In the past few years,deep learning has developed rapidly,and many researchers try to combine their subjects with deep learning.The algorithm based on Recurrent Neural Network(RNN)has been successfully applied in the ...In the past few years,deep learning has developed rapidly,and many researchers try to combine their subjects with deep learning.The algorithm based on Recurrent Neural Network(RNN)has been successfully applied in the fields of weather forecasting,stock forecasting,action recognition,etc.because of its excellent performance in processing Spatio-temporal sequence data.Among them,algorithms based on LSTM and GRU have developed most rapidly because of their good design.This paper reviews the RNN-based Spatio-temporal sequence prediction algorithm,introduces the development history of RNN and the common application directions of the Spatio-temporal sequence prediction,and includes precipitation nowcasting algorithms and traffic flow forecasting algorithms.At the same time,it also compares the advantages and disadvantages,and innovations of each algorithm.The purpose of this article is to give readers a clear understanding of solutions to such problems.Finally,it prospects the future development of RNN in the Spatio-temporal sequence prediction algorithm.展开更多
To solve the problem of target damage assessment when fragments attack target under uncertain projectile and target intersection in an air defense intercept,this paper proposes a method for calculating target damage p...To solve the problem of target damage assessment when fragments attack target under uncertain projectile and target intersection in an air defense intercept,this paper proposes a method for calculating target damage probability leveraging spatio-temporal finite multilayer fragments distribution and the target damage assessment algorithm based on cloud model theory.Drawing on the spatial dispersion characteristics of fragments of projectile proximity explosion,we divide into a finite number of fragments distribution planes based on the time series in space,set up a fragment layer dispersion model grounded in the time series and intersection criterion for determining the effective penetration of each layer of fragments into the target.Building on the precondition that the multilayer fragments of the time series effectively assail the target,we also establish the damage criterion of the perforation and penetration damage and deduce the damage probability calculation model.Taking the damage probability of the fragment layer in the spatio-temporal sequence to the target as the input state variable,we introduce cloud model theory to research the target damage assessment method.Combining the equivalent simulation experiment,the scientific and rational nature of the proposed method were validated through quantitative calculations and comparative analysis.展开更多
Shallow earthquakes usually show obvious spatio-temporal clustering patterns. In this study, several spatio-temporal point process models are applied to investigate the clustering characteristics of the well-known Tan...Shallow earthquakes usually show obvious spatio-temporal clustering patterns. In this study, several spatio-temporal point process models are applied to investigate the clustering characteristics of the well-known Tangshan sequence based on classical empirical laws and a few assumptions. The relative fit of competing models is compared by Akalke Information Criterion. The spatial clustering pattern is well characterized by the model which gives the best fit to the data. A simulated aftershock sequence is generated by thinning algorithm and compared with the real seismicity.展开更多
