Search

The purpose of this study is to experimentally design the drying, calcination, and sintering processes of artificial lightweight aggregates through the orthogonal array, to expand the data using the results, and to model the manufacturing process of lightweight aggregates through machine-learning techniques. The experimental design of the process consisted of L18(3661), which means that 36 × 61 data can be obtained in 18 experiments using an orthogonal array design. After the experiment, the data were expanded to 486 instances and trained by several machine-learning techniques such as linear regression, random forest, and support vector regression (SVR). We evaluated the predictive performance of machine-learning models by comparing predicted and actual values. As a result, the SVR showed the best performance for predicting measured values. This model also worked well for predictions of untested cases. [ABSTRACT FROM AUTHOR]

• A standard flowchart from raw data collection to AI algorithm-based model development is proposed. • The interaction between shield machine and ground is simulated using AI algorithm. • The application scopes of machine learning and deep learning algorithms is investigated. The interaction between a shield machine and the ground is a complicated problem involving numerous extrinsic and intrinsic factors. Machine learning (ML) algorithms have been recently employed to predict tunnel-soil interactions. This study introduces a more powerful algorithm termed the deep learning (DL) long short-term memory (LSTM) neural network, to identify the interaction between a shield machine and the ground; this network can predict tunnelling-induced maximum settlement, the longitudinal settlement curve, and shield operational parameters. In addition, the generalisation ability of LSTM is comprehensively compared with that of a conventional ML algorithm—random forest (RF)—based on field records collected from two practical tunnel projects. A standard process of developing an ML or DL algorithm-based model, including the pre-processing of raw data, feature selection, determination of optimum hyper-parameters, and evaluation of prediction performance and generalization ability, was introduced. The results indicated that the RF-based model performs capably in terms of predicting tunnelling-induced maximum settlement, and that the LSTM-based model is suitable for predicting longitudinal settlement curves and shield operational parameters. Furthermore, the generalization ability of the LSTM-based model is better than that of the RF-based model. The strong robustness of the LSTM-based model enables its application in different types of tunnel projects. [ABSTRACT FROM AUTHOR]

The present study aims to compare the performance of two machine learning techniques that can unveil the relationship between the input and target variables and predict the ground vibration (peak particle velocity, PPV) due to quarry blasting. To this end, a Random Forest (RF) model and a Bayesian Network (BN) model were developed. Before developing these models, and in order to illustrate the necessity of proposing new intelligent systems, a new empirical equation is proposed, using maximum charge per delay and distance from the blast-face. The results confirm that there is indeed a need to develop intelligent systems with more input parameters. Thus, a Feature Selection (FS) model is applied to decrease the dimensionality of data and remove the irrelevant data. The outputs of this technique set five parameters, hole depth, power factor, stemming, maximum charge per delay and distance from the blast-face, as the most important model inputs necessary to predict PPV. After constructing FS-BN and FS-RF models and comparing them under different conditions (i.e., computational cost, accuracy and robustness), it is found that the developed FS-RF model can be introduced as a new model in the field of blasting environmental issues. The accuracy level of the FS-RF model is quite high; 92.95% and 90.32% for the train and test stages, respectively, while 92.95% and 87.09% accuracy is calculated for train and test of the FS-BN model. Thus, both developed hybrid models can effectively unveil the relationships between the input and target variables. • We measured the most effective parameters on peak particle velocity induced by blasting. • A new peak particle velocity empirical equation was proposed and compared with previous equations. • A feature selection model was applied to remove the irrelevant predictors. • Two hybrid models were developed to predict peak particle velocity. • A comparison between these models was made and the best among them was chosen. [ABSTRACT FROM AUTHOR]

This paper introduces a methodology for predicting and mapping surface motion beneath road pavement structures caused by environmental factors. Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) measurements, geospatial analyses, and Machine Learning Algorithms (MLAs) are employed for achieving the purpose. Two single learners, i.e., Regression Tree (RT) and Support Vector Machine (SVM), and two ensemble learners, i.e., Boosted Regression Trees (BRT) and Random Forest (RF) are utilized for estimating the surface motion ratio in terms of mm/year over the Province of Pistoia (Tuscany Region, central Italy, 964 km2), in which strong subsidence phenomena have occurred. The interferometric process of 210 Sentinel-1 images from 2014 to 2019 allows exploiting the average displacements of 52,257 Persistent Scatterers as output targets to predict. A set of 29 environmental-related factors are preprocessed by SAGA-GIS, version 2.3.2, and ESRI ArcGIS, version 10.5, and employed as input features. Once the dataset has been prepared, three wrapper feature selection approaches (backward, forward, and bi-directional) are used for recognizing the set of most relevant features to be used in the modeling. A random splitting of the dataset in 70% and 30% is implemented to identify the training and test set. Through a Bayesian Optimization Algorithm (BOA) and a 10-Fold Cross-Validation (CV), the algorithms are trained and validated. Therefore, the Predictive Performance of MLAs is evaluated and compared by plotting the Taylor Diagram. Outcomes show that SVM and BRT are the most suitable algorithms; in the test phase, BRT has the highest Correlation Coefficient (0.96) and the lowest Root Mean Square Error (0.44 mm/year), while the SVM has the lowest difference between the standard deviation of its predictions (2.05 mm/year) and that of the reference samples (2.09 mm/year). Finally, algorithms are used for mapping surface motion over the study area. We propose three case studies on critical stretches of two-lane rural roads for evaluating the reliability of the procedure. Road authorities could consider the proposed methodology for their monitoring, management, and planning activities. [ABSTRACT FROM AUTHOR]

