To effectively estimate the unknown aerodynamic parameters from the aircraft’s flight data,this paper proposes a novel aerodynamic parameter estimation method incorporating a stacked Long Short-Term Memory(LSTM)netwo...To effectively estimate the unknown aerodynamic parameters from the aircraft’s flight data,this paper proposes a novel aerodynamic parameter estimation method incorporating a stacked Long Short-Term Memory(LSTM)network model and the Levenberg-Marquardt(LM)method.The stacked LSTM network model was designed to realize the aircraft dynamics modeling by utilizing a frame of nonlinear functional mapping based entirely on the measured input-output data of the aircraft system without requiring explicit postulation of the dynamics.The LM method combines the already-trained LSTM network model to optimize the unknown aerodynamic parameters.The proposed method is applied by using the real flight data,generated by ATTAS aircraft and a bio-inspired morphing Unmanned Aerial Vehicle(UAV).The investigation reveals that for the two different flight data,the designed stacked LSTM network structure can maintain the efficacy of the network prediction capability only by appropriately adjusting the dropout rates of its hidden layers without changing other network parameters(i.e.,the initial weights,initial biases,number of hidden cells,time-steps,learning rate,and number of training iterations).Besides,the proposed method’s effectiveness and potential are demonstrated by comparing the estimated results of the ATTAS aircraft or the bio-inspired morphing UAV with the corresponding reference values or wind-tunnel results.展开更多
The Arkhangelsk Seismic Network(ASN)of the N.Laverov Federal Center for Integrated Arctic Research of the Ural Branch of the Russian Academy of Sciences,founded in 2003,includes 10 permanent seismic stations located o...The Arkhangelsk Seismic Network(ASN)of the N.Laverov Federal Center for Integrated Arctic Research of the Ural Branch of the Russian Academy of Sciences,founded in 2003,includes 10 permanent seismic stations located on the coasts of the White,Barents,and Kara Seas and on the Arctic archipelagos of Novaya Zemlya,Franz Josef Land,and Severnaya Zemlya.The network is registered with the International Federation of Digital Seismograph Networks and the International Seismological Center.We used not only ASN data to process earthquakes but also the waveforms of various international seismic stations.The 13,000 seismic events were registered using ASN data for 2012-2022,and for 5,500 of them,we determined the parameters of the earthquake epicenters from the European Arctic.The spatial distribution of epicenters shows that the ASN monitors not only the main seismically active zones but also weak seismicity on the shelf of the Barents and Kara Seas.The representative magnitude of ASN was ML,rep=3.5.The level of microseismic noise has seasonal variations that affect the registration capabilities of each station included in the ASN and the overall sensitivity of the network as a whole.In summer,the sensitivity of the ASN decreased owing to the increasing microseismic and ambient noises,whereas in winter,the sensitivity of the ASN increased significantly because of the decrease.展开更多
Textile-based,chip-less,wireless body sensor networks(WBANs)offer continuous,wireless monitoring of physiological signals from passive sensors distributed across body locations,representing a promising solution for da...Textile-based,chip-less,wireless body sensor networks(WBANs)offer continuous,wireless monitoring of physiological signals from passive sensors distributed across body locations,representing a promising solution for daily wearable sensing.Here,we introduce an all-textile,chipless,and battery-free textile-based body sensor network(tBSN)capable of simultaneously monitoring multiple passive sensors across the body.The tBSN is seamlessly integrated into conventional textiles via digital embroidery of flexible conductive fiber electrodes.Single-node tBSN exhibits robust wireless transmission over interconnect up to 40 cm and demonstrates durability under various conditions.By arranging multiple single-node sensor networks into a concentric multi-hub antenna architecture,we extend the system to a multi-node tBSN,enabling simultaneous wireless monitoring of distributed passive sensors within a single frequency scan.A wearable garment incorporating the multi-node tBSN tracked biomechanical signals from the vastus lateralis and knee joint during motion,highlighting its significant potential for personalized rehabilitation,fitness-assistive technologies,and advanced gait analysis.展开更多
Multimedia data have become popularly transmitted content in opportunistic networks. A large amount of video data easily leads to a low delivery ratio. Breaking up these big data into small pieces or fragments is a re...Multimedia data have become popularly transmitted content in opportunistic networks. A large amount of video data easily leads to a low delivery ratio. Breaking up these big data into small pieces or fragments is a reasonable option. The size of the fragments is critical to transmission efficiency and should be adaptable to the communication capability of a network. We propose a novel communication capacity calculation model of opportunistic network based on the classical random direction mobile model, define the restrain facts model of overhead, and present an optimal fragment size algorithm. We also design and evaluate the methods and algorithms with video data fragments disseminated in a simulated environment. Experiment results verified the effectiveness of the network capability and the optimal fragment methods.展开更多
