关键词： Gross primary productivity (GPP)   Sentinel-2 (S2)   Landsat 8   Machine learning (ML)   Neural networks (NN)   Radiative transfer modeling (RTM)   Hybrid approach   Soil-canopy-observation of photosynthesis and the energy balance (SCOPE)   C3 crops  

摘要： Satellite remote sensing has been widely used in the last decades for agricultural applications, both for assessing vegetation condition and for subsequent yield prediction. Existing remote sensing-based methods to estimate gross primary productivity (GPP), which is an important variable to indicate crop photosynthetic function and stress, typically rely on empirical or semi-empirical approaches, which tend to over-simplify photosynthetic mechanisms. In this work, we take advantage of all parallel developments in mechanistic photosynthesis modeling and satellite data availability for an advanced monitoring of crop productivity. In particular, we combine process-based modeling with the soil-canopy energy balance radiative transfer model (SCOPE) with Sentinel-2 and Landsat 8 optical remote sensing data and machine learning methods in order to estimate crop GPP. With this approach, we by-pass the need for an intermediate step to retrieve the set of vegetation biophysical parameters needed to accurately model photosynthesis, while still accounting for the complex processes of the original physically-based model. Several implementations of the machine learning models are tested and validated using simulated and flux tower-based GPP data. Our final neural network model is able to estimate GPP at the tested flux tower sites with r(2) of 0.92 and RMSE of 1.38 gC d(-1) m(-2), which outperforms empirical models based on vegetation indices. The first test of applicability of this model to Landsat 8 data showed good results (r(2) of 0.82 and RMSE of 1.97 gC d(-1) m(-2)), which suggests that our approach can be further applied to other sensors. Modeling and testing is restricted to C3 crops in this study, but can be extended to C4 crops by producing a new training dataset with SCOPE that accounts for the different photosynthetic pathways. Our model successfully estimates GPP across a variety of C3 crop types and environmental conditions even though it does not use any local info

关键词： Prosthetic hip implant   Polyethylene wear   Pin-on-disc   Machine learning  

摘要： Pin-on-disc (PoD) experiments are widely used to quantify and rank wear of different material couples for prosthetic hip implant bearings. However, polyethylene wear results obtained from different PoD experiments are sometimes difficult to compare, which potentially leaves information inaccessible. We use machine learning methods to implement several data-driven models, and subsequently validate them by quantifying the prediction error with respect to published experimental data. A data-driven model can supplement results from PoD wear experiments, and enables predicting polyethylene wear of new PoD experiments based on its operating parameters. It also reveals the relative contribution of individual PoD operating parameters to the resulting polyethylene wear, thus informing design of experiments, and potentially reducing the need for time consuming PoD wear measurements.

关键词： Domain-specific text   Machine learning   Readability   Support vector machine   Text mining  

摘要： Text readability assessment is a challenging interdisciplinary endeavor with rich practical implications. It has long drawn the attention of researchers internationally, and the readability models since developed have been widely applied to various fields. Previous readability models have only made use of linguistic features employed for general text analysis and have not been sufficiently accurate when used to gauge domain-specific texts. In view of this, this study proposes a latent-semantic-analysis (LSA)-constructed hierarchical conceptual space that can be used to train a readability model to accurately assess domain-specific texts. Compared with a baseline reference using a traditional model, the new model improves by 13.88% to achieve 68.98% of accuracy when leveling social science texts, and by 24.61% to achieve 73.96% of accuracy when assessing natural science texts. We then combine the readability features developed for the current study with general linguistic features, and the accuracy of leveling social science texts improves by an even higher degree of 31.58% to achieve 86.68%, and that of natural science texts by 26.56% to achieve 75.91%. These results indicate that the readability features developed in this study can be used both to train a readability model for leveling domain-specific texts and also in combination with the more common linguistic features to enhance the efficacy of the model. Future research can expand the generalizability of the model by assessing texts from different fields and grade levels using the proposed method, thus enhancing the practical applications of this new method.

关键词： classification models   decision tree (DT)   GIIA sPLA(2) inhibitors   random forest (RF)   support vector machine (SVM)  

摘要： GIIA secreted phospholipase A(2) (GIIA sPLA(2)) is a potent target for drug discovery. To distinguish the activity level of the inhibitors of GIIA sPLA(2), we built 24 classification models by three machine learning algorithms including support vector machine (SVM), decision tree (DT), and random forest (RF) based on 452 compounds. The molecules were represented by CORINA descriptors, MACCS fingerprints, and ECFP4 fingerprints, respectively. The dataset was split into a training set containing 312 compounds and a test set containing 140 compounds by Kohonen's self-organizing map (SOM) strategy and a random strategy. A recursive feature elimination (RFE) method and an information gain (IG) method were used in the selection of molecular descriptors. Three favorable performing models were obtained. They were built by SVM algorithm with CORINA descriptors (Models 1A and 2A) and ECFP4 fingerprints (Model 10A). In the prediction of test set of Model 10A, the accuracy reached 90.71%, and the Matthews correlation coefficient (MCC) values reached 0.82. In addition, the 452 inhibitors were clustered into eight subsets by K-Means algorithm for analyzing their structural features. It was found that highly active inhibitors mainly contained indole scaffold or indolizine scaffold and four side chains.

