关键词： 扩散加权成像   前列腺癌   机器学习  

摘要： 探究使用机器学习方法,提升对扩散加权成像(DWI)多参数图的前列腺癌(PCa)诊断的准确性。对39例前列腺癌患者、56例良性患者,进行磁共振扩散加权图像的采集,并使用传统单指数模型(Mono)、拉伸指数模型(SEM)、弥散张量成像(DTI)模型、弥散峰度成像(DKI)模型以及体内素不相干运动扩散(IVIM)模型等5种重建模型,得到共计16个参数图,而后对于每一个参数图进行直方图分析,得到相关图像特征后使用机器学习的方法进行分类。使用支持向量机和随机森林两种分类器对前列腺病变进行良恶性分类,随机森林分类器的AUC值可以达到0.98,具有较高的分类性能。另外,对特征进行重要性排序后,发现DKI参数图是肿瘤分类的重要指标。

关键词： 打入桩   轴向承载力   极端梯度提升   回归算法   机器学习  

摘要： 在复杂的工程地质环境中,打入桩的轴向承载力的预测是设计和施工的一个重大挑战。本研究将利用机器学习工具一极端梯度提升算法(XGBoost)预测打入桩的轴向承载力,对桩身最大压缩应力(MCS)、最大拉伸应力(MTS)和每英尺锤击数(BPF)进行了研究,并与反向传播神经网络(BPNN)和随机森林(RF)算法进行了比较分析。利用美国北卡罗来纳州的桩数据库中4000多个数据集生成训练和预测样本。利用均方根误差(RMSE)、平均绝对误差(MAE)和线性相关系数(R^2)等性能指标对三种回归算法的有效性进行了验证。结果表明,与其他两种方法相比.XGBoost算法在解决桩、锤、土以及施工工艺等复杂非线性问题时,具有更高的稳定性和预测精度。XGBoost算法作为一种可靠的机器学习算法,可以为其他类似桩基工程轴向承载力的预测提供参考。

关键词： 机器学习   嘉兴   小微企业   信用风险   实证分析  

摘要： 以嘉兴市2013-2017年发生信贷业务的小微企业为研究对象,对2646家小微企业2013-2017年的金融信用信息进行实证分析,构建了5类小微企业信用风险评估模型,结果显示,随机森林模型更适用于嘉兴市小微企业信用风险评估,根据该方法将小微企业风险分为“高档”“中档”“低档”3类,提出了政策建议。

关键词： 非编码RNA-蛋白质相互作用   LightGBM   随机森林   极端梯度增强算法   卷积自编码器  

摘要： 目的非编码RNA-蛋白质的相互作用(noncoding RNA-protein interactions,ncRPI)具有重要的生物学意义,目前预测其相互作用已成为当下研究非编码RNA (noncoding RNA,ncRNA)和蛋白质功能的重要途径之一。方法本研究基于ncRNA和蛋白质的序列信息提取特征,运用卷积自编码器预处理原始数据,训练三个机器学习模型:LightGBM(LBM)、随机森林(random forest,RF)和极端梯度增强算法(extreme gradient boosting,XGB),预测ncRNA与蛋白质的相互作用。结果在RPI369和RPI488两个数据集做5倍交叉验证,LBM、RF与XGB三个模型在两个数据集均达到较高的预测准确率,在RPI369数据集三个模型的预测准确率分别为0.757(LBM)、0.791(RF)、0.791(XGB),在RPI488数据集三个模型的预测准确率分别为0.918(LBM)、0.908(RF)、0.918(XGB);三个模型在RPI1807、RPI2241、RPI13254大数据集也取得较高的AUC(area under curve)值,在RPI1807三个模型的AUC值均为0.99,在RPI2241三个模型最低AUC值为0.87,在RPI13254三个模型最低AUC值为0.81,都表现出较好的预测准确性。结论机器学习方法能够预测ncRNA与蛋白质是否存在相互作用。

