关键词： 迁移学习   输入输出一致性   领域调整   超光谱数据分类   遥感   光谱导数特征   深度置信网络  

摘要： 随着遥感技术的不断发展,我们能获得的遥感图像不仅在数量上呈现爆炸式增长,而且光谱特征维度也进一步增加。然而,人工标定遥感图像费时费力,所以需要借助机器学习方法自动处理图像。本文的研究工作主要包括分类算法设计和光谱特征学习。域调整(Domain adaptation)方法主要处理原始域(source domain)和目标域(target domain)数据分布存在一定差异而又相互联系的问题,同时,要求两个域的分类任务一致。在遥感图像分类领域,这个现象非常普遍,例如同一地区采集的遥感数据,其采集时间、天气条件、大气环境等可能不同；或是同一遥感探测器采集的数据,也可能来自不同地点(即便拥有类似的地貌特征)。处理这类数据,直接使用基于独立同分布假设的分类模型,一般达不到令人满意的效果。在本文中,我们提出了一个基于输入输出空间一致性假设的域调整算法。我们从目标域中选择高置信度权值的半标记点,同时删除不符合目标域数据分布的原始域训练点,迭代式的重新训练分类模型。因此,我们将该算法命名为输入输出一致性域调整算法(input-consistent-output domain adaptation, ICODA)。ICODA算法在两个实际超光谱数据集(Botswana和KSC)上,进行验证评测。相关实验结果表明,ICODA算法所获得的最终分类正确率要比一般传统分类器要提高不少。另外,在光谱特征基础上,做简单计算可以得到光谱导数特征,该特征很容易反映光谱曲线的变化趋势。现有的研究工作,采取不同手段将此特征融入到原始光谱特征中,用于遥感数据分类。本文研究在没有其它数据预处理手段(e.g.降维、特征混合等)情况下,光谱导数特征对传统分类器有效的条件。在大量实验基础上,我们得出在以下两个条件下,原光谱特征融入一阶导数特征会较大提高分类正确率：1)训练集相对较小；2)训练集质量较差,受噪音影响大。同时,大量免费下载的遥感数据可用于深度学习的无监督特征学习。本文在NASA AVIRIS墨西哥湾溢油数据上,应用深度置信网络(DBN)学习算法探测溢油区域,所得实验分类结果和RGB波段导出彩图具有很高的吻合性。

关键词： 生物学   信息   支持向量机  

摘要： 生物学的新发现将极大地依赖于我们在多个维度和不同尺度下对多样化的数据进行组合和关联的分析能力,而不再仅依赖对传统领域的继续关注。在生物信息的存储、获取、联网、处理、浏览以及可视化等方面,都对理论、算法和软件的发展提出了迫切的需要,计算机科学也从生命系统中获得启示,产生了许多新概念,包括:决策树、随机森林、支持向量机、人工神经网络等等。这样的学科交叉丰富了各个相关领域,这将在未来的几十年中得到进一步发展。

关键词： environmental   information   fingerprints   Fingerprints   Erbium   TEST SETS   chemical compounds   environmental chemistry   Estrogen Receptors   Support Vector Network   Active  

摘要： There are thousands of environmental chemicals subject to regulatory decisions for endocrine disrupting potential. The ToxCast and Tox21 programs have tested similar to 8200 chemicals in a broad screening panel of in vitro high-throughput screening (HTS) assays for estrogen receptor (ER) agonist and antagonist activity. The present work uses this large data set to develop in silico quantitative structure-activity relationship (QSAR) models using machine learning (ML) methods and a novel approach to manage the imbalanced data distribution. Training compounds from the ToxCast project were categorized as active or inactive (binding or nonbinding) classes based on a composite ER Interaction Score derived from a collection of 13 ER in vitro assays. A total of 1537 chemicals from ToxCast were used to derive and optimize the binary classification models while 5073 additional chemicals from the Tox21 project, evaluated in 2 of the 13 in vitro assays, were used to externally validate the model performance. In order to handle the imbalanced distribution of active and inactive chemicals, we developed a cluster-selection strategy to minimize information loss and increase predictive performance and compared this strategy to three currently popular techniques: cost-sensitive learning, oversampling of the minority class, and undersampling of the majority class. QSAR classification models were built to relate the molecular structures of chemicals to their ER activities using linear discriminant analysis (LDA), classification and regression trees (CART), and support vector machines (SVM) with 51 molecular descriptors from QikProp and 4328 bits of structural fingerprints as explanatory variables. A random forest (RF) feature selection method was employed to extract the structural features most relevant to the ER activity. The best model was obtained using SVM in combination with a subset of descriptors identified from a large set via the RF algorithm, which recognized the active and

