关键词： AUTHORSHIP -- Attribution   MACHINE learning   ARTIFICIAL intelligence   MACHINE theory   MULTIVARIATE analysis   CORRELATION (Statistics)  

摘要： We compare and benchmark the performance of five classification methods, four of which are taken from the machine learning literature, in a classic authorship attribution problem involving the Federalist Papers. Cross-validation results are reported for each method, and each method is further employed in classifying the disputed papers and the few papers that are generally understood to be coauthored. These tests are performed using two separate feature sets: a "raw" feature set containing all words and word bigrams that are common to all of the authors, and a second "pre-processed" feature set derived by reducing the raw feature set to include only words meeting a minimum relative frequency threshold. Each of the methods tested performed well, but nearest shrunken centroids and regularized discriminant analysis had the best overall performances with 0/70 cross-validation errors.

关键词： Accessibility evaluation   chemical compounds   cross-validation   Machine Learning   compounds   Minute   Learning methods   Accessibility   limits (mathematics)   general assessment   SYNTHETICS  

摘要： With de novo rational drug design, scientists can rapidly generate a very large number of potentially biologically active probes. However, many of them may be synthetically infeasible and, therefore, of limited value to drug developers. On the other hand, most of the tools for synthetic accessibility evaluation are very slow and can process only a few molecules per minute. In this study, we present two approaches to quickly predict the synthetic accessibility of chemical compounds by utilizing support vector machines operating on molecular descriptors. The first approach, RSSVM, is designed to identify the compounds that can be synthesized using a specific set of reactions and starting materials and builds its model by training on the compounds identified as synthetically accessible or not by retrosynthetic analysis. The second approach, DRSVM, is designed to provide a more general assessment of synthetic accessibility that is not tied to any set of reactions or starting materials. The training set compounds for this approach are selected from a diverse library based on the number of other similar compounds within the same library. Both approaches have been shown to perform very well in their corresponding areas of applicability with the RSSVM achieving a receiver operator characteristic score of 0.952 in cross-validation experiments and the DRSVM achieving a score of 0.888 on an independent set of compounds. Our implementations can successfully process thousands of compounds per minute.

关键词： BACTERIAL genetics   GENES   MACHINE learning   GENOMES   SALMONELLA typhimurium  

摘要： Background: Identifying essential genes in bacteria supports to identify potential drug targets and an understanding of minimal requirements for a synthetic cell. However, experimentally assaying the essentiality of their coding genes is resource intensive and not feasible for all bacterial organisms, in particular if they are infective. Results: We developed a machine learning technique to identify essential genes using the experimental data of genome-wide knock-out screens from one bacterial organism to infer essential genes of another related bacterial organism. We used a broad variety of topological features, sequence characteristics and co-expression properties potentially associated with essentiality, such as flux deviations, centrality, codon frequencies of the sequences, co-regulation and phyletic retention. An organism-wise cross-validation on bacterial species yielded reliable results with good accuracies (area under the receiver-operator-curve of 75%-81%). Finally, it was applied to drug target predictions for Salmonella typhimurium. We compared our predictions to the viability of experimental knock-outs of S. typhimurium and identified 35 enzymes, which are highly relevant to be considered as potential drug targets. Specifically, we detected promising drug targets in the non-mevalonate pathway. Conclusions: Using elaborated features characterizing network topology, sequence information and microarray data enables to predict essential genes from a bacterial reference organism to a related query organism without any knowledge about the essentiality of genes of the query organism. In general, such a method is beneficial for inferring drug targets when experimental data about genome-wide knockout screens is not available for the investigated organism.