Point-of-interest(POI)recommendations in location-based social networks(LBSNs)have developed rapidly by incorporating feature information and deep learning methods.However,most studies have failed to accurately reflec...Point-of-interest(POI)recommendations in location-based social networks(LBSNs)have developed rapidly by incorporating feature information and deep learning methods.However,most studies have failed to accurately reflect different users’preferences,in particular,the short-term preferences of inactive users.To better learn user preferences,in this study,we propose a long-short-term-preference-based adaptive successive POI recommendation(LSTP-ASR)method by combining trajectory sequence processing,long short-term preference learning,and spatiotemporal context.First,the check-in trajectory sequences are adaptively divided into recent and historical sequences according to a dynamic time window.Subsequently,an adaptive filling strategy is used to expand the recent check-in sequences of users with inactive check-in behavior using those of similar active users.We further propose an adaptive learning model to accurately extract long short-term preferences of users to establish an efficient successive POI recommendation system.A spatiotemporal-context-based recurrent neural network and temporal-context-based long short-term memory network are used to model the users’recent and historical checkin trajectory sequences,respectively.Extensive experiments on the Foursquare and Gowalla datasets reveal that the proposed method outperforms several other baseline methods in terms of three evaluation metrics.More specifically,LSTP-ASR outperforms the previously best baseline method(RTPM)with a 17.15%and 20.62%average improvement on the Foursquare and Gowalla datasets in terms of the Fβmetric,respectively.展开更多
Objective:The goal of this study was to get preliminary insight on the intra-tumor heterogeneity in colitisassociated cancer(CAC)and to reveal a potential evolutionary trajectory from ulcerative colitis(UC)to CAC at t...Objective:The goal of this study was to get preliminary insight on the intra-tumor heterogeneity in colitisassociated cancer(CAC)and to reveal a potential evolutionary trajectory from ulcerative colitis(UC)to CAC at the single-cell level.Methods:Fresh samples of tumor tissues and adjacent UC tissues from a CAC patient with pT3N1M0 stage cancer were examined by single-cell RNA sequencing(scRNA-seq).Data from The Cancer Genome Atlas(TCGA)and The Human Protein Atlas were used to confirm the different expression levels in normal and tumor tissues and to determine their relationships with patient prognosis.Results:Ultimately,4,777 single-cell transcriptomes(1,220 genes per cell)were examined,of which 2,250(47%)and 2,527(53%)originated from tumor and adjacent UC tissues,respectively.We defined the composition of cancer-associated stromal cells and identified six cell clusters,including myeloid,T and B cells,fibroblasts,endothelial and epithelial cells.Notable pathways and transcription factors involved in these cell clusters were analyzed and described.Moreover,the precise cellular composition and developmental trajectory from UC to UCassociated colon cancer were graphed,and it was predicted that CD74,CLCA1,and DPEP1 played a potential role in disease progression.Conclusions:scRNA-seq technology revealed intra-tumor cell heterogeneity in UC-associated colon cancer,and might provide a promising direction to identify novel potential therapeutic targets in the evolution from UC to CAC.展开更多
Climate sequences can be applied to defining sensitive climate zones, and then the mining of spatio-temporal teleconnection patterns is useful for learning from the past and preparing for the future. However, scale-de...Climate sequences can be applied to defining sensitive climate zones, and then the mining of spatio-temporal teleconnection patterns is useful for learning from the past and preparing for the future. However, scale-dependency in this kind of pattern is still not well handled by existing work. Therefore, in this study, the multi-scale regionalization is embedded into the spatio-temporal teleconnection pattern mining between anomalous sea and land climatic events. A modified scale-space clustering algorithm is first developed to group climate sequences into multi-scale climate zones. Then, scale variance analysis method is employed to identify climate zones at characteristic scales, indicating the main characteristics of geographical phenomena. Finally, by using the climate zones identified at characteristic scales, a time association rule mining algorithm based on sliding time windows is employed to discover spatio-temporal teleconnection patterns. Experiments on sea surface temperature, sea level pressure, land precipitation and land temperature datasets show that many patterns obtained by the multi-scale approach are coincident with prior knowledge, indicating that this method is effective and reasonable. In addition, some unknown teleconnection patterns discovered from the multi-scale approach can be further used to guide the prediction of land climate.展开更多