关键词： Terrorism  

摘要： In this paper, we employ machine learning methods to solve the problem of countering terrorism and extremism by using information from the Internet. This problem involves retrieving electronic messages, documents, and web resources that potentially contain information of terrorist or extremist nature, identifying the structure of user groups and online communities that disseminate this information, monitoring and modeling information flows in these communities, as well as assessing threats and predicting risks based on monitoring results. We propose some original language-independent algorithms for pattern-based information retrieval, thematic modeling, and prediction of message flow characteristics, as well as assessment and prediction of potential risk coming from members of online communities by using data on the structure of relations in these communities, which makes it possible to detect potentially dangerous users even without full access to the content they distribute, e.g., through private channels and chat rooms.

关键词： Auctions   bidding   regularized linear regression   forecasting  

摘要： It is well-known that empirical analysis suffers from multicollinearity and high dimensionality. In particular, this is much more severe in an empirical study of itemized bids in highway procurement auctions. To overcome this obstacle, this article employs the regularized linear regression for the estimation of a more precise interval for project winning bids. The approach is put to the test using empirical data of highway procurement auctions in Vermont. In our empirical analysis, we first choose a set of crucial tasks that determine a bidder's bid amounts by using the random forest variable selection method. Given the selected tasks, project bid forecasting is conducted. We compare our proposed methodology with the least square linear model based on the bias and the standard root mean square error of the bid estimates. There is evidence supporting that the suggested approach provides superior forecasts for an interval of winning bids over the competing model. As far as we know, this article is the first attempt to provide reference bids of highway construction contracts.

关键词： 数据挖掘   疾病分类   医疗大数据   决策树算法  

摘要： 随着医院信息系统(HIS)在全国各大医院的推广和应用,会有大量和病人相关的临床数据每天在医院中记录,而这些真实的数据随着规模积累的增加,存在着对病人和医生来说潜在、有价值的信息作用也会越来越大。本文会根据医院信息系统(HIS),通过决策树算法,针对疾病诊断的影响因子进行预测分析,得出一个有效帮助诊断的分析模型,通过一段时间论证分析,该模型会在临床应用中有一定的指导作用。

关键词： intensive care unit   ventilator-associated pneumonia   artificial neural network   support vector machine   ensemble neural networks   cross-validation  

摘要： One concern to the patients is the off-line detection of pneumonia infection status after using the ventilator in the intensive care unit. Hence, machine learning methods for ventilator-associated pneumonia (VAP) rapid diagnose are proposed. A popular device, Cyranose 320 e-nose, is usually used in research on lung disease, which is a highly integrated system and sensor comprising 32 array using polymer and carbon black materials. In this study, a total of 24 subjects were involved, including 12 subjects who are infected with pneumonia, and the rest are non-infected. Three layers of back propagation artificial neural network and support vector machine (SVM) methods were applied to patients' data to predict whether they are infected with VAP with Pseudomonas aeruginosa infection. Furthermore, in order to improve the accuracy and the generalization of the prediction models, the ensemble neural networks (ENN) method was applied. In this study, ENN and SVM prediction models were trained and tested. In order to evaluate the models' performance, a fivefold cross-validation method was applied. The results showed that both ENN and SVM models have high recognition rates of VAP with Pseudomonas aeruginosa infection, with 0.9479 +/- 0.0135 and 0.8686 +/- 0.0422 accuracies, 0.9714 +/- 0.0131, 0.9250 +/- 0.0423 sensitivities, and 0.9288 +/- 0.0306, 0.8639 +/- 0.0276 positive predictive values, respectively. The ENN model showed better performance compared to SVM in the recognition of VAP with Pseudomonas aeruginosa infection. The areas under the receiver operating characteristic curve of the two models were 0.9842 +/- 0.0058 and 0.9410 +/- 0.0301, respectively, showing that both models are very stable and accurate classifiers. This study aims to assist the physician in providing a scientific and effective reference for performing early detection in Pseudomonas aeruginosa infection or other diseases.

关键词： 人脸识别   机器学习   像素特征   模型训练  

摘要： 随着时代的进步,人类发展的脚步愈来愈向着先进、科技的方面前行,AI的出现很好地说明了这一特点。AI技术运用在人类生活中的方方面面,而离人们生活最近的则为人脸识别方面技术的应用。本文首先回顾人脸识别的研究进展,据不同时间段所进行的研究历程进行分析;随后介绍人脸识别工作原理以及分析人脸识别目前存在的问题并据其弊端提出一定的改进措施;最后并对人脸识别的发展进行展望。

关键词： 机器学习   竞争性自适应重加权   主成分分析   偏最小二乘   支持向量机  

摘要： 为实现对过量使用1-MCP化学保鲜剂猕猴桃快速、无损检测,提出高光谱技术结合机器学习建立识别模型的检测方法。首先对空白猕猴桃和过量化学保鲜猕猴桃在865.11～1 711.71 nm范围内进行高光谱数据采集。然后选用标准正态变量变换方法预处理原始光谱数据以去除噪声,采用波段比算法增强图像,数学形态学算法提取感兴趣区域,进而计算光谱平均值。最后采用主成份分析(PCA)、竞争性自适应加权(CARS)方法对全光谱数据(FS)进行特征提取,去除干扰项;以PCA和CARS提取的特征量和FS数据作为输入,结合偏最小二乘(PLS)和支持向量机(SVM)建立12个识别模型。试验结果表明,基于PLS和SVM建立的识别模型均能够有效检测过量化学保鲜猕猴桃,其中CARS-SVM模型性能最好,平均正确识别率达100%,运行速度最快,仅为0.015 348 s,满足工程实践中实时性高的要求,为快速、无损检测猕猴桃果品安全提供理论支撑。