关键词： 机器学习   网络攻击   结合语义   信息安全   恶意代码   多态蠕虫签名提取  

摘要： 近两年中美国因病毒、间谍软件等网络攻击损失近85亿美元，而中国大陆更是有数以亿计的大量主机和网络被恶意攻击、破坏和篡改。一方面，种类繁多功能各异的诸如virus，worm，rootkit,spyware，botnets,adware等malware层出不穷，黑客攻击方式、手段与过程不断复杂深化；另一方面，信息系统漏洞不断增长，漏洞越来越多。强大的经济利益的驱动使得恶意代码检测(detection)与防范(defense)技术仍是信息安全届亟需解决的No.1问题。攻击者不断升级并复杂化新的攻击手段，防守者根据攻击提出防护措施，例如修补patch,注入防护疫苗（vaccin）等；进一步地，攻击者提出新的反检测(anti-detection)和规避（evasion）技术，防护者也要不断更新防护技术。攻防双方不断博弈（game）,两者在动态平衡中，不断将局部的马鞍点（saddle point）向前推进。统计机器学习源于统计，长于关系推理和知识的自动学习，已在文本分析，视频分析，图像理解，语音信号识别取得极好的效果。我们把恶意代码检测与攻击比作一场猫捉老鼠的游戏，统计机器学习能不能有效的扮演“猫”的角色，能不能在已有的恶意代码检测与分析的基础上在如虎添翼？我们将通过几个具体的案例分析来回答上述问题。本文论域中的恶意代码包含两类，第一类是基于packet的恶意代码，例如多态蠕虫，通过网络传播的shellcode;第二类是基于文件的恶意代码，例如被攻陷（compromised）的exe文件或者dll文件。最后我们还给出了一个机器学习在多线程程序安全中的应用案例分析。\n 第二章中，提出了一种结合语义的多态蠕虫签名提取算法，用于检测多态蠕虫。字符串提取和匹配技术已经广泛的用于基于签名提取的恶意代码检测中。但是，如何快速有效的产生蠕虫签名尤其在敌手（adversarial）环境中仍然是一个十分挑战的问题。一方面，攻击者有足够的自由来操纵攻击packet中的字符分布来逃脱检测；另一方面，因为恶意流池（a suspicious flow pool）在签名产生过程中使用，攻击者可以注入噪声字节到恶意流池中，从而误导签名产生过程。为了解决上述攻击，我们提出了SAS，一种新的结合语义（semantic aware）的统计算法用于自动产生签名。当SAS处理来自于恶意流池中的packet时，它使用数据流分析技术来移除正常的packet和恶意packet中的正常字节。结果上，那些相关于语义的字节被保留下来。基于这些

关键词： 机器学习方法   神经网络方法   环境科学   计算机智能   人工智能   年代   信息  

摘要： 机器学习是计算机智能（也叫人工智能）的一个主要的子领域。它的主要目标就是利用计算的方法从数据中提取信息。神经网络方法，一般被认为是机器学习研究中的第一次突破，它自上世纪80年代以来开始流行，而核方法是在上世纪90年代后半期作为机器学习研究的第二波高潮而到来的。本书对于机器学习方法和它在环境科学中的应用给出了统一的处理。

关键词： 集成学习   子分类器   基因数据   机器学习方法   子空间优化  

摘要： 当前,集成学习是机器学习和数据挖掘领域中热门的研究方向。集成学习是使用一系列学习器进行学习,再按照某种规则把各个学习器结果进行整合从而获得比单个学习器更好的学习效果的一种机器学习方法。集成学习在生产、科研和生活中有着广泛应用前景。本文主要在子空间的优化以及子分类器的选择上对集成学习作了较深入的研究,并将这些改进的算法应用到基因数据分析中,主要工作包括如下几个方面:\n 1.提出了一种基于遗传算法的子分类器选择分类集成算法GASS。为了解决由不同的子空间生成的子分类器(Subclassifier)之间存在的相关性或冗余性对分类过程产生不必要时间与空间消耗以及对分类结果的影响,探索了如何在这些子分类器中选择尽量少的分类器而分类集成的效果尽量好,此方法叫做子分类器选择(SubclassifierSelection)。从实验结果看,GASS在时间开销和分类精确度方面都达到了比较好的效果,本文对遗传算法中适应度函数的参数也做了相应讨论与分析。\n 2.提出了一种基于Simba的子空间优化算法FSEL。该算法利用基于假设间隔的特征选择算法Simba对数据集的各个特征按其贡献度进行排序,得到一个特征贡献度序列,并对这个序列进行分段,并对各个段区设定选择特征的比例,这样既可以按设定取到贡献度大的特征,也能做到对不同贡献度的特征的选取保证了分类器的差异性,以达到最好的分类效果。实验结果表明分类结果得到了较大提高,并且对分段段数和段区比例等参数都做了不同的设置并对结果进行讨论分析。\n 3.将GASS算法和FSEL算法应用到高维基因数据分析中。GASS算法通过将高维特征进行子空间选择,并过滤掉相关性大的子分类器;FSEL算法对高维特征进行子空间优化,特征子空间尽量选择贡献度较大的特征,忽略贡献度很小的特征,并且在不同的贡献度上做到平衡。实验效果表明GASS算法和FSEL算法对于高维基因数据也有较好的效果。

关键词： gamma-secretase inhibitors   machine learning   support vector machine (SVM)   random forest (RF)   virtual screening  