In order to avoid the influence of noise variance on the filtering performances, a modified adaptive weighted averaging (MAWA) filtering algorithm is proposed for noisy image sequences. Based upon adaptive weighted av...In order to avoid the influence of noise variance on the filtering performances, a modified adaptive weighted averaging (MAWA) filtering algorithm is proposed for noisy image sequences. Based upon adaptive weighted averaging pixel values in consecutive frames, this algorithm achieves the filtering goal by assigning smaller weights to the pixels with inappropriate estimated motion trajectory for noise. It only utilizes the intensity of pixels to suppress noise and accordingly is independent of noise variance. To evaluate the performance of the proposed filtering algorithm, its mean square error and percentage of preserved edge points were compared with those of traditional adaptive weighted averaging and non-adaptive mean filtering algorithms under different noise variances. Relevant results show that the MAWA filtering algorithm can preserve image structures and edges under motion after attenuating noise, and thus may be used in image sequence filtering.展开更多
Pedestrian trajectory prediction is pivotal and challenging in applications such as autonomous driving,social robotics,and intelligent surveillance systems.Pedestrian trajectory is governed not only by individual inte...Pedestrian trajectory prediction is pivotal and challenging in applications such as autonomous driving,social robotics,and intelligent surveillance systems.Pedestrian trajectory is governed not only by individual intent but also by interactions with surrounding agents.These interactions are critical to trajectory prediction accuracy.While prior studies have employed Convolutional Neural Networks(CNNs)and Graph Convolutional Networks(GCNs)to model such interactions,these methods fail to distinguish varying influence levels among neighboring pedestrians.To address this,we propose a novel model based on a bidirectional graph attention network and spatio-temporal graphs to capture dynamic interactions.Specifically,we construct temporal and spatial graphs encoding the sequential evolution and spatial proximity among pedestrians.These features are then fused and processed by the Bidirectional Graph Attention Network(Bi-GAT),which models the bidirectional interactions between the target pedestrian and its neighbors.The model computes node attention weights(i.e.,similarity scores)to differentially aggregate neighbor information,enabling fine-grained interaction representations.Extensive experiments conducted on two widely used pedestrian trajectory prediction benchmark datasets demonstrate that our approach outperforms existing state-of-theartmethods regarding Average Displacement Error(ADE)and Final Displacement Error(FDE),highlighting its strong prediction accuracy and generalization capability.展开更多
船舶轨迹预测是智能航运系统的核心技术之一。现有船舶轨迹预测方法较少考虑目标间运动的相互影响,导致预测准确率低且计算量大。为解决上述问题,提出一种基于组稀疏长短期记忆(Sparse Group Long short-term memory Network,SGLNet)模...船舶轨迹预测是智能航运系统的核心技术之一。现有船舶轨迹预测方法较少考虑目标间运动的相互影响,导致预测准确率低且计算量大。为解决上述问题,提出一种基于组稀疏长短期记忆(Sparse Group Long short-term memory Network,SGLNet)模型的船舶轨迹预测方法。利用编码层对输入的目标船舶运动轨迹数据进行编码,通过长短期记忆网络捕捉每个目标的运动特征;基于笛卡尔积构建水面目标周身网格空间,建立感知社交池化层,共享空间近端目标的隐藏状态;设计基于稀疏表示的掩码模型,对SGLNet网络参数量进行压缩。实验结果表明,相比其他序列预测网络模型,船舶轨迹预测精度提高了55.8%,模型参数量降低了12.77%。该方法满足了水面态势感知中对于船舶轨迹的需求,为构建智能航运系统提供了新的技术路径。展开更多
Stem cells(SCs)with their self-renewal and pluripotent differentiation potential,show great promise for therapeutic applications to some refractory diseases such as stroke,Parkinsonism,myocardial infarction,and diabet...Stem cells(SCs)with their self-renewal and pluripotent differentiation potential,show great promise for therapeutic applications to some refractory diseases such as stroke,Parkinsonism,myocardial infarction,and diabetes.Furthermore,as seed cells in tissue engineering,SCs have been applied widely to tissue and organ regeneration.However,previous studies have shown that SCs are heterogeneous and consist of many cell subpopulations.Owing to this heterogeneity of cell