摘要： The reference evapotranspiration (ET0) estimates is important for water resources and irrigation management. The Penman-Monteith equation is known for its accuracy but requires a high number of climatic parameters that are not always available. Thus, this study aimed to evaluate the performance of machine learning techniques (cubist regression, artificial neural network with Bayesian regularization, support vector machine with linear kernel function) and stepwise multiple linear regression method to estimate daily ET(0)with limited weather data in a Brazilian agricultural frontier (MATOPIBA). Climatic data from 2000 to 2016 obtained from 23 weather stations were used. Five data scenarios were evaluated: (i) all variables, (ii) radiation and temperature, (iii) temperature and relative humidity, (iv) wind speed and temperature, and (v) temperature. The results showed that the machine learning methods are robust in estimating ET0, even in the absence of some variables. Among the methods evaluated using only temperature data, the cubist regression showed better performance. When estimating water demand for soybean and maize crops using only temperature, the cubist regression and calibrated Hargreaves-Samani equation showed the smallest errors.

关键词： Machine learning (ML)   nanodevice   nonequilibrium   Green's function (NEGF) simulations  

摘要： As the device size scalesdown to the nanometer regime, quantum effects play an important role in device characteristicsand performance. Quantum transport device simulation based on the nonequilibrium Green's function (NEGF) has been extensively applied to simulate the nanoscaledevices. TheNEGF simulations, however, can be computationally expensive, especially in the presence of scattering. In this study, a machine learning (ML)-based framework is developed, targeting on replacing the computationally intensive NEGF simulations. This framework first learns a sparse representation of a quantum transport property of interest and then trains a model to describe the quantitative mapping relation between the device parameters and properties. Also, the accuracy is further improved with the application of feature engineering. As an example, a graphene-ferroelectric-metal (GFM) ferroelectric tunnel junction (FTJ) is simulated. The results show that the ML-based framework allows circumventing the NEGF calculation and simultaneously maintaining high accuracy in quantum transmissions and tunneling I - V characteristics. This ML-based framework can be applied to speed up the quantum transport device simulations and enable efficient tunneling device design.

关键词： Debris flow   Himalayas area   Bayes discriminant analysis   Logistic regression   Random forest   Susceptibility  

摘要： Debris flows destroys the facilities and seriously threatens human lives, especially in mountainous area. Susceptibility mapping is the key for hazard prevention. The aim of the present study is to compare the performance of three methods including Bayes discriminant analysis (BDA), logistic regression (LR) and random forest (RF) for debris flow susceptibility mapping from three aspects: applicability, analyticity and accuracy. Nyalam county, a debris flow-prone area, located in Southern Tibet, was selected as the study area. Firstly, the dataset containing 49 debris flow inventories and 16 conditioning factors was prepared. Subsequently, divided the dataset into two groups with a ratio of 70/30 for training and validation purposes, and repeated 5 times to obtain 5 different groups. Then, 16 factors were involved in the modeling of RF, of which 11 factors with low linear correlation were for BDA and LR. Finally, receiver operating characteristic curves, the area under curve (AUC) and contingency tables were applied to evaluated the accuracy performance of the 3 models. The prediction rates were 74.6-81.8%, 74.6-83.6% and 80-92.7%, for the BDA, LR and FR, while the AUC values of three models were 0.72-0.78, 0.82-0.92 and 0.90-0.99, respectively. Compare to LR an BDA, RF not only effectively process and preserved dataset without priori assumption and the obtained susceptibility zoning map and major factors were reasonable. The conclusion of the current study is useful for risk mitigation and land use planning in the study area and provide related references to other researches.

关键词： Machine learning   Mutation   Position specific mutation   One-hot encoding   Haemophilia   Factor VIII  

摘要： Haemophilia is an X-linked genetic disorder in which A and B types are the most common that occur due to absence or lack of protein factors VIII and IX, respectively. Severity of the disease depends on mutation. Available Machine Learning (ML) methods that predict the mutational severity by using traditional encoding approaches, generally have high time complexity and compromised accuracy. In this study, Haemophilia 'A' patient mutation dataset containing 7784 mutations was processed by the proposed Position-Specific Mutation (PSM) and One-Hot Encoding (OHE) technique to predict the disease severity. The dataset processed by PSM and OHE methods was analyzed and trained for classification of mutation severity level using various ML algorithms. Surprisingly, PSM outperformed OHE, both in terms of time efficiency and accuracy, with training and prediction time improvement in the range of approximately 91 to 98% and 80 to 99% respectively. The severity prediction accuracy also improved by using PSM with different ML algorithms.

关键词： Gene expression analysis   Machine learning   Metastasis   Prostate cancer  

摘要： The present study aimed to identify the genes associated with the involvement of adjunct lymph nodes of patients with prostate cancer (PCa) and to provide valuable information for the identification of potential diagnostic biomarkers and pathological genes in PCa metastasis. The most important candidate genes were identified through several machine learning approaches including K-means clustering, neural network, Naive Bayesian classifications and PCA with or without downsampling. In total, 21 genes associated with lymph nodes involvement were identified. Among them, nine genes have been identified in metastatic prostate cancer, six have been found in the other metastatic cancers and four in other local cancers. The amplification of the candidate genes was evaluated in the other PCa datasets. Besides, we identified a validated set of genes involved in the PCa metastasis. The amplification of SPAG1 and PLEKHF2 genes were associated with decreased survival in patients with PCa.

