Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decode...Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decoder (ACSF-ED) network to predict the action and locate the object efficiently. In the Adaptive Cross-Scale Fusion Spatio-Temporal Encoder (ACSF ST-Encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-temporal information modeling. Within the Shared-Head Decoder structure, a shared classification and regression detection head is constructed. A multi-constraint loss function composed of one-to-one, one-to-many, and contrastive denoising losses is designed to address the problem of insufficient constraint force in predicting results with traditional methods. This loss function enhances the accuracy of model classification predictions and improves the proximity of regression position predictions to ground truth objects. The proposed method model is evaluated on the popular dataset UCF101-24 and JHMDB-21. Experimental results demonstrate that the proposed method achieves an accuracy of 81.52% on the Frame-mAP metric, surpassing current existing methods.展开更多
As pivotal supporting technologies for smart manufacturing and digital engineering,model-based and data-driven methods have been widely applied in many industrial fields,such as product design,process monitoring,and s...As pivotal supporting technologies for smart manufacturing and digital engineering,model-based and data-driven methods have been widely applied in many industrial fields,such as product design,process monitoring,and smart maintenance.While promising,both methods have issues that need to be addressed.For example,model-based methods are limited by low computational accuracy and a high computational burden,and data-driven methods always suffer from poor interpretability and redundant features.To address these issues,the concept of data-model fusion(DMF)emerges as a promising solution.DMF involves integrating model-based methods with data-driven methods by incorporating big data into model-based methods or embedding relevant domain knowledge into data-driven methods.Despite growing efforts in the field of DMF,a unanimous definition of DMF remains elusive,and a general framework of DMF has been rarely discussed.This paper aims to address this gap by providing a thorough overview and categorization of both data-driven methods and model-based methods.Subsequently,this paper also presents the definition and categorization of DMF and discusses the general framework of DMF.Moreover,the primary seven applications of DMF are reviewed within the context of smart manufacturing and digital engineering.Finally,this paper directs the future directions of DMF.展开更多
Considering the difficulty of integrating the depth points of nautical charts of the East China Sea into a global high-precision Grid Digital Elevation Model(Grid-DEM),we proposed a“Fusion based on Image Recognition(...Considering the difficulty of integrating the depth points of nautical charts of the East China Sea into a global high-precision Grid Digital Elevation Model(Grid-DEM),we proposed a“Fusion based on Image Recognition(FIR)”method for multi-sourced depth data fusion,and used it to merge the electronic nautical chart dataset(referred to as Chart2014 in this paper)with the global digital elevation dataset(referred to as Globalbath2002 in this paper).Compared to the traditional fusion of two datasets by direct combination and interpolation,the new Grid-DEM formed by FIR can better represent the data characteristics of Chart2014,reduce the calculation difficulty,and be more intuitive,and,the choice of different interpolation methods in FIR and the influence of the“exclusion radius R”parameter were discussed.FIR avoids complex calculations of spatial distances among points from different sources,and instead uses spatial exclusion map to perform one-step screening based on the exclusion radius R,which greatly improved the fusion status of a reliable dataset.The fusion results of different experiments were analyzed statistically with root mean square error and mean relative error,showing that the interpolation methods based on Delaunay triangulation are more suitable for the fusion of nautical chart depth of China,and factors such as the point density distribution of multiple source data,accuracy,interpolation method,and various terrain conditions should be fully considered when selecting the exclusion radius R.展开更多
With the advancement of human-computer interaction,surface electromyography(sEMG)-based gesture recognition has garnered increasing attention.However,effectively utilizing the spatio-temporal dependencies in sEMG sign...With the advancement of human-computer interaction,surface electromyography(sEMG)-based gesture recognition has garnered increasing attention.However,effectively utilizing the spatio-temporal dependencies in sEMG signals and integrating multiple key features remain significant challenges for existing techniques.To address this issue,we propose a model named the Two-Stream Hybrid Spatio-Temporal Fusion Network(TS-HSTFNet).Specifically,we design a dynamic spatio-temporal graph convolution module that employs an adaptive dynamic adjacency matrix to explore the spatial dynamic patterns in the sEMG signals fully.Additionally,a spatio-temporal attention fusion module is designed to fully utilize the potential correlations among multiple features for the final fusion.The results indicate that the proposed TS-HSTFNet model achieves 84.96%and 88.08%accuracy on the Ninapro DB2 and Ninapro DB5 datasets,respectively,demonstrating high precision in gesture recognition.Our work emphasizes the importance of extracting spatio-temporal features in gesture recognition and provides a novel approach for multi-source information fusion.展开更多
Multi-source information fusion （MSIF） is imported into structural damage diagnosis methods to improve the validity of damage detection. After the introduction of the basic theory, the function model, classification...Multi-source information fusion （MSIF） is imported into structural damage diagnosis methods to improve the validity of damage detection. After the introduction of the basic theory, the function model, classifications and mathematical methods of MSIF, a structural damage detection method based on MSIF is presented, which is to fuse two or more damage character vectors from different structural damage diagnosis methods on the character-level. In an experiment of concrete plates, modal information is measured and analyzed. The structural damage detection method based on MSIF is taken to localize cracks of concrete plates and it is proved to be effective. Results of damage detection by the method based on MSIF are compared with those from the modal strain energy method and the flexibility method. Damage, which can hardly be detected by using the single damage identification method, can be diagnosed by the damage detection method based on the character-level MSIF technique. Meanwhile multi-location damage can be identified by the method based on MSIF. This method is sensitive to structural damage and different mathematical methods for MSIF have different preconditions and applicabilities for diversified structures. How to choose mathematical methods for MSIF should be discussed in detail in health monitoring systems of actual structures.展开更多
