关键词： GCMs   machine learning   multi-model ensemble   random forest   support vector machine  

摘要： Global climate models (GCMs) are useful tools for assessing climate change impacts on temperature and rainfall. Although climate data from various GCMs have been increasingly used in climate change impact studies, GCMs configurations and module characteristics vary from one to another. Therefore, it is crucial to assess different GCMs to confirm the extent to which they can reproduce the observed temperature and rainfall. Rather than assessing the interdependence of each GCM, the purpose of this study is to compare the capacity of four different multi-model ensemble (MME) methods (random forest [RF], support vector machine [SVM], Bayesian model averaging [BMA] and the arithmetic ensemble mean [EM]) in reproducing observed monthly rainfall and temperature. Of these four methods, the RF and SVM demonstrated a significant improvement over EM and BMA in terms of performance criteria. The relative importance of each GCM based on the RF ensemble in reproducing rainfall and temperature could also be ranked. We compared the GCMs importance and Taylor skill score and found that their correlation was 0.95 for temperature and 0.54 for rainfall. Our results also demonstrated that the number of GCMs ensemble simulations could be reduced from 33 to 25 in RF model while maintaining predictive error less than 2%. Having such a representative subset of simulations could reduce computational costs for climate impact modelling and maintain the quality of ensemble at the same time. We conclude that machine learning MME could be efficient and useful with improved accuracy in reproducing historical climate variables.

关键词： Email   Detection   Machine learning   Analysis   Malware   Features  

摘要： In recent years, cyber-attacks against businesses and organizations have increased. Such attacks usually result in significant damage to the organization, such as the loss and/or leakage of sensitive and confidential information. Because email communication is an integral part of daily business operations, attackers frequently leverage email as an attack vector in order to initially penetrate the targeted organization. Email message allows the attacker to deliver dangerous content to the victim, such as malicious attachments or links to malicious websites. Existing email analysis solutions analyze only specific parts of the email using rule-based methods, while other important parts remain unanalyzed. Existing anti-virus engines primarily use signature-based detection methods, and therefore are insufficient for detecting new unknown malicious emails. Machine learning methods have been shown to be effective at detecting maliciousness in various domains and particularly in email. Previous works which used machine learning methods suggested sets of features which offer a limited perspective over the whole email message. In this paper, we propose a novel set of general descriptive features extracted from all email components (header, body, and attachments) for enhanced detection of malicious emails using machine learning methods. The proposed features are extracted just from the email itself;therefore, our features are independent, since the extraction process does not require an Internet connection or the use of external services or other tools, thereby meeting the needs of real-time detection systems. We conducted an extensive evaluation of our new novel features against sets of features suggested by previous academic work using a collection of 33,142 emails which contains 38.73% malicious and 61.27% benign emails. The results show that malicious emails can be detected effectively when using our novel features with machine learning algorithms. Moreover, our novel feat

关键词： 文本聚类   机器学习方法   应用   K-means   聚类算法   中文分词   LDA  

摘要： 本文主要从原理上介绍了两种文本聚类的算法——K-means和LDA。文章第一部分介绍了文本聚类的背景,包括定义、应用和意义;文章第二部分介绍了当前的研究背景以及研究热点;第三部分介绍了文本聚类的一般步骤,涉及到的技术有中文分词和聚类算法;最后一部分为总结展望。

关键词： 数据挖掘   机器学习   网络异常检测监督   执行   回归   同化  

摘要： 近年来,随着互联网技术的飞速发展,网络的覆盖面积逐渐扩大,而相应的规模和结构也变得日益复杂,导致网络安全问题频发,成为人们关注的重点。本文分别介绍了基于数据挖掘和基于机器学习方法的两种网络异常检测技术的内容和特点,希望能够为相关的工作提供借鉴和参考。

关键词： 基性-超基性岩   定量分类模型   铜镍矿床   成矿预测   北山地区  

摘要： 岩浆岩分类是研究岩浆岩成因及其成矿作用的基础,传统的岩浆岩二维图解分类方法,因仅有个别元素参与分类、岩石矿物学定名无法保证统一性等因素,其分类结果不够精确。本文基于地质大数据研究基本思想、方法,应用多元统计"聚类分析"和"判别分析"的算法,分别构建起"北山地区基性-超基性岩氧化物定量分类系列模型"和"北山地区基性-超基性岩氧化物+微量元素定量分类系列模型"。前者将北山地区406件基性-超基性岩样本,在10个氧化物变量空间分为2大类共9个小类,其中89%的含矿样本分布在占总样本量44%的3个小类中。后者将北山地区266件基性-超基性岩样本,在34个氧化物及微量元素变量空间分为2大类共8个小类,其中98%的含矿样本分布在占总样本量33%的2个小类中,且81%的含矿样本分布在仅占总样本量21%的Ⅰ222分类中,在该分类中含矿样本数占该分类样本的61%,则有理由认为剩余39%的样本所在岩体为找矿的有利岩体。上述二个模型分类结果中含矿样本对定量分类的高度选择性,充分证明所建定量分类系列模型对北山地区基性-超基性岩成矿岩体分类的高度有效性,为北山地区基性-超基性岩成矿岩体预测研究提供了依据。

