关键词： Ternary classification   Machine leaming methods   Estrogen receptor activities  

摘要： Endocrine-disrupting chemicals (EDCs), which can threaten ecological safety and be harmful to human beings, have been cause for wide concern. There is a high demand for efficient methodologies for evaluating potential EDCs in the environment Herein an evaluation platform was developed using novel and statistically robust ternary models via different machine learning models (i.e., linear discriminant analysis, classification and regression tree, and support vector machines). The platform is aimed at effectively classifying chemicals with agonistic, antagonistic, or no estrogen receptor (ER) activities. A total of 440 chemicals from the literature were selected to derive and optimize the three-class model. One hundred and nine new chemicals appeared on the 2014 EPA list for EDC screening, which were used to assess the predictive performances by comparing the E-screen results with the predicted results of the classification models. The best model was obtained using support vector machines (SVM) which recognized agonists and antagonists with accuracies of 76.6% and 75.0%, respectively, on the test set (with an overall predictive accuracy of 75.2%), and achieved a 10-fold cross-validation (CV) of 73.4%. The external predicted accuracy validated by the E-screen assay was 87.5%, which demonstrated the application value for a virtual alert for EDCs with ER agonistic or antagonistic activities. It was demonstrated that the ternary computational model could be used as a faster and less expensive method to identify EDCs that act through nuclear receptors, and to classify these chemicals into different mechanism groups. (C) 2016 Elsevier B.V. All rights reserved.

关键词： 网络舆情   机器学习   特征提取   支持向量机  

摘要： 本文重点是对网络用户中的网络舆情倾向性进行分析,构建一种准确率更高的模型来实现情感倾向判断。网络舆情倾向性分析主要是通过机器学习的方法和制定部分规则的方法,从而能够更加准确地判断出句子的情感倾向性,进而能在实际生活中进行有针对性地积极引导调控。基于此,提出一个设想,对于机器学习的方法之间的结合与本身的改进,再加入规则的制定,能够提高机器对情感句子的分析准确率。对于模型应用之前的特征提取的方法进行比较选取,通过特定的特征选取方式使得构造向量空间更加准确,再通过比较不同分类算法进行比较选取。

关键词： soil water retention curve   hysteresis   support vector machines   main wetting branch   main drying branch  

摘要： In this paper, we estimated using the machine learning methodology the main wetting branch of the soil water retention curve based on the knowledge of the main drying branch and other, optional, basic soil characteristics (particle size distribution, bulk density, organic matter content, or soil specific surface). The support vector machine algorithm was used for the models' development. The data needed by this algorithm for model training and validation consisted of 104 different undisturbed soil core samples collected from the topsoil layer (A horizon) of different soil profiles in Poland. The main wetting and drying branches of SWRC, as well as other basic soil physical characteristics, were determined for all soil samples. Models relying on different sets of input parameters were developed and validated. The analysis showed that taking into account other input parameters (i.e., particle size distribution, bulk density, organic matter content, or soil specific surface) than information about the drying branch of the SWRC has essentially no impact on the models' estimations. Developed models are validated and compared with well-known models that can be used for the same purpose, such as the Mualem (1977) (M77) and Kool and Parker (1987) (KP87) models. The developed models estimate the main wetting SWRC branch with estimation errors (RMSE=50.018 m(3)/m(3)) that are significantly lower than those for the M77 (RMSE=50.025 m(3)/m(3)) or KP87 (RMSE=0.047 m(3)/m(3)) models.

关键词： 足球竞彩市场   期望进球数   决策树模型   投注策略   投资收益率   机器学习  

摘要： 随着足球竞彩市场的快速发展，分析博彩公司的盘口成为一个越来越重要的课题。本文利用亚洲盘口和大小球盘的盘口数据，推导出了市场期望进球数算法，以市场期望进球数作为切入点，分析盘口的涨跌趋势，确定亚盘闭盘的投注策略。本文提出用模式识别的方式，利用机器学习中的决策树模型预测期望进球数的涨跌模式，基于决策树模型预测期望进球趋势的准确率比随机猜测有显著提高。本文以确定亚盘闭盘时的投资策略为目标，采用过滤式特征选择方法，建立了改进的k-means半监督聚类集成模型。我们采用交叉验证方法选择模型参数，以预测准确率和回报率作为两种度量性能的准则，模型的预测准确率达到了55％，回报率为2.5％。本文还研究了500等权指数由专家意见导出的二元预测问题，利用改进的机器学习算法集成专家意见，比较了Probit模型、改进的AdaBoost方法和SVM算法的预测性能。研究发现SVM算法的预测准确率最高，Probit模型的投资收益率最高。

关键词： 维吾尔文   情感词典   情感分析   机器学习  

摘要： 随着互联网整体水平的提高,大量基于维吾尔文的网络信息不断建立,引起了对不同领域的信息进行情感倾向性分析的迫切需要。该文考虑到维吾尔文没有足够的情感训练语料和完整的情感词典,结合机器学习方法和词典方法的优点,构建一个分类器模型LCUSCM(Lexicon-based and Corpus-based Uyghur Text Sentiment Classification Model),先用自己构建的维吾尔文情感词典对语料进行高质量的情感分类,分类过程中对词典进行递归扩充,再根据每条句子的情感得分,从词典分类的结果中选择一部分语料来训练一个分类器并改进第一步的分类结果。此方法的正确率比单独使用机器学习方法提高了9.13%,比词典方法提高了1.82%。

关键词： Energy   Molecular structure   Molecular modeling   Machine learning   Molecules  

摘要： Machine learning algorithms were explored for the fast estimation of HOMO and LUMO orbital energies calculated by DFT B3LYP, on the basis of molecular descriptors exclusively based on connectivity. The whole project involved the retrieval and generation of molecular structures, quantum chemical calculations for a database with >111 000 structures, development of new molecular descriptors, and training/validation of machine learning models. Several machine learning algorithms were screened, and an applicability domain was defined based oil Euclidean distances to the training set. Random forest models predicted an external test set of 9989 compounds achieving mean absolute error (MAE) up to 0.15 and 0.16 eV for the HOMO and LUMO orbitals, respectively. The impact of the quantum chemical calculation protocol was assessed with a subset of compounds. Inclusion of the orbital energy calculated by PM7 as an additional descriptor significantly improved the quality of estimations (reducing the MAE in >30%).