The problem of the unmanned surface vessel (USV) path planning in static and dynamic obstacle environments is addressed in this paper. Multi-behavior fusion based potential field method is proposed, which contains thr...The problem of the unmanned surface vessel (USV) path planning in static and dynamic obstacle environments is addressed in this paper. Multi-behavior fusion based potential field method is proposed, which contains three behaviors: goal-seeking, boundary-memory following and dynamic-obstacle avoidance. Then, different activation conditions are designed to determine the current behavior. Meanwhile, information on the positions, velocities and the equation of motion for obstacles are detected and calculated by sensor data. Besides, memory information is introduced into the boundary following behavior to enhance cognition capability for the obstacles, and avoid local minima problem caused by the potential field method. Finally, the results of theoretical analysis and simulation show that the collision-free path can be generated for USV within different obstacle environments, and further validated the performance and effectiveness of the presented strategy.展开更多
Satellite remote sensing of inland water body requires a high spatial resolution and a multiband narrow spectral resolution, which makes the fusion between panchromatic(PAN) and multi-spectral(MS) images particularly ...Satellite remote sensing of inland water body requires a high spatial resolution and a multiband narrow spectral resolution, which makes the fusion between panchromatic(PAN) and multi-spectral(MS) images particularly important. Taking the Daquekou section of the Qiantang River as an observation target, four conventional fusion methods widely accepted in satellite image processing, including pan sharpening(PS), principal component analysis(PCA), Gram-Schmidt(GS), and wavelet fusion(WF), are utilized to fuse MS and PAN images of GF-1.The results of subjective and objective evaluation methods application indicate that GS performs the best,followed by the PCA, the WF and the PS in the order of descending. The existence of a large area of the water body is a dominant factor impacting the fusion performance. Meanwhile, the ability of retaining spatial and spectral informations is an important factor affecting the fusion performance of different fusion methods. The fundamental difference of reflectivity information acquisition between water and land is the reason for the failure of conventional fusion methods for land observation such as the PS to be used in the presence of the large water body. It is suggested that the adoption of the conventional fusion methods in the observing water body as the main target should be taken with caution. The performances of the fusion methods need re-assessment when the large-scale water body is present in the remote sensing image or when the research aims for the water body observation.展开更多
Weighted fusion algorithms,which can be applied in the area of multi-sensor data fusion,are advanced based on weighted least square method.A weighted fusion algorithm,in which the relationship between weight coefficie...Weighted fusion algorithms,which can be applied in the area of multi-sensor data fusion,are advanced based on weighted least square method.A weighted fusion algorithm,in which the relationship between weight coefficients and measurement noise is established,is proposed by giving attention to the correlation of measurement noise.Then a simplified weighted fusion algorithm is deduced on the assumption that measurement noise is uncorrelated.In addition,an algorithm,which can adjust the weight coefficients in the simplified algorithm by making estimations of measurement noise from measurements,is presented.It is proved by emulation and experiment that the precision performance of the multi-sensor system based on these algorithms is better than that of the multi-sensor system based on other algorithms.展开更多
For quantitatively explaining the correlations between the vascular plant species abundance (VPSA) and habitat factors, a spatial simulation method has been developed to simulate the distribution of VPSA on the Qingha...For quantitatively explaining the correlations between the vascular plant species abundance (VPSA) and habitat factors, a spatial simulation method has been developed to simulate the distribution of VPSA on the Qinghai-Tibet Plateau. In this paper, the vascular plant type, land cover, mean annual biotemperature, average total annual precipitation, topographic relief, patch connectivity and ecological diversity index were selected to screen the best correlation equation between the VPSA and habitat factors on the basis of 37 national nature reserves on the Qinghai-Tibet Plateau. The research results show that the coefficient of determination between VPSA and habitat factors is 0.94, and the mean error is 2.21 types per km<sup>2</sup>. The distribution of VPSA gradually decreases from southeast to northwest, and reduces with increasing altitude except the desert area of Qaidam Basin. Furthermore, the scenarios of VPSA on the Qinghai-Tibet Plateau during the periods from 1981 to 2010 (T0), from 2011 to 2040 (T2), from 2041 to 2070 (T3) and from 2071 to 2100 (T4) were simulated by combining the land cover change and the climatic scenarios of CMIP5 RCP2.6, RCP4.5 and RCP8.5. The simulated results show that the VPSA would generally decrease on the Qinghai-Tibet Plateau from T0 to T4. The VPSA has the largest change ratio under RCP8.5 scenario, and the smallest change ratio under RCP2.6 scenario. In general, the dynamic change of habitat factors would directly affect the spatial distribution of VPSA on the Qinghai- Tibet Plateau in the future.展开更多
It is known that the exploitation of opencast coal mines has seriously damaged the environments in the semi-arid areas.Vegetation status can reliably reflect the ecological degeneration and restoration in the opencast...It is known that the exploitation of opencast coal mines has seriously damaged the environments in the semi-arid areas.Vegetation status can reliably reflect the ecological degeneration and restoration in the opencast mining areas in the semi-arid areas.Long-time series MODIS NDVI data are widely used to simulate the vegetation cover to reflect the disturbance and restoration of local ecosystems.In this study, both qualitative(linear regression method and coefficient of variation(CoV)) and quantitative(spatial buffer analysis, and change amplitude and the rate of change in the average NDVI) analyses were conducted to analyze the spatio-temporal dynamics of vegetation during 2000–2017 in Jungar Banner of Inner Mongolia Autonomous Region, China, at the large(Jungar Banner and three mine groups) and small(three types of functional areas: opencast coal mining excavation areas, reclamation areas and natural areas) scales.The results show that the rates of change in the average NDVI in the reclamation areas(20%–60%) and opencast coal mining excavation areas(10%–20%) were considerably higher than that in the natural areas(<7%).The vegetation in the reclamation areas experienced a trend of increase(3–5 a after reclamation)-decrease(the sixth year of reclamation)-stability.The vegetation in Jungar Banner has a spatial heterogeneity under the influences of mining and reclamation activities.The ratio of vegetation improvement area to vegetation degradation area in the west, southwest and east mine groups during 2000–2017 was 8:1, 20:1 and 33:1, respectively.The regions with the high CoV of NDVI above 0.45 were mainly distributed around the opencast coal mining excavation areas, and the regions with the CoV of NDVI above 0.25 were mostly located in areas with low(28.8%) and medium-low(10.2%) vegetation cover.The average disturbance distances of mining activities on vegetation in the three mine groups(west, southwest and east) were 800, 800 and 1000 m, respectively.The greater the scale of mining, the farther the disturbance distances of mining activities on vegetation.We conclude that vegetation reclamation will certainly compensate for the negative impacts of opencast coal mining activities on vegetation.Sufficient attention should be paid to the proportional allocation of plant species(herbs and shrubs) in the reclamation areas, and the restored vegetation in these areas needs to be protected for more than 6 a.Then, as the repair time increased, the vegetation condition of the reclamation areas would exceed that of the natural areas.展开更多
