In predicting palm oil mill effluent (POME) degradation efficiency, previous developed quadratic model quantitatively evaluated the effects of O2 flowrate, TiO2 loadings and initial concentration of POME in labscale photocatalytic system, which however suffered from low generalization due to the overfitting behaviour. Evidently, high RMSE (131.61) and low R2 (-630.49) obtained indicates its insufficiency in describing POME degradation at unseen factor ranges, hence verified the fact of poor generalization. To overcome this issue, several models were developed via machine learning-assisted techniques, namely Gaussian Process Regression (GPR), Linear Regression (LR), Decision Tree (DT), Supported Vector Machine (SVM) and Regression Tree Ensemble (RTE), subsequently being assessed systematically. To achieve high generalization, all models were subjected to 'train-all-test-all' strategy, 5-fold and 10-fold cross validation. Specifically, GPR model was furnished with high accuracy in 'train-all-test-all' strategy, judging from its low RMSE (1.0394) and high R2 (0.9962), which however menaced by the risk of overfitting. In contrast, despite relatively poorer RMSE and R2 (1.7964 and 0.9886) obtained in 5-fold cross validation, GPR model was rendered with highest generalization, while sufficiently preserving its accuracy in development process. Besides, SVM and RTE models were also demonstrated promising R2 (0.9372 and 0.9208), which however shadowed by their high RMSEs (4.2174 and 4.7366). Furthermore, the extraordinary generalization of GPR model was coincidentally verified in 10-fold cross validation. The lowest RMSE (2.1624) and highest R2 (0.9835) obtained with feature number of 36 asserted its sufficiency in both generalization and accuracy prospect. Other models were all rendered with slight lower R2 (> 0.9), plausibly due to the higher RMSE (> 4.0). According to GPR model, optimized POME degradation (52.52%) can be obtained at 70 mL/min of O2, 70.0 g/L of TiO2 and 250 ppm of POME concentration, with only ∼3% error as compared to the actual data.
This study investigated the pretreatment and post-treatment effects of dipyridamole (20 mg/kg/day, p.o.) in gentamicin-induced acute nephrotoxicity in rats. Rats were administered gentamicin (100 mg/kg/day, i.p.) for 8 days. Gentamicin-administered rats exhibited renal structural and functional changes as assessed in terms of a significant increase in serum creatinine and urea and kidney weight to body weight ratio as compared to normal rats. Renal histopathological studies revealed a marked incidence of acute tubular necrosis in gentamicin-administered rats. These renal structural and functional abnormalities in gentamicin-administered rats were accompanied with elevated serum uric acid level, and renal inflammation as assessed in terms of decrease in interleukin-10 levels. Dipyridamole pretreatment in gentamicin-administered rats afforded a noticeable renoprotection by markedly preventing renal structural and functional abnormalities, renal inflammation and serum uric acid elevation. On the other hand, dipyridamole post-treatment did not significantly prevent uric acid elevation and renal inflammation, and resulted in comparatively less protection on renal function although it markedly reduced the incidence of tubular necrosis. In conclusion, uric acid elevation and renal inflammation could play key roles in gentamicin-nephrotoxicity. Dipyridamole pretreatment markedly prevented gentamicin-induced acute nephrotoxicity, while its post-treatment resulted in comparatively less renal functional protection.