Video emotion recognition is widely used due to its alignment with the temporal characteristics of human emotional expression,but existingmodels have significant shortcomings.On the one hand,Transformermultihead self-...Video emotion recognition is widely used due to its alignment with the temporal characteristics of human emotional expression,but existingmodels have significant shortcomings.On the one hand,Transformermultihead self-attention modeling of global temporal dependency has problems of high computational overhead and feature similarity.On the other hand,fixed-size convolution kernels are often used,which have weak perception ability for emotional regions of different scales.Therefore,this paper proposes a video emotion recognition model that combines multi-scale region-aware convolution with temporal interactive sampling.In terms of space,multi-branch large-kernel stripe convolution is used to perceive emotional region features at different scales,and attention weights are generated for each scale feature.In terms of time,multi-layer odd-even down-sampling is performed on the time series,and oddeven sub-sequence interaction is performed to solve the problem of feature similarity,while reducing computational costs due to the linear relationship between sampling and convolution overhead.This paper was tested on CMU-MOSI,CMU-MOSEI,and Hume Reaction.The Acc-2 reached 83.4%,85.2%,and 81.2%,respectively.The experimental results show that the model can significantly improve the accuracy of emotion recognition.展开更多
Startups form an information network that reflects their growth trajectories through information flow channels established by shared investors.However,traditional static network metrics overlook temporal dynamics and ...Startups form an information network that reflects their growth trajectories through information flow channels established by shared investors.However,traditional static network metrics overlook temporal dynamics and rely on single indicators to assess startups’roles in predicting future success,failing to comprehensively capture topological variations and structural diversity.To address these limitations,we construct a temporal information network using 14547 investment records from 1013 global blockchain startups between 2004 and 2020,sourced from Crunchbase.We propose two dynamic methods to characterize the information flow:temporal random walk(sTRW)for modeling information flow trajectories and temporal betweenness centrality(tTBET)for identifying key information hubs.These methods enhance walk coverage while ensuring random stability,allowing for more effective identification of influential startups.By integrating sTRW and tTBET,we develop a comprehensive metric to evaluate a startup’s influence within the network.In experiments assessing startups’potential for future success—where successful startups are defined as those that have undergone M&A or IPO—incorporating this metric improves accuracy,recall,and F1 score by 0.035,0.035,and 0.042,respectively.Our findings indicate that information flow from key startups to others diminishes as the network distance increases.Additionally,successful startups generally exhibit higher information inflows than outflows,suggesting that actively seeking investment-related information contributes to startup growth.Our research provides valuable insights for formulating startup development strategies and offers practical guidance for market regulators.展开更多
Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases.Accurately predicting microbe-disease interactions(MDIs)offers critical insigh...Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases.Accurately predicting microbe-disease interactions(MDIs)offers critical insights for disease intervention and pharmaceutical research.Current advanced AI-based technologies automatically generate robust representations of microbes and diseases,enabling effective MDI predictions.However,these models continue to face significant challenges.A major issue is their reliance on complex feature extractors and classifiers,which substantially diminishes the models’generalizability.To address this,we introduce a novel graph autoencoder framework that utilizes decoupled representation learning and multi-scale information fusion strategies to efficiently infer potential MDIs.Initially,we randomly mask portions of the input microbe-disease graph based on Bernoulli distribution to boost self-supervised training and minimize noise-related performance degradation.Secondly,we employ decoupled representation learning technology,compelling the graph neural network(GNN)to independently learn the weights for each feature subspace,thus enhancing its expressive power.Finally,we implement multi-scale information fusion technology to amalgamate the multi-layer outputs of GNN,reducing information loss due to occlusion.Extensive experiments on public datasets demonstrate that our model significantly surpasses existing top MDI prediction models.This indicates that our model can accurately predict unknown MDIs and is likely to aid in disease discovery and precision pharmaceutical research.Code and data are accessible at:https://github.com/shmildsj/MDI-IFDRL.展开更多
Cadastral Information System (CIS) is designed for the office automation of cadastral management. With the development of the market economics in China, cadastral management is facing many new problems. The most cruci...Cadastral Information System (CIS) is designed for the office automation of cadastral management. With the development of the market economics in China, cadastral management is facing many new problems. The most crucial one is the temporal problem in cadastral management. That is, CIS must consider both spatial data and temporal data. This paper reviews the situation of the current CIS and provides a method to manage the spatiotemporal data of CIS, and takes the CIS for Guangdong Province as an example to explain how to realize it in practice.展开更多