states,gene expression is highly diverse between cells even within a single tissue,making precise identification and analysis of biological properties difficult,which hinders their further research and applications.Therefore,a defined understanding of the heterogeneity is a key to research of SCs.Traditional ensemble-based sequencing approaches,such as microarrays,reflect an average of expression levels across a large population,which overlook unique biological behaviors of individual cells,conceal cell-to-cell variations,and cannot understand the heterogeneity of SCs radically.The development of high throughput single cell RNA sequencing(scRNA-seq)has provided a new research tool in biology,ranging from identification of novel cell types and exploration of cell markers to the analysis of gene expression and predicating developmental trajectories.scRNA-seq has profoundly changed our understanding of a series of biological phenomena.Currently,it has been used in research of SCs in many fields,particularly for the research of heterogeneity and cell subpopulations in early embryonic development.In this review,we focus on the scRNA-seq technique and its applications to research of SCs.展开更多
The advent of single-cell RNA sequencing(scRNA-seq)has provided insight into the tumour immune microenvironment(TIME).This review focuses on the application of scRNA-seq in investigation of the TIME.Over time,scRNA-se...The advent of single-cell RNA sequencing(scRNA-seq)has provided insight into the tumour immune microenvironment(TIME).This review focuses on the application of scRNA-seq in investigation of the TIME.Over time,scRNA-seq methods have evolved,and components of the TIME have been deciphered with high resolution.In this review,we first introduced the principle of scRNA-seq and compared different sequencing approaches.Novel cell types in the TIME,a continuous transitional state,and mutual intercommunication among TIME components present potential targets for prognosis prediction and treatment in cancer.Thus,we concluded novel cell clusters of cancerassociated fibroblasts(CAFs),T cells,tumour-associated macrophages(TAMs)and dendritic cells(DCs)discovered after the application of scRNA-seq in TIME.We also proposed the development of TAMs and exhausted T cells,as well as the possible targets to interrupt the process.In addition,the therapeutic interventions based on cellular interactions in TIME were also summarized.For decades,quantification of the TIME components has been adopted in clinical practice to predict patient survival and response to therapy and is expected to play an important role in the precise treatment of cancer.Summarizing the current findings,we believe that advances in technology and wide application of single-cell analysis can lead to the discovery of novel perspectives on cancer therapy,which can subsequently be implemented in the clinic.Finally,we propose some future directions in the field of TIME studies that can be aided by scRNA-seq technology.展开更多
This paper presents the methods and results for the trajectory design and optimization for the low earth orbit (LEO) satellites in formation to observe the geostationary orbit (GEO) satellites’ beams. The background ...This paper presents the methods and results for the trajectory design and optimization for the low earth orbit (LEO) satellites in formation to observe the geostationary orbit (GEO) satellites’ beams. The background of the trajectory design mission is the 9th China Trajectory Optimization Competition (CTOC9). The formation is designed according to the observation demands. The flying sequence is determined by a reference satellite using a proposed improved ephemeris matching method (IEMM). The formation is changed, maintained and transferred following the reference satellite employing a multi-impulse control method (MICM). Then the total observation value is computed by propagating the orbits of the satellites according to the sequence and transfer strategies. Based on the above methods, we have obtained a fourth prize in the CTOC9. The proposed methods are not only fit for this competition, but can also be used to fulfill the trajectory design missions for similar multi-object explorations.展开更多
