In the fifth generation(5G)wireless system,a closed-loop power control(CLPC)scheme based on deep Q learning network(DQN)is introduced to intelligently adjust the transmit power of the base station(BS),which can improv...In the fifth generation(5G)wireless system,a closed-loop power control(CLPC)scheme based on deep Q learning network(DQN)is introduced to intelligently adjust the transmit power of the base station(BS),which can improve the user equipment(UE)received signal to interference plus noise ratio(SINR)to a target threshold range.However,the selected power control(PC)action in DQN is not accurately matched the fluctuations of the wireless environment.Since the experience replay characteristic of the conventional DQN scheme leads to a possibility of insufficient training in the target deep neural network(DNN).As a result,the Q-value of the sub-optimal PC action exceed the optimal one.To solve this problem,we propose the improved DQN scheme.In the proposed scheme,we add an additional DNN to the conventional DQN,and set a shorter training interval to speed up the training of the DNN in order to fully train it.Finally,the proposed scheme can ensure that the Q value of the optimal action remains maximum.After multiple episodes of training,the proposed scheme can generate more accurate PC actions to match the fluctuations of the wireless environment.As a result,the UE received SINR can achieve the target threshold range faster and keep more stable.The simulation results prove that the proposed scheme outperforms the conventional schemes.展开更多
Corneal injuries will cause corneal surface diseases that may lead to blindness in millions of people worldwide.There is a tremendous need for biomaterials that can promote corneal regeneration with practical feasibil...Corneal injuries will cause corneal surface diseases that may lead to blindness in millions of people worldwide.There is a tremendous need for biomaterials that can promote corneal regeneration with practical feasibility.Here we demonstrate a strategy of a protein coating for corneal injury regeneration.We synthesize an o-nitrosobenzaldehyde group(NB)-modified gelatin(GelNB),which could adhere directly to the corneal surface with covalent bonding to form a thin molecular coating.The molecular coating could avoid rapid clearance and provide a favorable environment for cell migration,thereby effectively accelerating corneal repair and regeneration.The histological structure of the regenerated cornea is more similar to the native cornea.This molecular coating can be used conveniently as an eye drop solution,which makes it a promising strategy for corneal regeneration.展开更多
文摘In the fifth generation(5G)wireless system,a closed-loop power control(CLPC)scheme based on deep Q learning network(DQN)is introduced to intelligently adjust the transmit power of the base station(BS),which can improve the user equipment(UE)received signal to interference plus noise ratio(SINR)to a target threshold range.However,the selected power control(PC)action in DQN is not accurately matched the fluctuations of the wireless environment.Since the experience replay characteristic of the conventional DQN scheme leads to a possibility of insufficient training in the target deep neural network(DNN).As a result,the Q-value of the sub-optimal PC action exceed the optimal one.To solve this problem,we propose the improved DQN scheme.In the proposed scheme,we add an additional DNN to the conventional DQN,and set a shorter training interval to speed up the training of the DNN in order to fully train it.Finally,the proposed scheme can ensure that the Q value of the optimal action remains maximum.After multiple episodes of training,the proposed scheme can generate more accurate PC actions to match the fluctuations of the wireless environment.As a result,the UE received SINR can achieve the target threshold range faster and keep more stable.The simulation results prove that the proposed scheme outperforms the conventional schemes.
基金This work was supported by the National Key R&D Program of China(2017YFA0104900)National Natural Science Foundation of China(31830029,32000957,81972053).
文摘Corneal injuries will cause corneal surface diseases that may lead to blindness in millions of people worldwide.There is a tremendous need for biomaterials that can promote corneal regeneration with practical feasibility.Here we demonstrate a strategy of a protein coating for corneal injury regeneration.We synthesize an o-nitrosobenzaldehyde group(NB)-modified gelatin(GelNB),which could adhere directly to the corneal surface with covalent bonding to form a thin molecular coating.The molecular coating could avoid rapid clearance and provide a favorable environment for cell migration,thereby effectively accelerating corneal repair and regeneration.The histological structure of the regenerated cornea is more similar to the native cornea.This molecular coating can be used conveniently as an eye drop solution,which makes it a promising strategy for corneal regeneration.