关键词： Fused features   LBP   Pixel based results   PF clustering   Weiner Filter  

摘要： Background and Objective: Brain tumor occurs because of anomalous development of cells. It is one of the major reasons of death in adults around the globe. Millions of deaths can be prevented through early detection of brain tumor. Earlier brain tumor detection using Magnetic Resonance Imaging (MRI) may increase patient's survival rate. In MRI, tumor is shown more clearly that helps in the process of further treatment. This work aims to detect tumor at an early phase. Methods: In this manuscript, Weiner filter with different wavelet bands is used to de-noise and enhance the input slices. Subsets of tumor pixels are found with Potential Field (PF) clustering. Furthermore, global threshold and different mathematical morphology operations are used to isolate the tumor region in Fluid Attenuated Inversion Recovery (Flair) and T2 MRI. For accurate classification, Local Binary Pattern (LBP) and Gabor Wavelet Transform (GWT) features are fused. Results: The proposed approach is evaluated in terms of peak signal to noise ratio (PSNR), mean squared error (MSE) and structured similarity index (SSIM) yielding results as 76.38, 0.037 and 0.98 on T2 and 76.2, 0.039 and 0.98 on Flair respectively. The segmentation results have been evaluated based on pixels, individual features and fused features. At pixels level, the comparison of proposed approach is done with ground truth slices and also validated in terms of foreground (FG) pixels, background (BG) pixels, error region (ER) and pixel quality (Q). The approach achieved 0.93 FG and 0.98 BG precision and 0.010 ER on a local dataset. On multimodal brain tumor segmentation challenge dataset BRATS 2013, 0.93 FG and 0.99 BG precision and 0.005 ER are acquired. Similarly on BRATS 2015, 0.97 FG and 0.98 BG precision and 0.015 ER are obtained. In terms of quality, the average Q value and deviation are 0.88 and 0.017. At the fused feature based level, specificity, sensitivity, accuracy, area under the curve (AUC) and dice similarity coef

关键词： Outcome prediction   Parkinson's disease   Montreal cognitive assessment (MoCA)   Predictor algorithms   Feature selection  

摘要： Background: Given the increasing recognition of the significance of non-motor symptoms in Parkinson's disease, we investigate the optimal use of machine learning methods for the prediction of the Montreal Cognitive Assessment (MoCA) score at year 4 from longitudinal data obtained at years 0 and 1. Methods: We selected n = 184 PD subjects from the Parkinson's Progressive Marker Initiative (PPMI) database (93 features). A range of robust predictor algorithms (accompanied with automated machine learning hyperparameter tuning) and feature subset selector algorithms (FSSAs) were selected. We utilized 65%, 5% and 30% of patients in each arrangement for training, training validation and final testing respectively (10 randomized arrangements). For further testing, we enrolled 308 additional patients. Results: First, we employed 10 predictor algorithms, provided with all 93 features;an error of 1.83 +/- 0.13 was obtained by LASSOLAR (Least Absolute Shrinkage and Selection Operator - Least Angle Regression). Subsequently, we used feature subset selection followed by predictor algorithms. GA (Genetic Algorithm) selected 18 features;subsequently LOLIMOT (Local Linear Model Trees) reached an error of 1.70 +/- 0.10. DE (Differential evolution) also selected 18 features and coupled with Thiel-Sen regression arrived at a similar performance. NSGAII (Non-dominated sorting genetic algorithm) yielded the best performance: it selected six vital features, which combined with LOLIMOT reached an error of 1.68 +/- 0.12. Finally, using this last approach on independent test data, we reached an error of 1.65. Conclusion: By employing appropriate optimization tools (including automated hyperparameter tuning), it is possible to improve prediction of cognitive outcome. Overall, we conclude that optimal utilization of FSSAs and predictor algorithms can produce very good prediction of cognitive outcome in PD patients.

关键词： Technical state   circuit breaker   short circuit currents   technical diagnostics   machine learning   pattern recognition   gradient boosted trees algorithm   sample  

摘要： This paper is devoted to improving the assessment of the technical state (health index) of power circuit breakers through the use of machine learning, which allows to formalize expert knowledge, to identify implicit correlations and dependencies, and to automate the decision-making process under uncertainty. The paper proves the possibility of using machine learning based on decision trees to solve the task of assessing the power circuit breakers technical state and solves the problem of determining its optimal parameters and the training sample. The authors of the study carried out approbation of the developed model for assessing the technical state of breakers based on analyzing a large area of electrical networks in the Sverdlovsk Region, the Russian Federation, which proved its efficiency. The necessity of taking into account short-circuit currents when recognizing the pattern of the power breakers technical state is substantiated.

