Metal-organic frameworks(MOFs)have been developed as an ideal platform for exploration of the relationship between intrinsic structure and catalytic activity,but the limited catalytic activity and stability has hamper...Metal-organic frameworks(MOFs)have been developed as an ideal platform for exploration of the relationship between intrinsic structure and catalytic activity,but the limited catalytic activity and stability has hampered their practical use in water splitting.Herein,we develop a bond length adjustment strategy for optimizing naphthalene-based MOFs that synthesized by acid etching Co-naphthalenedicarboxylic acid-based MOFs(donated as AE-CoNDA)to serve as efficient catalyst for water splitting.AE-CoNDA exhibits a low overpotential of 260 mV to reach 10 mA cm^(−2)and a small Tafel slope of 62 mV dec^(−1)with excellent stability over 100 h.After integrated AE-CoNDA onto BiVO_(4),photocurrent density of 4.3 mA cm^(−2)is achieved at 1.23 V.Experimental investigations demonstrate that the stretched Co-O bond length was found to optimize the orbitals hybridization of Co 3d and O 2p,which accounts for the fast kinetics and high activity.Theoretical calculations reveal that the stretched Co-O bond length strengthens the adsorption of oxygen-contained intermediates at the Co active sites for highly efficient water splitting.展开更多
Short-term prediction of traffic flow is one of the most essential elements of all proactive traffic control systems.The aim of this paper is to provide a model based on neural networks(NNs)for multi-step-ahead traffi...Short-term prediction of traffic flow is one of the most essential elements of all proactive traffic control systems.The aim of this paper is to provide a model based on neural networks(NNs)for multi-step-ahead traffic prediction.NNs'dependency on parameter setting is the major challenge in using them as a predictor.Given the fact that the best combination of NN parameters results in the minimum error of predicted output,the main problem is NN optimization.So,it is viable to set the best combination of the parameters according to a specific traffic behavior.On the other hand,an automatic method—which is applicable in general cases—is strongly desired to set appropriate parameters for neural networks.This paper defines a self-adjusted NN using the non-dominated sorting genetic algorithm II(NSGA-II)as a multi-objective optimizer for short-term prediction.NSGA-II is used to optimize the number of neurons in the first and second layers of the NN,learning ratio and slope of the activation function.This model addresses the challenge of optimizing a multi-output NN in a self-adjusted way.Performance of the developed network is evaluated by application to both univariate and multivariate traffic flow data from an urban highway.Results are analyzed based on the performance measures,showing that the genetic algorithm tunes the NN as well without any manually pre-adjustment.The achieved prediction accuracy is calculated with multiple measures such as the root mean square error(RMSE),and the RMSE value is 10 and 12 in the best configuration of the proposed model for single and multi-step-ahead traffic flow prediction,respectively.展开更多
基金supported by the National Key Research and Development Program of China (2022YFB4002100)the development project of Zhejiang Province's "Jianbing" and "Lingyan" (2023C01226)+4 种基金the National Natural Science Foundation of China (22278364, U22A20432, 22238008, 22211530045, and 22178308)the Fundamental Research Funds for the Central Universities (226-2022-00044 and 226-2022-00055)the Science Foundation of Donghai Laboratory (DH-2022ZY0009)the Startup Foundation for Hundred-Talent Program of Zhejiang UniversityScientific Research Fund of Zhejiang Provincial Education Department.
文摘Metal-organic frameworks(MOFs)have been developed as an ideal platform for exploration of the relationship between intrinsic structure and catalytic activity,but the limited catalytic activity and stability has hampered their practical use in water splitting.Herein,we develop a bond length adjustment strategy for optimizing naphthalene-based MOFs that synthesized by acid etching Co-naphthalenedicarboxylic acid-based MOFs(donated as AE-CoNDA)to serve as efficient catalyst for water splitting.AE-CoNDA exhibits a low overpotential of 260 mV to reach 10 mA cm^(−2)and a small Tafel slope of 62 mV dec^(−1)with excellent stability over 100 h.After integrated AE-CoNDA onto BiVO_(4),photocurrent density of 4.3 mA cm^(−2)is achieved at 1.23 V.Experimental investigations demonstrate that the stretched Co-O bond length was found to optimize the orbitals hybridization of Co 3d and O 2p,which accounts for the fast kinetics and high activity.Theoretical calculations reveal that the stretched Co-O bond length strengthens the adsorption of oxygen-contained intermediates at the Co active sites for highly efficient water splitting.
文摘Short-term prediction of traffic flow is one of the most essential elements of all proactive traffic control systems.The aim of this paper is to provide a model based on neural networks(NNs)for multi-step-ahead traffic prediction.NNs'dependency on parameter setting is the major challenge in using them as a predictor.Given the fact that the best combination of NN parameters results in the minimum error of predicted output,the main problem is NN optimization.So,it is viable to set the best combination of the parameters according to a specific traffic behavior.On the other hand,an automatic method—which is applicable in general cases—is strongly desired to set appropriate parameters for neural networks.This paper defines a self-adjusted NN using the non-dominated sorting genetic algorithm II(NSGA-II)as a multi-objective optimizer for short-term prediction.NSGA-II is used to optimize the number of neurons in the first and second layers of the NN,learning ratio and slope of the activation function.This model addresses the challenge of optimizing a multi-output NN in a self-adjusted way.Performance of the developed network is evaluated by application to both univariate and multivariate traffic flow data from an urban highway.Results are analyzed based on the performance measures,showing that the genetic algorithm tunes the NN as well without any manually pre-adjustment.The achieved prediction accuracy is calculated with multiple measures such as the root mean square error(RMSE),and the RMSE value is 10 and 12 in the best configuration of the proposed model for single and multi-step-ahead traffic flow prediction,respectively.
