Search

Studying the dynamic viscosity (DV) is a key factor to determine the nanofluids' hydrodynamic behavior (NFs). In this research, the effect of volume fraction (φ), shear rate (SR), and temperature (T) on the DV, and torque of SiO 2 nanoparticles (NPs)/ Ethylene glycol (EG) nanofluid (NF) are studied with an artificial neural network (ANN). Different machine learning (ML) models are examined to predict the rheological properties, and then the best model is selected for prediction. The results show that the torque mostly increased linearly with the SR in all samples. The slope of this enhancing trend is higher for lower T. The Gaussian Process Regression (GPR) models with the Matérn covariance function provided the best results on both datasets to predict the DV. The correlation results provided by this method to predict the DV in terms of Pearson's Linear Correlation Coefficient (PLCC), and Spearman's Rank Order Correlation Coefficient (SROCC) were 0.999 and 1, respectively. R squared (R2) was 0.996 and, the Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) values of about 0.24 and 1.61 represented the accuracy and power of this method to predict the DV values unseen data by the model. The GPR torque predictor model performed very well by providing a correlation of about 0.98 and an RMSE of about 4. Matérn covariance functions that used separate length scales per predictor with ν = 3 / 2 (ardmatern 32) and ν = 5 / 2 (ardmatern52) were superior to other functions. All 100 models trained on each dataset were well-trained and quite reliable. The trained models were accurate enough to be used in related applications. [ABSTRACT FROM AUTHOR]

• Advanced modeling analysis of liquid-phase drug dissolution. • Validation of models using experimental data of drug solubility. • ET model was chosen as the most accurate and general model of process. Green processing based on supercritical solvents has attracted much attention recently in different fields such as pharmaceutical industry due to its superior characteristics. Comprehensive modeling was performed in this study to analyze the preparation of nanomedicine using green supercritical processing. Computational analysis was performed in order to estimate the solubility at different pressures and temperatures. The model was developed based on the input parameters and can estimate the only output of the process which is drug solubility in the supercritical solvent. In this work, we examined how temperature and pressure affect EXE (Exemestane) drug solubility using different tree-based ensemble methods. The models used in this analysis are the Random Forest (RF), the Extremely Randomized Tree (ET), and the Gradient Boosting (GB). Model optimization and hyper-parameter tuning are also accomplished with the aid of Golden eagle optimizer (GEOA). The R2 values for the test phases of ET, GB, and RF were 0.993, 0.985, and 0.978, respectively. The scores are 0.9945, 0.9758, and 0.9904 in train phases. Specifically, the ET model was chosen since it is the most accurate one. Error rates for this model are 2.317 with MSE, 1.522 with RMSE, and 0.2113 with MAPE. [ABSTRACT FROM AUTHOR]

• Solubility enhancement through SCCO 2 system. • Machine learning approaches to estimate and optimize the salicylsalicylic acid. • KNN model has been used as the best model to optimize the solubility of drug. Over the last decades, significant drawbacks of organic solvents such as high toxicity have motivated the scientists to find more eco-friendly solvents. Supercritical fluids (SCFs), especially SCCO 2 , are known as a promising class of solvent, which have shown their indisputable potential of application in industrial-based pharmaceutical activities due to possessing various advantages such as high abundancy, low cost, and insignificant toxicity. Machine Learning (ML) is considered as a numerical approach to estimate drug solubility in pharmaceutical industry. The purpose of this manuscript is to estimate the solubility of salicylsalicylic acid in SCCO 2 and compare it with experimental data using machine learning (ML) approach. A regression problem with 32 input vectors is the subject of this study, which is being conducted. This dataset contains two input features (P and T) and one output feature. We utilized Decision Tree (DT), K-nearest neighbor (KNN), and Multilayer perceptron (MLP) regression models as the first time for salicylsalicylic acid, which had error rates of 1.10E-01, 1.07E-01, and 7.13E-01, respectively, when using the MAPE measure. In addition, the R-squared scores for the DT, KNN, and MLP models are 0.974, 0.996, and 0.809, respectively. The third statistic is MAE, in which the error rates of models are 5.27E-05 for DT, 5.53E-05 for KNN, and 2.61E-04 for MLP. The error rates of DT, KNN, and MLP are all 5.27E-05. Finally, KNN was the most general model, with optimal values of P = 400, T = 338.0, and Y = 0.00388 being obtained. [ABSTRACT FROM AUTHOR]

• Solubility enhancement through advanced artificial intelligence model. • Applying different modeless of machine learning such as Random Forest, Extremely Random Trees, and Gradient Boosting Trees. • The GBRT has shown the less error rate and can be used as the best model. Over the last ten years, the application of novel mathematical models of Machine Learning employed to model the solubility of drugs especially anticancer drugs, in supercritical carbon dioxide (ScCO 2) system has gained remarkable popularity. In this research, three distinct ensemble models have been employed on the data as a novel method for busulfan as anticancer drug for the first time, based on decision trees, including Random Forest (RF), Gradient Boosting Trees (GBRT), and Extremely Randomized Tree (ERT) to predict the solubility of busulfan as an anticancer drug. The dataset has two input parameters, T = Temperature and P = Pressure, and Y = Solubility is the single output. After implementing and tuning these ensemble models' hyper parameters, the performance has been assessed through several metrics. All three models show R-squared score of more than 0.9, but in terms of RMSE, the error rates are 1.80E-04, 1.72E-04, and 1.03E-04 for RF, ERT, and GBRT models, respectively. Also, MAPE metrics 4.51E-01, 4.87E-01, and 3.62E-01 errors had found for RF, ERT, and GBRT models, respectively. GBRT has been selected as the best model due to the less rate of RMSE and MAPE. An analysis has also been performed to find the optimal amount of solubility, which can be considered the (x1 = 38.3, x2 = 333.1, Y = 1.36E-03) vector. [ABSTRACT FROM AUTHOR]