为克服传统白鲸优化算法(Beluga Whale Optimization,BWO)在3-5-3多项式插值机械臂轨迹优化中存在的路径长、时间耗费高及易陷入局部最优的问题,本文提出了一种增强型白鲸-蝠鲼融合优化算法(Enhanced Beluga Whale and manta ray fusion...为克服传统白鲸优化算法(Beluga Whale Optimization,BWO)在3-5-3多项式插值机械臂轨迹优化中存在的路径长、时间耗费高及易陷入局部最优的问题,本文提出了一种增强型白鲸-蝠鲼融合优化算法(Enhanced Beluga Whale and manta ray fusion Optimization algorithm,EBWO).该算法以机械臂最优运动时间为目标,构建约束优化模型,并通过增广拉格朗日乘子法转化为无约束形式.首先,利用改进的对数非线性Halton混沌序列优化种群初始化,提高搜索多样性与质量;其次,设计多方向正余弦白鲸位置更新机制,增强开发阶段搜索能力;再次,在中期迭代阶段引入改进的蝠鲼旋风链式觅食策略,并结合Levy飞行机制构建新觅食因子,以强化局部开发与全局跳跃能力;最后,提出基于资源竞争耦合机制的自适应鲸落策略,并引入量子隧穿效应,以提升算法跳出局部最优的能力与收敛速度.实验结果表明:在3-5-3轨迹优化中,EBWO较于传统BWO将时间优化效果提升了8.69%,并且与未优化的轨迹相比,优化后的时间缩短了42.13%.这一结果验证了其在复杂优化任务时的有效性与实用性.展开更多
基金This work was supported by the National Natural Science Foundation of China(Grant No.42075007)the Open Project of Provincial Key Laboratory for Computer Information Processing Technology under Grant KJS1935Soochow University,and the Priority Academic Program Development of Jiangsu Higher Education Institutions。
文摘In the past few years,deep learning has developed rapidly,and many researchers try to combine their subjects with deep learning.The algorithm based on Recurrent Neural Network(RNN)has been successfully applied in the fields of weather forecasting,stock forecasting,action recognition,etc.because of its excellent performance in processing Spatio-temporal sequence data.Among them,algorithms based on LSTM and GRU have developed most rapidly because of their good design.This paper reviews the RNN-based Spatio-temporal sequence prediction algorithm,introduces the development history of RNN and the common application directions of the Spatio-temporal sequence prediction,and includes precipitation nowcasting algorithms and traffic flow forecasting algorithms.At the same time,it also compares the advantages and disadvantages,and innovations of each algorithm.The purpose of this article is to give readers a clear understanding of solutions to such problems.Finally,it prospects the future development of RNN in the Spatio-temporal sequence prediction algorithm.
基金supported by National Natural Science Foundation of China(Grant No.62073256)the Shaanxi Provincial Science and Technology Department(Grant No.2023-YBGY-342).
文摘To solve the problem of target damage assessment when fragments attack target under uncertain projectile and target intersection in an air defense intercept,this paper proposes a method for calculating target damage probability leveraging spatio-temporal finite multilayer fragments distribution and the target damage assessment algorithm based on cloud model theory.Drawing on the spatial dispersion characteristics of fragments of projectile proximity explosion,we divide into a finite number of fragments distribution planes based on the time series in space,set up a fragment layer dispersion model grounded in the time series and intersection criterion for determining the effective penetration of each layer of fragments into the target.Building on the precondition that the multilayer fragments of the time series effectively assail the target,we also establish the damage criterion of the perforation and penetration damage and deduce the damage probability calculation model.Taking the damage probability of the fragment layer in the spatio-temporal sequence to the target as the input state variable,we introduce cloud model theory to research the target damage assessment method.Combining the equivalent simulation experiment,the scientific and rational nature of the proposed method were validated through quantitative calculations and comparative analysis.
基金supported by National Natural Science of Foundation of China(No.10871026)
文摘Shallow earthquakes usually show obvious spatio-temporal clustering patterns. In this study, several spatio-temporal point process models are applied to investigate the clustering characteristics of the well-known Tangshan sequence based on classical empirical laws and a few assumptions. The relative fit of competing models is compared by Akalke Information Criterion. The spatial clustering pattern is well characterized by the model which gives the best fit to the data. A simulated aftershock sequence is generated by thinning algorithm and compared with the real seismicity.
基金the National Natural Science Foundation of China(Grant Nos.62102347,62376041,62172352)Guangdong Ocean University Research Fund Project(Grant No.060302102304).