关键词： Air pollution   PM2.5 components   Geostatistical interpolation   Machine learning  

摘要： Numerous modeling approaches to estimate concentrations of PM2.5 components have been developed to derive better exposures for health studies, including geostatistical interpolation approaches, land use regression models and, models based on remote sensing technology. Recently, there have been some efforts to develop models based on machine learning algorithms. Each one of these exposure assessment methods has inherent uncertainties resulting in varying levels of exposure misclassification. To date, only a few studies have attempted to systematically compare exposure estimates from different PM2.5 constituent models. Our research addresses this gap, by comparing the predictive capabilities of ordinary geostatistical interpolation (Ordinary Kriging - OK), hybrid interpolation (combination of Empirical Bayesian Kriging and land use regression), and machine learning techniques (forest-based regression) for estimating PM2.5 constituents in Eastern Massachusetts in the United States. We compared the estimates of 10 ambient PM2.5 components, which included Al, Cu, Fe, K, Ni, Pb, S, Ti, V, and Zn. The OK model performed poorest for all PM2.5 components, with an R-2 under 0.30. The hybrid model presented a slight improvement, especially for Cu and Fe, for which the R-2 value increased to 0.62 and 0.59, respectively. These elements presented the highest R-2 value from the hybrid model. The forest model presented the best performance, with R-2 values higher than 0.7 for most of the particle components, including Cu, Fe, Ni, Pb, Ti, and V. Same as observed with the hybrid model, the forest model for Cu and Fe explained the highest concentration variance, with a R-2 value equal to 0.88 and 0.92, respectively. The forest model for K, S, and Zn performed poorest with an R-2 value of 0.54, 0.37, and 0.44, respectively. The results presented here can be useful for the environmental health community to more accurately estimate PM2.5 constituents over space.

关键词： Oxidoreductase subfamily classes   standardization normal distribution PSSM   correlation coefficient PSSM   RFE-SND-CC-PSSM   recursive feature elimination   SVM  

摘要： Oxidoreductase is an enzyme that widely exists in organisms. It plays an important role in cellular energy metabolism and biotransformation processes. Oxidoreductases have many subclasses with different functions, creating an important classification task in bioinformatics. In this paper, a dataset of 2640 oxidoreductase sequences was used to perform an analysis and comparison. The idea of dipeptides was introduced to process the Position Specific Score Matrix (PSSM), since each dipeptide consists of two amino acids and each column of PSSM corresponds to the information of one amino acid. Two kinds of dipeptide scores were proposed, the Standardization Normal Distribution PSSM (SND-PSSM) and the Correlation Coefficient PSSM (CC-PSSM). Recursive Feature Elimination (RFE) is used to extract features from the SND-PSSM and CC-PSSM, and the two sets of extracted features are combined to form a new feature matrix, the RFE-SND-CC-PSSM. The results show that, with the proposed method and a kernel-based nonlinear SVM classifier, the accuracy can reach 95.56% by the Jackknife test. Our method greatly improves the accuracy of oxidoreductase subclass prediction. Using this method to predict the categories of the 6 major types of enzymes effectively improves its prediction accuracy to 94.54%, indicating that this method has general applicability to other protein problems. The results show that our method is effective and universally applicable, and might be complementary to the existing methods.

关键词： Electrical vehicle   Heat pump   Refrigerant injection   Machine learning   SVR   Adaboost.R2  

摘要： A method to predict the performance of R134a heat pump with EVI (Economized Vapor Injection), is proposed in the present study. Models using SVR (Support Vector Regression) as the base estimator and Adaboost.R2 as the ensemble method, are established to predict the heating capacity and COP of the heat pump. Different feature sets for the model input are formed, based on the working principle of the heat pump system and correlation analysis. Parameters of the models are optimized to improve prediction performance. The simulation results are compared with the experimental results, and the relative errors for heating capacity and COP prediction are within 8.5%. Moreover, the impacts of injection pressure on the EVI heat pump system are discussed and simulated using the model established. The optimum injection pressure of the heat pump system can be obtained from the model under different working conditions.