The rapid development and widespread adoption of Internet technology have significantly increased Internet traffic,highlighting the growing importance of network security.Intrusion Detection Systems(IDS)are essential ...The rapid development and widespread adoption of Internet technology have significantly increased Internet traffic,highlighting the growing importance of network security.Intrusion Detection Systems(IDS)are essential for safeguarding network integrity.To address the low accuracy of existing intrusion detection models in identifying network attacks,this paper proposes an intrusion detection method based on the fusion of Spatial Attention mechanism and Residual Neural Network(SA-ResNet).Utilizing residual connections can effectively capture local features in the data;by introducing a spatial attention mechanism,the global dependency relationships of intrusion features can be extracted,enhancing the intrusion recognition model’s focus on the global features of intrusions,and effectively improving the accuracy of intrusion recognition.The proposed model in this paper was experimentally verified on theNSL-KDD dataset.The experimental results showthat the intrusion recognition accuracy of the intrusion detection method based on SA-ResNet has reached 99.86%,and its overall accuracy is 0.41% higher than that of traditional Convolutional Neural Network(CNN)models.展开更多
Pulmonary nodules represent an early manifestation of lung cancer.However,pulmonary nodules only constitute a small portion of the overall image,posing challenges for physicians in image interpretation and potentially...Pulmonary nodules represent an early manifestation of lung cancer.However,pulmonary nodules only constitute a small portion of the overall image,posing challenges for physicians in image interpretation and potentially leading to false positives or missed detections.To solve these problems,the YOLOv8 network is enhanced by adding deformable convolution and atrous spatial pyramid pooling(ASPP),along with the integration of a coordinate attention(CA)mechanism.This allows the network to focus on small targets while expanding the receptive field without losing resolution.At the same time,context information on the target is gathered and feature expression is enhanced by attention modules in different directions.It effectively improves the positioning accuracy and achieves good results on the LUNA16 dataset.Compared with other detection algorithms,it improves the accuracy of pulmonary nodule detection to a certain extent.展开更多
In this paper,a new single-DOF(degree of freedom)spatial five-link RPRPS mechanism is proposed.The mechanism is designed to develop a new ground mechanism that can move in a consistent direction and change direction u...In this paper,a new single-DOF(degree of freedom)spatial five-link RPRPS mechanism is proposed.The mechanism is designed to develop a new ground mechanism that can move in a consistent direction and change direction using only one actuator.When the actuator rotates in one direction,the ground mobile mechanism can perform a“crawling”motion in a straight line.When the actuator rotates reversely in a special position,it can change the direction of“crawling”motion.Firstly,the concept of the RPRPS mechanism is described,explaining the connection relationships and grounding points between each link.The degree of freedom of the RPRPS mechanism obtained through mobility analysis is 1.Subsequently,the locomotion of the RPRPS mechanism in crawling and turning modes is analyzed separately.Describing the RPRPS mechanism’s movement path through a triangular mesh formed during landing,obtaining the RPRPS mechanism’s cycle step size and steering angle.The RPRPS mechanism’s movement path is described through a triangular mesh formed landing during,from which the mechanism’s cycle step size and steering angle are obtained.Feasibility analysis of turning motion through the positional relationship of COG point on different support surfaces of the RPRPS mechanism.A physical prototype of the RPRPS mechanism is developed,and experiments are conducted on both crawling and turning modes.The results are consistent with the theoretical analysis and verify the feasibility of the proposed mechanism.展开更多
Automated fiber placement(AFP)enables the efficient and precise fabrication of complex-shaped aerospace composite structures with lightweight and high-performance properties.However,due to the excessive compression on...Automated fiber placement(AFP)enables the efficient and precise fabrication of complex-shaped aerospace composite structures with lightweight and high-performance properties.However,due to the excessive compression on the inner edge of the tow placed along the curved trajectory,the resulting defects represented by buckling and wrinkles in spatial tow steering can induce poor manufacturing accuracy and quality degradation of products.In this paper,a theoretical model of tow buckling based on the first-order shear deformation laminate theory,linear elastic adhesion interface and Hertz compaction contact theory is proposed to analyze the formation mechanism of the wrinkles and predict the formation of defects by solving the critical radius of the trajectory,and finite element analysis involving the cohesive zone modeling(CZM)is innovated to simulate the local buckling state of the steered tow in AFP.Additionally,numerical parametric studies and experimental results indicate that mechanical properties and geometric parameters of the prepreg,the curvature of the placement trajectory and critical process parameters have a significant impact on buckling formation,and optimization of process parameters can achieve effective suppression of placement defects.This research proposes a theoretical modeling method for tow buckling,and conducts in-depth research on defect formation and suppression methods based on finite element simulation and placement experiments.展开更多