In the paper, the rational breather soliton and kink solitary wave solution of the (2+1)-dimensional PBLMP equation are obtained by adopting Hirota bilinear method and selecting different test functions. Furthermore, ...In the paper, the rational breather soliton and kink solitary wave solution of the (2+1)-dimensional PBLMP equation are obtained by adopting Hirota bilinear method and selecting different test functions. Furthermore, it has been found that the fusion and degeneration of the kink solitary wave occur when interaction between the rational breather soliton and the kink solitary wave happens. These phenomena are very helpful in researching soliton dynamical complexity in the higher dimensional systems.展开更多
The control rod drive mechanism(CRDM)is an essential part of the control and safety protection system of pressurized water reactors.Current CRDM simulations are mostly performed collectively using a single method,igno...The control rod drive mechanism(CRDM)is an essential part of the control and safety protection system of pressurized water reactors.Current CRDM simulations are mostly performed collectively using a single method,ignoring the influence of multiple motion units and the differences in various features among them,which strongly affect the efficiency and accuracy of the simulations.In this study,we constructed a flow field fusion simulation method based on model features by combining key motion unit analysis and various simulation methods and then applied the method to the CRDM simulation process.CRDM performs motion unit decomposition through the structural hierarchy of function-movement-action method,and the key meta-actions are identified as the nodes in the flow field simulation.We established a fused feature-based multimethod simulation process and processed the simulation methods and data according to the features of the fluid domain space and the structural complexity to obtain the fusion simulation results.Compared to traditional simulation methods and real measurements,the simulation method provides advantages in terms of simulation efficiency and accuracy.展开更多
False data injection attack(FDIA)can affect the state estimation of the power grid by tampering with the measured value of the power grid data,and then destroying the stable operation of the smart grid.Existing work u...False data injection attack(FDIA)can affect the state estimation of the power grid by tampering with the measured value of the power grid data,and then destroying the stable operation of the smart grid.Existing work usually trains a detection model by fusing the data-driven features from diverse power data streams.Data-driven features,however,cannot effectively capture the differences between noisy data and attack samples.As a result,slight noise disturbances in the power grid may cause a large number of false detections for FDIA attacks.To address this problem,this paper designs a deep collaborative self-attention network to achieve robust FDIA detection,in which the spatio-temporal features of cascaded FDIA attacks are fully integrated.Firstly,a high-order Chebyshev polynomials-based graph convolution module is designed to effectively aggregate the spatio information between grid nodes,and the spatial self-attention mechanism is involved to dynamically assign attention weights to each node,which guides the network to pay more attention to the node information that is conducive to FDIA detection.Furthermore,the bi-directional Long Short-Term Memory(LSTM)network is introduced to conduct time series modeling and long-term dependence analysis for power grid data and utilizes the temporal self-attention mechanism to describe the time correlation of data and assign different weights to different time steps.Our designed deep collaborative network can effectively mine subtle perturbations from spatiotemporal feature information,efficiently distinguish power grid noise from FDIA attacks,and adapt to diverse attack intensities.Extensive experiments demonstrate that our method can obtain an efficient detection performance over actual load data from New York Independent System Operator(NYISO)in IEEE 14,IEEE 39,and IEEE 118 bus systems,and outperforms state-of-the-art FDIA detection schemes in terms of detection accuracy and robustness.展开更多
In cabin-type component alignment, digital measurement technology is usually adopted to provide guidance for assembly. Depending on the system of measurement, the alignment process can be divided into measurement-assi...In cabin-type component alignment, digital measurement technology is usually adopted to provide guidance for assembly. Depending on the system of measurement, the alignment process can be divided into measurement-assisted assembly(MAA) and force-driven assembly. In MAA,relative pose between components is directly measured to guide assembly, while in force-driven assembly, only contact state can be recognized according to measured six-dimensional force and torque(6 D F/T) and the process is completed based on preset assembly strategy. Aiming to improve the efficiency of force-driven cabin-type component alignment, this paper proposed a heuristic alignment method based on multi-source data fusion. In this method, measured 6 D F/T, pose data and geometric information of components are fused to calculate the relative pose between components and guide the movement of pose adjustment platform. Among these data types, pose data and measured 6 D F/T are combined as data set. To collect the data sets needed for data fusion, dynamic gravity compensation method and hybrid motion control method are designed. Then the relative pose calculation method is elaborated, which transforms collected data sets into discrete geometric elements and calculates the relative poses based on the geometric information of components.Finally, experiments are conducted in simulation environment and the results show that the proposed alignment method is feasible and effective.展开更多
Considering that there is no single full reference image quality assessment method that could give the best performance in all situations, some multi-method fusion metrics were proposed. Machine learning techniques ar...Considering that there is no single full reference image quality assessment method that could give the best performance in all situations, some multi-method fusion metrics were proposed. Machine learning techniques are often involved in such multi-method fusion metrics so that its output would be more consistent with human visual perceptions. On the other hand, the robustness and generalization ability of these multi-method fusion metrics are questioned because of the scarce of images with mean opinion scores. In order to comprehensively validate whether or not the generalization ability of such multi-method fusion IQA metrics are satisfying, we construct a new image database which contains up to 60 reference images. The newly built image database is then used to test the generalization ability of different multi-method fusion IQA metrics. Cross database validation experiment indicates that in our new image database, the performances of all the multi-method fusion IQA metrics have no statistical significant different with some single-method IQA metrics such as FSIM and MAD. In the end, a thorough analysis is given to explain why the performance of multi-method fusion IQA framework drop significantly in cross database validation.展开更多