关键词： Research Article  

摘要： The goal of this work is to introduce new metrics to assess risk of Alzheimer's disease (AD) which we call AD Pattern Similarity (AD-PS) scores. These metrics are the conditional probabilities modeled by large-scale regularized logistic regression. The AD-PS scores derived from structural MRI and cognitive test data were tested across different situations using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) study. The scores were computed across groups of participants stratified by cognitive status, age and functional status. Cox proportional hazards regression was used to evaluate associations with the distribution of conversion times from mild cognitive impairment to AD. The performances of classifiers developed using data from different types of brain tissue were systematically characterized across cognitive status groups. We also explored the performance of anatomical and cognitive-anatomical composite scores generated by combining the outputs of classifiers developed using different types of data. In addition, we provide the AD-PS scores performance relative to other metrics used in the field including the Spatial Pattern of Abnormalities for Recognition of Early AD (SPARE-AD) index and total hippocampal volume for the variables examined.

关键词： confinement coefficient   reinforced concrete columns   M5' machine learning method   model tree   new formula  

摘要： Predicting the lateral confinement coefficient in reinforced concrete columns is a very important issue in structural engineering. Therefore, several experimental formulas have developed to predict it. Recently, soft computing tools such as artificial neural networks have been used to predict the confinement coefficient. However, these tools are not as transparent as empirical formulas. In this study, another soft computing approach, i.e. model trees have been used for predicting the confinement coefficient. The main advantage of model trees is that, unlike the other data learning tools, they are easier to use and more importantly they represent understandable mathematical rules. In this paper, a new formula that includes some structural parameter is derived using dimensionless parameter for estimating the confinement coefficient. A comparison is made between the estimated confinement coefficient by this new formula and formula given by others researches shows the accuracy of prediction.

关键词： Diesel engine modelling   Engine performance   Kernel based extreme learning machine   Hybrid inference   Data exponentiality   Data scarcity  

摘要： Traditional methods on creating diesel engine models include the analytical methods like multi-zone models and the intelligent based models like artificial neural network (ANN) based models. However, those analytical models require excessive assumptions while those ANN models have many drawbacks such as the tendency to overfitting and the difficulties to determine the optimal network structure. In this paper, several emerging advanced machine learning techniques, including least squares support vector machine (LS-SVM), relevance vector machine (RVM), basic extreme learning machine (ELM) and kernel based ELM, are newly applied to the modelling of diesel engine performance. Experiments were carried out to collect sample data for model training and verification. Limited by the experiment conditions, only 24 sample data sets were acquired, resulting in data scarcity. Six-fold cross-validation is therefore adopted to address this issue. Some of the sample data are also found to suffer from the problem of data exponentiality, where the engine performance output grows up exponentially along the engine speed and engine torque. This seriously deteriorates the prediction accuracy. Thus, logarithmic transformation of dependent variables is utilized to pre-process the data. Besides, a hybrid of leave-one-out cross-validation and Bayesian inference is, for the first time, proposed for the selection of hyperparameters of kernel based ELM. A comparison among the advanced machine learning techniques, along with two traditional types of ANN models, namely back propagation neural network (BPNN) and radial basis function neural network (RBFNN), is conducted. The model evaluation is made based on the time complexity, space complexity, and prediction accuracy. The evaluation results show that kernel based ELM with the logarithmic transformation and hybrid inference is far better than basic ELM, LS-SVM, RVM, BPNN and RBFNN, in terms of prediction accuracy and training time. (C) 2013 Else

