Machine learning-based prediction of effluent total suspended solids in a wastewater treatment plant using different feature selection approaches: A comparative study.

Accurately predicting the characteristics of effluent, discharged from wastewater treatment plants (WWTPs) is crucial for reducing sampling requirements, labor, costs, and environmental pollution. Machine learning (ML) techniques can be effective in achieving this goal. To optimize ML-based models, various feature selection (FS) methods are employed. This study aims to investigate the impact of six FS methods (categorized as Wrapper, Filter, and Embedded methods) on the accuracy of three supervised ML algorithms in predicting total suspended solids (TSS) concentration in the effluent of a municipal wastewater treatment plant. Based on the features proposed by each FS method, five distinct scenarios were defined. Within each scenario, three ML algorithms, namely artificial neural network-multi layer perceptron (ANN-MLP), K-nearest neighbors (KNN), and adaptive boosting (AdaBoost) were applied. The features utilized for predicting TSS concentration in the WWTP effluent included BOD5, COD, TSS, TN, NH3 in the influent, and BOD5, COD, residual Cl2, NO3, TN, NH4 in the effluent. To construct the models, the dataset was randomly divided into training and testing subsets, and K-fold cross-validation was employed to control overfitting and underfitting. The evaluation metrics that are used are root mean squared error (RMSE), mean absolute error (MAE), and correlation coefficient (R2). The most efficient scenario was identified as Scenario IV, with the Sequential Backward Selection FS method. The features selected by this method were CODe, BOD5e, BOD5i, TNi. Furthermore, the ANN-MLP algorithm demonstrated the best performance, achieving the highest R2 value. This algorithm exhibited acceptable performance in both the training and testing subsets (R2 = 0.78 and R2 = 0.8, respectively).

Isolate Whey Protein Promotes Fluid Balance and Endurance Capacity Better Than Isolate Casein and Carbohydrate-Electrolyte Solution in a Warm, Humid Environment.

Protein ingestion is known to enhance post-exercise hydration. Whether the type of protein (i.e., whey, casein) can alter this response is unknown. Accordingly, this study aimed to compare the effects of the addition of milk-derived whey isolate or casein protein to carbohydrate-electrolyte (CE) drinks on post-exercise rehydration and endurance capacity. Thirty male soldiers (age: 24 ± 2.1 y; VO2max: 49.3 ± 4.7 mL/kg/min) were recruited. Upon losing ~2.2% of body mass by running in warm and humid conditions (32.3 °C, 76% relative humidity [RH]), participants ingested either a CE solution (66 g/L carbohydrate [CHO]), or CE plus isolate whey protein (CEW, 44 g/L CHO, 22 g/L isolate whey), or CE plus isolate casein protein (CEC, 44 g/L CHO, 22 g/L isolate casein) beverage in a volume equal to 150% of body mass loss. At the end of the 3 h rehydration period, a positive fluid balance was higher with CEW (0.22 L) compared to CEC (0.19 L) and CE (0.12 L). Overall mean fluid retention was higher in CEW (80.35%) compared with the CE (76.67%) and CEC trials (78.65%). The time of the endurance capacity test [Cooper 2.4 km (1.5 miles) run test] was significantly higher in CEC (14.25 ± 1.58 min) and CE [(12.90 ± 1.01 min; (p = 0.035)] than in CEW [(11.40 ± 1.41 min); (p = 0.001)]. The findings of this study indicate that the inclusion of isolate whey protein in a CE solution yields superior outcomes in terms of rehydration and enhanced endurance capacity, as compared to consuming the CE solution alone or in conjunction with isolate casein protein.