关键词： australian real house price index   autoregression   forecasting   machine learning   neural networks   time series  

摘要： We employ 47 different algorithms to forecast Australian log real house prices and growth rates, and compare their ability to produce accurate out-of-sample predictions. The algorithms, which are specified in both single- and multi-equation frameworks, consist of traditional time series models, machine learning (ML) procedures, and deep learning neural networks. A method is adopted to compute iterated multistep forecasts from nonlinear ML specifications. While the rankings of forecast accuracy depend on the length of the forecast horizon, as well as on the choice of the dependent variable (log price or growth rate), a few generalizations can be made. For one- and two-quarter-ahead forecasts we find a large number of algorithms that outperform the random walk with drift benchmark. We also report several such outperformances at longer horizons of four and eight quarters, although these are not statistically significant at any conventional level. Six of the eight top forecasts (4 horizons x 2 dependent variables) are generated by the same algorithm, namely a linear support vector regressor (SVR). The other two highest ranked forecasts are produced as simple mean forecast combinations. Linear autoregressive moving average and vector autoregression models produce accurate olne-quarter-ahead predictions, while forecasts generated by deep learning nets rank well across medium and long forecast horizons.

关键词： Relapsed/refractory DLBCL   Imbalanced data   Classification and possibility prediction   Machine learning   Indicators  

摘要： Background: Treatments are limited for patients with relapsed/refractory Diffuse large B-cell lymphoma (DLBCL), and their survival rate is low. Prediction of the recurrence hazard for each patient could provide a reference regarding chemotherapy regimens for clinicians to extend patients' period of long-term remission. As current strategies cannot satisfy such need, we have established predictive models to classify patients with DLBCL with complete remission who had recurrences in 2 years from ones who did not. Methods: We assessed 518 patients with DLBCL and measured 52 variables of each patient. They were treated between January 2011 and July 2016. 17 variables were first selected by variable selection methods (including Lasso, Adaptive Lasso, and Elastic net). Then, we set classifiers and probability models for imbalanced data by combining the SMOTE sampling, cost-sensitive, and ensemble learning (consisting of AdaBoost, voting strategy, and Stacking) methods with the machine learning methods (Support Vector Machine, BackPropagation Artificial Neural Network, Random Forest), respectively. Last, assessed their performance. Results: The disease stage and other 5 variables are significant indicators for recurrence. The SVM with AdaBoost ensemble learning method modeling by SMOTE data performs the best (Sensitivity=97.3%, AUC=96%, RMSE=19.6%, G-mean=96%) in all classifiers. The SVM with AdaBoost method(AUC=98.7%, RMSE=17.7%, MXE=12.7%, Cal mean=3.2%, 1350=2.5%, 1351=4%, BSALL=3.1%) and random forest (AUC=99.5%, RMSE=19.8%, MXE=16.2%, Cal mean=9.1%, 1350=4.8%, 1351=2.9%, BSALL=3.9%) both modeling by SMOTE sampling data perform well in probability models. Conclusions: This predictive model has high accuracy for almost all DLBCL patients and the six indicators can be recurrence signals. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Left-sided colon cancer   Right-sided colon cancer   Machine learning   Mutations   Gene expression  

摘要： BackgroundIn recent years, the differences between left-sided colon cancer (LCC) and right-sided colon cancer (RCC) have received increasing attention due to the clinicopathological variation between them. However, some of these differences have remained unclear and conflicting results have been *** The Cancer Genome Atlas (TCGA), we obtained RNA sequencing data and gene mutation data on 323 and 283 colon cancer patients, respectively. Differential analysis was firstly done on gene expression data and mutation data between LCC and RCC, separately. Machine learning (ML) methods were then used to select key genes or mutations as features to construct models to classify LCC and RCC patients. Finally, we conducted correlation analysis to identify the correlations between differentially expressed genes (DEGs) and mutations using logistic regression (LR) *** found distinct gene mutation and expression patterns between LCC and RCC patients and further selected the 30 most important mutations and 17 most important gene expression features using ML methods. The classification models created using these features classified LCC and RCC patients with high accuracy (areas under the curve (AUC) of 0.8 and 0.96 for mutation and gene expression data, respectively). The expression of PRAC1 and BRAF V600E mutation (rs113488022) were the most important feature for each model. Correlations of mutations and gene expression data were also identified using LR models. Among them, rs113488022 was found to have significance relevance to the expression of four genes, and thus should be focused on in further *** the basis of ML methods, we found some key molecular differences between LCC and RCC, which could differentiate these two groups of patients with high accuracy. These differences might be key factors behind the variation in clinical features between LCC and RCC and thus help to improve treatment, such as determining the appropriate therapy

关键词： Machine learning   force fields   molecular dynamics   ab initiomolecular dynamics   instant modelling  

摘要： Ab initiomolecular dynamics (AIMD) has become a popular simulation technique but long simulation times are often hampered due to its high computational effort. Alternatively, classical molecular dynamics (MD) based on force fields may be used, which, however, has certain shortcomings compared to AIMD. In order to alleviate that situation, a trajectory-based machine learning (TrajML) approach is introduced for the construction of force fields by learning from AIMD trajectories. Only nuclear trajectories are required, which can be obtained by other methods beyond AIMD as well. We developed an easy-to-use MD machine learning package (TrajML MD) for instant modelling of the force field and system-focussed prediction of molecular configurations for MD trajectories. It consumes similar computational resources as classical MD but can simulate complex systems with a higher accuracy due to the targeted learning on the system of interest.