Multispectral pedestrian detection technology leverages infrared images to provide reliable information for visible light images, demonstrating significant advantages in low-light conditions and background occlusion s...Multispectral pedestrian detection technology leverages infrared images to provide reliable information for visible light images, demonstrating significant advantages in low-light conditions and background occlusion scenarios. However, while continuously improving cross-modal feature extraction and fusion, ensuring the model’s detection speed is also a challenging issue. We have devised a deep learning network model for cross-modal pedestrian detection based on Resnet50, aiming to focus on more reliable features and enhance the model’s detection efficiency. This model employs a spatial attention mechanism to reweight the input visible light and infrared image data, enhancing the model’s focus on different spatial positions and sharing the weighted feature data across different modalities, thereby reducing the interference of multi-modal features. Subsequently, lightweight modules with depthwise separable convolution are incorporated to reduce the model’s parameter count and computational load through channel-wise and point-wise convolutions. The network model algorithm proposed in this paper was experimentally validated on the publicly available KAIST dataset and compared with other existing methods. The experimental results demonstrate that our approach achieves favorable performance in various complex environments, affirming the effectiveness of the multispectral pedestrian detection technology proposed in this paper.展开更多
After illustrating the concept of Urban Growth Theory and Urban Growth Management,by taking relevant theoretical research literatures for reference,based on the specific conditions of Chongqing City,the paper had anal...After illustrating the concept of Urban Growth Theory and Urban Growth Management,by taking relevant theoretical research literatures for reference,based on the specific conditions of Chongqing City,the paper had analyzed the spatial growth and evolution of Chongqing City,and the spatial influence mechanism for urban growth management.The spatial influence mechanism of Chongqing urban growth had been divided into four aspects including natural environment,economic development,urban traffic organization and regional policy planning,which were considered as the primary mechanism,driving mechanism,essential condition and driving force of urban spatial growth and development,respectively.From the perspective of analyzing problems,the comprehensive analysis had been conducted on the urban growth management in economy and planning,and corresponding urban growth space management strategies had been formulated.From the perspective of combining theory with practice,it had studied and revealed the spatial influence mechanism for urban growth management,which was of practical guiding significance to the development of Chongqing urban space pattern,and also vital significance to the construction of theoretical system of Chinese urban management and guidance of further development and renovation of specific urban planning.展开更多
The representation of spatial variation of soil properties in the form of random fields permits advanced probabilistic assessment of slope stability.In many studies,the safety margin of the system is typically charact...The representation of spatial variation of soil properties in the form of random fields permits advanced probabilistic assessment of slope stability.In many studies,the safety margin of the system is typically characterized by the term“probability of failure(Pfailure)”.As the intensity and spatial distribution of soil properties vary in different random field realizations,the failure mechanism and deformation field of a slope can vary as well.Not only can the location of the failure surfaces vary,but the mode of failure also changes.Such information is equally valuable to engineering practitioners.In this paper,two slope examples that are modified from a real case study are presented.The first example pertains to the stability analysis of a multi-layer-slope while the second example deals with the serviceability analysis of a multi-layer c-φslope.In addition,due to the large number of simulations needed to reveal the full picture of the failure mechanism,Convolutional Neural Networks(CNNs)that adopt a U-Net architecture is proposed to offer a soft computing strategy to facilitate the investigation.The spatial distribution of the failure surfaces,the statistics of the sliding volume,and the statistics of the deformation field are presented.The results also show that the proposed deep-learning model is effective in predicting the failure mechanism and deformation field of slopes in spatially variable soils;therefore encouraging probabilistic study of slopes in practical scenarios.展开更多