文摘Point-of-interest(POI)recommendations in location-based social networks(LBSNs)have developed rapidly by incorporating feature information and deep learning methods.However,most studies have failed to accurately reflect different users’preferences,in particular,the short-term preferences of inactive users.To better learn user preferences,in this study,we propose a long-short-term-preference-based adaptive successive POI recommendation(LSTP-ASR)method by combining trajectory sequence processing,long short-term preference learning,and spatiotemporal context.First,the check-in trajectory sequences are adaptively divided into recent and historical sequences according to a dynamic time window.Subsequently,an adaptive filling strategy is used to expand the recent check-in sequences of users with inactive check-in behavior using those of similar active users.We further propose an adaptive learning model to accurately extract long short-term preferences of users to establish an efficient successive POI recommendation system.A spatiotemporal-context-based recurrent neural network and temporal-context-based long short-term memory network are used to model the users’recent and historical checkin trajectory sequences,respectively.Extensive experiments on the Foursquare and Gowalla datasets reveal that the proposed method outperforms several other baseline methods in terms of three evaluation metrics.More specifically,LSTP-ASR outperforms the previously best baseline method(RTPM)with a 17.15%and 20.62%average improvement on the Foursquare and Gowalla datasets in terms of the Fβmetric,respectively.
基金supported by National Key Research and Development Program of China(No.2017YFC1308800)Industry-University-Research Innovation Fund in Ministry of Education of the People’s Republic of China(No.2018A01013)。
文摘Objective:The goal of this study was to get preliminary insight on the intra-tumor heterogeneity in colitisassociated cancer(CAC)and to reveal a potential evolutionary trajectory from ulcerative colitis(UC)to CAC at the single-cell level.Methods:Fresh samples of tumor tissues and adjacent UC tissues from a CAC patient with pT3N1M0 stage cancer were examined by single-cell RNA sequencing(scRNA-seq).Data from The Cancer Genome Atlas(TCGA)and The Human Protein Atlas were used to confirm the different expression levels in normal and tumor tissues and to determine their relationships with patient prognosis.Results:Ultimately,4,777 single-cell transcriptomes(1,220 genes per cell)were examined,of which 2,250(47%)and 2,527(53%)originated from tumor and adjacent UC tissues,respectively.We defined the composition of cancer-associated stromal cells and identified six cell clusters,including myeloid,T and B cells,fibroblasts,endothelial and epithelial cells.Notable pathways and transcription factors involved in these cell clusters were analyzed and described.Moreover,the precise cellular composition and developmental trajectory from UC to UCassociated colon cancer were graphed,and it was predicted that CD74,CLCA1,and DPEP1 played a potential role in disease progression.Conclusions:scRNA-seq technology revealed intra-tumor cell heterogeneity in UC-associated colon cancer,and might provide a promising direction to identify novel potential therapeutic targets in the evolution from UC to CAC.
基金Projects(41601424,41171351)supported by the National Natural Science Foundation of ChinaProject(2012CB719906)supported by the National Basic Research Program of China(973 Program)+2 种基金Project(14JJ1007)supported by the Hunan Natural Science Fund for Distinguished Young Scholars,ChinaProject(2017M610486)supported by the China Postdoctoral Science FoundationProjects(2017YFB0503700,2017YFB0503601)supported by the National Key Research and Development Foundation of China
文摘Climate sequences can be applied to defining sensitive climate zones, and then the mining of spatio-temporal teleconnection patterns is useful for learning from the past and preparing for the future. However, scale-dependency in this kind of pattern is still not well handled by existing work. Therefore, in this study, the multi-scale regionalization is embedded into the spatio-temporal teleconnection pattern mining between anomalous sea and land climatic events. A modified scale-space clustering algorithm is first developed to group climate sequences into multi-scale climate zones. Then, scale variance analysis method is employed to identify climate zones at characteristic scales, indicating the main characteristics of geographical phenomena. Finally, by using the climate zones identified at characteristic scales, a time association rule mining algorithm based on sliding time windows is employed to discover spatio-temporal teleconnection patterns. Experiments on sea surface temperature, sea level pressure, land precipitation and land temperature datasets show that many patterns obtained by the multi-scale approach are coincident with prior knowledge, indicating that this method is effective and reasonable. In addition, some unknown teleconnection patterns discovered from the multi-scale approach can be further used to guide the prediction of land climate.
