An effective approach for describing complicated water quality processes is very important for river water quality management. We built two artificial neural network(ANN) models,a feed-forward back-propagation(BP) mod...An effective approach for describing complicated water quality processes is very important for river water quality management. We built two artificial neural network(ANN) models,a feed-forward back-propagation(BP) model and a radial basis function(RBF) model,to simulate the water quality of the Yangtze and Jialing Rivers in reaches crossing the city of Chongqing,P. R. China. Our models used the historical monitoring data of biological oxygen demand,dissolved oxygen,ammonia,oil and volatile phenolic compounds. Comparison with the one-dimensional traditional water quality model suggest that both BP and RBF models are superior; their higher accuracy and better goodness-of-fit indicate that the ANN calculation of water quality agrees better with measurement. It is demonstrated that ANN modeling can be a tool for estimating the water quality of the Yangtze River. Of the two ANN models,the RBF model calculates with a smaller mean error,but a larger root mean square error. More effort to identify out the causes of these differences would help optimize the structures of neural network water-quality models.展开更多
Reinforcement learning is an excellent approach which is used in artificial intelligence,automatic control, etc. However, ordinary reinforcement learning algorithm, such as Q-learning with lookup table cannot cope wit...Reinforcement learning is an excellent approach which is used in artificial intelligence,automatic control, etc. However, ordinary reinforcement learning algorithm, such as Q-learning with lookup table cannot cope with extremely complex and dynamic environment due to the huge state space. To reduce the state space, modular neural network Q-learning algorithm is proposed, which combines Q-learning algorithm with neural network and module method. Forward feedback neural network, Elman neural network and radius-basis neural network are separately employed to construct such algorithm. It is revealed that Elman neural network Q-learning algorithm has the best performance under the condition that the same neural network training method, i.e. gradient descent error back-propagation algorithm is applied.展开更多
基金Funded by the Natural Science Foundation of China (No. 59778021)
文摘An effective approach for describing complicated water quality processes is very important for river water quality management. We built two artificial neural network(ANN) models,a feed-forward back-propagation(BP) model and a radial basis function(RBF) model,to simulate the water quality of the Yangtze and Jialing Rivers in reaches crossing the city of Chongqing,P. R. China. Our models used the historical monitoring data of biological oxygen demand,dissolved oxygen,ammonia,oil and volatile phenolic compounds. Comparison with the one-dimensional traditional water quality model suggest that both BP and RBF models are superior; their higher accuracy and better goodness-of-fit indicate that the ANN calculation of water quality agrees better with measurement. It is demonstrated that ANN modeling can be a tool for estimating the water quality of the Yangtze River. Of the two ANN models,the RBF model calculates with a smaller mean error,but a larger root mean square error. More effort to identify out the causes of these differences would help optimize the structures of neural network water-quality models.
文摘Reinforcement learning is an excellent approach which is used in artificial intelligence,automatic control, etc. However, ordinary reinforcement learning algorithm, such as Q-learning with lookup table cannot cope with extremely complex and dynamic environment due to the huge state space. To reduce the state space, modular neural network Q-learning algorithm is proposed, which combines Q-learning algorithm with neural network and module method. Forward feedback neural network, Elman neural network and radius-basis neural network are separately employed to construct such algorithm. It is revealed that Elman neural network Q-learning algorithm has the best performance under the condition that the same neural network training method, i.e. gradient descent error back-propagation algorithm is applied.
