Machine Learning-Based Comparative Analysis of the Determinants of Gold Prices

A comparative analysis of biomass torrefaction severity index prediction from machine learning

Genomic prediction through machine learning and neural networks for traits with epistasis

Completing the machine learning saga in fractional snow cover estimation from MODIS Terra reflectance data: Random forests versus support vector regression

The Indonesian composite stock price index is an indicator of changes in stock prices as a guide for investors to invest in reducing risk. The regression model for Indonesian Composite Index (ICI) has the response variable as stock prices with fluctuation behavior and several financial predictor variables, the model tends to violate the assumptions of normality, homoscedasticity, autocorrelation and multicollinearity. This problem can be overcome by modeling the composite stock price index by using the Artificial Neural Network (ANN) and nonparametric regression of Multivariate Adaptive Regression Spline (MARS). In this study, the time series data from the composite stock price index starting from April 2003 to March 2018 with its predictor variables are crude-oil prices, interest rates, inflation, exchange rates, gold prices, Dow Jones price, and Nikkei 225 Index. The both methods give better goodness of fit, where the coefficient of determination ANN is 0.98925 and the MARS determination coefficient is 0.99427. While based on the Mean Absolute Percentage Error (MAPE) of ANN was obtained 6.16383 and the MAPE value of MARS is 4.51372. This means that the ANN method and nonparametric MARS regression method have good performance to forecast the value of the Indonesian composite stock price index in the future, but in this case of data the nonparametric MARS regression method shows the accuracy of the model is slightly better than ANN.

The gas Centrifuge is a very hard equipment to model, because it involves a gas dynamic with many complications, such as hypersonic waves and rarefied regions combined with continuous flow areas. Therefore, data analysis regressions remain currently a very important technique to understand and describe the problem in a practical way. This paper intends to apply and compare several regression techniques using machine learning, to obtain a hydraulic and a separative power model of gas centrifuge used in enrichment plants. For this purpose, a set of normalized data composed of 134 experimental lines was used, observing the variables of interest, the separation power (dU), and the waste pressure (Pw), through the following explanatory variables: feed flow (F), cut (q), and product pressure (Pp). The comparisons were presented between the results obtained for the models generated by the following: algorithms, multivariate regression, multivariate adaptive regression splines – MARS, bootstrap aggregating multivariate adaptive regression splines – Bagging MARS, artificial neural network – ANN, extreme gradient boosting – XGBoost, support vector regression– Poly SVR, radial basis Function support vector regression – RBF SVR, K-nearest neighbors – KNN and Stacked Ensemble. That way, to avoid overfitting and provide insights about generalization of the models in unseen data, during the training phase, the k-fold cross validation approach was used. Subsequently, the residuals were analyzed, and the models were compared by the following metrics: Root mean square error – RMSE; Mean squared error – MSE; Mean absolute error – MAE; and Coefficient of determination – R2.

Short-term electricity demand forecasting using machine learning methods enriched with ground-based climate and ECMWF Reanalysis atmospheric predictors in southeast Queensland, Australia

Soft-computing techniques for fire safety parameter predictions in flammability studies are essential for describing a material fire behaviour. This study proposed, two novel Artificial Intelligence developed models, Multivariate Adaptive Regression Splines (MARS) and Random Forest (RF) methods, to model and predict peak heat release rate (pHRR) of Polymethyl methacrylate (PMMA) from Microscale Combustion Calorimetry (MCC) experiment. From the statistical analysis, MARS presented the highest coefficient of determination (R2) values of (0.9998) and (0.9996) for training and testing respectively, with low MAD, MAPE and RMSE values. Comparatively, MARS outperformed RF in the predictions of pHRR, through its model algorithms that generated optimized equations for pHRR predictions, covering all non-linearity points of the experimental data. Amongst the input variables (sample mass, THR, HRC, pTemp and pTime), heating rate (β), highly influenced pHRR outcome predictions from MARS and RF models. However, to validate the performance and applicability of the proposed models. Results of MARS and RF were benchmarked with that from Artificial Neural Network (ANN) methods. The MARS and RF models observed the least error deviation when compared with pHRR results for PMMA from the ANN models. This study therefore, recommends the adoption of MARS and RF in the predictions of flammability characteristics of polymeric materials.