Heat response time (HRT) is one of the key dynamic response characteristics of urban centralized heating system (UCHS). HRT is also critical to the operation dispatch of large-scale UCHS. This study proposes a data-driven approach to identify and predict HRT. Due to the diversity of operational data, this study applies correlation analysis and feature fusion (both linear and nonlinear) to generate feature sets. This study further develops the prediction models of HRT made up of three different feature sets and four machine learning models: Linear Regression (LR), Support Vector Machine Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). A UCHS in Zhengzhou is selected as the demo site to show the effectiveness of this approach. HRT of investigated substations range from 1000 to 3000 s. The correlation analysis indicates that the heating area's square root is most relevant to HRT (correlation coefficient close to 0.68) compared to other features. Feature fusion is critical in HRT analysis. The performances of all four prediction models are improved with fused features added to sets. XGBoost model outperforms other models in terms of model accuracy. Quantification of HRT could be useful in the optimized operation control of large-scale UCHS. • Quantification of heat response time (HRT) is critical to heating system operation. • A new data-driven method is proposed to identify HRT. • The square root of heating area is found to be the most relevant feature to HRT. • LR, SVR, RF and XGBoost are proposed to predict HRT. • The XGBoost model using FS3 performs best with the prediction R 2 of 0.80 [ABSTRACT FROM AUTHOR]

The foot strike pattern performed during running is an important variable for runners, performance practitioners, and industry specialists. Versatile, wearable sensors may provide foot strike information while encouraging the collection of diverse information during ecological running. The purpose of the current study was to predict foot strike angle and classify foot strike pattern from LoadsolTM wearable pressure insoles using three machine learning techniques (multiple linear regression―MR, conditional inference tree―TREE, and random forest―FRST). Model performance was assessed using three-dimensional kinematics as a ground-truth measure. The prediction-model accuracy was similar for the regression, inference tree, and random forest models (RMSE: MR = 5.16°, TREE = 4.85°, FRST = 3.65°; MAPE: MR = 0.32°, TREE = 0.45°, FRST = 0.33°), though the regression and random forest models boasted lower maximum precision (13.75° and 14.3°, respectively) than the inference tree (19.02°). The classification performance was above 90% for all models (MR = 90.4%, TREE = 93.9%, and FRST = 94.1%). There was an increased tendency to misclassify mid foot strike patterns in all models, which may be improved with the inclusion of more mid foot steps during model training. Ultimately, wearable pressure insoles in combination with simple machine learning techniques can be used to predict and classify a runner's foot strike with sufficient accuracy. [ABSTRACT FROM AUTHOR]

Around 800,000 people worldwide die from suicide every year and it's the 10th leading cause of death in the US. It is of great value to build a mathematic model that can accurately predict suicide especially in high-risk populations. Several different ML-based models were trained and evaluated using features obtained from electronic medical records (EMRs). The contribution of each feature was calculated to determine how it impacted the model predictions. The best-performing model was selected for analysis and decomposition. Random forest showed the best performance with true positive rates (TPR) and positive predictive values (PPV) of greater than 80%. The use of Aripiprazole, Levomilnacipran, Sertraline, Tramadol, Fentanyl, or Fluoxetine, a diagnosis of autistic disorder, schizophrenic disorder, or substance use disorder at the time of a diagnosis of both PTSD and bipolar disorder, were strong indicators for no SREs within one year. The use of Trazodone and Citalopram at baseline predicted the onset of SREs within one year. Additional features with potential protective or hazardous effects for SREs were identified by the model. We constructed an ML-based model that was successful in identifying patients in a subpopulation at high-risk for SREs within a year of diagnosis of both PTSD and bipolar disorder. The model also provides feature decompositions to guide mechanism studies. The validation of this model with additional EMR datasets will be of great value in resource allocation and clinical decision making. [ABSTRACT FROM AUTHOR]