Polygala tenuifolia,commonly known as Yuanzhi(YZ)in Chinese,has been shown to possess antiinsomnia properties.However,the material basis and the mechanism underlying its sedative-hypnotic effects remain unclear.Herein...Polygala tenuifolia,commonly known as Yuanzhi(YZ)in Chinese,has been shown to possess antiinsomnia properties.However,the material basis and the mechanism underlying its sedative-hypnotic effects remain unclear.Herein,we investigated the active components and neurochemical mechanism of YZ extracts using liquid chromatography tandem mass spectrometry(LC-MS/MS)-based pharmacometabolomics and mass spectrometry imaging(MSI)-based spatial resolved metabolomics.According to the results,17 prototypes out of 101 ingredients in the YZ extract were detected in both the plasma and brain,which might be the major components contributing to the sedative-hypnotic effects.Network pharmacology analysis revealed that these prototypes may exert their effects through neuroactive ligand-receptor interaction,serotonergic synapse,dopaminergic synapse,and dopaminergic synapse,among other pathways.LC-MS/MS-based targeted metabolomics and Western blot(WB)revealed that tryptophan-serotonin-melatonin(Trp-5-HT-Mel)and tyrosine-norepinephrine-adrenaline(Tyr-Ne-Ad)are the key regulated pathways.Dopa decarboxylase(DDC)upregulation and phenylethanolamine Nmethyltransferase(PNMT)downregulation further confirmed these pathways.Furthermore,MSI-based spatially resolved metabolomics revealed notable alterations in 5-HT in the pineal gland(PG),and Ad in the brainstem,including the middle brain(MB),pons(PN),and hypothalamus(HY).In summary,this study illustrates the efficacy of an integrated multidimensional metabolomics approach in unraveling the sedative-hypnotic effects and neurochemical mechanisms of a Chinese herbal medicine,YZ.展开更多
In this paper, a four-dimensional coordinated path planning algorithm for multiple UAVs is proposed, in which time variable is taken into account for each UAV as well as collision free and obstacle avoidance. A Spatia...In this paper, a four-dimensional coordinated path planning algorithm for multiple UAVs is proposed, in which time variable is taken into account for each UAV as well as collision free and obstacle avoidance. A Spatial Refined Voting Mechanism(SRVM) is designed for standard Particle Swarm Optimization(PSO) to overcome the defects of local optimal and slow convergence.For each generation candidate particle positions are recorded and an adaptive cube is formed with own adaptive side length to indicate occupied regions. Then space voting begins and is sorted based on voting results, whose centers with bigger voting counts are seen as sub-optimal positions. The average of all particles of corresponding dimensions are calculated as the refined solutions. A time coordination method is developed by generating specified candidate paths for every UAV, making them arrive the same destination with the same time consumption. A spatial-temporal collision avoidance technique is introduced to make collision free. Distance to destination is constructed to improve the searching accuracy and velocity of particles. In addition, the objective function is redesigned by considering the obstacle and threat avoidance, Estimated Time of Arrival(ETA), separation maintenance and UAV self-constraints. Experimental results prove the effectiveness and efficiency of the algorithm.展开更多
Chinese railway has entered the ＂HSR era＂, while the structure of ＂four vertical and four horizontal＂ railways for transit passengers is almost completed. Taking the Beijing-Shanghai High-Speed Rail （hereinafter ...Chinese railway has entered the ＂HSR era＂, while the structure of ＂four vertical and four horizontal＂ railways for transit passengers is almost completed. Taking the Beijing-Shanghai High-Speed Rail （hereinafter referred to as HSR） as an example, this paper first explores HSR＇s effects on the spatial structure of regional tourist flows using the social network analysis. Next, it notes changes in the accessibility of regional transportation. After analyzing the factors including initial endowment of regional tourism resources, hospitality facilities, the density of the regional tourism transportation network, and locations, the paper discusses the mechanisms through which HSR affects regional tourist flows. The study shows the following： （1） HSR＇s effects on the spatial structure of regional tourist flows are manifested through the Matthew effect, the filtering effect, the diffusion effect and the overlying effect, and （2） the Matthew effect of HSR is manifested under an obvious interaction of the location, the initial endowment of tourism resources, hospitality capacity, tourist transportation network density and ＂time-space compression＂. The filtering effect of HSR is manifested for those tourism nodes without favorable location conditions, endowment of tourism resources, hospitality capacity, or tourist transportation network density and without obvious benefits from ＂time-space compression＂. Those tourism nodes that boast advantages in terms of lo- cation condition, endowment of tourism resources, hospitality capacity, tourist transportation network density and obvious ＂time-space compression＂ will become sources for the diffusion effect. HSR will strengthen the aggregation effects of tourist flow in these diffusion sources, which will thereafter diffuse to peripheral tourist areas, manifesting ＂aggregation-diffusion＂. HSR has overlapped tourists＇ spatial traveling range over large-scale spaces. However, the overlying effect is only generated in those tourism nodes with a favorable location condition, an endowment of tourism resources, hospitality capacity, tourist transportation network den- sity, and obvious ＂time-space compression＂.展开更多