With the popularity of 5G and the rapid development of mobile terminals,an endless stream of short video software exists.Browsing short-form mobile video in fragmented time has become the mainstream of user’s life.He...With the popularity of 5G and the rapid development of mobile terminals,an endless stream of short video software exists.Browsing short-form mobile video in fragmented time has become the mainstream of user’s life.Hence,designing an efficient short video recommendation method has become important for major network platforms to attract users and satisfy their requirements.Nevertheless,the explosive growth of data leads to the low efficiency of the algorithm,which fails to distill users’points of interest on one hand effectively.On the other hand,integrating user preferences and the content of items urgently intensify the requirements for platform recommendation.In this paper,we propose a collaborative filtering algorithm,integrating time context information and user context,which pours attention into expanding and discovering user interest.In the first place,we introduce the temporal context information into the typical collaborative filtering algorithm,and leverage the popularity penalty function to weight the similarity between recommended short videos and the historical short videos.There remains one more point.We also introduce the user situation into the traditional collaborative filtering recommendation algorithm,considering the context information of users in the generation recommendation stage,and weight the recommended short-formvideos of candidates.At last,a diverse approach is used to generate a Top-K recommendation list for users.And through a case study,we illustrate the accuracy and diversity of the proposed method.展开更多
The dynamic parameters of multiple projectiles that are fired using multi-barrel weapons in highfrequency continuous firing modes are important indicators to measure the performance of these weapons.The characteristic...The dynamic parameters of multiple projectiles that are fired using multi-barrel weapons in highfrequency continuous firing modes are important indicators to measure the performance of these weapons.The characteristics of multiple projectiles are high randomness and large numbers launched in a short period of time,making it very difficult to obtain the real dispersion parameters of the projectiles due to the occlusion or coincidence of multiple projectiles.Using six intersecting-screen testing system,in this paper,we propose an association recognition and matching algorithm of multiple projectiles using a temporal and spatial information constraint mechanism.We extract the output signal from each detection screen and then use the wavelet transform to process the output signal.We present a method to identify and extract the time values on which the projectiles pass through the detection screens using the wavelet transform modulus maximum theory.We then use the correlation of the output signals of three parallel detection screens to establish a correlation coefficient recognition constraint function for the multiple projectiles.Based on the premise of linear projectile motion,we establish a temporal and spatial constraint matching model using the projectile’s position coordinates in each detection screen and the projectile’s time constraints within the multiple intersecting-screen geometry.We then determine the time values of the multiple projectiles in each detection screen using an iterative search cycle registration,and finally obtain the flight parameters for the multiple projectiles in the presence of uncertainty.The proposed method and algorithm were verified experimentally and can solve the problem of uncertainty in projectiles flight parameter under different multiple projectile firing states.展开更多
Bus arrival time prediction contributes to the quality improvement of public transport services.Passengers can arrange departure time effectively if they know the accurate bus arrival time in advance.We proposed a mac...Bus arrival time prediction contributes to the quality improvement of public transport services.Passengers can arrange departure time effectively if they know the accurate bus arrival time in advance.We proposed a machine⁃learning approach,RTSI⁃ResNet,to forecast the bus arrival time at target stations.The residual neural network framework was employed to model the bus route temporal⁃spatial information.It was found that the bus travel time on a segment between two stations not only had correlation with the preceding buses,but also had common change trends with nearby downstream/upstream segments.Two features about bus travel time and headway were extracted from bus route including target section in both forward and reverse directions to constitute the route temporal⁃spatial information,which reflects the road traffic conditions comprehensively.Experiments on the bus trajectory data of route No.10 in Shenzhen public transport system demonstrated that the proposed RTSI⁃ResNet outperformed other well⁃known methods(e.g.,RNN/LSTM,SVM).Specifically,the advantage was more significant when the distance between bus and the target station was farther.展开更多
The shortest path is a widely studied network science problem and has attracted great attention.Nevertheless,it draws little attention in temporal networks,in which temporal edges determine information dissemination.I...The shortest path is a widely studied network science problem and has attracted great attention.Nevertheless,it draws little attention in temporal networks,in which temporal edges determine information dissemination.In this paper,we propose an information spreading-based method to calculate the shortest paths distribution in temporal networks.We verify our method on both artificial and real-world temporal networks and obtain a good agreement.We further generalize our method to identify influential nodes and found an effective method.Finally,we verify the influential nodes identifying method on four networks.展开更多