There have been abundant experimental studies exploring ultra-high-performance concrete (UHPC) in recent years. However, the relationships between the engineering properties of UHPC and its mixture composition are highly nonlinear and difficult to delineate using traditional statistical methods. There is a need for robust and advanced methods that can streamline the diverse pertinent experimental data available to create predictive tools with superior accuracy and provide insight into its nonlinear materials science aspects. Machine learning is a powerful tool that can unravel underlying patterns in complex data. Accordingly, this study endeavors to employ state-of-the-art machine learning techniques to predict the compressive strength of UHPC using a comprehensive experimental database retrieved from the open literature consisting of 810 test observations and 15 input features. A novel approach based on tabular generative adversarial networks was used to generate 6513 plausible synthetic data for training robust machine learning models, including random forest, extra trees, and gradient boosting regression. While the models were trained using the synthetic data, their ability to generalize their predictions was tested on the 810 experimental data thus far unknown and never presented to the models. The results indicate that the developed models achieved outstanding predictive performance. Parametric studies using the models were able to provide insight into the strength development mechanisms of UHPC and the significance of the various influential parameters. [ABSTRACT FROM AUTHOR]

• We used a random forest algorithm to create a predictive model for depression. • The performance was good with an AUC of 0.839, sensitivity of 0.723, and specificity of 0.824. • Prescription of benzodiazepines had the greatest influence on the future onset of depression. Depression is a mental illness that causes significant disturbances in daily life. Depression is commonly associated with low mood, severe health problems, and substantial socioeconomic burden; hence, it is necessary to be able to detect depression earlier. We utilized the medical check-up cohort database of the National Health Insurance Sharing Service in Korea. We split the total dataset into training (70%) and test (30%) sets. Subsequently, five-fold cross validation was performed in the training set. The holdout test set was only used in the last step to evaluate the performance of the predictive model. Random forest algorithm was used for the predictive model. The analysis included 433,190 individuals who had a national medical check-up from 2009–2015, which included 10,824 (2.56%) patients in the depression group. The area under the receiver-operating curve was 0.849. Other performance metrics included a sensitivity of 0.737, specificity of 0.824, positive predictive value of 0.097, negative predictive value of 0.992, and accuracy of 0.780. Our predictive model could contribute to proactively reducing depression prevalence by administering interventions to prevent depression in patients receiving medical check-up. Future studies are needed to prospectively validate the predictability of this model. [ABSTRACT FROM AUTHOR]

• First reports on the ensemble learning (EL) algorithms for reference evapotranspiration (ETo) prediction in Bangladesh. • Random tree (RT) model outperforms other models to estimate daily ETo. • The RT and RF models have suggested as the promising potentials for daily ETo estimate. • Wind speed and solar radiation are the highest contributing variables influencing the observed and predicted ETo changes. Ensemble learning (EL), an alternative approach in the machine-learning field, offers an accurate reference evapotranspiration (ETo) prediction, which is of paramount significance for the hydrological studies and agricultural water practices. Although the FAO-56 Penman-Monteith (PM) equation is regarded as an ideal model for estimating ETo, its applicability is limited due to the absence of required climatic datasets in many regions of the world. Despite its significance, only a few studies use the EL algorithms for the ETo prediction perspective. In this study, we contribute to fill this gap from a two-fold way. First, we present the potential of new EL Random Tree (RT), Bagging and Random Subspace (RS) algorithms which were compared with two commonly used Random Forest (RF), and Support Vector Machine (SVM) algorithms for predicting daily ETo with the climatic data-limited humid region in Bangladesh during 1983–2017 using a five-fold cross-validation scheme. Second, we explore the role of contributing variables influencing ETo change at the regional scale. When a lack of climatic datasets, Tmax (maximum temperature), Tmin (minimum temperature) and Rs (solar radiation) as 3 input combinations obtained the reasonable precision for estimating ETo in all climatic regions except for south-central and south-western regions. Compared to other state-of-arts models, the RT model performed superior to predict ETo in all input combinations followed by the RF, Bagging, RS, and SVM. Considering less difficulty level, high prediction accuracy, more dependability and fewer computation costs of studied models, RT and RF models have been suggested as the promising potentials for daily ETo estimate in subtropical climate regions of Bangladesh and also may be applicable worldwide in the similar climates. The importance analysis from the RF model depicted that the wind speed (U2) and solar radiation (Rs) are the largest influential variables affecting the observed and predicted daily ETo changes in Bangladesh. [ABSTRACT FROM AUTHOR]