The pre-research on mobility analysis presented a unified-mobility formula and a methodology based on reciprocal screw theory by HUANG, which focused on classical and modem parallel mechanisms. However its range of ap...The pre-research on mobility analysis presented a unified-mobility formula and a methodology based on reciprocal screw theory by HUANG, which focused on classical and modem parallel mechanisms. However its range of application needs to further extend to general multi-loop spatial mechanism. This kind of mechanism is not only more complex in structure but also with strong motion coupling among loops, making the mobility analysis even more complicated, and the relevant research has long been ignored. It is focused on how to apply the new principle for general spatial mechanism to those various multi-loop spatial mechanisms, and some new meaningful knowledge is further found. Several typical examples of the genera/multi-loop spatial mechanisms with motion couple even strong motion couple are considered. These spatial mechanisms include different closing way： over-constraint appearing in rigid closure, in movable closure, and in dynamic closure as well; these examples also include two different new methods to solve this kind of issue： the way to recognize over-constraints by analyzing relative movement between two connected links and by constructing a virtual loop to recognize over-constraints. In addition, over-constraint determination tabulation is brought to analyze the motion couple. The researches above are all based upon the screw theory. All these multi-loop spatial mechanisms with different kinds of structures can completely be solved by following the directions and examples, and the new mobility theory based on the screw theory is also proved to be valid. This study not only enriches and develops the theory and makes the theory more universal, but also has a special meaning for innovation in mechanical engineering.展开更多
Water-induced landslides in hydropower reservoirs pose a great threat to both project operation and human life.This paper examines three large reservoirs in Sichuan Province,China.Field surveys,site monitoring data an...Water-induced landslides in hydropower reservoirs pose a great threat to both project operation and human life.This paper examines three large reservoirs in Sichuan Province,China.Field surveys,site monitoring data analyses and numerical simulations are used to analyze the spatial distribution and failure mechanisms of water-induced landslides in reservoir areas.First,the general rules of landslide development in the reservoir area are summarized.The first rule is that most of the landslides have rear edge elevations of 100e500 m above the normal water level of the reservoir,with volumes in the range of 106 e107 m 3.When the volume exceeds a certain amount,the number of sites at which the landscape can withstand landslides is greatly reduced.Landslide hazards mainly occur in the middle section of the reservoir and less in the annex of the dam site and the latter half of the reservoir area.The second rule is that sedimentary rocks such as sandstone are more prone to landslide hazards than other lithologies.Then,the failure mechanism of changes in the water level that reduces the stability of the slope composed of different geomaterials is analyzed by a proposed slope stability framework that considers displacement and is discussed with the monitoring results.Permeability is an essential parameter for understanding the diametrically opposed deformation behavior of landslides experiencing filling-drawdown cycles during operation.This study seeks to provide inspiration to subsequent researchers,as well as guidance to technicians,on landslide prevention and control in reservoir areas.展开更多
Spatial equality of access to basic public services, especially medical care services which are directly related to life safety, is the first step to achieve the goal of equalization of basic public services for all t...Spatial equality of access to basic public services, especially medical care services which are directly related to life safety, is the first step to achieve the goal of equalization of basic public services for all the people proposed by central government of China. Using the spatial analysis and the statistical analysis, this study evaluates the spatial differentiation of medical care facilities accessibility by constructing STT(Shortest Travel-Time) and SAI(Spatial Accessibility Index). And then this study explores the neighborhood effects on the medical care facilities accessibility in Beijing, with a particular focus on the effect of neighborhood migrant proportion by constructing spatial dependent regression model. The spatial accessibility analysis of medical care facilities show that the spatial distribution of medical care facilities was basically consistent with administrative regions but not with population demands. Bivariate LISA cluster maps identify that suburban areas are the overlapped clusters of high percent of migrants and limited medical care services. This is associated with the public service allocation rule in China, which stresses equality within urban areas and within rural areas but overlooks equality between urban areas and