In addition, with intelligent algorithm, the boundary values of operating parameters are determined. The genetic algorithm (GA) and particle swarm optimization (PSO) are combined into a GA-PSO hybrid algorithm.
algorithm, we used the Extra Trees Regressor in the scikit-learn Python programming package40. Table2indicates the corresponding parameter setting. The number of trees was set to 1,000 because of the performance limit of the machine server we used. The maximum depth of the tree, the minimum ...
Predicting carbon futures prices based on a new hybrid machine learning: Comparative study of carbon prices in different periods 2023, Journal of Environmental Management Citation Excerpt : Genetic algorithm (GA) combines biogenetics and natural selection algorithm. It improves individual fitness through ...
In the learning process, prioritized experience replay and multi-step learning are designed for the improvement on the final performance. Simulations are represented to show the practicality and potential of the proposed algorithm. Results show that the hybrid deep reinforcement learning algorithm in ...
(30%) datasets. The site-specific influencing factors were selected by employing a multicollinearity test. The relationship between past landslide occurrences and influencing factors was established using the frequency ratio method. The effectiveness of machine learning models was verified through performance...
In the ML algorithm, the hyper-parameter is the parameter set before the learning process, rather than that obtained through training model. In general, it is necessary to select a set of optimal hyper-parameters for the learning machine to improve the efficiency and generalization performance of...
Representation learning using a DNN requires a large set of training examples [10]. This is the main motivation for this study to use a DNN as a representation learner and a traditional ML algorithm as a classifier. A DNN is trained on the original training examples, but for the classificati...
(HML) algorithm utilized a similar method; However, it firstly has a reduced-order (but fast enough) numerical submodel that can give a rough estimate of the results, and secondly a machine learning submodel within this hybrid implementation improves the accuracy of the low-fidelity results to...
As a matter of comparison, a decision tree algorithm predicting only the growth rate fromCmed(the RandomForestRegressor function from the sci-kit learn package27having 1000 estimators and other parameters left with default values) reach a regression performance of 0.71 ± 0.01 with the same...
Two regressing schemes applied in hybrid SVR models improved the accuracy of predictions compared to SVR models and empirical relations. Show abstract Prediction of the axial compressive strength of circular concrete-filled steel tube columns using sine cosine algorithm-support vector regression 2021, ...