• The study provides inspiration to use simulation data for yield predictive modeling. • The proposed machine learning algorithm approach has achieved 93.8% accuracy. • Interactions between bee species composition and weather are significant in yield variability. • Prediction showed that wet rainy springs will greatly reduce blueberry yield in the future. The most challenging task in the agricultural sector is to accurately predict crop yield. A typical machine learning algorithm often uses real data to predict crop yield. In this study, we used data generated by the Wild Blueberry Pollination Model, a spatially explicit simulation model validated by field observation and experimental data collected in Maine USA during the last 30 years. The main aim of this study is to evaluate the relative importance of bee species composition and weather factors in regulating wild blueberry agroecosystems. Specifically, we sought to reveal how bee species composition and weather affect yield and to predict optimal bee species composition and weather conditions that achieve the best yield using computer simulation and machine learning algorithms. Multiple linear regression (MLR), boosted decision trees (BDT), random forest (RF), and extreme gradient boosting (XGBoost) were evaluated as predictive tools. We also performed a predictor selection before submitting our data to the learning algorithms. In this way, we are able to reduce the dimension of the input without a significant drop in prediction accuracy. As a result, clone size, honeybee, bumblebee, Andrena bee species, Osmia bee species, maximum of upper-temperature ranges, and the number of days with precipitation were chosen as the best predictor variable subset. The results showed that the XGBoost outperformed other algorithms in all measures of model performance for predicting the yield of wild blueberry by achieving a coefficient of determination (R2) of 0.938, root mean square error (RMSE) of 343.026, mean absolute error (MAE) of 206 and relative root mean square error (RRMSE) of 5.444%. The results are consistent with previous work on predicting wild blueberry fruit yield using digital color photography by (Zaman et al., 2008). This study showed that crop yield predictions can be based on computer simulation modeling datasets. Therefore, if a reasonable prediction can be reached, this study should have a significant impact, especially when data collection in the field is challenging. [ABSTRACT FROM AUTHOR]

Background: Cytokines act by binding to specific receptors in the plasma membrane of target cells. Knowledge of cytokine–receptor interaction (CRI) is very important for understanding the pathogenesis of various human diseases—notably autoimmune, inflammatory and infectious diseases—and identifying potential therapeutic targets. Recently, machine learning algorithms have been used to predict CRIs. "Gold Standard" negative datasets are still lacking and strong biases in negative datasets can significantly affect the training of learning algorithms and their evaluation. To mitigate the unrepresentativeness and bias inherent in the negative sample selection (non-interacting proteins), we propose a clustering-based approach for representative negative sample selection. Results: We used deep autoencoders to investigate the effect of different sampling approaches for non-interacting pairs on the training and the performance of machine learning classifiers. By using the anomaly detection capabilities of deep autoencoders we deduced the effects of different categories of negative samples on the training of learning algorithms. Random sampling for selecting non-interacting pairs results in either over- or under-representation of hard or easy to classify instances. When K-means based sampling of negative datasets is applied to mitigate the inadequacies of random sampling, random forest (RF) together with the combined feature set of atomic composition, physicochemical-2grams and two different representations of evolutionary information performs best. Average model performances based on leave-one-out cross validation (loocv) over ten different negative sample sets that each model was trained with, show that RF models significantly outperform the previous best CRI predictor in terms of accuracy (+ 5.1%), specificity (+ 13%), mcc (+ 0.1) and g-means value (+ 5.1). Evaluations using tenfold cv and training/testing splits confirm the competitive performance. Conclusions: A comparative analysis was performed to assess the effect of three different sampling methods (random, K-means and uniform sampling) on the training of learning algorithms using different evaluation methods. Models trained on K-means sampled datasets generally show a significantly improved performance compared to those trained on random selections—with RF seemingly benefiting most in our particular setting. Our findings on the sampling are highly relevant and apply to many applications of supervised learning approaches in bioinformatics. [ABSTRACT FROM AUTHOR]

This article highlights the industry experience of the development and practical implementation of a short-term photovoltaic forecasting system based on machine learning methods for a real industry-scale photovoltaic power plant implemented in a Russian power system using remote data acquisition. One of the goals of the study is to improve photovoltaic power plants generation forecasting accuracy based on open-source meteorological data, which is provided in regular weather forecasts. In order to improve the robustness of the system in terms of the forecasting accuracy, we apply newly derived feature introduction, a factor obtained as a result of feature engineering procedure, characterizing the relationship between photovoltaic power plant energy production and solar irradiation on a horizontal surface, thus taking into account the impacts of atmospheric and electrical nature. The article scrutinizes the application of different machine learning algorithms, including Random Forest regressor, Gradient Boosting Regressor, Linear Regression and Decision Trees regression, to the remotely obtained data. As a result of the application of the aforementioned approaches together with hyperparameters, tuning and pipelining of the algorithms, the optimal structure, parameters and the application sphere of different regressors were identified for various testing samples. The mathematical model developed within the framework of the study gave us the opportunity to provide robust photovoltaic energy forecasting results with mean accuracy over 92% for mostly-sunny sample days and over 83% for mostly cloudy days with different types of precipitation. [ABSTRACT FROM AUTHOR]