基金Supported by National Natural Science Foundation of China (No.30500129)
文摘In order to avoid the influence of noise variance on the filtering performances, a modified adaptive weighted averaging (MAWA) filtering algorithm is proposed for noisy image sequences. Based upon adaptive weighted averaging pixel values in consecutive frames, this algorithm achieves the filtering goal by assigning smaller weights to the pixels with inappropriate estimated motion trajectory for noise. It only utilizes the intensity of pixels to suppress noise and accordingly is independent of noise variance. To evaluate the performance of the proposed filtering algorithm, its mean square error and percentage of preserved edge points were compared with those of traditional adaptive weighted averaging and non-adaptive mean filtering algorithms under different noise variances. Relevant results show that the MAWA filtering algorithm can preserve image structures and edges under motion after attenuating noise, and thus may be used in image sequence filtering.
基金funded by the National Natural Science Foundation of China,grant number 624010funded by the Natural Science Foundation of Anhui Province,grant number 2408085QF202+1 种基金funded by the Anhui Future Technology Research Institute Industry Guidance Fund Project,grant number 2023cyyd04funded by the Project of Research of Anhui Polytechnic University,grant number Xjky2022150.
文摘Pedestrian trajectory prediction is pivotal and challenging in applications such as autonomous driving,social robotics,and intelligent surveillance systems.Pedestrian trajectory is governed not only by individual intent but also by interactions with surrounding agents.These interactions are critical to trajectory prediction accuracy.While prior studies have employed Convolutional Neural Networks(CNNs)and Graph Convolutional Networks(GCNs)to model such interactions,these methods fail to distinguish varying influence levels among neighboring pedestrians.To address this,we propose a novel model based on a bidirectional graph attention network and spatio-temporal graphs to capture dynamic interactions.Specifically,we construct temporal and spatial graphs encoding the sequential evolution and spatial proximity among pedestrians.These features are then fused and processed by the Bidirectional Graph Attention Network(Bi-GAT),which models the bidirectional interactions between the target pedestrian and its neighbors.The model computes node attention weights(i.e.,similarity scores)to differentially aggregate neighbor information,enabling fine-grained interaction representations.Extensive experiments conducted on two widely used pedestrian trajectory prediction benchmark datasets demonstrate that our approach outperforms existing state-of-theartmethods regarding Average Displacement Error(ADE)and Final Displacement Error(FDE),highlighting its strong prediction accuracy and generalization capability.
文摘船舶轨迹预测是智能航运系统的核心技术之一。现有船舶轨迹预测方法较少考虑目标间运动的相互影响,导致预测准确率低且计算量大。为解决上述问题,提出一种基于组稀疏长短期记忆(Sparse Group Long short-term memory Network,SGLNet)模型的船舶轨迹预测方法。利用编码层对输入的目标船舶运动轨迹数据进行编码,通过长短期记忆网络捕捉每个目标的运动特征;基于笛卡尔积构建水面目标周身网格空间,建立感知社交池化层,共享空间近端目标的隐藏状态;设计基于稀疏表示的掩码模型,对SGLNet网络参数量进行压缩。实验结果表明,相比其他序列预测网络模型,船舶轨迹预测精度提高了55.8%,模型参数量降低了12.77%。该方法满足了水面态势感知中对于船舶轨迹的需求,为构建智能航运系统提供了新的技术路径。
基金Supported by the National Natural Science Foundation of China,No.81670951
文摘Stem cells(SCs)with their self-renewal and pluripotent differentiation potential,show great promise for therapeutic applications to some refractory diseases such as stroke,Parkinsonism,myocardial infarction,and diabetes.Furthermore,as seed cells in tissue engineering,SCs have been applied widely to tissue and organ regeneration.However,previous studies have shown that SCs are heterogeneous and consist of many cell subpopulations.Owing to this heterogeneity of cell states,gene expression is highly diverse between cells even within a single tissue,making precise identification and analysis of biological properties difficult,which hinders their further research and applications.Therefore,a defined understanding of the heterogeneity is a key to research of SCs.Traditional ensemble-based sequencing approaches,such as microarrays,reflect an average of expression levels across a large population,which overlook unique biological behaviors of individual cells,conceal cell-to-cell variations,and cannot understand the heterogeneity of SCs radically.The development of high throughput single cell RNA sequencing(scRNA-seq)has provided a new research tool in biology,ranging from identification of novel cell types and exploration of cell markers to the analysis of gene expression and predicating developmental trajectories.scRNA-seq has profoundly changed our understanding of a series of biological phenomena.Currently,it has been used in research of SCs in many fields,particularly for the research of heterogeneity and cell subpopulations in early embryonic development.In this review,we focus on the scRNA-seq technique and its applications to research of SCs.
