Target maneuver recognition is a prerequisite for air combat situation awareness,trajectory prediction,threat assessment and maneuver decision.To get rid of the dependence of the current target maneuver recognition me...Target maneuver recognition is a prerequisite for air combat situation awareness,trajectory prediction,threat assessment and maneuver decision.To get rid of the dependence of the current target maneuver recognition method on empirical criteria and sample data,and automatically and adaptively complete the task of extracting the target maneuver pattern,in this paper,an air combat maneuver pattern extraction based on time series segmentation and clustering analysis is proposed by combining autoencoder,G-G clustering algorithm and the selective ensemble clustering analysis algorithm.Firstly,the autoencoder is used to extract key features of maneuvering trajectory to remove the impacts of redundant variables and reduce the data dimension;Then,taking the time information into account,the segmentation of Maneuver characteristic time series is realized with the improved FSTS-AEGG algorithm,and a large number of maneuver primitives are extracted;Finally,the maneuver primitives are grouped into some categories by using the selective ensemble multiple time series clustering algorithm,which can prove that each class represents a maneuver action.The maneuver pattern extraction method is applied to small scale air combat trajectory and can recognize and correctly partition at least 71.3%of maneuver actions,indicating that the method is effective and satisfies the requirements for engineering accuracy.In addition,this method can provide data support for various target maneuvering recognition methods proposed in the literature,greatly reduce the workload and improve the recognition accuracy.展开更多
In order to research the feasibility of using the selective adsorption principle to achieve automatic shaping of nano patterns,in this study,using the liquid gallium as the conductive ink and graphene as the printing ...In order to research the feasibility of using the selective adsorption principle to achieve automatic shaping of nano patterns,in this study,using the liquid gallium as the conductive ink and graphene as the printing plate surface,by changing the surface wettability of patterned areas on the nanoscale of graphene printed boards,the automatic formation of liquid gallium patterns on the graphene printed plate surface was simulated.The results indicated that liquid gallium can achieve automatic patterning on the surface of graphene patterned areas;the greater the interaction energy between gallium and carbon atoms,the clearer the pattern;gallium liquid is prone to remain in complex local positions of the pattern,making it difficult to shape the pattern;if the spacing between adjacent pattern lines is too large or too small,it will result in residual gallium liquid between the lines;increasing the thickness of the gallium film will cause the pattern to expand beyond the boundary,but increasing the thickness of the gallium film can also enhance the thickness and uniformity of the pattern lines.In summary,the principle of selective adsorption can be used to achieve the automatic formation of nano patterns,and the pattern formation effect is influenced by factors such as atomic interaction energy and pattern configuration.展开更多
The rapid identification of planting patterns for major crops in a large irrigated district has vital importance for irrigation management,water fee collection,and crop yield estimation.In this study,the OTSU algorith...The rapid identification of planting patterns for major crops in a large irrigated district has vital importance for irrigation management,water fee collection,and crop yield estimation.In this study,the OTSU algorithm and Mean-Shift algorithm were employed to automatically determine threshold values for mapping two main rotated crop patterns at the pixel scale.A time series analysis was conducted to extract the spatial distribution of rice-wheat and wheat-maize rotations in the Chuanhang irrigation district from 2016 to 2020.The results demonstrate that both threshold segmentation algorithms are reliable in extracting the spatial distribution of the crops,with an overall accuracy exceeding 80%.Additionally,both Kappa coefficients surpass 0.7,indicating better performance by OTSU method.Over the period from 2016 to 2020,the area occupied by rice-wheat rotation cropping ranged from 12500 to 14400 hm 2;whereas wheat-maize rotation cropping exhibited smaller and more variable areas ranging from 19730 to 34070 hm 2.These findings highlight how remote sensing-based approaches can provide reliable support for rapidly and accurately identifying the spatial distribution of main crop rotation patterns within a large irrigation district.展开更多
基金supported by the National Natural Science Foundation of China (Project No.72301293)。
文摘Target maneuver recognition is a prerequisite for air combat situation awareness,trajectory prediction,threat assessment and maneuver decision.To get rid of the dependence of the current target maneuver recognition method on empirical criteria and sample data,and automatically and adaptively complete the task of extracting the target maneuver pattern,in this paper,an air combat maneuver pattern extraction based on time series segmentation and clustering analysis is proposed by combining autoencoder,G-G clustering algorithm and the selective ensemble clustering analysis algorithm.Firstly,the autoencoder is used to extract key features of maneuvering trajectory to remove the impacts of redundant variables and reduce the data dimension;Then,taking the time information into account,the segmentation of Maneuver characteristic time series is realized with the improved FSTS-AEGG algorithm,and a large number of maneuver primitives are extracted;Finally,the maneuver primitives are grouped into some categories by using the selective ensemble multiple time series clustering algorithm,which can prove that each class represents a maneuver action.The maneuver pattern extraction method is applied to small scale air combat trajectory and can recognize and correctly partition at least 71.3%of maneuver actions,indicating that the method is effective and satisfies the requirements for engineering accuracy.In addition,this method can provide data support for various target maneuvering recognition methods proposed in the literature,greatly reduce the workload and improve the recognition accuracy.
文摘In order to research the feasibility of using the selective adsorption principle to achieve automatic shaping of nano patterns,in this study,using the liquid gallium as the conductive ink and graphene as the printing plate surface,by changing the surface wettability of patterned areas on the nanoscale of graphene printed boards,the automatic formation of liquid gallium patterns on the graphene printed plate surface was simulated.The results indicated that liquid gallium can achieve automatic patterning on the surface of graphene patterned areas;the greater the interaction energy between gallium and carbon atoms,the clearer the pattern;gallium liquid is prone to remain in complex local positions of the pattern,making it difficult to shape the pattern;if the spacing between adjacent pattern lines is too large or too small,it will result in residual gallium liquid between the lines;increasing the thickness of the gallium film will cause the pattern to expand beyond the boundary,but increasing the thickness of the gallium film can also enhance the thickness and uniformity of the pattern lines.In summary,the principle of selective adsorption can be used to achieve the automatic formation of nano patterns,and the pattern formation effect is influenced by factors such as atomic interaction energy and pattern configuration.
基金Jiangsu Water Science and Technology Project(2021081)。
文摘The rapid identification of planting patterns for major crops in a large irrigated district has vital importance for irrigation management,water fee collection,and crop yield estimation.In this study,the OTSU algorithm and Mean-Shift algorithm were employed to automatically determine threshold values for mapping two main rotated crop patterns at the pixel scale.A time series analysis was conducted to extract the spatial distribution of rice-wheat and wheat-maize rotations in the Chuanhang irrigation district from 2016 to 2020.The results demonstrate that both threshold segmentation algorithms are reliable in extracting the spatial distribution of the crops,with an overall accuracy exceeding 80%.Additionally,both Kappa coefficients surpass 0.7,indicating better performance by OTSU method.Over the period from 2016 to 2020,the area occupied by rice-wheat rotation cropping ranged from 12500 to 14400 hm 2;whereas wheat-maize rotation cropping exhibited smaller and more variable areas ranging from 19730 to 34070 hm 2.These findings highlight how remote sensing-based approaches can provide reliable support for rapidly and accurately identifying the spatial distribution of main crop rotation patterns within a large irrigation district.
