Distributed/parallel-processing system like sun grid engine(SGE) that utilizes multiple nodes/cores is proposed for the faster processing of large sized satellite image data. After verification, distributed process en...Distributed/parallel-processing system like sun grid engine(SGE) that utilizes multiple nodes/cores is proposed for the faster processing of large sized satellite image data. After verification, distributed process environment for pre-processing performance can be improved by up to 560.65% from single processing system. Through this, analysis performance in various fields can be improved, and moreover, near-real time service can be achieved in near future.展开更多
Objective The most prevalent mRNA modification,N6-methyladenosine(m^(6)A)plays an important role in various RNA metabolism,including gene expression and translation.By recruiting different“reader”proteins and their ...Objective The most prevalent mRNA modification,N6-methyladenosine(m^(6)A)plays an important role in various RNA metabolism,including gene expression and translation.By recruiting different“reader”proteins and their cofactors,m^(6)A modification can affect messenger RNA(mRNA)degradation,splicing,nuclear export and translation.However,the selective mechanism by which m^(6)A sites regulate mRNA translation through m^(6)A reader YTHDF1 binding remains poorly understood,due to a lack of computational methods for identifying context-specific m^(6)A sites that regulate translation.To address this,we developed a novel computational framework named m^(6)ATEpre,the first tool designed to predict cell-specific m^(6)A sites that regulate translation efficiency.Methods m^(6)ATEpre integrates multi-omics data,introduces a novel feature representation strategy for m^(6)A site sequences,and employs an autoencoder to effectively capture embedded feature representations.Specifically,m^(6)ATEpre first integrated MeRIP-seq data and PAR-CLIP data through overlapping m^(6)A sites with YTHDF1 binding sites and identified YTHDF1-mediated m^(6)A sites.Then,m^(6)ATEpre detected the translation gene by analyzing the Ribo-seq data under YTHDF1 knockdown vs control condition.Genes whose translation is mediated by YTHDF1 in an m^(6)A-dependent manner were identified by a significant decrease in translation efficiency upon YTHDF1 knockdown.Next,we proposed a binary vector indicating the presence or absence of YTHDF1 binding motifs to characterize each m^(6)A site sequence.This represents a novel feature representation strategy for m^(6)A sites.m^(6)ATEpre utilized the autoencoder to extract the potentially important feature representations and constructed a multilayer perceptron neural networks model to predict potential m^(6)A sites that regulating translation efficiency.Results A comprehensive evaluation of m^(6)ATEpre was conducted through a series of experiments.We compared its performance against that of a similar prediction task model,as well as other classifiers.The results indicate that m^(6)ATEpre achieved the best prediction performance.In addition,we analyzed different feature representation strategies and performed ablation experiments to validate the rationality of the model design.The results demonstrate that our proposed feature representation strategy has a greater advantage in improving prediction performance.In the HeLa cell line,bioinformatic analysis of the metagene distribution and sequence minimum free energy of m^(6)A sites regulating translation efficiency(m^(6)A-reg-TE sites)revealed their specific properties in translation regulation.Functional enrichment analysis indicated that m^(6)A-reg-TE genes are associated with specific biological processes and KEGG pathways.By integrating the binding sites of YTHDF1 co-factors with m^(6)A-reg-TE sites,we revealed that YTHDF1-mediated and m^(6)A-dependent translation efficiency regulation requires the cooperation of multiple translation-regulatory RNA-binding proteins among its co-factors in the HeLa cell line.Furthermore,we extended our predictions to the dataset of the HEK293T cell line.Similarly,bioinformatic analysis of the metagene distribution and functional enrichment revealed the cell-specific characteristic of these predicted m^(6)A-reg-TE sites in HEK293T cells.Likewise,integrated analysis of multiple YTHDF1 co-factors and m^(6)A-reg-TE sites predicted in the HEK293T cell line reveals their m^(6)A-dependent cooperation in regulating translation efficiency.Conclusion m^(6)ATEpre is a timely tool that will advance our understanding of the mechanisms of m^(6)A regulation in translation efficiency.The source code and datasets used in this work can be downloaded from https://www.scidb.cn/s/bAZZFr.展开更多
In order to meet the demands for high transmission rates and high service quality in broadband wireless communication systems, orthogonal frequency division multiplexing （OFDM） has been adopted in some standards. Ho...In order to meet the demands for high transmission rates and high service quality in broadband wireless communication systems, orthogonal frequency division multiplexing （OFDM） has been adopted in some standards. However, the inter-block interference （IBI） and inter-carrier interference （ICI） in an OFDM system affect the performance. To mitigate IBI and ICI, some pre-processing approaches have been proposed based on full channel state information （CSI）, which improved the system performance. A pre-processing filter based on partial CSI at the transmitter is designed and investigated. The filter coefficient is given by the optimization processing, the symbol error rate （SER） is tested, and the computation complexity of the proposed scheme is analyzed. Computer simulation results show that the proposed pre-processing filter can effectively mitigate IBI and ICI and the performance can be improved. Compared with pre-processing approaches at the transmitter based on full CSI, the proposed scheme has high spectral efficiency, limited CSI feedback and low computation complexity.展开更多