Problem:Chest radiography is a crucial tool for diagnosing thoracic disorders,but interpretation errors and a lack of qualified practitioners can cause delays in treatment.Aim:This study aimed to develop a reliable mu...Problem:Chest radiography is a crucial tool for diagnosing thoracic disorders,but interpretation errors and a lack of qualified practitioners can cause delays in treatment.Aim:This study aimed to develop a reliable multi-classification artificial intelligence(AI)tool to improve the accuracy and efficiency of chest radiograph diagnosis.Methods:We developed a convolutional neural network(CNN)capable of distinguishing among 26 thoracic diagnoses.The model was trained and externally validated using 795,055 chest radiographs from 13 datasets across 4 countries.Results:The CNN model achieved an average area under the curve(AUC)of 0.961 across all 26 diagnoses in the testing set.COVID-19 detection achieved perfect accuracy(AUC 1.000,[95%confidence interval{CI},1.000 to 1.000]),while effusion or pleural effusion detection showed the lowest accuracy(AUC 0.8453,[95%CI,0.8417 to 0.8489]).In external validation,the model demonstrated strong reproducibility and generalizability within the local dataset,achieving an AUC of 0.9634 for lung opacity detection(95%CI,0.9423 to 0.9702).The CNN outperformed both radiologists and nonradiological physicians,particularly in trans-device image recognition.Even for diseases not specifically trained on,such as aortic dissection,the AI model showed considerable scalability and enhanced diagnostic accuracy for physicians of varying experience levels(all P<0.05).Additionally,our model exhibited no gender bias(P>0.05).Conclusion:The developed AI algorithm,now available as professional web-based software,substantively improves chest radiograph interpretation.This research advances medical imaging and offers substantial diagnostic support in clinical settings.展开更多
基金co-supported by the National Natural Science Foundation of China(No.52192633)the Natural Science Foundation of Shaanxi Province,China(No.2022JC-03)the Fundamental Research Funds for the Central Universities,China(No.XJSJ23164)。
文摘To effectively estimate the unknown aerodynamic parameters from the aircraft’s flight data,this paper proposes a novel aerodynamic parameter estimation method incorporating a stacked Long Short-Term Memory(LSTM)network model and the Levenberg-Marquardt(LM)method.The stacked LSTM network model was designed to realize the aircraft dynamics modeling by utilizing a frame of nonlinear functional mapping based entirely on the measured input-output data of the aircraft system without requiring explicit postulation of the dynamics.The LM method combines the already-trained LSTM network model to optimize the unknown aerodynamic parameters.The proposed method is applied by using the real flight data,generated by ATTAS aircraft and a bio-inspired morphing Unmanned Aerial Vehicle(UAV).The investigation reveals that for the two different flight data,the designed stacked LSTM network structure can maintain the efficacy of the network prediction capability only by appropriately adjusting the dropout rates of its hidden layers without changing other network parameters(i.e.,the initial weights,initial biases,number of hidden cells,time-steps,learning rate,and number of training iterations).Besides,the proposed method’s effectiveness and potential are demonstrated by comparing the estimated results of the ATTAS aircraft or the bio-inspired morphing UAV with the corresponding reference values or wind-tunnel results.
基金supported by the Russian Federation Ministry of Science and Higher Education Research project N 122011300389-8.
文摘The Arkhangelsk Seismic Network(ASN)of the N.Laverov Federal Center for Integrated Arctic Research of the Ural Branch of the Russian Academy of Sciences,founded in 2003,includes 10 permanent seismic stations located on the coasts of the White,Barents,and Kara Seas and on the Arctic archipelagos of Novaya Zemlya,Franz Josef Land,and Severnaya Zemlya.The network is registered with the International Federation of Digital Seismograph Networks and the International Seismological Center.We used not only ASN data to process earthquakes but also the waveforms of various international seismic stations.The 13,000 seismic events were registered using ASN data for 2012-2022,and for 5,500 of them,we determined the parameters of the earthquake epicenters from the European Arctic.The spatial distribution of epicenters shows that the ASN monitors not only the main seismically active zones but also weak seismicity on the shelf of the Barents and Kara Seas.The representative magnitude of ASN was ML,rep=3.5.The level of microseismic noise has seasonal variations that affect the registration capabilities of each station included in the ASN and the overall sensitivity of the network as a whole.In summer,the sensitivity of the ASN decreased owing to the increasing microseismic and ambient noises,whereas in winter,the sensitivity of the ASN increased significantly because of the decrease.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(RS-2021-NR061513,RS-2025-16071089)supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(RS-2025-25420118)+1 种基金supported by the Council of Science&Technology(NST)grant by the Korea government(NSIT)(No.GTL25041-000)the DGIST R&D Program of the Ministry of Science and ICT(2025010373,25-IRJoint-06).