关键词： Artificial neural network   Bayesian network   Deforestation   Freely available data   Gaussian process   Logistic regression  

摘要： The range and quality of freely available geo-referenced datasets is increasing. We evaluate the usefulness of free datasets for deforestation prediction by comparing generalised linear models and generalised linear mixed models (GLMMs) with a variety of machine learning models (Bayesian networks, artificial neural networks and Gaussian processes) across two study regions. Freely available datasets were able to generate plausible risk maps of deforestation using all techniques for study zones in both Mexico and Madagascar. Artificial neural networks outperformed GLMMs in the Madagascan (average AUC 0.83 vs 0.80), but not the Mexican study zone (average AUC 0.81 vs 0.89). In Mexico and Madagascar, Gaussian processes (average AUC 0.89, 0.85) and structured Bayesian networks (average AUC 0.88, 0.82) performed at least as well as GLMMs (average AUC 0.89, 0.80). Bayesian networks produced more stable results across different sampling methods. Gaussian processes performed well (average AUC 0.85) with fewer predictor variables. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： BPNN   GRNNs   leaf area index   RBFNs   MSVR   retrieval  

摘要： Leaf area index (LAI) is an important biophysical parameter and the retrieval of LAI from remote sensing data is the only feasible method for generating LAI products at regional and global scales. However, most LAI retrieval methods use satellite observations at a specific time to retrieve LAI. Because of the impacts of clouds and aerosols, the LAI products generated by these methods are spatially incomplete and temporally discontinuous, and thus they cannot meet the needs of practical applications. To generate high-quality LAI products, four machine learning algorithms, including back-propagation neutral network (BPNN), radial basis function networks (RBFNs), general regression neutral networks (GRNNs), and multi-output support vector regression (MSVR) are proposed to retrieve LAI from time-series Moderate Resolution Imaging Spectroradiometer (MODIS) reflectance data in this study and performance of these machine learning algorithms is evaluated. The results demonstrated that GRNNs, RBFNs, and MSVR exhibited low sensitivity to training sample size, whereas BPNN had high sensitivity. The four algorithms performed slightly better with red, near infrared (NIR), and short wave infrared (SWIR) bands than red and NIR bands, and the results were significantly better than those obtained using single band reflectance data (red or NIR). Regardless of band composition, GRNNs performed better than the other three methods. Among the four algorithms, BPNN required the least training time, whereas MSVR needed the most for any sample size.

关键词： 机器学习   半监督学习   协同训练   众包   任务分配   模型复用  

摘要： 机器学习需要有标记数据来训练模型进行预测,有标记数据的获取通常需要人工参与,因此价格非常昂贵。在很多实际应用中,未标记数据可以较为容易地大量获取,如何利用廉价的未标记数据一直以来都是机器学习领域中的研究热点。目前出现了两种利用未标记数据的方法:一种是自动利用未标记数据辅助有标记数据提升学习性能的半监督学习;虽然该类方法大多能够提升学习性能,但都基于潜在的模型假设,当模型假设与数据分布存在偏差时可能会降低学习性能;另一种是通过众包以较低的代价给数据提供标记,进而可以精确利用未标记数据以降低学习风险。本文主要围绕半监督学习和众包进行研究,取得了以下进展:第一,针对半监督学习中的重要风范协同训练易受不充分视图的影响这一问题,提出了一种新型的加权协同训练算法。视图不充分时协同训练过程中会出现与最优分类器不一致的样本,该算法通过检测潜在的不一致样本并降低其权值以减少这些样本对训练过程的影响。实验结果表明,与标准的协同训练算法相比该算法有更好的泛化性能与更强的鲁棒性。第二,针对众包过程中任务标记依赖于任务难度这一特点,提出了一种新型的任务分配算法。该算法通过估计部分任务的难度构建训练集学得预测难度的模型,将任务分为简单和困难两类。对于简单的任务可利用众包进行标记;而对于困难的任务,则需雇佣专家为其提供高质量标记。实验结果表明该算法能够在提高标记质量的同时降低标记代价。此外,本文还对利用未标记数据的模型复用进行了研究,该场景中用户需要集成多个无法修改的预训练模型,针对这一问题,本文提出了一种新型的多视图模型复用算法。该算法通过信念传播估计预训练模型的可靠性,并基于未标记数据上的多视图一致性指导这一估计过程,进而利用估计得到的可靠性加权集成多个预训练模型。实验结果表明该方法能够显著提升分类精度。

关键词： 机器学习   软件自动化   问题解决方法的探究  

摘要： 随着我国经济技术的快速发展,我国计算机网络技术也有着很大的进步.现在网络的使用非常普遍,随着计算机林领域的快速发展,各行各业的其他领域也都参与其中,所以将其他行业串联起来互相渗透互相帮助形成了一个交叉互联的网络环境.所以对计算机的学习以及计算机软件的发展一直都是社会发展的主要关注问题.本文对两点进行了两个要点的讨论:一、软件中自动化系统的机器学习的方法探究;二、软件的学习中主要构架的建立.如果想快速发展计算机产业,这两点缺一不可.