This study presents a machine learning-based method for predicting fragment velocity distribution in warhead fragmentation under explosive loading condition.The fragment resultant velocities are correlated with key de...This study presents a machine learning-based method for predicting fragment velocity distribution in warhead fragmentation under explosive loading condition.The fragment resultant velocities are correlated with key design parameters including casing dimensions and detonation positions.The paper details the finite element analysis for fragmentation,the characterizations of the dynamic hardening and fracture models,the generation of comprehensive datasets,and the training of the ANN model.The results show the influence of casing dimensions on fragment velocity distributions,with the tendencies indicating increased resultant velocity with reduced thickness,increased length and diameter.The model's predictive capability is demonstrated through the accurate predictions for both training and testing datasets,showing its potential for the real-time prediction of fragmentation performance.展开更多
Recently, high-precision trajectory prediction of ballistic missiles in the boost phase has become a research hotspot. This paper proposes a trajectory prediction algorithm driven by data and knowledge(DKTP) to solve ...Recently, high-precision trajectory prediction of ballistic missiles in the boost phase has become a research hotspot. This paper proposes a trajectory prediction algorithm driven by data and knowledge(DKTP) to solve this problem. Firstly, the complex dynamics characteristics of ballistic missile in the boost phase are analyzed in detail. Secondly, combining the missile dynamics model with the target gravity turning model, a knowledge-driven target three-dimensional turning(T3) model is derived. Then, the BP neural network is used to train the boost phase trajectory database in typical scenarios to obtain a datadriven state parameter mapping(SPM) model. On this basis, an online trajectory prediction framework driven by data and knowledge is established. Based on the SPM model, the three-dimensional turning coefficients of the target are predicted by using the current state of the target, and the state of the target at the next moment is obtained by combining the T3 model. Finally, simulation verification is carried out under various conditions. The simulation results show that the DKTP algorithm combines the advantages of data-driven and knowledge-driven, improves the interpretability of the algorithm, reduces the uncertainty, which can achieve high-precision trajectory prediction of ballistic missile in the boost phase.展开更多
Estimating trawler fishing effort plays a critical role in characterizing marine fisheries activities,quantifying the ecological impact of trawling,and refining regulatory frameworks and policies.Understanding trawler...Estimating trawler fishing effort plays a critical role in characterizing marine fisheries activities,quantifying the ecological impact of trawling,and refining regulatory frameworks and policies.Understanding trawler fishing inputs offers crucial scientific data to support the sustainable management of offshore fishery resources in China.An XGBoost algorithm was introduced and optimized through Harris Hawks Optimization(HHO),to develop a model for identifying trawler fishing behaviour.The model demonstrated exceptional performance,achieving accuracy,sensitivity,specificity,and the Matthews correlation coefficient of 0.9713,0.9806,0.9632,and 0.9425,respectively.Using this model to detect fishing activities,the fishing effort of trawlers from Shandong Province in the sea area between 119°E to 124°E and 32°N to 40°N in 2021 was quantified.A heatmap depicting fishing effort,generated with a spatial resolution of 1/8°,revealed that fishing activities were predominantly concentrated in two regions:121.1°E to 124°E,35.7°N to 38.7°N,and 119.8°E to 122.8°E,33.6°N to 35.4°N.This research can provide a foundation for quantitative evaluations of fishery resources,which can offer vital data to promote the sustainable development of marine capture fisheries.展开更多
