In this study,a series of porous intelligent hydrogels were synthesized by radiation exhibiting the lower critical solution temperature（LCST） and fast response involving a combination of A’-isopropyl acrylamideas m...In this study,a series of porous intelligent hydrogels were synthesized by radiation exhibiting the lower critical solution temperature（LCST） and fast response involving a combination of A’-isopropyl acrylamideas monomer, polyethylene glycol（PEG） as pore-forming agent and N,N-methylene-bis-acrylamide as crosslinking agent.The hydrogels were analyzed by Fourier transform infrared spectroscopy,and the influence of radiation doses on their swelling and thermal behaviors were studied.Their surface morphologies were examined by scanning electron microscopy.The results showed that PEG molecules only acted as pore-forming agent in the cross-linked polymerization.Their swelling ratios reduced with increasing radiation doses.The LCST was around 37℃,and varied little with the radiation doses.The frozen water content of PNIPAM/PEG6000 hydrogel reduced with increasing the radiation dose,and was greater than that of PN1PAM hydrogel at 15 kGy.Hydrogel macropores were prepared by PEG agent,and the hydrogels without PEG had a dense surface.The porous hydrogels are expected to be applied in the field of artificial intelligence material.展开更多
开展脉冲重复间隔(Pulse Repetition Interval,PRI)模式识别工作是电子支援系统的一项重要任务。现代复杂电磁环境下,受雷达辐射源部署和接收设备本身影响,雷达脉冲丢失率极高,导致分选后PRI序列调制规律被破坏,现有的PRI模式识别方法...开展脉冲重复间隔(Pulse Repetition Interval,PRI)模式识别工作是电子支援系统的一项重要任务。现代复杂电磁环境下,受雷达辐射源部署和接收设备本身影响,雷达脉冲丢失率极高,导致分选后PRI序列调制规律被破坏,现有的PRI模式识别方法准确率不足。针对上述问题,从PRI序列还原角度出发,并结合PRI序列本质是时序序列的特点,提出GAIN-LSTM(Generative Adversarial Imputation Nets and Long Short Term Memory)网络架构,其先对丢失脉冲位置进行补全操作,恢复PRI调制规律,然后对还原后PRI序列进行调制模式识别。仿真结果表明,提出的GAIN-LSTM网络架构在脉冲丢失率70%时仍保持95%的正确识别率。展开更多
基金Supported by the Key Science and Technology Project of Henan Province(No.102101210100)the Natural Science Foundation ofHenan Province(No. 2011 B430023)
文摘In this study,a series of porous intelligent hydrogels were synthesized by radiation exhibiting the lower critical solution temperature（LCST） and fast response involving a combination of A’-isopropyl acrylamideas monomer, polyethylene glycol（PEG） as pore-forming agent and N,N-methylene-bis-acrylamide as crosslinking agent.The hydrogels were analyzed by Fourier transform infrared spectroscopy,and the influence of radiation doses on their swelling and thermal behaviors were studied.Their surface morphologies were examined by scanning electron microscopy.The results showed that PEG molecules only acted as pore-forming agent in the cross-linked polymerization.Their swelling ratios reduced with increasing radiation doses.The LCST was around 37℃,and varied little with the radiation doses.The frozen water content of PNIPAM/PEG6000 hydrogel reduced with increasing the radiation dose,and was greater than that of PN1PAM hydrogel at 15 kGy.Hydrogel macropores were prepared by PEG agent,and the hydrogels without PEG had a dense surface.The porous hydrogels are expected to be applied in the field of artificial intelligence material.
文摘开展脉冲重复间隔(Pulse Repetition Interval,PRI)模式识别工作是电子支援系统的一项重要任务。现代复杂电磁环境下,受雷达辐射源部署和接收设备本身影响,雷达脉冲丢失率极高,导致分选后PRI序列调制规律被破坏,现有的PRI模式识别方法准确率不足。针对上述问题,从PRI序列还原角度出发,并结合PRI序列本质是时序序列的特点,提出GAIN-LSTM(Generative Adversarial Imputation Nets and Long Short Term Memory)网络架构,其先对丢失脉冲位置进行补全操作,恢复PRI调制规律,然后对还原后PRI序列进行调制模式识别。仿真结果表明,提出的GAIN-LSTM网络架构在脉冲丢失率70%时仍保持95%的正确识别率。