The current life-prediction models for lithium-ion batteries have several problems, such as the construction of complex feature structures, a high number of feature dimensions, and inaccurate prediction results. To ov...The current life-prediction models for lithium-ion batteries have several problems, such as the construction of complex feature structures, a high number of feature dimensions, and inaccurate prediction results. To overcome these problems, this paper proposes a deep-learning model combining an autoencoder network and a long short-term memory network. First, this model applies the characteristics of the autoencoder to reduce the dimensionality of the high-dimensional features extracted from the battery data set and realize the fusion of complex time-domain features, which overcomes the problems of redundant model information and low computational efficiency. This model then uses a long short-term memory network that is sensitive to time-series data to solve the long-path dependence problem in the prediction of battery life. Lastly, the attention mechanism is used to give greater weight to features that have a greater impact on the target value, which enhances the learning effect of the model on the long input sequence. To verify the efficacy of the proposed model, this paper uses NASA's lithium-ion battery cycle life data set.展开更多
In order to obtain more accurate precipitation data and better simulate the precipitation on the Tibetan Plateau,the simulation capability of 14 Coupled Model Intercomparison Project Phase 6(CMIP6)models of historical...In order to obtain more accurate precipitation data and better simulate the precipitation on the Tibetan Plateau,the simulation capability of 14 Coupled Model Intercomparison Project Phase 6(CMIP6)models of historical precipitation(1982-2014)on the Qinghai-Tibetan Plateau was evaluated in this study.Results indicate that all models exhibit an overestimation of precipitation through the analysis of the Taylor index,temporal and spatial statistical parameters.To correct the overestimation,a fusion correction method combining the Backpropagation Neural Network Correction(BP)and Quantum Mapping(QM)correction,named BQ method,was proposed.With this method,the historical precipitation of each model was corrected in space and time,respectively.The correction results were then analyzed in time,space,and analysis of variance(ANOVA)with those corrected by the BP and QM methods,respectively.Finally,the fusion correction method results for each model were compared with the Climatic Research Unit(CRU)data for significance analysis to obtain the trends of precipitation increase and decrease for each model.The results show that the IPSL-CM6A-LR model is relatively good in simulating historical precipitation on the Qinghai-Tibetan Plateau(R=0.7,RSME=0.15)among the uncorrected data.In terms of time,the total precipitation corrected by the fusion method has the same interannual trend and the closest precipitation values to the CRU data;In terms of space,the annual average precipitation corrected by the fusion method has the smallest difference with the CRU data,and the total historical annual average precipitation is not significantly different from the CRU data,which is better than BP and QM.Therefore,the correction effect of the fusion method on the historical precipitation of each model is better than that of the QM and BP methods.The precipitation in the central and northeastern parts of the plateau shows a significant increasing trend.The correlation coefficients between monthly precipitation and site-detected precipitation for all models after BQ correction exceed 0.8.展开更多
Fusion and fission are two important phenomena that have been experimentally observed in many real physical models.In this paper,we investigate the two phenomena in the(2+1)-dimensional Hirota-Satsuma-Ito equation via...Fusion and fission are two important phenomena that have been experimentally observed in many real physical models.In this paper,we investigate the two phenomena in the(2+1)-dimensional Hirota-Satsuma-Ito equation via the physics-informed neural networks(PINN)method.By choosing suitable physically constrained initial boundary conditions,the data-driven fusion and fission solutions are obtained for the first time.Dynamical behaviors and error analysis of these solutions are investigated via illustratively numerical figures,which show that good results are achieved.It is pointed out that the PINN method adopted here can be effectively used to construct the data-driven fusion and fission solutions for other nonlinear integrable equations.Based on the powerful predictive capability of the PINN method and wide applications of fusion and fission in many physical areas,it is hoped that the data-driven solutions obtained here will be helpful for experts to predict or explain related physical phenomena.展开更多
In order to improve the accuracy of building structure identification using remote sensing images,a building structure classification method based on multi-feature fusion of UAV remote sensing image is proposed in thi...In order to improve the accuracy of building structure identification using remote sensing images,a building structure classification method based on multi-feature fusion of UAV remote sensing image is proposed in this paper.Three identification approaches of remote sensing images are integrated in this method:object-oriented,texture feature,and digital elevation based on DSM and DEM.So RGB threshold classification method is used to classify the identification results.The accuracy of building structure classification based on each feature and the multi-feature fusion are compared and analyzed.The results show that the building structure classification method is feasible and can accurately identify the structures in large-area remote sensing images.展开更多
Refined 3D modeling of mine slopes is pivotal for precise prediction of geological hazards.Aiming at the inadequacy of existing single modeling methods in comprehensively representing the overall and localized charact...Refined 3D modeling of mine slopes is pivotal for precise prediction of geological hazards.Aiming at the inadequacy of existing single modeling methods in comprehensively representing the overall and localized characteristics of mining slopes,this study introduces a new method that fuses model data from Unmanned aerial vehicles(UAV)tilt photogrammetry and 3D laser scanning through a data alignment algorithm based on control points.First,the mini batch K-Medoids algorithm is utilized to cluster the point cloud data from ground 3D laser scanning.Then,the elbow rule is applied to determine the optimal cluster number(K0),and the feature points are extracted.Next,the nearest neighbor point algorithm is employed to match the feature points obtained from UAV tilt photogrammetry,and the internal point coordinates are adjusted through the distanceweighted average to construct a 3D model.Finally,by integrating an engineering case study,the K0 value is determined to be 8,with a matching accuracy between the two model datasets ranging from 0.0669 to 1.0373 mm.Therefore,compared with the modeling method utilizing K-medoids clustering algorithm,the new modeling method significantly enhances the computational efficiency,the accuracy of selecting the optimal number of feature points in 3D laser scanning,and the precision of the 3D model derived from UAV tilt photogrammetry.This method provides a research foundation for constructing mine slope model.展开更多
基金support for this work was supported by Key Lab of Intelligent and Green Flexographic Printing under Grant ZBKT202301.