Accurate estimation of understory terrain has significant scientific importance for maintaining ecosystem balance and biodiversity conservation.Addressing the issue of inadequate representation of spatial heterogeneit...Accurate estimation of understory terrain has significant scientific importance for maintaining ecosystem balance and biodiversity conservation.Addressing the issue of inadequate representation of spatial heterogeneity when traditional forest topographic inversion methods consider the entire forest as the inversion unit,this study pro⁃poses a differentiated modeling approach to forest types based on refined land cover classification.Taking Puerto Ri⁃co and Maryland as study areas,a multi-dimensional feature system is constructed by integrating multi-source re⁃mote sensing data:ICESat-2 spaceborne LiDAR is used to obtain benchmark values for understory terrain,topo⁃graphic factors such as slope and aspect are extracted based on SRTM data,and vegetation cover characteristics are analyzed using Landsat-8 multispectral imagery.This study incorporates forest type as a classification modeling con⁃dition and applies the random forest algorithm to build differentiated topographic inversion models.Experimental re⁃sults indicate that,compared to traditional whole-area modeling methods(RMSE=5.06 m),forest type-based classi⁃fication modeling significantly improves the accuracy of understory terrain estimation(RMSE=2.94 m),validating the effectiveness of spatial heterogeneity modeling.Further sensitivity analysis reveals that canopy structure parame⁃ters(with RMSE variation reaching 4.11 m)exert a stronger regulatory effect on estimation accuracy compared to forest cover,providing important theoretical support for optimizing remote sensing models of forest topography.展开更多
为了应对乌克兰持续不断的战争带来的严峻挑战,EOS Data Analytics推出了“收获希望”计划,该计划旨在关注席卷乌克兰农业部门的危机。这个综合网页设有一张交互式地图,展示了2021—2024年乌克兰主要作物的历史和预测产量。此外,该倡议...为了应对乌克兰持续不断的战争带来的严峻挑战,EOS Data Analytics推出了“收获希望”计划,该计划旨在关注席卷乌克兰农业部门的危机。这个综合网页设有一张交互式地图,展示了2021—2024年乌克兰主要作物的历史和预测产量。此外,该倡议还介绍了乌克兰农业的现状及其对全球粮食安全的影响。出于支持乌克兰农民的承诺,该公司将在2024年向他们免费提供EOSDA作物监测服务,作为“收获希望”计划的一部分。该平台将帮助农民克服逆境,并确保乌克兰农业部门的可持续未来。展开更多
The reverse design of solid rocket motor(SRM)propellant grain involves determining the grain geometry to closely match a predefined internal ballistic curve.While existing reverse design methods are feasible,they ofte...The reverse design of solid rocket motor(SRM)propellant grain involves determining the grain geometry to closely match a predefined internal ballistic curve.While existing reverse design methods are feasible,they often face challenges such as lengthy computation times and limited accuracy.To achieve rapid and accurate matching between the targeted ballistic curve and complex grain shape,this paper proposes a novel reverse design method for SRM propellant grain based on time-series data imaging and convolutional neural network(CNN).First,a finocyl grain shape-internal ballistic curve dataset is created using parametric modeling techniques to comprehensively cover the design space.Next,the internal ballistic time-series data is encoded into three-channel images,establishing a potential relationship between the ballistic curves and their image representations.A CNN is then constructed and trained using these encoded images.Once trained,the model enables efficient inference of propellant grain dimensions from a target internal ballistic curve.This paper conducts comparative experiments across various neural network models,validating the effectiveness of the feature extraction method that transforms internal ballistic time-series data into images,as well as its generalization capability across different CNN architectures.Ignition tests were performed based on the predicted propellant grain.The results demonstrate that the relative error between the experimental internal ballistic curves and the target curves is less than 5%,confirming the validity and feasibility of the proposed reverse design methodology.展开更多
Heterogeneous federated learning(HtFL)has gained significant attention due to its ability to accommodate diverse models and data from distributed combat units.The prototype-based HtFL methods were proposed to reduce t...Heterogeneous federated learning(HtFL)has gained significant attention due to its ability to accommodate diverse models and data from distributed combat units.The prototype-based HtFL methods were proposed to reduce the high communication cost of transmitting model parameters.These methods allow for the sharing of only class representatives between heterogeneous clients while maintaining privacy.However,existing prototype learning approaches fail to take the data distribution of clients into consideration,which results in suboptimal global prototype learning and insufficient client model personalization capabilities.To address these issues,we propose a fair trainable prototype federated learning(FedFTP)algorithm,which employs a fair sampling training prototype(FSTP)mechanism and a hyperbolic space constraints(HSC)mechanism to enhance the fairness and effectiveness of prototype learning on the server in heterogeneous environments.Furthermore,a local prototype stable update(LPSU)mechanism is proposed as a means of maintaining personalization while promoting global consistency,based on contrastive learning.Comprehensive experimental results demonstrate that FedFTP achieves state-of-the-art performance in HtFL scenarios.展开更多
[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-base...[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.展开更多
基金supported by the Sharing and Diffusion of National R&D Outcome funded by the Korea Institute of Science and Technology Information
文摘Distributed/parallel-processing system like sun grid engine(SGE) that utilizes multiple nodes/cores is proposed for the faster processing of large sized satellite image data. After verification, distributed process environment for pre-processing performance can be improved by up to 560.65% from single processing system. Through this, analysis performance in various fields can be improved, and moreover, near-real time service can be achieved in near future.