Despite yielding considerable degrees of accuracy in landslide predictions, the outcomes of different landslide susceptibility models are prone to spatial disagreement; and therefore, uncertainties. Uncertainties in the results of various landslide susceptibility models create challenges in selecting the most suitable method to manage this complex natural phenomenon. This study aimed to propose an approach to reduce uncertainties in landslide prediction, diagnosing spatial agreement in machine learning-based landslide susceptibility maps. It first developed landslide susceptibility maps of Cox's Bazar district of Bangladesh, applying four machine learning algorithms: K-Nearest Neighbor (KNN), Multi-Layer Perceptron (MLP), Random Forest (RF), and Support Vector Machine (SVM), featuring hyperparameter optimization of 12 landslide conditioning factors. The results of all the four models yielded very high prediction accuracy, with the area under the curve (AUC) values range between 0.93 to 0.96. The assessment of spatial agreement of landslide predictions showed that the pixel-wise correlation coefficients of landslide probability between various models range from 0.69 to 0.85, indicating the uncertainty in predicted landslides by various models, despite their considerable prediction accuracy. The uncertainty was addressed by establishing a Logistic Regression (LR) model, incorporating the binary landslide inventory data as the dependent variable and the results of the four landslide susceptibility models as independent variables. The outcomes indicated that the RF model had the highest influence in predicting the observed landslide locations, followed by the MLP, SVM, and KNN models. Finally, a combined landslide susceptibility map was developed by integrating the results of the four machine learning-based landslide predictions. The combined map resulted in better spatial agreement (correlation coefficients range between 0.88 and 0.92) and greater prediction accuracy (0.97) compared to the individual models. The modelling approach followed in this study would be useful in minimizing uncertainties of various methods and improving landslide predictions. [ABSTRACT FROM AUTHOR]

The importance of price forecasting has gained attention over the last few years, with the growth of aggregators and the general opening of the European electricity markets. Market participants manage a tradeoff between, bidding in a lower price market (day-ahead), but with typically higher volume, or aiming for a lower volume market but with potentially higher returns (balance energy market). Companies try to forecast the extremes of revenues or prices, in order to manage risk and opportunity, assigning their assets in an optimal way. It is thought that in general, electricity markets have quasi-deterministic principles, rather than being based on speculation, hence the desire to forecast the price based on variables that can describe the outcome of the market. Many studies address this problem from a statistical approach or by performing multiple-variable regressions, but they very often focus only on the time series analysis. In 2019, the Loss of Load Probability (LOLP) was made available in the UK for the first time. Taking this opportunity, this study focusses on five LOLP variables (with different time-ahead estimations) and other quasi-deterministic variables, to explain the price behavior of a multi-variable regression model. These include base production, system load, solar and wind generation, seasonality, day-ahead price and imbalance volume contributions. Three machine-learning algorithms were applied to test for performance, Gradient Boosting (GB), Random Forest (RF) and XGBoost. XGBoost presented higher performance and so it was chosen for the implementation of the real time forecast step. The model returns a Mean Absolute Error (MAE) of 7.89 £/MWh, a coefficient of determination (R2 score) of 76.8% and a Mean Squared Error (MSE) of 124.74. The variables that contribute the most to the model are the Net Imbalance Volume, the LOLP (aggregated), the month and the De-rated margins (aggregated) with 28.6%, 27.5%, 14.0%, and 8.9% of weight on feature importance respectively. [ABSTRACT FROM AUTHOR]