Temporal information processing in the range of tens to hundreds of milliseconds is critical in many forms of sensory and motor tasks. However, little has been known about the neural mechanisms of temporal information...Temporal information processing in the range of tens to hundreds of milliseconds is critical in many forms of sensory and motor tasks. However, little has been known about the neural mechanisms of temporal information processing. Experimental observations indicate that sensory neurons of the nervous system do not show selective response to temporal properties of external stimuli. On the other hand, temporal selective neurons in the cortex have been reported in many species. Thus, processes which realize the temporal-to-spatial transformation of neuronal activities might be required for temporal information processing. In the present study, we propose a computational model to explore possible roles of electrical synapses in processing the duration of external stimuli. Firstly, we construct a small-scale network with neurons interconnected by electrical synapses in addition to chemical synapses. Basic properties of this small-scale neural network in processing duration information are analyzed. Secondly, a large-scale neural network which is more biologically realistic is further explored. Our results suggest that neural networks with electrical synapses functioning together with chemical synapses can effectively work for the temporal-to-spatial transformation of neuronal activities, and the spatially distributed sequential neural activities can potentially represent temporal information.展开更多
On the basis of the digital Weifang geospatial framework,Smart Weifang spatio-temporal information cloud platform(WFCP)integrated legal person information,population,place name and address data,macroeconomic data and ...On the basis of the digital Weifang geospatial framework,Smart Weifang spatio-temporal information cloud platform(WFCP)integrated legal person information,population,place name and address data,macroeconomic data and so on.And it also expanded the data contents,such as the indoor and outdoor data,the overground and underground data,panoramic data and real data.It also introduced the contents of historical geographical information in different periods and real-time location information,address information of sensing equipment,real-time perception and interpreting information.It has overcome the difficulties of real-time access of Internet of Things(IoT)perception,multi-node collaboration,64-bit support,cluster deployment and has the characteristics of spatio-temporal management,ondemand service,large data analysis and micro-service architecture.It built spatio-temporal information big data center and spatio-temporal information cloud platform,realized the convergence and management of the distributed big data,deeply applied for land,transportation,environmental protection,police and subdistrict five areas,by supporting the integrated application of multi-source information and supporting intelligent deep application.In the aspect of hardware environment construction,according to the top-level design and unified arrangement of Smart Weifang,the WFCP was migrated to Weifang cloud computing center,to achieve the on-demand computing resources and dynamic scheduling load-based computing resources,to support the generalizing load map application.展开更多
Smart city is the development of digital city; as its main supporting technology, the digital city geo-spatial framework has to be upgraded to the temporal-spatial information infrastructure (TSII). first, this paper ...Smart city is the development of digital city; as its main supporting technology, the digital city geo-spatial framework has to be upgraded to the temporal-spatial information infrastructure (TSII). first, this paper proposes the concept and basic framework of smart city and defines the concept of TSII - processes, integration, mining analysis, and share time-stamps geographic data - and the related policy, regulations and standards, technology, facilities, mechanism, and human resources. The framework has four components: the benchmark of time and space, temporal-spatial big data, the cloud service platform and the related supporting environment. Second, the temporal-spatial big data and cloud service platform are elaborated. finally, an application of TSII constructed by the Xicheng District Planning Bureau in Beijing is introduced, which provides a useful reference for the construction of smart city.展开更多
In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accurac...In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.展开更多
The Yellow River Basin in Sichuan Province(YRS)is undergoing severe soil erosion and exacerbated ecological vulnerability,which collectively pose formidable challenges for regional water conservation(WC)and sustainabl...The Yellow River Basin in Sichuan Province(YRS)is undergoing severe soil erosion and exacerbated ecological vulnerability,which collectively pose formidable challenges for regional water conservation(WC)and sustainable development.While effectively enhancing WC necessitates a comprehensive understanding of its driving factors and corresponding intervention strategies,existing studies have largely neglected the spatiotemporal heterogeneity of both natural and socio-economic drivers.Therefore,this study explored the spatiotemporal heterogeneity of WC drivers in YRS using multi-scale geographically weighted regression(MGWR)and geographically and temporally weighted regression(GTWR)models from an eco-hydrological perspective.We discovered that downstream regions,which are more developed,achieved significantly better WC than upstream regions.The results also demonstrated that the influence of temperature and wind speed is consistently dominant and temporally stable due to climate stability,while the influence of vegetation shifted from negative to positive around 2010,likely indicating greater benefits from understory vegetation.Economic growth positively impacted WC in upstream regions but had a negative effect in the more developed downstream regions.These findings highlight the importance of targeted water conservation strategies,including locally appropriate revegetation,optimization of agricultural and economic structures,and the establishment of eco-compensation mechanisms for ecological conservation and sustainable development.展开更多