rural areas; and stresses local resident demands but overlooks migrant demands. To estimate the effects on medical care accessibility of neighborhood migrant proportion, spatial dependence models are applied due to spatial dependence of accessibility of medical care facilities. The regression results show that neighborhoods with high percent of migrants, even conditioning on neighborhood SES, are related to limited spatial accessibility of medical care services. Besides neighborhood characteristics, another important factor influencing spatial accessibility of medical care services is the process of spatial spillover effects. This indicates that the attenuate accessibility of medical care services for migrants is not only because of their own constraints but also because of their proximity to other disadvantaged neighborhoods. Therefore, it is urgently needed to increase the medical facilities in the suburban areas, to take into account migrants' demands and to reduce residential segregation between local residents and migrants for local governments to achieve the goal of equalization of medical care service.展开更多
Scientific collaboration has become an important part of the people-to-people exchanges in the Belt and Road initiative,and remarkable progress has been made since 2013.Taking the 65 countries along the Belt and Road(...Scientific collaboration has become an important part of the people-to-people exchanges in the Belt and Road initiative,and remarkable progress has been made since 2013.Taking the 65 countries along the Belt and Road(BRI countries)as the research areas and using collaborated Web of Science(WOS)core collection papers to construct an international scientific collaboration matrix,the paper explores the spatial structure,hierarchy and formation mechanisms of scientific collaboration networks of 65 countries along the Belt and Road.The results show that:1)Beyond the Belt and Road regions(BRI regions),Central&Eastern Europe,China and West Asia&North Africa have formed a situation in which they all have the most external links with other countries beyond BRI regions.China has the dominant role over other BRI countries in generating scientific links.The overall spatial structure has changed to a skeleton structure consisting of many dense regions,such as Europe,North America,East Asia and Oceania.2)Within the Belt and Road regions,Central&Eastern Europe has become the largest collaboration partner with other sub-regions in BRI countries.The spatial structure of scientific collaboration networks has transformed from the‘dual core’composed of China and the Central&Eastern Europe region,to the‘multi-polarization’composed of‘one zone and multi-points’.3)The hierarchical structure of scientific collaboration networks presents a typical‘core-periphery’structure,and changes from‘single core’to‘double cores’.4)Among the formation mechanisms of scientific collaboration networks,scientific research strength and social proximity play the most important roles,while geographical distance gradually weakens the hindrance to scientific collaboration.展开更多
Urban agglomeration is made up of cities with different sizes to be linked by traffic network in a given area, and it is an inevitable result when urbanization reaches a certain level. Taking urban agglomeration in ce...Urban agglomeration is made up of cities with different sizes to be linked by traffic network in a given area, and it is an inevitable result when urbanization reaches a certain level. Taking urban agglomeration in central Jilin (UACJ) as an example, this article analyzes the formation mechanism and spatial pattern of urban agglomeration in the less-developed area. First, the dynamics of UACJ has been analyzed from the aspects of geographical condition, economic foundation, policy background, and traffic condition. Then the development process is divided into three stages-single city, city group and city cluster. Secondly, the central cities are identified from the aspects of city cen- trality, and the development axes are classified based on economic communication capacity. Finally, the urban agglo- meration is divided into five urban economic regions in order to establish the reasonable distribution of industries.展开更多
To improve the global stiffness and conveniently build a model of a compliant mechanism with spatial multiple degrees of freedom(DOF),the topology optimization method,combined with the isomorphic mapping matrix,is pro...To improve the global stiffness and conveniently build a model of a compliant mechanism with spatial multiple degrees of freedom(DOF),the topology optimization method,combined with the isomorphic mapping matrix,is proposed in this paper for structure synthesis of a 6-DOF spatial compliant mechanism.By using the differential approximation method,the Jacobian matrix of the Stewart prototype platform is calculated as the isomorphic mapping matrix,and its eigenvalues and eigenvectors are considered.Combining the isomorphic mapping matrix with the solid isotropic material with the penalization topology optimization method,the topological model of the 6-DOF spatial compliant mechanism is constructed,and a topological structure of the 6-DOF spatial compliant mechanism is derived which has the same differential kinematic characteristics as the Gough-Stewart prototype platform.Piezoelectric actuators are mounted inside the topological structure during the three-dimensional printing manufacturing process,and its driver directions are in accordance with the driver configuration directions of the Gough-Stewart prototype platform.The effectiveness of the proposed method for topological structure synthesis of the 6-DOF spatial compliant mechanism is demonstrated through several numerical examples and experimental studies.展开更多