文摘Objective The most prevalent mRNA modification,N6-methyladenosine(m^(6)A)plays an important role in various RNA metabolism,including gene expression and translation.By recruiting different“reader”proteins and their cofactors,m^(6)A modification can affect messenger RNA(mRNA)degradation,splicing,nuclear export and translation.However,the selective mechanism by which m^(6)A sites regulate mRNA translation through m^(6)A reader YTHDF1 binding remains poorly understood,due to a lack of computational methods for identifying context-specific m^(6)A sites that regulate translation.To address this,we developed a novel computational framework named m^(6)ATEpre,the first tool designed to predict cell-specific m^(6)A sites that regulate translation efficiency.Methods m^(6)ATEpre integrates multi-omics data,introduces a novel feature representation strategy for m^(6)A site sequences,and employs an autoencoder to effectively capture embedded feature representations.Specifically,m^(6)ATEpre first integrated MeRIP-seq data and PAR-CLIP data through overlapping m^(6)A sites with YTHDF1 binding sites and identified YTHDF1-mediated m^(6)A sites.Then,m^(6)ATEpre detected the translation gene by analyzing the Ribo-seq data under YTHDF1 knockdown vs control condition.Genes whose translation is mediated by YTHDF1 in an m^(6)A-dependent manner were identified by a significant decrease in translation efficiency upon YTHDF1 knockdown.Next,we proposed a binary vector indicating the presence or absence of YTHDF1 binding motifs to characterize each m^(6)A site sequence.This represents a novel feature representation strategy for m^(6)A sites.m^(6)ATEpre utilized the autoencoder to extract the potentially important feature representations and constructed a multilayer perceptron neural networks model to predict potential m^(6)A sites that regulating translation efficiency.Results A comprehensive evaluation of m^(6)ATEpre was conducted through a series of experiments.We compared its performance against that of a similar prediction task model,as well as other classifiers.The results indicate that m^(6)ATEpre achieved the best prediction performance.In addition,we analyzed different feature representation strategies and performed ablation experiments to validate the rationality of the model design.The results demonstrate that our proposed feature representation strategy has a greater advantage in improving prediction performance.In the HeLa cell line,bioinformatic analysis of the metagene distribution and sequence minimum free energy of m^(6)A sites regulating translation efficiency(m^(6)A-reg-TE sites)revealed their specific properties in translation regulation.Functional enrichment analysis indicated that m^(6)A-reg-TE genes are associated with specific biological processes and KEGG pathways.By integrating the binding sites of YTHDF1 co-factors with m^(6)A-reg-TE sites,we revealed that YTHDF1-mediated and m^(6)A-dependent translation efficiency regulation requires the cooperation of multiple translation-regulatory RNA-binding proteins among its co-factors in the HeLa cell line.Furthermore,we extended our predictions to the dataset of the HEK293T cell line.Similarly,bioinformatic analysis of the metagene distribution and functional enrichment revealed the cell-specific characteristic of these predicted m^(6)A-reg-TE sites in HEK293T cells.Likewise,integrated analysis of multiple YTHDF1 co-factors and m^(6)A-reg-TE sites predicted in the HEK293T cell line reveals their m^(6)A-dependent cooperation in regulating translation efficiency.Conclusion m^(6)ATEpre is a timely tool that will advance our understanding of the mechanisms of m^(6)A regulation in translation efficiency.The source code and datasets used in this work can be downloaded from https://www.scidb.cn/s/bAZZFr.
