Downloads & Free Reading Options - Results

This study evaluated the nature-inspired optimization algorithms to improve classification involving imbalanced class problems. The particle swarm optimization (PSO) and grey wolf optimizer (GWO) were used to adaptively balance the distribution and then four supervised machine learning classifiers artificial neural network (ANN), support vector machine (SVM), extreme gradient-boosted tree (XGBoost), and random forest (RF) were applied to maximize the classification performance for electricity fraud prediction. The imbalance data was balanced using random undersampling (RUS) and two nature-inspired algorithm techniques (PSO and GWO). Results showed that for the data balanced using random undersampling, ANN (Sentest = 50.31%), and XGBoost (Sentest = 66.32%) has better sensitivity than SVM (Sentest = 23.61%), while RF exhibits overfitting (Sentrain = 100%, Sentest = 71.25%). The classification performance of RF model hybrid with PSO improved tremendously (AccTest = 96.98%, Sentest = 94.87%, Spectest = 99.16%, Pretest = 99.14%, F1 Score = 96.96%, and area under the curve (AUC) = 0.989). This was closely followed by hybrid of XGBoost with PSO. Moreover, RF and XGBoost hybrid with GWO also showed an improvement and promising results. This study has showed that nature-inspired optimization algorithms (PSO and GWO) are effective methods in addressing imbalanced dataset.

The purpose of this systematic literature review (SLR) article is to discuss the findings of the state-of-art metaheuristic nature-inspired algorithm (MHNIA) in reservoir optimization operation. The rationale of this approach is to elucidate the optimal way as decision making that implemented MHNIA for several complex problems in reservoir optimization operation. Commonly, the metaheuristic optimization algorithm has always been used in hydrology field, especially in reservoir optimization. Hence, this presented study reviewed a considerable amount from the previous studies of commonly nature-based optimization algorithms applied in reservoir operations. Hence, preferred reporting items for systematic review and metaanalyses (PRISMA) has been used as guidance. The source was utilized from two primary journal databases: Scopus and web of science. According to the proposed search string, the findings managed to express into nine main themes which are optimize in water release, optimize reservoir operation problems, optimize hydropower operation, optimize condensate fluids in reservoir storage, optimize water pumped storage, optimize water quality control, optimize system performance operation, optimize water demand and optimize reservoir control as flood preventing. Overall, 24 articles that passed the minimum quality were retrieved using systematic searching strategies.