Under ideal conditions of nitrogen (N), maize (Zea mays L.) can grow to its full potential, reaching maximum plant height (PH). As a rapid and nondestructive approach, the analysis of unmanned aerial vehicles (UAV)-based imagery may be of assistance to estimate N and height. The main objective of this study is to present an approach to predict leaf nitrogen concentration (LNC, g kg−1) and PH (m) with machine learning techniques and UAV-based multispectral imagery in maize plants. An experiment with 11 maize cultivars under two rates of N fertilization was carried during the 2017/2018 and 2018/2019 crop seasons. The spectral vegetation indices (VI) normalized difference vegetation index (NDVI), normalized difference red-edge index (NDRE), green normalized difference vegetation (GNDVI), and the soil adjusted vegetation index (SAVI) were extracted from the images and, in a computational system, used alongside the spectral bands as input parameters for different machine learning models. A randomized 10-fold cross-validation strategy, with a total of 100 replicates, was used to evaluate the performance of 9 supervised machine learning (ML) models using the Pearson's correlation coefficient (r), mean absolute error (MAE), coefficient of regression (R²), and root mean square error (RMSE) metrics. The results indicated that the random forest (RF) algorithm performed better, with r and RMSE, respectively, of 0.91 and 1.9 g.kg−¹ for LNC, and 0.86 and 0.17 m for PH. It was also demonstrated that VIs contributed more to the algorithm's performances than individual spectral bands. This study concludes that the RF model is appropriate to predict both agronomic variables in maize and may help farmers to monitor their plants based upon their LNC and PH diagnosis and use this knowledge to improve their production rates in the subsequent seasons. [ABSTRACT FROM AUTHOR]

Simple Summary: Formulating accurate survival prediction models of oral and pharyngeal cancers (OPCs) is important, as they might impact the decisions of clinicians and patients. Improving the quality of these clinical prediction modelling studies can benefit the reliability of the developed models and facilitate their implementations in clinical practice. Given the growing trend on the application of machine learning methods in cancer research, we present the use of popular tree-based machine learning algorithms and compare them to the standard Cox regression as an aim to predict OPCs survival. The predictive models discussed here are based on a large cancer registry dataset incorporating various prognosis factors and different forms of bias. The comparable predictive performance between Cox and tree-based models suggested that these machine learning algorithms provide non-parametric alternatives to Cox regression and are of clinical use for estimating the survival probability of OPCs patients. This study aims to demonstrate the use of the tree-based machine learning algorithms to predict the 3- and 5-year disease-specific survival of oral and pharyngeal cancers (OPCs) and compare their performance with the traditional Cox regression. A total of 21,154 individuals diagnosed with OPCs between 2004 and 2009 were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. Three tree-based machine learning algorithms (survival tree (ST), random forest (RF) and conditional inference forest (CF)), together with a reference technique (Cox proportional hazard models (Cox)), were used to develop the survival prediction models. To handle the missing values in predictors, we applied the substantive model compatible version of the fully conditional specification imputation approach to the Cox model, whereas we used RF to impute missing data for the ST, RF and CF models. For internal validation, we used 10-fold cross-validation with 50 iterations in the model development datasets. Following this, model performance was evaluated using the C-index, integrated Brier score (IBS) and calibration curves in the test datasets. For predicting the 3-year survival of OPCs with the complete cases, the C-index in the development sets were 0.77 (0.77, 0.77), 0.70 (0.70, 0.70), 0.83 (0.83, 0.84) and 0.83 (0.83, 0.86) for Cox, ST, RF and CF, respectively. Similar results were observed in the 5-year survival prediction models, with C-index for Cox, ST, RF and CF being 0.76 (0.76, 0.76), 0.69 (0.69, 0.70), 0.83 (0.83, 0.83) and 0.85 (0.84, 0.86), respectively, in development datasets. The prediction error curves based on IBS showed a similar pattern for these models. The predictive performance remained unchanged in the analyses with imputed data. Additionally, a free web-based calculator was developed for potential clinical use. In conclusion, compared to Cox regression, ST had a lower and RF and CF had a higher predictive accuracy in predicting the 3- and 5-year OPCs survival using SEER data. The RF and CF algorithms provide non-parametric alternatives to Cox regression to be of clinical use for estimating the survival probability of OPCs patients. [ABSTRACT FROM AUTHOR]

With the development of machine learning technology, research cases for spatial estimation through machine learning approach (MLA) in addition to the traditional geostatistical techniques are increasing. MLA has the advantage that spatial estimation is possible without stationary hypotheses of data, but it is possible for the prediction results to ignore spatial autocorrelation. In recent studies, it was considered by using a distance matrix instead of raw coordinates. Although, the performance of spatial estimation could be improved through this approach, the computational complexity of MLA increased rapidly as the number of sample points increased. In this study, we developed a method to reduce the computational complexity of MLA while considering spatial autocorrelation. Principal component analysis is applied to it for extracting spatial features and reducing dimension of inputs. To verify the proposed approach, indicator Kriging was used as a benchmark model, and each performance of MLA was compared when using raw coordinates, distance vector, and spatial features extracted from distance vector as inputs. The proposed approach improved the performance compared to previous MLA and showed similar performance compared with Kriging. We confirmed that extracted features have characteristics of rigid classification in spatial estimation; on this basis, we conclude that the model could improve performance. [ABSTRACT FROM AUTHOR]

