Introduction Artificial intelligence(AI)is a transformative field of study focused on developing computational models that can perform tasks typically requiring human intelligence.Recent breakthroughs in AI have raise...Introduction Artificial intelligence(AI)is a transformative field of study focused on developing computational models that can perform tasks typically requiring human intelligence.Recent breakthroughs in AI have raised optimism about their potential to transform biological research.The study of the structure and function of biological macromolecules such as proteins and RNA represents a key application of AI in biology.展开更多
The transformative impact of artificial intelligence(AI)technologies on materials science has revolutionized the study of materials problems.By leveraging well-characterized datasets derived from the scientific litera...The transformative impact of artificial intelligence(AI)technologies on materials science has revolutionized the study of materials problems.By leveraging well-characterized datasets derived from the scientific literature,AI-powered tools such as Natural Language Processing(NLP)have opened new avenues to accelerate materials research.The advances in NLP techniques and the development of large language models(LLMs)facilitate the efficient extraction and utilization of information.This review explores the application of NLP tools in materials science,focusing on automatic data extraction,materials discovery,and autonomous research.We also discuss the challenges and opportunities associated with utilizing LLMs and outline the prospects and advancements that will propel the field forward.展开更多
Recent researches show that it is possible to achieve full-duplex system if the self-interference signal could be cancelled completely for 6G research.The majority of the overall self-interference cancellation is cont...Recent researches show that it is possible to achieve full-duplex system if the self-interference signal could be cancelled completely for 6G research.The majority of the overall self-interference cancellation is contributed by passive cancellation.The lowest complexity cancellation technique is digital cancellation.Therefore,this paper presents a novel passive cancellation technique based on multi-path effect and a novel digital cancellation method considering nonlinearity factor in full-duplex system.Therein,for passive cancellation method,theoretical analysis is presented and practical experiments show that it can achieve about 50 dB only in 10-cm space.For digital cancellation method,a model based on practical platform is given and it can achieve about 30 dB under high transmit power.In addition,two relay schemes based on full-duplex for two-way relay channel called FD-DF(full-duplex decode-and-forward)and FD-AF(full-duplex amplify-and-forward)are presented.Two proposed schemes can nearly double the system throughputs especially in high signal-to-noise radio regions compared with traditional AF scheme.展开更多
Temperature profile plays an important role in the field of atmospheric research.The infrared hyperspectral vertical detector equipped with meteorological satellites can provide relatively high spatiotemporal resoluti...Temperature profile plays an important role in the field of atmospheric research.The infrared hyperspectral vertical detector equipped with meteorological satellites can provide relatively high spatiotemporal resolution data,thus being widely used for temperature profile retrieval.In recent years,deep learning,especially convolutional neural networks(CNNs),has attracted much attention in various meteorological and climate tasks,including temperature retrieval.However,it is a completely data-driven approach,which may generate results that violate physical laws.To address this issue,we propose a physical knowledge constrained CNN for temperature profile retrieval in this paper.Specifically,we take advantage of the physical knowledge from weight function and ERA5 data,and use an attention module and a loss function to guide the learning of CNN.In order to test the performance of our proposed model,we collect the geostationary interferometric infrared sounder(GIIRS)data,L-band radiosonde data,ERA5 data,and the GIIRS L2 operational product in China for experiments.It is shown that the root mean square error(RMSE)and mean bias(MB)achieved by our proposed model are 2.06 and 0.072 K,respectively,both of which are better than 2 state-of-the-art neural network-based retrieval models and the operational product.展开更多
基金supported by the National Natural Science Foundation of China(82341086,32300521,2422013,32230018,32125007)the National Key Research and Development Project of China(2022YFF1203100)+2 种基金the Open Grant from the Pingyuan Laboratory(2023PY-OP-0104)the State Key Laboratory of Microbial Technology Open Projects Fund(M2023-20),the Intramural Joint Program Fund of the State Key Laboratory of Microbial Technology(SKLMTIJP-2024-02)the Double-First Class Initiative of Shandong University School of Life Sciences,the Young Innovation Team of Shandong Higher Education Institutions,and the Taishan Scholars Youth Expert Program of Shandong Province.
文摘Introduction Artificial intelligence(AI)is a transformative field of study focused on developing computational models that can perform tasks typically requiring human intelligence.Recent breakthroughs in AI have raised optimism about their potential to transform biological research.The study of the structure and function of biological macromolecules such as proteins and RNA represents a key application of AI in biology.
基金supported by the National Key Research and Development Program of China(2022YFB3707502)National Natural Science Foundation of China(92270001,52201061,U22A20106,52350710205)+1 种基金Guangdong Province Key Areas Research and Development Programs(2024B0101080003)Guangdong Basic and Applied Basic Research Foundation(2023A1515140101).
文摘The transformative impact of artificial intelligence(AI)technologies on materials science has revolutionized the study of materials problems.By leveraging well-characterized datasets derived from the scientific literature,AI-powered tools such as Natural Language Processing(NLP)have opened new avenues to accelerate materials research.The advances in NLP techniques and the development of large language models(LLMs)facilitate the efficient extraction and utilization of information.This review explores the application of NLP tools in materials science,focusing on automatic data extraction,materials discovery,and autonomous research.We also discuss the challenges and opportunities associated with utilizing LLMs and outline the prospects and advancements that will propel the field forward.
基金supported by the Natural Science Foundation of China(NSFC)(grant no.62088101).
文摘Recent researches show that it is possible to achieve full-duplex system if the self-interference signal could be cancelled completely for 6G research.The majority of the overall self-interference cancellation is contributed by passive cancellation.The lowest complexity cancellation technique is digital cancellation.Therefore,this paper presents a novel passive cancellation technique based on multi-path effect and a novel digital cancellation method considering nonlinearity factor in full-duplex system.Therein,for passive cancellation method,theoretical analysis is presented and practical experiments show that it can achieve about 50 dB only in 10-cm space.For digital cancellation method,a model based on practical platform is given and it can achieve about 30 dB under high transmit power.In addition,two relay schemes based on full-duplex for two-way relay channel called FD-DF(full-duplex decode-and-forward)and FD-AF(full-duplex amplify-and-forward)are presented.Two proposed schemes can nearly double the system throughputs especially in high signal-to-noise radio regions compared with traditional AF scheme.
基金supported by the National Natural Science Foundation of China(grant numbers U21B2049 and 62472230).
文摘Temperature profile plays an important role in the field of atmospheric research.The infrared hyperspectral vertical detector equipped with meteorological satellites can provide relatively high spatiotemporal resolution data,thus being widely used for temperature profile retrieval.In recent years,deep learning,especially convolutional neural networks(CNNs),has attracted much attention in various meteorological and climate tasks,including temperature retrieval.However,it is a completely data-driven approach,which may generate results that violate physical laws.To address this issue,we propose a physical knowledge constrained CNN for temperature profile retrieval in this paper.Specifically,we take advantage of the physical knowledge from weight function and ERA5 data,and use an attention module and a loss function to guide the learning of CNN.In order to test the performance of our proposed model,we collect the geostationary interferometric infrared sounder(GIIRS)data,L-band radiosonde data,ERA5 data,and the GIIRS L2 operational product in China for experiments.It is shown that the root mean square error(RMSE)and mean bias(MB)achieved by our proposed model are 2.06 and 0.072 K,respectively,both of which are better than 2 state-of-the-art neural network-based retrieval models and the operational product.