关键词： Machine learning   Virtual screening   Classification   Drug design  

摘要： A multidimensional analysis of machine learning methods performance in the classification of bioactive compounds was carried out. Eleven learning algorithms (including 4 meta-classifiers): J48, RandomForest, NaiveBayes, PART, Hyperpipes, SMO, Ibk, MultiBoostAB, Decorate, FilteredClassifier and Bagging, implemented in the WEKA package, were evaluated in the classification of 5 protein target ligands (cyclooxygenase-2, HIV-1 protease and metalloproteinase inhibitors, M-1 and 5-HT1A agonists), using 8 different fingerprints for molecular representation (EStateFP, FP, ExtFP, GraphFP, KlekFP, MACCSFP, PubChemFP, and SubFP). The influence of the number of actives in the training data as well as the computational expenses expressed by the time required for building a predictive model was also taken into account. Tests were performed for sets containing a similar number of actives and inactives and also for datasets recreating virtual screening conditions. In order to facilitate the interpretation of results, the evaluating parameters (recall, precision, and MCC) values were presented in the form of heat maps. The classification of cyclooxygenase-2 inhibitors was almost perfect regardless of the conditions, yet the results for the rest of the targets varied between different experiments. The performance of machine learning methods was improved by increasing the number of actives in the training data;however, the moving to virtual screening conditions was generally connected with a significant fall in precision. Some methods, e.g. SMO, Bagging, Decorate and MultiBoostAB, were more stable regarding changes in classification conditions, whereas in the case of the others, such as NaiveBayes, J48 or Hyperpipes, the performance strongly varied between different datasets, fingerprints and targets. The application of meta-learning led to an increase in the values of evaluating parameters. KlekFP was a fingerprint which yielded the best results, although its use was connected with g

关键词： Machine learning   Magnetic resonance imaging   Neuroimaging   Obsessive-compulsive disorder   Support vector regression   Symptom severity  

摘要： Background: Recently, machine learning methods have been used to discriminate, on an individual basis, patients from healthy controls through brain structural magnetic resonance imaging (MRI). However, the application of these methods to predict the severity of psychiatric symptoms is less common. Methods: Herein, support vector regression (SVR) was employed to evaluate whether gray matter volumes encompassing cortical-subcortical loops contain discriminative information to predict obsessive compulsive disorder (OCD) symptom severity in 37 treatment naive adult OCD patients. Results: The Pearson correlation coefficient between predicted and observed symptom severity scores was 0.49 (p=0.002) for total Dimensional Yale Brown Obsessive-Compulsive Scale (DY-BOCS) and 044 (p=0.006) for total Yale Brown Obsessive-Compulsive Scale (Y-BOCS). The regions that contained the most discriminative information were the left medial orbitofrontal cortex and the left putamen for both scales. Limitations: Our sample is relatively small and our results must be replicated with independent and larger samples. Conclusions: These results indicate that machine learning methods such as SVR analysis may identify neurobiological markers to predict OCD symptom severity based on individual structural MRI datasets. (C) 2013 Elsevier B.V. All rights reserved

关键词： Visualization   Machine-learning   Similarity   Fingerprints  

摘要： Fingerprint similarity is a common method for comparing chemical structures. Similarity is an appealing approach because, with many fingerprint types, it provides intuitive results: a chemist looking at two molecules can understand why they have been determined to be similar. This transparency is partially lost with the fuzzier similarity methods that are often used for scaffold hopping and tends to vanish completely when molecular fingerprints are used as inputs to machine-learning (ML) models. Here we present similarity maps, a straightforward and general strategy to visualize the atomic contributions to the similarity between two molecules or the predicted probability of a ML model. We show the application of similarity maps to a set of dopamine D3 receptor ligands using atom-pair and circular fingerprints as well as two popular ML methods: random forests and naive Bayes. An open-source implementation of the method is provided.

关键词： classification   spam host   Spamdexing   web spam   WEBSPAM-UK2006   WEBSPAM-UK2007  

摘要： In this paper, we present recent contributions for the battle against one of the main problems faced by search engines: the spamdexing or web spamming. They are malicious techniques used in web pages with the purpose of circumvent the search engines in order to achieve good visibility in search results. To better understand the problem and finding the best setup and methods to avoid such virtual plague, in this paper we present a comprehensive performance evaluation of several established machine learning techniques. In our experiments, we employed two real, public and large datasets: the WEBSPAM-UK2006 and the WEBSPAM-UK2007 collections. The samples are represented by content-based, link-based, transformed link-based features and their combinations. The found results indicate that bagging of decision trees, multilayer perceptron neural networks, random forest and adaptive boosting of decision trees are promising in the task of web spam classification. [ABSTRACT FROM AUTHOR]