并探索该异质性的决定因素。然而,参数设定差异和算法差异都会损害处理效应异质性分析结果的稳健性。

关键词： 阿尔茨海默病   磁共振成像   机器学习   正则化   逻辑回归   支持向量机   分类   预测  

摘要： 目的利用机器学习算法对分类模型进行优化,实现对阿尔茨海默病(AD)病程的分类预测。资料与方法纳入543例研究对象,根据疾病发展病程分为认知功能正常(CN)组、早期轻度认知功能下降(EMCI)组、晚期轻度认知功能下降(LMCI)组和AD组。收集结构磁共振成像(sMRI)和人口统计学指标共276项数据。将正则化惩罚项L1与逻辑回归模型(LR)和支持向量机(SVM)模型分别融合进行特征选择和学习器训练,获取表征性强的特征集合;同时对AD的病程进行两两分类,以十折交叉验证评估两种模型的分类准确率。采用受试者工作特征(ROC)曲线评价模型的分类性能。结果L1-LR和L1-SVM模型在AD病程转化时均表现出较好的分类效果。其中,L1-SVM模型区分CN组与LMCI组、CN组与AD组、EMCI组与AD组的准确率最高,分别为93.63%、100.00%和99.32%。L1-SVM模型区分CN组和AD组的准确率和特异度均为100.00%,ROC曲线下面积为1.00。L1-SVM整体平均准确率为91.49%,略高于L1-LR的90.81%。结论L1-SVM和L1-LR两种模型在不同的病程分类组中分类效果不同,均可作为AD的早期辅助诊断工具,其中L1-SVM模型的预测效能更好。

关键词： 混杂复合材料   等效热传导性能   机器学习方法   小波变换  

摘要： 混杂复合材料是一种新型复合材料,其复杂的细观结构导致预测其等效热传导性能极富挑战性.本文结合渐近均匀化方法、小波变换方法和机器学习方法发展了一种新的可以有效预测混杂复合材料等效热传导性能的小波-机器学习混合方法.该方法主要包括离线多尺度建模和在线机器学习两部分.首先借助渐近均匀化方法通过离线多尺度建模建立了混杂复合材料的热传导性能材料数据库,然后利用小波变换方法对离线的材料数据库进行预处理,接下来分别运用人工神经网络和支持向量回归方法建立混杂复合材料等效热传导性能预测的在线机器学习模型.最后通过对周期和随机混杂复合材料进行数值实验,验证了小波-机器学习混合方法的有效性,数值实验结果表明小波-神经网络混合方法具有最优的预测效果和抗噪能力.此外,需要强调的是对于具有高维大规模数据特征的随机混杂复合材料,小波-机器学习混合方法不仅可以提取离线材料数据库的重要特征,还可以显著减少在线监督学习的输入数据规模并提高机器学习模型的训练效率及抗噪性能.本文建立的小波-机器学习混合方法不仅适用于混杂复合材料等效热传导性能的预测,还可进一步推广应用于复合材料等效物理、力学性能的预测.