文摘Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decoder (ACSF-ED) network to predict the action and locate the object efficiently. In the Adaptive Cross-Scale Fusion Spatio-Temporal Encoder (ACSF ST-Encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-temporal information modeling. Within the Shared-Head Decoder structure, a shared classification and regression detection head is constructed. A multi-constraint loss function composed of one-to-one, one-to-many, and contrastive denoising losses is designed to address the problem of insufficient constraint force in predicting results with traditional methods. This loss function enhances the accuracy of model classification predictions and improves the proximity of regression position predictions to ground truth objects. The proposed method model is evaluated on the popular dataset UCF101-24 and JHMDB-21. Experimental results demonstrate that the proposed method achieves an accuracy of 81.52% on the Frame-mAP metric, surpassing current existing methods.
基金supported in part by the National Natural Science Foundation of China(NSFC)under Grants(52275471 and 52120105008)the Beijing Outstanding Young Scientist Program,and the New Cornerstone Science Foundation through the XPLORER PRIZE.
文摘As pivotal supporting technologies for smart manufacturing and digital engineering,model-based and data-driven methods have been widely applied in many industrial fields,such as product design,process monitoring,and smart maintenance.While promising,both methods have issues that need to be addressed.For example,model-based methods are limited by low computational accuracy and a high computational burden,and data-driven methods always suffer from poor interpretability and redundant features.To address these issues,the concept of data-model fusion(DMF)emerges as a promising solution.DMF involves integrating model-based methods with data-driven methods by incorporating big data into model-based methods or embedding relevant domain knowledge into data-driven methods.Despite growing efforts in the field of DMF,a unanimous definition of DMF remains elusive,and a general framework of DMF has been rarely discussed.This paper aims to address this gap by providing a thorough overview and categorization of both data-driven methods and model-based methods.Subsequently,this paper also presents the definition and categorization of DMF and discusses the general framework of DMF.Moreover,the primary seven applications of DMF are reviewed within the context of smart manufacturing and digital engineering.Finally,this paper directs the future directions of DMF.
基金Supported by the National Key R&D Program of China (No.2023YFC3008100)the National Natural Science Foundation of China (No.U23A2033)
文摘Considering the difficulty of integrating the depth points of nautical charts of the East China Sea into a global high-precision Grid Digital Elevation Model(Grid-DEM),we proposed a“Fusion based on Image Recognition(FIR)”method for multi-sourced depth data fusion,and used it to merge the electronic nautical chart dataset(referred to as Chart2014 in this paper)with the global digital elevation dataset(referred to as Globalbath2002 in this paper).Compared to the traditional fusion of two datasets by direct combination and interpolation,the new Grid-DEM formed by FIR can better represent the data characteristics of Chart2014,reduce the calculation difficulty,and be more intuitive,and,the choice of different interpolation methods in FIR and the influence of the“exclusion radius R”parameter were discussed.FIR avoids complex calculations of spatial distances among points from different sources,and instead uses spatial exclusion map to perform one-step screening based on the exclusion radius R,which greatly improved the fusion status of a reliable dataset.The fusion results of different experiments were analyzed statistically with root mean square error and mean relative error,showing that the interpolation methods based on Delaunay triangulation are more suitable for the fusion of nautical chart depth of China,and factors such as the point density distribution of multiple source data,accuracy,interpolation method,and various terrain conditions should be fully considered when selecting the exclusion radius R.
基金Funding from the Key Research and development plan of Shaanxi Province"Human robot interaction technology and implementation of bionic robotic arm based on remote operation"(2023-ZDLGY-24).
文摘With the advancement of human-computer interaction,surface electromyography(sEMG)-based gesture recognition has garnered increasing attention.However,effectively utilizing the spatio-temporal dependencies in sEMG signals and integrating multiple key features remain significant challenges for existing techniques.To address this issue,we propose a model named the Two-Stream Hybrid Spatio-Temporal Fusion Network(TS-HSTFNet).Specifically,we design a dynamic spatio-temporal graph convolution module that employs an adaptive dynamic adjacency matrix to explore the spatial dynamic patterns in the sEMG signals fully.Additionally,a spatio-temporal attention fusion module is designed to fully utilize the potential correlations among multiple features for the final fusion.The results indicate that the proposed TS-HSTFNet model achieves 84.96%and 88.08%accuracy on the Ninapro DB2 and Ninapro DB5 datasets,respectively,demonstrating high precision in gesture recognition.Our work emphasizes the importance of extracting spatio-temporal features in gesture recognition and provides a novel approach for multi-source information fusion.
基金The National High Technology Research and Develop-ment Program of China(863Program)(No.2006AA04Z416)the Na-tional Science Fund for Distinguished Young Scholars(No.50725828)the Excellent Dissertation Program for Doctoral Degree of Southeast University(No.0705)
文摘Multi-source information fusion （MSIF） is imported into structural damage diagnosis methods to improve the validity of damage detection. After the introduction of the basic theory, the function model, classifications and mathematical methods of MSIF, a structural damage detection method based on MSIF is presented, which is to fuse two or more damage character vectors from different structural damage diagnosis methods on the character-level. In an experiment of concrete plates, modal information is measured and analyzed. The structural damage detection method based on MSIF is taken to localize cracks of concrete plates and it is proved to be effective. Results of damage detection by the method based on MSIF are compared with those from the modal strain energy method and the flexibility method. Damage, which can hardly be detected by using the single damage identification method, can be diagnosed by the damage detection method based on the character-level MSIF technique. Meanwhile multi-location damage can be identified by the method based on MSIF. This method is sensitive to structural damage and different mathematical methods for MSIF have different preconditions and applicabilities for diversified structures. How to choose mathematical methods for MSIF should be discussed in detail in health monitoring systems of actual structures.