基金supported by the National Key Research Development Program of China(2021YFA1301203)the National Natural Science Foundation of China(82103031,82103918,81973408)+6 种基金the Clinical Research Incubation Project,West China Hospital,Sichuan University(22HXFH019)the China Postdoctoral Science Foundation(2019 M653416)the International Cooperation Project of Chengdu Municipal Science and Technology Bureau(2020-GH02-00017-HZ)the“1.3.5 Project for Disciplines of Excellence,West China Hospital,Sichuan University”(ZYJC18035,ZYJC18025,ZYYC20003,ZYJC18003)the GIST Research Institute(GRI)IIBR grants funded by the GISTthe National Research Foundation of Korea funded by the Korean government(MSIP)(2019R1C1C1005403,2019R1A4A1028802 and2021M3H9A2097520)the Post-Doctor Research Project,West China Hospital,Sichuan University(2021HXBH054)。
文摘The advent of single-cell RNA sequencing(scRNA-seq)has provided insight into the tumour immune microenvironment(TIME).This review focuses on the application of scRNA-seq in investigation of the TIME.Over time,scRNA-seq methods have evolved,and components of the TIME have been deciphered with high resolution.In this review,we first introduced the principle of scRNA-seq and compared different sequencing approaches.Novel cell types in the TIME,a continuous transitional state,and mutual intercommunication among TIME components present potential targets for prognosis prediction and treatment in cancer.Thus,we concluded novel cell clusters of cancerassociated fibroblasts(CAFs),T cells,tumour-associated macrophages(TAMs)and dendritic cells(DCs)discovered after the application of scRNA-seq in TIME.We also proposed the development of TAMs and exhausted T cells,as well as the possible targets to interrupt the process.In addition,the therapeutic interventions based on cellular interactions in TIME were also summarized.For decades,quantification of the TIME components has been adopted in clinical practice to predict patient survival and response to therapy and is expected to play an important role in the precise treatment of cancer.Summarizing the current findings,we believe that advances in technology and wide application of single-cell analysis can lead to the discovery of novel perspectives on cancer therapy,which can subsequently be implemented in the clinic.Finally,we propose some future directions in the field of TIME studies that can be aided by scRNA-seq technology.
文摘This paper presents the methods and results for the trajectory design and optimization for the low earth orbit (LEO) satellites in formation to observe the geostationary orbit (GEO) satellites’ beams. The background of the trajectory design mission is the 9th China Trajectory Optimization Competition (CTOC9). The formation is designed according to the observation demands. The flying sequence is determined by a reference satellite using a proposed improved ephemeris matching method (IEMM). The formation is changed, maintained and transferred following the reference satellite employing a multi-impulse control method (MICM). Then the total observation value is computed by propagating the orbits of the satellites according to the sequence and transfer strategies. Based on the above methods, we have obtained a fourth prize in the CTOC9. The proposed methods are not only fit for this competition, but can also be used to fulfill the trajectory design missions for similar multi-object explorations.