ABSTRACTAccurate simulation of extreme events of runoff is very important for public safety and hydrological engineering. The simulation of extreme events mainly employs the rainfall-runoff models. This paper tests the potential of soft computing technique-based rainfall-runoff models to simulate the peak runoff events in order to develop an alarming system. This study mainly focusses on hybrid Artificial Neural Networks (ANNs) and Multivariate Adaptive Regression Splines (MARS). The six different regression models used are conventional Artificial Neural Network (ANN), Wavelet Artificial Neural Network (WANN), Bootstrapped Artificial Neural Network (BANN), Wavelet Bootstrapped Artificial Neural Network (WBANN), Multivariate Adaptive Regression Splines (MARS) and Wavelet Multivariate Adaptive Regression Splines (WMARS). The potential inputs were selected based on Auto Correlation Function (ACF) and Cross Correlation Functions (CCF). To implement the methodology, the Jhelum basin in the northern part of India was selected. Based on the results, it was found that all the models except BANN showed overall good performance. The WANN model (NSE = 0.95, RMSE = 1943.15 cusecs, MAPE = 25.5, R = 0.96, DA = 46.8) shows slightly better performance than ANN, WBANN, MARS and WMARS and far better than BANN. The accuracy of the forecasts was checked between WANN and ANN, WBANN and BANN, WMARS and MARS. The results show that decomposition method improves the forecasting accuracy of time series data. Again, the simulation of the peak events was done using the above six models. The efficiency of the models was evaluated on the basis of Normalized Root Mean Square Error (NRMSE). It was found that WANN outperforms the other five models with NRMSE (0.37) for all peak events. All the other models except BANN showed fair results with NRMSE for ANN = 0.66, MARS = 0.68, WBANN = 0.68 and WMARS = 0.53. Thus, it is recommended from the present study that WANN model is more promising for the simulation of peak events in time series data.

Efficiency of three advanced data-driven models for predicting axial compression capacity of CFDST columns

AimsPredicting the risk of malignant arrhythmias (MA) in hospitalized patients with heart failure (HF) is challenging. Machine learning (ML) can handle a large volume of complex data more effectively than traditional statistical methods. This study explored the feasibility of ML methods for predicting the risk of MA in hospitalized HF patients.Methods and resultsWe evaluated the baseline data and MA events of 2794 hospitalized HF patients in the HF cohort in Anhui Province and randomly divided the study population into training and validation sets in a 7:3 ratio. The Lasso‐logistic regression, multivariate adaptive regression splines (MARS), classification and regression tree (CART), random forest (RF), and eXtreme gradient boosting (XGBoost) algorithms were used to construct risk prediction models in the training set, and model performance was verified in the validation set. The area under the receiver operating characteristic curve (AUC) and Brier score were employed to evaluate the discrimination and calibration of the model, respectively. Clinical utility of the Lasso‐logistic regression model was analysed using decision curve analysis (DCA). The median (Q1, Q3) age of the study population was 70 (61, 77) years, and 39.5% were female. MA events occurred in 117 patients (4.2%) during hospitalization. In the training set (n = 1964), the AUC of the XGBoost model was 0.998 [95% confidence interval (CI) 0.997–1.000], which was higher than the other models (all P < 0.001). In the validation set (n = 830), there was no significant difference in AUC of Lasso‐logistic model 1 [AUC: 0.867 (95% CI 0.819–0.915)], Lasso‐logistic model 2 [AUC: 0.828 (95% CI 0.764–0.892)], MARS model [AUC: 0.852 (95% CI 0.793–0.910)], RF model [AUC: 0.804 (95% CI 0.726–0.881)], and XGBoost model [AUC: 0.864 (95% CI 0.810–0.918); all P > 0.05], which were higher than that of CART model [AUC: 0.743 (95% CI 0.661–0.824); all P < 0.05]. Brier scores for all prediction models were less than 0.05. DCA results showed that the Lasso‐logistic model had a net clinical benefit. Oral antiarrhythmic drug, left bundle branch block, serum magnesium, d‐dimer, and random blood glucose were significant predictors in half or more of the models.ConclusionsThe current study findings suggest that ML models based on the Lasso‐logistic regression, MARS, RF, and XGBoost algorithms can effectively predict the risk of MA in hospitalized HF patients. The Lasso‐logistic model had better clinical interpretability and ease of use than the other models.