文摘Textile-based,chip-less,wireless body sensor networks(WBANs)offer continuous,wireless monitoring of physiological signals from passive sensors distributed across body locations,representing a promising solution for daily wearable sensing.Here,we introduce an all-textile,chipless,and battery-free textile-based body sensor network(tBSN)capable of simultaneously monitoring multiple passive sensors across the body.The tBSN is seamlessly integrated into conventional textiles via digital embroidery of flexible conductive fiber electrodes.Single-node tBSN exhibits robust wireless transmission over interconnect up to 40 cm and demonstrates durability under various conditions.By arranging multiple single-node sensor networks into a concentric multi-hub antenna architecture,we extend the system to a multi-node tBSN,enabling simultaneous wireless monitoring of distributed passive sensors within a single frequency scan.A wearable garment incorporating the multi-node tBSN tracked biomechanical signals from the vastus lateralis and knee joint during motion,highlighting its significant potential for personalized rehabilitation,fitness-assistive technologies,and advanced gait analysis.
基金supported by the Shaanxi Natural Science Foundation Research Plan (No. 2015JQ6238)the China Scholarship Council+3 种基金the National Natural Science Foundation of China(Nos. 61373083 and 61402273)the Fundamental Research Funds for the Central Universities of China (No. GK201401002)the Program of Shaanxi Science and Technology Innovation Team of China (No. 2014KTC18)the 111 Programme of Introducing Talents of Discipline to Universities (No. B16031)
文摘Multimedia data have become popularly transmitted content in opportunistic networks. A large amount of video data easily leads to a low delivery ratio. Breaking up these big data into small pieces or fragments is a reasonable option. The size of the fragments is critical to transmission efficiency and should be adaptable to the communication capability of a network. We propose a novel communication capacity calculation model of opportunistic network based on the classical random direction mobile model, define the restrain facts model of overhead, and present an optimal fragment size algorithm. We also design and evaluate the methods and algorithms with video data fragments disseminated in a simulated environment. Experiment results verified the effectiveness of the network capability and the optimal fragment methods.
基金supported by the Fundamental Research Funds for the Central Universities(2019PT350005)National Natural Science Foundation of China(nos.81970444 and 82300345)+6 种基金Beijing Municipal Science and Technology Project(Z201100005420030)National high level talents special supportplan(2020-RSW02)CAMS Innovation Fund for MedicalSciences(2021-I2M-1-065)Sanming Project of Medicine in Shenzhen(SZSM202011013)the project for the distinguishing academic discipline of Fuwai Hospital(2022-FWQN16)the National High Level Hospital Clinical Research Funding(2023-GSP-QN-23)the National High Level Hospital Clinical Research Funding(2023-GSP-RC-04).
文摘Problem:Chest radiography is a crucial tool for diagnosing thoracic disorders,but interpretation errors and a lack of qualified practitioners can cause delays in treatment.Aim:This study aimed to develop a reliable multi-classification artificial intelligence(AI)tool to improve the accuracy and efficiency of chest radiograph diagnosis.Methods:We developed a convolutional neural network(CNN)capable of distinguishing among 26 thoracic diagnoses.The model was trained and externally validated using 795,055 chest radiographs from 13 datasets across 4 countries.Results:The CNN model achieved an average area under the curve(AUC)of 0.961 across all 26 diagnoses in the testing set.COVID-19 detection achieved perfect accuracy(AUC 1.000,[95%confidence interval{CI},1.000 to 1.000]),while effusion or pleural effusion detection showed the lowest accuracy(AUC 0.8453,[95%CI,0.8417 to 0.8489]).In external validation,the model demonstrated strong reproducibility and generalizability within the local dataset,achieving an AUC of 0.9634 for lung opacity detection(95%CI,0.9423 to 0.9702).The CNN outperformed both radiologists and nonradiological physicians,particularly in trans-device image recognition.Even for diseases not specifically trained on,such as aortic dissection,the AI model showed considerable scalability and enhanced diagnostic accuracy for physicians of varying experience levels(all P<0.05).Additionally,our model exhibited no gender bias(P>0.05).Conclusion:The developed AI algorithm,now available as professional web-based software,substantively improves chest radiograph interpretation.This research advances medical imaging and offers substantial diagnostic support in clinical settings.