摘要： gamma-Secretase inhibitors have been explored for the prevention and treatment of Alzheimer's disease (AD). Methods for prediction and screening of gamma-secretase inhibitors are highly desired for facilitating the design of novel therapeutic agents against AD, especially when incomplete knowledge about the mechanism and three-dimensional structure of gamma-secretase. We explored two machine learning methods, support vector machine (SVM) and random forest (RF), to develop models for predicting gamma-secretase inhibitors of diverse structures. Quantitative analysis of the receiver operating characteristic (ROC) curve was performed to further examine and optimize the models. Especially, the Youden index (YI) was initially introduced into the ROC curve of RF so as to obtain an optimal threshold of probability for prediction. The developed models were validated by an external testing set with the prediction accuracies of SVM and RE 96.48 and 98.83% for gamma-secretase inhibitors and 98.18 and 99.27% for noninhibitors, respectively. The different feature selection methods were used to extract the physicochemical features most relevant to gamma-secretase inhibition. To the best of our knowledge, the RF model developed in this work is the first model with a broad applicability domain, based on which the virtual screening of gamma-secretase inhibitors against the ZINC database was performed, resulting in 368 potential hit candidates. (C) 2009 Wiley Periodicals, Inc. J Comput Chem 31: 1249-1258, 2010

关键词： Vasodilators   Identification   Molecular descriptors   Machine learning   Support vector machine (SVM)  

摘要： Vasodilators have been extensively used in the treatment of various vascular diseases. With the aim of developing the accurate computational models for identifying vasodilators of diverse structures, several machine learning methods, such as C4.5 decision tree (C4.5 DT), k-nearest neighbor (k-NN), and support vector machine (SVM), were explored in this work. These identification models were trained by using 198 three-dimensional molecular descriptors and a group of 635 compounds including 308 vasodilators and 327 non-vasodilators, in which feature selection was conducted to optimize the training models and select the most appropriate descriptors for identifying the vasodilators. An independent validation set of 74 vasodilators and 87 non-vasodilators was subsequently used to evaluate the performance of the developed identification models. The identification rates of these models are in the range of 78.38%-97.30% for vasodilators and 83.91%-86.21% for non-vasodilators. Our investigation reveals that the explored machine learning methods, especially SVM, are potentially useful for the identification of vasodilators. (C) 2010 Elsevier B.V. All rights reserved.

关键词： Internet traffic   Network traffic classification   Machine learning   Feature selection   SVM  

摘要： Accurate and timely traffic classification is critical in network security monitoring and traffic engineering. Traditional methods based on port numbers and protocols have proven to be ineffective in terms of dynamic port allocation and packet encapsulation. The signature matching methods, on the other hand, require a known signature set and processing of packet payload, can only handle the signatures of a limited number of IP packets in real-time. A machine learning method based on SVM (supporting vector machine) is proposed in this paper for accurate Internet traffic classification. The method classifies the Internet traffic into broad application categories according to the network flow parameters obtained from the packet headers. An optimized feature set is obtained via multiple classifier selection methods. Experimental results using traffic from campus backbone show that an accuracy of 99.42% is achieved with the regular biased training and testing samples. An accuracy of 97.17% is achieved when un-biased training and testing samples are used with the same feature set. Furthermore, as all the feature parameters are computable from the packet headers, the proposed method is also applicable to encrypted network traffic.

关键词： 软件故障定位度量   语句执行次数   机器学习方法   多变量预测模型  

摘要： 为定位具有故障的语句，人们在测试用例执行信息的基础上开发了多种语句级的可疑度度量，并用它们来对语句的可疑度进行排序，帮助程序员更快的找出存在故障的语句。其中的一些度量方法如SAFL[1]能在一定程度上减少冗余测试用例的影响，大大改进语句级可疑度度量的精确度。\n 然而先前的研究工作都没有将语句执行次数作为影响因子加入分析过程；且研究者的工作都集中在对单个可疑度度量的性能分析上，而没有考虑这些度量联合使用时的效果。本文针对这两个问题，提出了两种新的分别针对单个度量和多个度量联合的故障定位方法：（1）将语句执行次数作为一个重要影响因子加入测试用例的矩阵执行模型，同时结合SAFL的去冗思想，得出一种新的语句级故障定位度量；（2）利用机器学习方法建立多变量的预测模型，在此基础上对语句的可疑度进行排序。\n 本文首先对六种语句级故障定位方法的结果进行了比较，在此基础上进行了基于语句执行次数的故障定位实验和基于机器学习方法的实验。初步的实验结果表明，两种新的方法均能够提高语句的故障定位性能，其中多变量预测模型将有更深远的启发研究意义。