Thermal conductivity prediction of nano enhanced phase change materials: A comparative machine learning approach

Retrieval of fractional snow covered area from MODIS data by multivariate adaptive regression splines

Exploring machine learning and multi-task learning to estimate meteorological data and reference evapotranspiration across Brazil

Scour depth prediction downstream of hydraulic structures is an important task for maintaining their safety and long-term stability. The present study, for accurate modelling of scour depth caused by free-falling hydraulic jets, conducted a comparative investigation of the performance of various machine learning (ML) models. Black-box ML models were selected for their strong nonlinear learning capability. In addition, white-box ML models were chosen because they can provide explicit mathematical expressions. Several ML models, including Artificial Neural Networks (ANN), Support Vector Regression (SVR), Classification and Regression Trees (CART), Group Method of Data Handling (GMDH), Multi-Expression Programming (MEP), Multivariate Adaptive Regression Splines (MARS), and Stronger Variable Creator Machines (SVCM), were used. In addition, hybrid ML models were developed by combining Particle Swarm Optimization (PSO) with MARS, ANN, and SVR to improve the performance of standalone approaches. For the evaluation of the ML models, statistical indicators, the objective function (OBJ) criterion, uncertainty analysis (U95), and graphical plots were employed. The results revealed that the hybrid optimization ML approaches increased the accuracy compared to their standalone counterparts. The SVR-PSO model achieved the best accuracy with the lowest OBJ (0.07995) and U95 (0.0638) values, followed closely by MARS-PSO, MEP, and ANN-PSO. Comparison of the present ML methods with previous reported ML methods highlighted their superior performance for modelling of scour depth.

Biomass is a key biophysical parameter for precision agriculture and plant breeding. Fast, accurate and non-destructive monitoring of biomass enables various applications related to crop growth. In this paper, strawberry dry biomass weight was modeled using 4 canopy geometric parameters (area, average height, volume, standard deviation of height) and 25 spectral variables (5 band original reflectance values and 20 vegetation indices (VIs)) extracted from the Unmanned Aerial Vehicle (UAV) multispectral imagery. Six regression techniques—multiple linear regression (MLR), random forest (RF), support vector machine (SVM), multivariate adaptive regression splines (MARS), eXtreme Gradient Boosting (XGBoost) and artificial neural network (ANN)—were employed and evaluated for biomass prediction. The ANN had the highest accuracy in a five-fold cross-validation, with R2 of 0.89~0.93, RMSE of 7.16~8.98 g and MAE of 5.06~6.29 g. As for the other five models, the addition of VIs increased the R2 from 0.77~0.80 to 0.83~0.86, and reduced the RMSE from 8.89~9.58 to 7.35~8.09 g and the MAE from 6.30~6.70 to 5.25~5.47 g, respectively. Red-edge-related VIs, including the normalized difference red-edge index (NDRE), simple ratio vegetation index red-edge (SRRedEdge), modified simple ratio red-edge (MSRRedEdge) and chlorophyll index red and red-edge (CIred&amp;RE), were the most influential VIs for biomass modeling. In conclusion, the combination of canopy geometric parameters and VIs obtained from the UAV imagery was effective for strawberry dry biomass estimation using machine learning models.