• 275 schizophrenia patients were assessed to identify demographic, clinical, and sociocultural variables as predictors. • Seven machine learning classification algorithms were utilized to predict for past instances of physical violence. • This study determined that the random forest model performed marginally better than other algorithms. Patients with schizophrenia have been shown to have an increased risk for physical violence. While certain features have been identified as risk factors, it has been difficult to integrate these variables to identify violent patients. The present study thus attempts to develop a clinically-relevant predictive tool. In a population of 275 schizophrenia patients, we identified 103 participants as violent and 172 as non-violent through electronic medical documentation, and conducted cross-sectional assessments to identify demographic, clinical, and sociocultural variables. Using these predictors, we utilized seven machine learning classification algorithms to predict for past instances of physical violence. Our classification algorithms predicted with significant accuracy compared to random discrimination alone, and had varying degrees of predictive power, as described by various performance measures. We determined that the random forest model performed marginally better than other algorithms, with an accuracy of 62% and an area under the receiver operator characteristic curve (AUROC) of 0.63. To summarize, machine learning classification algorithms are becoming increasingly valuable, though, optimization of these models is needed to better complement diagnostic decisions regarding early interventional measures to predict instances of physical violence. [ABSTRACT FROM AUTHOR]

District heating systems are an important part of the future smart energy systems and are seen in the European Union as a vehicle for reaching energy efficiency targets. Integrating different energy systems requires high prediction accuracy for all energy sub-systems. Within this paper a data analysis was made with the goal of identifying a high accuracy prediction model and ranking the most influential parameters on heat consumption of final consumers in district heating systems. The data set consisted of the actual billing data comprising of 260 buildings and it was additionally supplemented by the behavioural data obtained from interviews and questionnaires conducted on the demonstration building in Zagreb, Croatia. The authors choose regression trees, random forest and regression support vector machines as algorithms for testing prediction accuracy and evaluating the variable importance ranking on the data set. The best performing algorithm was random forest, resulting with high prediction accuracy and the root mean squared error of prediction of specific annual heat consumption below 1 kWh/m2. Furthermore, all analysed machine learning algorithms ranked importance variables for both technical and behavioural parameters, giving the indication what parameters should be influenced in order to reach specific targets, such as energy savings. [ABSTRACT FROM AUTHOR]

Depletion of river sand due to large-scale concrete production has caused many environmental problems. To address this issue, river sand can be replaced with sand manufactured from waste deposits. To facilitate manufactured-sand concrete production, this study proposes three tree-based models: one individual model (regression tree (RT)), and two ensemble models (random forest (RF) and gradient boosted regression tree (GBRT)) to predict its mechanical properties, such as uniaxial compressive strength (UCS), and splitting tensile strength (STS). These tree-based models were trained and tested on a dataset collected from previous literature. In addition, to understand the importance of each input variable on the mechanical properties of manufactured-sand concrete, the variable importance is calculated using the RF algorithm. The results show that the highest correlation coefficients are achieved by GBRT in predicting UCS (0.9887) and STS (0.9666), which respectively increase by 3.0%–10.8% and 16.0%–21.6% in comparison with the models in previous literature. The mechanical properties UCS and STS are highly sensitive to the curing age with relative importance of 36.8% and 40.3%, respectively. To facilitate the application of the tree-based models in predicting mechanical properties of manufactured-sand concrete, a graphical user interface has been designed in this study. • The mechanical properties of manufactured-sand concrete were predicted by tree-based models. • Firefly algorithm was used to tune the hyperparameters of the tree-based models. • Importance of input variables was calculated using random forest algorithm. • A GUI was developed to facilitate the application of the proposed models. [ABSTRACT FROM AUTHOR]

Selective laser melting (SLM), which is a powder bed fusion additive manufacturing method, is advantageous for fabricating of near-net-shape metal products. The microstructure of Ti-6Al-4V alloy fabricated by SLM and followed by post heat treatment intricately contributes to the mechanical properties. In this study, the microstructural features were quantitatively extracted from the scanning electron microscopy images by applying machine learning with a random forest algorithm and various image analysis techniques. These microstructural features together with defect-characterizing ones from X-ray computed tomography were used to develop a prediction model by multiple linear regression analysis for the tensile properties of heat-treated SLMed Ti-6Al-4V alloys. The analysis revealed that both yield strength (σ YS) and ultimate tensile strength (σ UTS) have a linear correlation with the reciprocal square root of the α grain size, and they were also attributed to other microstructural features depending on solution treatment parameters. The multiple linear regression models showed an error of less than 2.0% for σ YS and σ UTS prediction accuracies. On the other hand, the prediction of the fracture elongation and elasticity had significant scatter, implying that there are features, such as dislocation characteristics, that are missing for proper prediction. [ABSTRACT FROM AUTHOR]