Detecting abnormal cervical cells is crucial for early identification and timely treatment of cervical cancer.However,this task is challenging due to the morphological similarities between abnormal and normal cells an...Detecting abnormal cervical cells is crucial for early identification and timely treatment of cervical cancer.However,this task is challenging due to the morphological similarities between abnormal and normal cells and the significant variations in cell size.Pathologists often refer to surrounding cells to identify abnormalities.To emulate this slide examination behavior,this study proposes a Multi-Scale Feature Fusion Network(MSFF-Net)for detecting cervical abnormal cells.MSFF-Net employs a Cross-Scale Pooling Model(CSPM)to effectively capture diverse features and contextual information,ranging from local details to the overall structure.Additionally,a Multi-Scale Fusion Attention(MSFA)module is introduced to mitigate the impact of cell size variations by adaptively fusing local and global information at different scales.To handle the complex environment of cervical cell images,such as cell adhesion and overlapping,the Inner-CIoU loss function is utilized to more precisely measure the overlap between bounding boxes,thereby improving detection accuracy in such scenarios.Experimental results on the Comparison detector dataset demonstrate that MSFF-Net achieves a mean average precision(mAP)of 63.2%,outperforming state-of-the-art methods while maintaining a relatively small number of parameters(26.8 M).This study highlights the effectiveness of multi-scale feature fusion in enhancing the detection of cervical abnormal cells,contributing to more accurate and efficient cervical cancer screening.展开更多
Recently,information acquired at the canopy top,such as spectral and textural data,has been widely used to estimate plant nitrogen(N)accumulation(PNA).The response of crops to N uptake involves not only changes in hor...Recently,information acquired at the canopy top,such as spectral and textural data,has been widely used to estimate plant nitrogen(N)accumulation(PNA).The response of crops to N uptake involves not only changes in horizontal canopy top information but also an increase in vertical plant height(PH).It remains unclear whether the fusion of spectral indices with PH can improve the estimation performance of PNA models based on spectral remote sensing across different growth stages.展开更多
Accurate valve nozzle detection is an important component of industrial visual inspection systems;however,structural complexity,scale variation,illumination fluctuation,and partial occlusion remain challenging factors...Accurate valve nozzle detection is an important component of industrial visual inspection systems;however,structural complexity,scale variation,illumination fluctuation,and partial occlusion remain challenging factors that affect detection stability.This study presents YOLOv12-Enhanced,a refined singlestage detection framework developed for industrial valve nozzle scenarios.The proposed approach incorporates three architectural modifications:a RepViT backbone to enhance hierarchical feature representation through structural re-parameterization and global–local modeling,a Spatial Pyramid Pooling Fast(SPPF)module combined with C2PSA attention to strengthen multi-scale contextual feature extraction,and a Global Edge Information Fusion(GEIF)module to integrate shallow edge information with deep semantic features for improved boundary alignment.Experimental evaluation on the Pascal Visual Object Classes(VOC)dataset shows that the proposed model achieves 71.0%mAP50 and 54.4%mAP50–95 under identical training conditions,exceeding the baseline YOLOv12n.Ablation experiments further demonstrate that each module contributes incremental performance gains.Evaluation on a self-constructed valve nozzle dataset consisting of 500 real industrial images indicates stable detection behavior under varying illumination and partial occlusion conditions.The experimental findings suggest that the proposed structural refinements provide a balanced enhancement in feature representation and localization precision while maintaining comparable computational complexity.展开更多
Temporal relation computation is one of the tasks of the extraction of temporal arguments from event, and it is also the ultimate goal of temporal information processing. However, temporal relation computation based o...Temporal relation computation is one of the tasks of the extraction of temporal arguments from event, and it is also the ultimate goal of temporal information processing. However, temporal relation computation based on machine learning requires a lot of hand-marked work, and exploring more features from discourse. A method of two-stage machine learning based on temporal relation computation （TSMLTRC） is proposed in this paper for the shortcomings of current temporal relation computation between two events. The first stage is to get the main temporal attributes of event based on classification learning. The second stage is to compute the event temporal relation in the discourse through employing the result of the first stage as the basic features, and also employing some new linguistic characteristics. Experiments show that, compared with the artificial golden rule, the computational efficiency in the first stage is much higher, and the F1-Score of event temporal relation which is computed through combining multi-features may be increased at 85.8% in the second stage.展开更多
Abnormal crowd behaviors in high density situations can pose great danger to public safety. Despite the extensive installation of closed-circuit television(CCTV) cameras, it is still difficult to achieve real-time ale...Abnormal crowd behaviors in high density situations can pose great danger to public safety. Despite the extensive installation of closed-circuit television(CCTV) cameras, it is still difficult to achieve real-time alerts and automated responses from current systems. Two major breakthroughs have been reported in this research. Firstly, a spatial-temporal texture extraction algorithm is developed. This algorithm is able to effectively extract video textures with abundant crowd motion details. It is through adopting Gaborfiltered textures with the highest information entropy values. Secondly, a novel scheme for defining crowd motion patterns(signatures)is devised to identify abnormal behaviors in the crowd by employing an enhanced gray level co-occurrence matrix model. In the experiments, various classic classifiers are utilized to benchmark the performance of the proposed method. The results obtained exhibit detection and accuracy rates which are, overall, superior to other techniques.展开更多
基金supported,in part,by the National Nature Science Foundation of China under Grant 62272236,62376128in part,by the Natural Science Foundation of Jiangsu Province under Grant BK20201136,BK20191401.