基金financially supported by the National Natural Science Foundation of China(Grant No.51879049)DK-I Dynamic Positioning System Console Project
文摘The problem of the unmanned surface vessel (USV) path planning in static and dynamic obstacle environments is addressed in this paper. Multi-behavior fusion based potential field method is proposed, which contains three behaviors: goal-seeking, boundary-memory following and dynamic-obstacle avoidance. Then, different activation conditions are designed to determine the current behavior. Meanwhile, information on the positions, velocities and the equation of motion for obstacles are detected and calculated by sensor data. Besides, memory information is introduced into the boundary following behavior to enhance cognition capability for the obstacles, and avoid local minima problem caused by the potential field method. Finally, the results of theoretical analysis and simulation show that the collision-free path can be generated for USV within different obstacle environments, and further validated the performance and effectiveness of the presented strategy.
基金The National Key Research and Development Program of China under contract Nos 2016YFC1400901 and 2018YFC1406600the National Natural Science Foundation of China under contract No.40706057+1 种基金the Environmental Protection and Science and Technology Plan Project of Zhejiang Province of China under contract No.2013A021the Research Center for Air Pollution and Health of Zhejiang University
文摘Satellite remote sensing of inland water body requires a high spatial resolution and a multiband narrow spectral resolution, which makes the fusion between panchromatic(PAN) and multi-spectral(MS) images particularly important. Taking the Daquekou section of the Qiantang River as an observation target, four conventional fusion methods widely accepted in satellite image processing, including pan sharpening(PS), principal component analysis(PCA), Gram-Schmidt(GS), and wavelet fusion(WF), are utilized to fuse MS and PAN images of GF-1.The results of subjective and objective evaluation methods application indicate that GS performs the best,followed by the PCA, the WF and the PS in the order of descending. The existence of a large area of the water body is a dominant factor impacting the fusion performance. Meanwhile, the ability of retaining spatial and spectral informations is an important factor affecting the fusion performance of different fusion methods. The fundamental difference of reflectivity information acquisition between water and land is the reason for the failure of conventional fusion methods for land observation such as the PS to be used in the presence of the large water body. It is suggested that the adoption of the conventional fusion methods in the observing water body as the main target should be taken with caution. The performances of the fusion methods need re-assessment when the large-scale water body is present in the remote sensing image or when the research aims for the water body observation.
文摘Weighted fusion algorithms,which can be applied in the area of multi-sensor data fusion,are advanced based on weighted least square method.A weighted fusion algorithm,in which the relationship between weight coefficients and measurement noise is established,is proposed by giving attention to the correlation of measurement noise.Then a simplified weighted fusion algorithm is deduced on the assumption that measurement noise is uncorrelated.In addition,an algorithm,which can adjust the weight coefficients in the simplified algorithm by making estimations of measurement noise from measurements,is presented.It is proved by emulation and experiment that the precision performance of the multi-sensor system based on these algorithms is better than that of the multi-sensor system based on other algorithms.
基金National Key R&D Program of China,No.2017YFA0603702,No.2018YFC0507200National Natural Science Foundation of China,No.41271406,No.91325204Innovation Project of LREIS(O88RA600YA)
文摘For quantitatively explaining the correlations between the vascular plant species abundance (VPSA) and habitat factors, a spatial simulation method has been developed to simulate the distribution of VPSA on the Qinghai-Tibet Plateau. In this paper, the vascular plant type, land cover, mean annual biotemperature, average total annual precipitation, topographic relief, patch connectivity and ecological diversity index were selected to screen the best correlation equation between the VPSA and habitat factors on the basis of 37 national nature reserves on the Qinghai-Tibet Plateau. The research results show that the coefficient of determination between VPSA and habitat factors is 0.94, and the mean error is 2.21 types per km<sup>2</sup>. The distribution of VPSA gradually decreases from southeast to northwest, and reduces with increasing altitude except the desert area of Qaidam Basin. Furthermore, the scenarios of VPSA on the Qinghai-Tibet Plateau during the periods from 1981 to 2010 (T0), from 2011 to 2040 (T2), from 2041 to 2070 (T3) and from 2071 to 2100 (T4) were simulated by combining the land cover change and the climatic scenarios of CMIP5 RCP2.6, RCP4.5 and RCP8.5. The simulated results show that the VPSA would generally decrease on the Qinghai-Tibet Plateau from T0 to T4. The VPSA has the largest change ratio under RCP8.5 scenario, and the smallest change ratio under RCP2.6 scenario. In general, the dynamic change of habitat factors would directly affect the spatial distribution of VPSA on the Qinghai- Tibet Plateau in the future.
基金supported by the National Key Research and Development Program of China (2016YFC0501107)the Project of Ordos Science and Technology Program (2017006)the Special Project of Science and Technology Basic Work of Ministry of Science and Technology of China (2014FY110800)
文摘It is known that the exploitation of opencast coal mines has seriously damaged the environments in the semi-arid areas.Vegetation status can reliably reflect the ecological degeneration and restoration in the opencast mining areas in the semi-arid areas.Long-time series MODIS NDVI data are widely used to simulate the vegetation cover to reflect the disturbance and restoration of local ecosystems.In this study, both qualitative(linear regression method and coefficient of variation(CoV)) and quantitative(spatial buffer analysis, and change amplitude and the rate of change in the average NDVI) analyses were conducted to analyze the spatio-temporal dynamics of vegetation during 2000–2017 in Jungar Banner of Inner Mongolia Autonomous Region, China, at the large(Jungar Banner and three mine groups) and small(three types of functional areas: opencast coal mining excavation areas, reclamation areas and natural areas) scales.The results show that the rates of change in the average NDVI in the reclamation areas(20%–60%) and opencast coal mining excavation areas(10%–20%) were considerably higher than that in the natural areas(<7%).The vegetation in the reclamation areas experienced a trend of increase(3–5 a after reclamation)-decrease(the sixth year of reclamation)-stability.The vegetation in Jungar Banner has a spatial heterogeneity under the influences of mining and reclamation activities.The ratio of vegetation improvement area to vegetation degradation area in the west, southwest and east mine groups during 2000–2017 was 8:1, 20:1 and 33:1, respectively.The regions with the high CoV of NDVI above 0.45 were mainly distributed around the opencast coal mining excavation areas, and the regions with the CoV of NDVI above 0.25 were mostly located in areas with low(28.8%) and medium-low(10.2%) vegetation cover.The average disturbance distances of mining activities on vegetation in the three mine groups(west, southwest and east) were 800, 800 and 1000 m, respectively.The greater the scale of mining, the farther the disturbance distances of mining activities on vegetation.We conclude that vegetation reclamation will certainly compensate for the negative impacts of opencast coal mining activities on vegetation.Sufficient attention should be paid to the proportional allocation of plant species(herbs and shrubs) in the reclamation areas, and the restored vegetation in these areas needs to be protected for more than 6 a.Then, as the repair time increased, the vegetation condition of the reclamation areas would exceed that of the natural areas.