基金supported by the National Natural Science Foundation of China(60902045)the National High-Tech Research and Developmeent Program of China(863 Program)(2011AA01A105)
文摘In order to meet the demands for high transmission rates and high service quality in broadband wireless communication systems, orthogonal frequency division multiplexing （OFDM） has been adopted in some standards. However, the inter-block interference （IBI） and inter-carrier interference （ICI） in an OFDM system affect the performance. To mitigate IBI and ICI, some pre-processing approaches have been proposed based on full channel state information （CSI）, which improved the system performance. A pre-processing filter based on partial CSI at the transmitter is designed and investigated. The filter coefficient is given by the optimization processing, the symbol error rate （SER） is tested, and the computation complexity of the proposed scheme is analyzed. Computer simulation results show that the proposed pre-processing filter can effectively mitigate IBI and ICI and the performance can be improved. Compared with pre-processing approaches at the transmitter based on full CSI, the proposed scheme has high spectral efficiency, limited CSI feedback and low computation complexity.
基金supported by Poongsan-KAIST Future Research Center Projectthe fund support provided by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(Grant No.2023R1A2C2005661)。
文摘This study presents a machine learning-based method for predicting fragment velocity distribution in warhead fragmentation under explosive loading condition.The fragment resultant velocities are correlated with key design parameters including casing dimensions and detonation positions.The paper details the finite element analysis for fragmentation,the characterizations of the dynamic hardening and fracture models,the generation of comprehensive datasets,and the training of the ANN model.The results show the influence of casing dimensions on fragment velocity distributions,with the tendencies indicating increased resultant velocity with reduced thickness,increased length and diameter.The model's predictive capability is demonstrated through the accurate predictions for both training and testing datasets,showing its potential for the real-time prediction of fragmentation performance.
基金the National Natural Science Foundation of China (Grants No. 12072090 and No.12302056) to provide fund for conducting experiments。
文摘Recently, high-precision trajectory prediction of ballistic missiles in the boost phase has become a research hotspot. This paper proposes a trajectory prediction algorithm driven by data and knowledge(DKTP) to solve this problem. Firstly, the complex dynamics characteristics of ballistic missile in the boost phase are analyzed in detail. Secondly, combining the missile dynamics model with the target gravity turning model, a knowledge-driven target three-dimensional turning(T3) model is derived. Then, the BP neural network is used to train the boost phase trajectory database in typical scenarios to obtain a datadriven state parameter mapping(SPM) model. On this basis, an online trajectory prediction framework driven by data and knowledge is established. Based on the SPM model, the three-dimensional turning coefficients of the target are predicted by using the current state of the target, and the state of the target at the next moment is obtained by combining the T3 model. Finally, simulation verification is carried out under various conditions. The simulation results show that the DKTP algorithm combines the advantages of data-driven and knowledge-driven, improves the interpretability of the algorithm, reduces the uncertainty, which can achieve high-precision trajectory prediction of ballistic missile in the boost phase.
文摘Estimating trawler fishing effort plays a critical role in characterizing marine fisheries activities,quantifying the ecological impact of trawling,and refining regulatory frameworks and policies.Understanding trawler fishing inputs offers crucial scientific data to support the sustainable management of offshore fishery resources in China.An XGBoost algorithm was introduced and optimized through Harris Hawks Optimization(HHO),to develop a model for identifying trawler fishing behaviour.The model demonstrated exceptional performance,achieving accuracy,sensitivity,specificity,and the Matthews correlation coefficient of 0.9713,0.9806,0.9632,and 0.9425,respectively.Using this model to detect fishing activities,the fishing effort of trawlers from Shandong Province in the sea area between 119°E to 124°E and 32°N to 40°N in 2021 was quantified.A heatmap depicting fishing effort,generated with a spatial resolution of 1/8°,revealed that fishing activities were predominantly concentrated in two regions:121.1°E to 124°E,35.7°N to 38.7°N,and 119.8°E to 122.8°E,33.6°N to 35.4°N.This research can provide a foundation for quantitative evaluations of fishery resources,which can offer vital data to promote the sustainable development of marine capture fisheries.