文摘Video emotion recognition is widely used due to its alignment with the temporal characteristics of human emotional expression,but existingmodels have significant shortcomings.On the one hand,Transformermultihead self-attention modeling of global temporal dependency has problems of high computational overhead and feature similarity.On the other hand,fixed-size convolution kernels are often used,which have weak perception ability for emotional regions of different scales.Therefore,this paper proposes a video emotion recognition model that combines multi-scale region-aware convolution with temporal interactive sampling.In terms of space,multi-branch large-kernel stripe convolution is used to perceive emotional region features at different scales,and attention weights are generated for each scale feature.In terms of time,multi-layer odd-even down-sampling is performed on the time series,and oddeven sub-sequence interaction is performed to solve the problem of feature similarity,while reducing computational costs due to the linear relationship between sampling and convolution overhead.This paper was tested on CMU-MOSI,CMU-MOSEI,and Hume Reaction.The Acc-2 reached 83.4%,85.2%,and 81.2%,respectively.The experimental results show that the model can significantly improve the accuracy of emotion recognition.
基金the funding from the National Natural Science Foundation of China(Grant Nos.42001236,71991481,and 71991480)Young Elite Scientist Sponsor-ship Program by Bast(Grant No.BYESS2023413)。
文摘Startups form an information network that reflects their growth trajectories through information flow channels established by shared investors.However,traditional static network metrics overlook temporal dynamics and rely on single indicators to assess startups’roles in predicting future success,failing to comprehensively capture topological variations and structural diversity.To address these limitations,we construct a temporal information network using 14547 investment records from 1013 global blockchain startups between 2004 and 2020,sourced from Crunchbase.We propose two dynamic methods to characterize the information flow:temporal random walk(sTRW)for modeling information flow trajectories and temporal betweenness centrality(tTBET)for identifying key information hubs.These methods enhance walk coverage while ensuring random stability,allowing for more effective identification of influential startups.By integrating sTRW and tTBET,we develop a comprehensive metric to evaluate a startup’s influence within the network.In experiments assessing startups’potential for future success—where successful startups are defined as those that have undergone M&A or IPO—incorporating this metric improves accuracy,recall,and F1 score by 0.035,0.035,and 0.042,respectively.Our findings indicate that information flow from key startups to others diminishes as the network distance increases.Additionally,successful startups generally exhibit higher information inflows than outflows,suggesting that actively seeking investment-related information contributes to startup growth.Our research provides valuable insights for formulating startup development strategies and offers practical guidance for market regulators.
基金supported by the Natural Science Foundation of Wenzhou University of Technology,China(Grant No.:ky202211).
文摘Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases.Accurately predicting microbe-disease interactions(MDIs)offers critical insights for disease intervention and pharmaceutical research.Current advanced AI-based technologies automatically generate robust representations of microbes and diseases,enabling effective MDI predictions.However,these models continue to face significant challenges.A major issue is their reliance on complex feature extractors and classifiers,which substantially diminishes the models’generalizability.To address this,we introduce a novel graph autoencoder framework that utilizes decoupled representation learning and multi-scale information fusion strategies to efficiently infer potential MDIs.Initially,we randomly mask portions of the input microbe-disease graph based on Bernoulli distribution to boost self-supervised training and minimize noise-related performance degradation.Secondly,we employ decoupled representation learning technology,compelling the graph neural network(GNN)to independently learn the weights for each feature subspace,thus enhancing its expressive power.Finally,we implement multi-scale information fusion technology to amalgamate the multi-layer outputs of GNN,reducing information loss due to occlusion.Extensive experiments on public datasets demonstrate that our model significantly surpasses existing top MDI prediction models.This indicates that our model can accurately predict unknown MDIs and is likely to aid in disease discovery and precision pharmaceutical research.Code and data are accessible at:https://github.com/shmildsj/MDI-IFDRL.
文摘Cadastral Information System (CIS) is designed for the office automation of cadastral management. With the development of the market economics in China, cadastral management is facing many new problems. The most crucial one is the temporal problem in cadastral management. That is, CIS must consider both spatial data and temporal data. This paper reviews the situation of the current CIS and provides a method to manage the spatiotemporal data of CIS, and takes the CIS for Guangdong Province as an example to explain how to realize it in practice.
文摘With the popularity of 5G and the rapid development of mobile terminals,an endless stream of short video software exists.Browsing short-form mobile video in fragmented time has become the mainstream of user’s life.Hence,designing an efficient short video recommendation method has become important for major network platforms to attract users and satisfy their requirements.Nevertheless,the explosive growth of data leads to the low efficiency of the algorithm,which fails to distill users’points of interest on one hand effectively.On the other hand,integrating user preferences and the content of items urgently intensify the requirements for platform recommendation.In this paper,we propose a collaborative filtering algorithm,integrating time context information and user context,which pours attention into expanding and discovering user interest.In the first place,we introduce the temporal context information into the typical collaborative filtering algorithm,and leverage the popularity penalty function to weight the similarity between recommended short videos and the historical short videos.There remains one more point.We also introduce the user situation into the traditional collaborative filtering recommendation algorithm,considering the context information of users in the generation recommendation stage,and weight the recommended short-formvideos of candidates.At last,a diverse approach is used to generate a Top-K recommendation list for users.And through a case study,we illustrate the accuracy and diversity of the proposed method.