基金Supported by National Natural Science Foundation of China under Grant No.11361048
文摘In the paper, the rational breather soliton and kink solitary wave solution of the (2+1)-dimensional PBLMP equation are obtained by adopting Hirota bilinear method and selecting different test functions. Furthermore, it has been found that the fusion and degeneration of the kink solitary wave occur when interaction between the rational breather soliton and the kink solitary wave happens. These phenomena are very helpful in researching soliton dynamical complexity in the higher dimensional systems.
基金supported by the National Natural Science Foundation of China (No. 52075350)the Special City School Strategic Cooperation Project of Sichuan University and Zigong (No.2021CDZG-3)
文摘The control rod drive mechanism(CRDM)is an essential part of the control and safety protection system of pressurized water reactors.Current CRDM simulations are mostly performed collectively using a single method,ignoring the influence of multiple motion units and the differences in various features among them,which strongly affect the efficiency and accuracy of the simulations.In this study,we constructed a flow field fusion simulation method based on model features by combining key motion unit analysis and various simulation methods and then applied the method to the CRDM simulation process.CRDM performs motion unit decomposition through the structural hierarchy of function-movement-action method,and the key meta-actions are identified as the nodes in the flow field simulation.We established a fused feature-based multimethod simulation process and processed the simulation methods and data according to the features of the fluid domain space and the structural complexity to obtain the fusion simulation results.Compared to traditional simulation methods and real measurements,the simulation method provides advantages in terms of simulation efficiency and accuracy.
基金supported in part by the Research Fund of Guangxi Key Lab of Multi-Source Information Mining&Security(MIMS21-M-02).
文摘False data injection attack(FDIA)can affect the state estimation of the power grid by tampering with the measured value of the power grid data,and then destroying the stable operation of the smart grid.Existing work usually trains a detection model by fusing the data-driven features from diverse power data streams.Data-driven features,however,cannot effectively capture the differences between noisy data and attack samples.As a result,slight noise disturbances in the power grid may cause a large number of false detections for FDIA attacks.To address this problem,this paper designs a deep collaborative self-attention network to achieve robust FDIA detection,in which the spatio-temporal features of cascaded FDIA attacks are fully integrated.Firstly,a high-order Chebyshev polynomials-based graph convolution module is designed to effectively aggregate the spatio information between grid nodes,and the spatial self-attention mechanism is involved to dynamically assign attention weights to each node,which guides the network to pay more attention to the node information that is conducive to FDIA detection.Furthermore,the bi-directional Long Short-Term Memory(LSTM)network is introduced to conduct time series modeling and long-term dependence analysis for power grid data and utilizes the temporal self-attention mechanism to describe the time correlation of data and assign different weights to different time steps.Our designed deep collaborative network can effectively mine subtle perturbations from spatiotemporal feature information,efficiently distinguish power grid noise from FDIA attacks,and adapt to diverse attack intensities.Extensive experiments demonstrate that our method can obtain an efficient detection performance over actual load data from New York Independent System Operator(NYISO)in IEEE 14,IEEE 39,and IEEE 118 bus systems,and outperforms state-of-the-art FDIA detection schemes in terms of detection accuracy and robustness.
基金co-supported by the Special Research on Civil Aircraft of China (No.MJZ-2017-J-96)the Defense Industrial Technology Development Program of China (No.JCKY2016206B009)。
文摘In cabin-type component alignment, digital measurement technology is usually adopted to provide guidance for assembly. Depending on the system of measurement, the alignment process can be divided into measurement-assisted assembly(MAA) and force-driven assembly. In MAA,relative pose between components is directly measured to guide assembly, while in force-driven assembly, only contact state can be recognized according to measured six-dimensional force and torque(6 D F/T) and the process is completed based on preset assembly strategy. Aiming to improve the efficiency of force-driven cabin-type component alignment, this paper proposed a heuristic alignment method based on multi-source data fusion. In this method, measured 6 D F/T, pose data and geometric information of components are fused to calculate the relative pose between components and guide the movement of pose adjustment platform. Among these data types, pose data and measured 6 D F/T are combined as data set. To collect the data sets needed for data fusion, dynamic gravity compensation method and hybrid motion control method are designed. Then the relative pose calculation method is elaborated, which transforms collected data sets into discrete geometric elements and calculates the relative poses based on the geometric information of components.Finally, experiments are conducted in simulation environment and the results show that the proposed alignment method is feasible and effective.
基金supported by “the Fundamental Research Funds for the Central Universities” No.2018CUCTJ081
文摘Considering that there is no single full reference image quality assessment method that could give the best performance in all situations, some multi-method fusion metrics were proposed. Machine learning techniques are often involved in such multi-method fusion metrics so that its output would be more consistent with human visual perceptions. On the other hand, the robustness and generalization ability of these multi-method fusion metrics are questioned because of the scarce of images with mean opinion scores. In order to comprehensively validate whether or not the generalization ability of such multi-method fusion IQA metrics are satisfying, we construct a new image database which contains up to 60 reference images. The newly built image database is then used to test the generalization ability of different multi-method fusion IQA metrics. Cross database validation experiment indicates that in our new image database, the performances of all the multi-method fusion IQA metrics have no statistical significant different with some single-method IQA metrics such as FSIM and MAD. In the end, a thorough analysis is given to explain why the performance of multi-method fusion IQA framework drop significantly in cross database validation.