基金Supported by the National Natural Science Foundation of China(42401488,42071351)the National Key Research and Development Program of China(2020YFA0608501,2017YFB0504204)+4 种基金the Liaoning Revitalization Talents Program(XLYC1802027)the Talent Recruited Program of the Chinese Academy of Science(Y938091)the Project Supported Discipline Innovation Team of the Liaoning Technical University(LNTU20TD-23)the Liaoning Province Doctoral Research Initiation Fund Program(2023-BS-202)the Basic Research Projects of Liaoning Department of Education(JYTQN2023202)。
文摘Accurate estimation of understory terrain has significant scientific importance for maintaining ecosystem balance and biodiversity conservation.Addressing the issue of inadequate representation of spatial heterogeneity when traditional forest topographic inversion methods consider the entire forest as the inversion unit,this study pro⁃poses a differentiated modeling approach to forest types based on refined land cover classification.Taking Puerto Ri⁃co and Maryland as study areas,a multi-dimensional feature system is constructed by integrating multi-source re⁃mote sensing data:ICESat-2 spaceborne LiDAR is used to obtain benchmark values for understory terrain,topo⁃graphic factors such as slope and aspect are extracted based on SRTM data,and vegetation cover characteristics are analyzed using Landsat-8 multispectral imagery.This study incorporates forest type as a classification modeling con⁃dition and applies the random forest algorithm to build differentiated topographic inversion models.Experimental re⁃sults indicate that,compared to traditional whole-area modeling methods(RMSE=5.06 m),forest type-based classi⁃fication modeling significantly improves the accuracy of understory terrain estimation(RMSE=2.94 m),validating the effectiveness of spatial heterogeneity modeling.Further sensitivity analysis reveals that canopy structure parame⁃ters(with RMSE variation reaching 4.11 m)exert a stronger regulatory effect on estimation accuracy compared to forest cover,providing important theoretical support for optimizing remote sensing models of forest topography.
文摘为了应对乌克兰持续不断的战争带来的严峻挑战,EOS Data Analytics推出了“收获希望”计划,该计划旨在关注席卷乌克兰农业部门的危机。这个综合网页设有一张交互式地图,展示了2021—2024年乌克兰主要作物的历史和预测产量。此外,该倡议还介绍了乌克兰农业的现状及其对全球粮食安全的影响。出于支持乌克兰农民的承诺,该公司将在2024年向他们免费提供EOSDA作物监测服务,作为“收获希望”计划的一部分。该平台将帮助农民克服逆境,并确保乌克兰农业部门的可持续未来。
文摘The reverse design of solid rocket motor(SRM)propellant grain involves determining the grain geometry to closely match a predefined internal ballistic curve.While existing reverse design methods are feasible,they often face challenges such as lengthy computation times and limited accuracy.To achieve rapid and accurate matching between the targeted ballistic curve and complex grain shape,this paper proposes a novel reverse design method for SRM propellant grain based on time-series data imaging and convolutional neural network(CNN).First,a finocyl grain shape-internal ballistic curve dataset is created using parametric modeling techniques to comprehensively cover the design space.Next,the internal ballistic time-series data is encoded into three-channel images,establishing a potential relationship between the ballistic curves and their image representations.A CNN is then constructed and trained using these encoded images.Once trained,the model enables efficient inference of propellant grain dimensions from a target internal ballistic curve.This paper conducts comparative experiments across various neural network models,validating the effectiveness of the feature extraction method that transforms internal ballistic time-series data into images,as well as its generalization capability across different CNN architectures.Ignition tests were performed based on the predicted propellant grain.The results demonstrate that the relative error between the experimental internal ballistic curves and the target curves is less than 5%,confirming the validity and feasibility of the proposed reverse design methodology.
基金supported by the Natural Science Foundation of Xinjiang Uygur Autonomous Region(No.2022D01B187).
文摘Heterogeneous federated learning(HtFL)has gained significant attention due to its ability to accommodate diverse models and data from distributed combat units.The prototype-based HtFL methods were proposed to reduce the high communication cost of transmitting model parameters.These methods allow for the sharing of only class representatives between heterogeneous clients while maintaining privacy.However,existing prototype learning approaches fail to take the data distribution of clients into consideration,which results in suboptimal global prototype learning and insufficient client model personalization capabilities.To address these issues,we propose a fair trainable prototype federated learning(FedFTP)algorithm,which employs a fair sampling training prototype(FSTP)mechanism and a hyperbolic space constraints(HSC)mechanism to enhance the fairness and effectiveness of prototype learning on the server in heterogeneous environments.Furthermore,a local prototype stable update(LPSU)mechanism is proposed as a means of maintaining personalization while promoting global consistency,based on contrastive learning.Comprehensive experimental results demonstrate that FedFTP achieves state-of-the-art performance in HtFL scenarios.
文摘[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.