基金been supported by Project of the National Natural Science Foundation of China(No.62073256)the Shaanxi Provincial Science and Technology Department(No.2020GY-125)Xi’an Science and Technology Innovation talent service enterprise project(No.2020KJRC0041)。
文摘The dynamic parameters of multiple projectiles that are fired using multi-barrel weapons in highfrequency continuous firing modes are important indicators to measure the performance of these weapons.The characteristics of multiple projectiles are high randomness and large numbers launched in a short period of time,making it very difficult to obtain the real dispersion parameters of the projectiles due to the occlusion or coincidence of multiple projectiles.Using six intersecting-screen testing system,in this paper,we propose an association recognition and matching algorithm of multiple projectiles using a temporal and spatial information constraint mechanism.We extract the output signal from each detection screen and then use the wavelet transform to process the output signal.We present a method to identify and extract the time values on which the projectiles pass through the detection screens using the wavelet transform modulus maximum theory.We then use the correlation of the output signals of three parallel detection screens to establish a correlation coefficient recognition constraint function for the multiple projectiles.Based on the premise of linear projectile motion,we establish a temporal and spatial constraint matching model using the projectile’s position coordinates in each detection screen and the projectile’s time constraints within the multiple intersecting-screen geometry.We then determine the time values of the multiple projectiles in each detection screen using an iterative search cycle registration,and finally obtain the flight parameters for the multiple projectiles in the presence of uncertainty.The proposed method and algorithm were verified experimentally and can solve the problem of uncertainty in projectiles flight parameter under different multiple projectile firing states.
基金Sponsored by the Transportation Science and Technology Planning Project of Henan Province,China(Grant No.2019G-2-2).
文摘Bus arrival time prediction contributes to the quality improvement of public transport services.Passengers can arrange departure time effectively if they know the accurate bus arrival time in advance.We proposed a machine⁃learning approach,RTSI⁃ResNet,to forecast the bus arrival time at target stations.The residual neural network framework was employed to model the bus route temporal⁃spatial information.It was found that the bus travel time on a segment between two stations not only had correlation with the preceding buses,but also had common change trends with nearby downstream/upstream segments.Two features about bus travel time and headway were extracted from bus route including target section in both forward and reverse directions to constitute the route temporal⁃spatial information,which reflects the road traffic conditions comprehensively.Experiments on the bus trajectory data of route No.10 in Shenzhen public transport system demonstrated that the proposed RTSI⁃ResNet outperformed other well⁃known methods(e.g.,RNN/LSTM,SVM).Specifically,the advantage was more significant when the distance between bus and the target station was farther.
基金Project supported by the National Natural Science Foundation of China(Grant No.61903266)China Postdoctoral Science Foundation(Grant No.2018M631073)+2 种基金China Postdoctoral Science Special Foundation(Grant No.2019T120829)the Fundamental Research Funds for the Central Universities,ChinaSichuan Science and Technology Program,China(Grant No.20YYJC4001)。
文摘The shortest path is a widely studied network science problem and has attracted great attention.Nevertheless,it draws little attention in temporal networks,in which temporal edges determine information dissemination.In this paper,we propose an information spreading-based method to calculate the shortest paths distribution in temporal networks.We verify our method on both artificial and real-world temporal networks and obtain a good agreement.We further generalize our method to identify influential nodes and found an effective method.Finally,we verify the influential nodes identifying method on four networks.
文摘Temporal information processing in the range of tens to hundreds of milliseconds is critical in many forms of sensory and motor tasks. However, little has been known about the neural mechanisms of temporal information processing. Experimental observations indicate that sensory neurons of the nervous system do not show selective response to temporal properties of external stimuli. On the other hand, temporal selective neurons in the cortex have been reported in many species. Thus, processes which realize the temporal-to-spatial transformation of neuronal activities might be required for temporal information processing. In the present study, we propose a computational model to explore possible roles of electrical synapses in processing the duration of external stimuli. Firstly, we construct a small-scale network with neurons interconnected by electrical synapses in addition to chemical synapses. Basic properties of this small-scale neural network in processing duration information are analyzed. Secondly, a large-scale neural network which is more biologically realistic is further explored. Our results suggest that neural networks with electrical synapses functioning together with chemical synapses can effectively work for the temporal-to-spatial transformation of neuronal activities, and the spatially distributed sequential neural activities can potentially represent temporal information.