关键词： 机器学习   天然气水合物   稳定带   支持向量机  

摘要： 随着互联网大数据发展,人工智能算法逐渐能自动学习数据特征和挖掘大数据隐藏的信息,且其预测结果具有极高的准确度和可靠性。机器学习是人工智能的核心算法,目前已应用于多个领域,在地球科学领域的应用也已兴起。天然气水合物稳定带是评估水合物资源潜力的关键参数,其准确性直接影响水合物勘探进程和结果。前人在计算水合物稳定带厚度时往往采用较为简单的模型,忽略气体组分、热导率等因素的影响,计算结果存在较大偏差。基于不同海水盐度和气体组分条件下的天然气水合物实验数据构建机器学习模型,利用机器学习算法预测天然气水合物的相平衡条件;进而结合南海北部的气体组分、热流、热导率等数据,计算得到南海北部水合物稳定带厚度。结果分析表明机器学习模型预测的水合物相平衡曲线与实验数据高度吻合,决定系数高达0.997。计算的南海北部水合物稳定带厚度与水合物钻井和地震资料揭示的结果基本一致。本研究提供了一个机器学习算法在水合物稳定带厚度估算中的应用实例,表明人工智能算法在未来天然气水合物资源预测和潜力评价中具有较大的应用前景。

关键词： Exchange rates   Forecasting   Machine learning   Purchasing power parity   Uncovered interest rate parity   Taylor-rule exchange rate models  

摘要： Using methods from machine learning we show that fundamentals from simple exchange rate models (PPP or UIRP) or Taylor-rule based models lead to improved exchange rate forecasts for major currencies over the floating period era 1973-2014 at a 1-month forecast horizon which beat the no-change forecast. Fundamentals thus contain useful information and exchange rates are forecastable even for short horizons. Such conclusions cannot be obtained when using rolling or recursive OLS regressions as used in the literature. The methods we use - sequential ridge regression and the exponentially weighted average strategy, both with discount factors - do not estimate an underlying model but combine the fundamentals to directly output forecasts. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Anatomy   Molecular fingerprints   Molecular modeling   Machine learning   Receptors  

摘要： The farnesoid X receptor (FXR) emerges as a promising drug target involved in regulating various metabolic pathways, yet some xenobiotic compounds binding to FXR would be an important determinant to induce the receptor dysfunctions that lead to undesirable side effects. Thus, it is critical to identify potential xenobiotics that disrupt normal FXR functions. In this work, five machine learning methods coupled with eight molecular fingerprints and 20 molecular descriptors were used to develop classification models for prediction of FXR binders. The built models were evaluated using the test set and two external validation sets. The best model was obtained using a combination of molecular descriptors and fingerprints, which exhibited the AUC values of 0.83 and 0.92 for the test set and the first external validation set, respectively. The overall prediction accuracy for the second external validation set with the best model was over 85%. Furthermore, several representative privileged substructures that are essential for FXR binders, such as benzimidazole, indole, and stilbene moiety, were detected using information gain and substructure frequency analysis. The applicability domain analysis via the Euclidean distance-based approach demonstrated a marked impact on the improvement of prediction accuracy. Overall, our built models could be helpful to rapidly identify potential chemicals binding to FXR.

关键词： Forest Fire danger   Geographical Information System   Artificial Neural Network   Differential Flower Pollination   Backpropagation  

摘要： Forest fire danger map at regional scale is considered of utmost importance for local authority to efficiently allocate its resources to fire prevention measures and establish appropriate land use plans. This study aims at introduce a new machine learning method, named as DFP-MnBpAnn, based on Artificial Neural Network (Ann) with a novel hybrid training algorithm of Differential Flower Pollination (DFP) and mini-match backpropagation (MnBp) for spatial modeling of forest fire danger. Tropical forest of the Lam Dong province (Vietnam) was used as case study. To achieve this task, a Geographical Information System (GIS) database of the forest fire for the study area was established. Accordingly, DFP, as a metaheuristic method, is used to optimize the weights and structure of Ann to fit the GIS database at hand. Whereas, MnBp is employed periodically during the DFP-based optimization process, in which MnBp acts as a local search aiming to accelerate both the quality of the found solutions and the convergence rate. Experimental outcomes demonstrate that the proposed DFP-MnBpAnn model is superior to other benchmark methods with satisfactory prediction accuracy (Classification Accuracy Rate = 88.43%). This fact confirms that DFP-MnBpAnn is a promising alternative for the problem of large-scale forest fire danger mapping.