基金supported by the National Natural Science Foundation of China (No.61871350)the Zhejiang Science and Technology Plan Project (No.2019C011123)the Zhejiang Province Basic Public Welfare Research Project (No.LGG19F030011)。
文摘The current life-prediction models for lithium-ion batteries have several problems, such as the construction of complex feature structures, a high number of feature dimensions, and inaccurate prediction results. To overcome these problems, this paper proposes a deep-learning model combining an autoencoder network and a long short-term memory network. First, this model applies the characteristics of the autoencoder to reduce the dimensionality of the high-dimensional features extracted from the battery data set and realize the fusion of complex time-domain features, which overcomes the problems of redundant model information and low computational efficiency. This model then uses a long short-term memory network that is sensitive to time-series data to solve the long-path dependence problem in the prediction of battery life. Lastly, the attention mechanism is used to give greater weight to features that have a greater impact on the target value, which enhances the learning effect of the model on the long input sequence. To verify the efficacy of the proposed model, this paper uses NASA's lithium-ion battery cycle life data set.
文摘In order to obtain more accurate precipitation data and better simulate the precipitation on the Tibetan Plateau,the simulation capability of 14 Coupled Model Intercomparison Project Phase 6(CMIP6)models of historical precipitation(1982-2014)on the Qinghai-Tibetan Plateau was evaluated in this study.Results indicate that all models exhibit an overestimation of precipitation through the analysis of the Taylor index,temporal and spatial statistical parameters.To correct the overestimation,a fusion correction method combining the Backpropagation Neural Network Correction(BP)and Quantum Mapping(QM)correction,named BQ method,was proposed.With this method,the historical precipitation of each model was corrected in space and time,respectively.The correction results were then analyzed in time,space,and analysis of variance(ANOVA)with those corrected by the BP and QM methods,respectively.Finally,the fusion correction method results for each model were compared with the Climatic Research Unit(CRU)data for significance analysis to obtain the trends of precipitation increase and decrease for each model.The results show that the IPSL-CM6A-LR model is relatively good in simulating historical precipitation on the Qinghai-Tibetan Plateau(R=0.7,RSME=0.15)among the uncorrected data.In terms of time,the total precipitation corrected by the fusion method has the same interannual trend and the closest precipitation values to the CRU data;In terms of space,the annual average precipitation corrected by the fusion method has the smallest difference with the CRU data,and the total historical annual average precipitation is not significantly different from the CRU data,which is better than BP and QM.Therefore,the correction effect of the fusion method on the historical precipitation of each model is better than that of the QM and BP methods.The precipitation in the central and northeastern parts of the plateau shows a significant increasing trend.The correlation coefficients between monthly precipitation and site-detected precipitation for all models after BQ correction exceed 0.8.
基金supported by the National Natural Science Foundation of China under grant Nos.12371250 and 12205154Jiangsu Provincial Natural Science Foundation under grant Nos.BK20221508 and BK20210380Jiangsu Qinglan High-level Talent Project and High-level Personnel Project under grant No.JSSCBS20210277.
文摘Fusion and fission are two important phenomena that have been experimentally observed in many real physical models.In this paper,we investigate the two phenomena in the(2+1)-dimensional Hirota-Satsuma-Ito equation via the physics-informed neural networks(PINN)method.By choosing suitable physically constrained initial boundary conditions,the data-driven fusion and fission solutions are obtained for the first time.Dynamical behaviors and error analysis of these solutions are investigated via illustratively numerical figures,which show that good results are achieved.It is pointed out that the PINN method adopted here can be effectively used to construct the data-driven fusion and fission solutions for other nonlinear integrable equations.Based on the powerful predictive capability of the PINN method and wide applications of fusion and fission in many physical areas,it is hoped that the data-driven solutions obtained here will be helpful for experts to predict or explain related physical phenomena.
基金sponsored by National Key R&D Program of China(2018YFC1504504)Youth Foundation of Yunnan Earthquake Agency(2021K01)Project of Yunnan Earthquake Agency“Chuan bang dai”(CQ3-2021001).
文摘In order to improve the accuracy of building structure identification using remote sensing images,a building structure classification method based on multi-feature fusion of UAV remote sensing image is proposed in this paper.Three identification approaches of remote sensing images are integrated in this method:object-oriented,texture feature,and digital elevation based on DSM and DEM.So RGB threshold classification method is used to classify the identification results.The accuracy of building structure classification based on each feature and the multi-feature fusion are compared and analyzed.The results show that the building structure classification method is feasible and can accurately identify the structures in large-area remote sensing images.
基金funded by National Natural Science Foundation of China(Grant Nos.42272333,42277147).
文摘Refined 3D modeling of mine slopes is pivotal for precise prediction of geological hazards.Aiming at the inadequacy of existing single modeling methods in comprehensively representing the overall and localized characteristics of mining slopes,this study introduces a new method that fuses model data from Unmanned aerial vehicles(UAV)tilt photogrammetry and 3D laser scanning through a data alignment algorithm based on control points.First,the mini batch K-Medoids algorithm is utilized to cluster the point cloud data from ground 3D laser scanning.Then,the elbow rule is applied to determine the optimal cluster number(K0),and the feature points are extracted.Next,the nearest neighbor point algorithm is employed to match the feature points obtained from UAV tilt photogrammetry,and the internal point coordinates are adjusted through the distanceweighted average to construct a 3D model.Finally,by integrating an engineering case study,the K0 value is determined to be 8,with a matching accuracy between the two model datasets ranging from 0.0669 to 1.0373 mm.Therefore,compared with the modeling method utilizing K-medoids clustering algorithm,the new modeling method significantly enhances the computational efficiency,the accuracy of selecting the optimal number of feature points in 3D laser scanning,and the precision of the 3D model derived from UAV tilt photogrammetry.This method provides a research foundation for constructing mine slope model.