文摘On the basis of the digital Weifang geospatial framework,Smart Weifang spatio-temporal information cloud platform(WFCP)integrated legal person information,population,place name and address data,macroeconomic data and so on.And it also expanded the data contents,such as the indoor and outdoor data,the overground and underground data,panoramic data and real data.It also introduced the contents of historical geographical information in different periods and real-time location information,address information of sensing equipment,real-time perception and interpreting information.It has overcome the difficulties of real-time access of Internet of Things(IoT)perception,multi-node collaboration,64-bit support,cluster deployment and has the characteristics of spatio-temporal management,ondemand service,large data analysis and micro-service architecture.It built spatio-temporal information big data center and spatio-temporal information cloud platform,realized the convergence and management of the distributed big data,deeply applied for land,transportation,environmental protection,police and subdistrict five areas,by supporting the integrated application of multi-source information and supporting intelligent deep application.In the aspect of hardware environment construction,according to the top-level design and unified arrangement of Smart Weifang,the WFCP was migrated to Weifang cloud computing center,to achieve the on-demand computing resources and dynamic scheduling load-based computing resources,to support the generalizing load map application.
文摘Smart city is the development of digital city; as its main supporting technology, the digital city geo-spatial framework has to be upgraded to the temporal-spatial information infrastructure (TSII). first, this paper proposes the concept and basic framework of smart city and defines the concept of TSII - processes, integration, mining analysis, and share time-stamps geographic data - and the related policy, regulations and standards, technology, facilities, mechanism, and human resources. The framework has four components: the benchmark of time and space, temporal-spatial big data, the cloud service platform and the related supporting environment. Second, the temporal-spatial big data and cloud service platform are elaborated. finally, an application of TSII constructed by the Xicheng District Planning Bureau in Beijing is introduced, which provides a useful reference for the construction of smart city.
基金supported by the National Natural Science Foundation of China(62272049,62236006,62172045)the Key Projects of Beijing Union University(ZKZD202301).
文摘In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.
基金supported by the funding provided by the State Key Laboratory of Hydraulics and Mountain River Engineering(SKHL2210)National Natural Science Foundation of China(42171304)+1 种基金the Sichuan Science and Technology Program(2023YFS0380)Natural Science Foundation of Jiangsu Province of China(BK20242018)。
文摘The Yellow River Basin in Sichuan Province(YRS)is undergoing severe soil erosion and exacerbated ecological vulnerability,which collectively pose formidable challenges for regional water conservation(WC)and sustainable development.While effectively enhancing WC necessitates a comprehensive understanding of its driving factors and corresponding intervention strategies,existing studies have largely neglected the spatiotemporal heterogeneity of both natural and socio-economic drivers.Therefore,this study explored the spatiotemporal heterogeneity of WC drivers in YRS using multi-scale geographically weighted regression(MGWR)and geographically and temporally weighted regression(GTWR)models from an eco-hydrological perspective.We discovered that downstream regions,which are more developed,achieved significantly better WC than upstream regions.The results also demonstrated that the influence of temperature and wind speed is consistently dominant and temporally stable due to climate stability,while the influence of vegetation shifted from negative to positive around 2010,likely indicating greater benefits from understory vegetation.Economic growth positively impacted WC in upstream regions but had a negative effect in the more developed downstream regions.These findings highlight the importance of targeted water conservation strategies,including locally appropriate revegetation,optimization of agricultural and economic structures,and the establishment of eco-compensation mechanisms for ecological conservation and sustainable development.
基金funded by the China Chongqing Municipal Science and Technology Bureau,grant numbers 2024TIAD-CYKJCXX0121,2024NSCQ-LZX0135Chongqing Municipal Commission of Housing and Urban-Rural Development,grant number CKZ2024-87+3 种基金the Chongqing University of Technology graduate education high-quality development project,grant number gzlsz202401the Chongqing University of Technology-Chongqing LINGLUE Technology Co.,Ltd.,Electronic Information(Artificial Intelligence)graduate joint training basethe Postgraduate Education and Teaching Reform Research Project in Chongqing,grant number yjg213116the Chongqing University of Technology-CISDI Chongqing Information Technology Co.,Ltd.,Computer Technology graduate joint training base.