A long short-term memory (LSTM) network is proposed for the quick prediction of significant wave height with higher accuracy than conventional neural network. The LSTM network is used for 1-h and 6-h predictions at ten stations with different environmental conditions. Using the wind speed of the past 4 h and the wave height and wind direction of the past 1 h as input parameters, the LSTM prediction results were obtained, and compared with results from a back propagation neural network, extreme learning machine, support vector machine, residual network, and random forest algorithm. Five statistical indicators were used to evaluate the results comprehensively. The minimum mean absolute error percentage of the 1-h and 6-h forecasts was 5.14% and 5.24%, respectively. The results demonstrate that the LSTM can achieve stable prediction effects, with accurate 1-h predictions and satisfactory 6-h predictions. In addition, predictions for four time spans, namely 12 h, 1 day, 2 days, and 3 days, were determined for Station 41008. The results show the powerful ability of LSTM to perform long-term prediction. The simulating waves nearshore-LSTM (SWAN-LSTM) model was proposed to make a single-point prediction, and it outperformed the standard SWAN model with an improvement in accuracy of over 65%. • LSTM neural network method is used for significant wave height prediction. • Significant wave height predictions are simulated by 6 algorithms in 10 stations. • Every 1hr, 6 h s, 12 h s, 1 day, 2 days, 3 days wave height predictions are carried out. • 5 indicators are used to evaluate the prediction results of different data volumes. • A SWAN-LSTM model are proposed to improve the accuracy of SWAN model. [ABSTRACT FROM AUTHOR]

The study evaluated the prediction accuracy of breast cancer using the K-nearest neighbor (k-NN) classifier algorithm. Methods The breast cancer dataset (containing 569 records and 32 attributes) was obtained from University of California Irvine (UCI) machine learning repository. Data were segmented into a training dataset containing the first 469 observations to build the k-NN model and a testing dataset containing the remaining observations was used to simulate new patients. [Extracted from the article]

Meteorological disasters are the result of the interaction of multiple factors and multiple systems. In order to improve the accuracy of prediction, it is necessary not only to consider the characteristics and cycles of each subsystem, but also to study the interaction of all systems. Based on the summer precipitation data and 130 circulation indexes of 34 national meteorological observation stations in Chongqing from 1961 to 2010, the prediction model of Chongqing summer precipitation was established based on the decision tree and the stochastic forest algorithm based on machine learning, and the prediction test of 2011–2018 was carried out independently by the model. Compared with the results of the single-factor prediction model, the trend consistency rate increased by 37.5% and 12.5% respectively. In addition, when using the random forest model to predict summer precipitation in Chongqing from 2014 to 2018, the 5-year average Ps, Cc and PC scores were 84.6, 0.27 and 67.1, respectively, which were significantly improved compared with 72.4, −0.12 and 52.9 of the current climate forecasting methods, and the forecast quality of the random forest was relatively stable. The multi-system collaborative impact model based on decision tree and random forest algorithm can achieve high accuracy and stability. Thus, this method can not only be an effective means for the diagnosis and prediction of climate causes, but also has a good theoretical and practical value for the prediction of extreme disasters. [ABSTRACT FROM AUTHOR]

Parameter study on galloping of iced transmission lines with different structural, ice and wind parameters is carried out by means of the finite element method (FEM), and a dataset is then created based on the numerical results. The random forests algorithm is used to set up a classification model to predict the galloping mode and vertical vibration mode. Using the span length, initial conductor tension, ice thickness, initial wind attack angle, wind velocity and the galloping mode as well as the vertical vibration mode obtained by the classification model as the input variables, a back-propagation (BP) neural network model is created to predict the galloping features including the frequencies, vibration amplitudes and the maximum conductor tension. The dataset created based on the parameter study is divided into two sub-datasets for training and testing of the two machine learning models respectively. The effects of the input variables on the output variables are quantified with a feature importance analysis for the classification model and a global sensitivity analysis for the feature prediction model respectively. The two models are finally integrated into one to predict galloping features efficiently and quickly. Making use of the proposed method, an early warning system for galloping of transmission lines may be able to be set up in the future. • Parameter study on galloping of iced transmission lines are carried out to construct a dataset of galloping samples. • Galloping classification model based on Random forests algorithm is created to estimate mode and vertical vibration mode. • Galloping feature prediction model based on BP neural network is created to predict galloping features. • A new method for early warning of galloping and prediction of galloping features of iced transmission lines is proposed. [ABSTRACT FROM AUTHOR]