文摘Detecting abnormal cervical cells is crucial for early identification and timely treatment of cervical cancer.However,this task is challenging due to the morphological similarities between abnormal and normal cells and the significant variations in cell size.Pathologists often refer to surrounding cells to identify abnormalities.To emulate this slide examination behavior,this study proposes a Multi-Scale Feature Fusion Network(MSFF-Net)for detecting cervical abnormal cells.MSFF-Net employs a Cross-Scale Pooling Model(CSPM)to effectively capture diverse features and contextual information,ranging from local details to the overall structure.Additionally,a Multi-Scale Fusion Attention(MSFA)module is introduced to mitigate the impact of cell size variations by adaptively fusing local and global information at different scales.To handle the complex environment of cervical cell images,such as cell adhesion and overlapping,the Inner-CIoU loss function is utilized to more precisely measure the overlap between bounding boxes,thereby improving detection accuracy in such scenarios.Experimental results on the Comparison detector dataset demonstrate that MSFF-Net achieves a mean average precision(mAP)of 63.2%,outperforming state-of-the-art methods while maintaining a relatively small number of parameters(26.8 M).This study highlights the effectiveness of multi-scale feature fusion in enhancing the detection of cervical abnormal cells,contributing to more accurate and efficient cervical cancer screening.
基金supported by the National Key Research and Development Plan Project Sub-Topic of China(Grant Nos.2022YFD1901500 and 2022YFD1901505-07)the National Natural Science Foundation of China(Grant No.32260531)+1 种基金the Key Laboratory of Molecular Breeding for Grain and Oil Crops in Guizhou Province,China(Grant No.Qiankehezhongyindi[2023]8)the Key Laboratory of Functional Agriculture of Guizhou Provincial Higher Education Institutions,China(Grant No.Qianjiaoji[2023]007).
文摘Recently,information acquired at the canopy top,such as spectral and textural data,has been widely used to estimate plant nitrogen(N)accumulation(PNA).The response of crops to N uptake involves not only changes in horizontal canopy top information but also an increase in vertical plant height(PH).It remains unclear whether the fusion of spectral indices with PH can improve the estimation performance of PNA models based on spectral remote sensing across different growth stages.
文摘Accurate valve nozzle detection is an important component of industrial visual inspection systems;however,structural complexity,scale variation,illumination fluctuation,and partial occlusion remain challenging factors that affect detection stability.This study presents YOLOv12-Enhanced,a refined singlestage detection framework developed for industrial valve nozzle scenarios.The proposed approach incorporates three architectural modifications:a RepViT backbone to enhance hierarchical feature representation through structural re-parameterization and global–local modeling,a Spatial Pyramid Pooling Fast(SPPF)module combined with C2PSA attention to strengthen multi-scale contextual feature extraction,and a Global Edge Information Fusion(GEIF)module to integrate shallow edge information with deep semantic features for improved boundary alignment.Experimental evaluation on the Pascal Visual Object Classes(VOC)dataset shows that the proposed model achieves 71.0%mAP50 and 54.4%mAP50–95 under identical training conditions,exceeding the baseline YOLOv12n.Ablation experiments further demonstrate that each module contributes incremental performance gains.Evaluation on a self-constructed valve nozzle dataset consisting of 500 real industrial images indicates stable detection behavior under varying illumination and partial occlusion conditions.The experimental findings suggest that the proposed structural refinements provide a balanced enhancement in feature representation and localization precision while maintaining comparable computational complexity.
基金Project supported the National Natural Science Foundation of China(Grant No.60975033)the Basic Scientific Research Project of International Centre for Bamboo Rattan(Grant No.1632009006)the Shanghai Leading Academic Discipline Project(Grant No.J50103)
文摘Temporal relation computation is one of the tasks of the extraction of temporal arguments from event, and it is also the ultimate goal of temporal information processing. However, temporal relation computation based on machine learning requires a lot of hand-marked work, and exploring more features from discourse. A method of two-stage machine learning based on temporal relation computation （TSMLTRC） is proposed in this paper for the shortcomings of current temporal relation computation between two events. The first stage is to get the main temporal attributes of event based on classification learning. The second stage is to compute the event temporal relation in the discourse through employing the result of the first stage as the basic features, and also employing some new linguistic characteristics. Experiments show that, compared with the artificial golden rule, the computational efficiency in the first stage is much higher, and the F1-Score of event temporal relation which is computed through combining multi-features may be increased at 85.8% in the second stage.
基金funded by Chinese National Natural Science Foundation (No. 61671377)Shaanxi Smart City Technology Project of Xianyang (No. 2017k01-25-5)
文摘Abnormal crowd behaviors in high density situations can pose great danger to public safety. Despite the extensive installation of closed-circuit television(CCTV) cameras, it is still difficult to achieve real-time alerts and automated responses from current systems. Two major breakthroughs have been reported in this research. Firstly, a spatial-temporal texture extraction algorithm is developed. This algorithm is able to effectively extract video textures with abundant crowd motion details. It is through adopting Gaborfiltered textures with the highest information entropy values. Secondly, a novel scheme for defining crowd motion patterns(signatures)is devised to identify abnormal behaviors in the crowd by employing an enhanced gray level co-occurrence matrix model. In the experiments, various classic classifiers are utilized to benchmark the performance of the proposed method. The results obtained exhibit detection and accuracy rates which are, overall, superior to other techniques.