Ni51Ti49 at.%bulk was additively manufactured by laser-directed energy deposition(DED)to reveal the microstructure evolution,phase distribution,and mechanical properties.It is found that the localized remelting,reheat...Ni51Ti49 at.%bulk was additively manufactured by laser-directed energy deposition(DED)to reveal the microstructure evolution,phase distribution,and mechanical properties.It is found that the localized remelting,reheating,and heat accumulation during DED leads to the spatial heterogeneous distribution of columnar crystal and equiaxed crystal,a gradient distribution of Ni4Ti3 precipitates along the building direction,and preferential formation of Ni4Ti3 precipitates in the columnar zone.The austenite transformation finish temperature(Af)varies from-12.65℃(Z=33 mm)to 60.35℃(Z=10 mm),corresponding to tensile yield strength(σ0.2)changed from 120±30 MPa to 570±20 MPa,and functional properties changed from shape memory effect to superelasticity at room temperature.The sample in the Z=20.4 mm height has the best plasticity of 9.6%and the best recoverable strain of 4.2%.This work provided insights and guidelines for the spatial characterization of DEDed NiTi.展开更多
Alluviation and sedimentation of the Yellow River are important factors influencing the surface soil structure and organic carbon content in its lower reaches.Selecting Kaifeng and Zhoukou as typical cases of the Yell...Alluviation and sedimentation of the Yellow River are important factors influencing the surface soil structure and organic carbon content in its lower reaches.Selecting Kaifeng and Zhoukou as typical cases of the Yellow River flooding area,the field survey,soil sample collection,laboratory experiment and Geographic Information System(GIS)spatial analysis methods were applied to study the spatial distribution characteristics and change mechanism of organic carbon components at different soil depths.The results revealed that the soil total organic carbon(TOC),active organic carbon(AOC)and nonactive organic carbon(NOC)contents ranged from 0.05–30.03 g/kg,0.01–8.86 g/kg and 0.02–23.36 g/kg,respectively.The TOC,AOC and NOC contents in the surface soil layer were obviously higher than those in the lower soil layer,and the sequence of the content and change range within a single layer was TOC>NOC>AOC.Geostatistical analysis indicated that the TOC,AOC and NOC contents were commonly influenced by structural and random factors,and the influence magnitudes of these two factors were similar.The overall spatial trends of TOC,AOC and NOC remained relatively consistent from the 0–20 cm layer to the 20–100 cm layer,and the transition between high-and low-value areas was obvious,while the spatial variance was high.The AOC and NOC contents and spatial distribution better reflected TOC spatial variation and carbon accumulation areas.The distribution and depth of the sediment,agricultural land-use type,cropping system,fertilization method,tillage process and cultivation history were the main factors impacting the spatial variation in the soil organic carbon(SOC)components.Therefore,increasing the organic matter content,straw return,applying organic manure,adding exogenous particulate matter and conservation tillage are effective measures to improve the soil quality and attain sustainable agricultural development in the alluvial/sedimentary zone of the Yellow River.展开更多
Folk song as a representative of traditional Chinese folk culture is the expression of landscape culture in a certain regional space.According to landscape gene theory,gene structure of folk song cultural landscape wa...Folk song as a representative of traditional Chinese folk culture is the expression of landscape culture in a certain regional space.According to landscape gene theory,gene structure of folk song cultural landscape was recognized from two dimensions:subject form and cultural environment,and quantitative data were combined to analyze spatial distribution features of folk song cultural landscape genes.According to the analysis,in terms of style,work song is mainly distributed on plains,mountain song is distributed in mountainous areas,and ditty in the eastern watershed of the Yangtze River,in terms of theme,work and production folk songs are mainly distributed in eastern regions with intensive farming,while love and marriage folk songs in regions far away from the Central Plain Culture.Folk song cultural landscape is a result of the interaction between man and geographical conditions,residents in different geographical environments have different perception spaces to create folk songs with regional cultural symbols.展开更多
Aiming at the problem that the existing models have a poor segmentation effect on imbalanced data sets with small-scale samples,a bilateral U-Net network model with a spatial attention mechanism is designed.The model ...Aiming at the problem that the existing models have a poor segmentation effect on imbalanced data sets with small-scale samples,a bilateral U-Net network model with a spatial attention mechanism is designed.The model uses the lightweight MobileNetV2 as the backbone network for feature hierarchical extraction and proposes an Attentive Pyramid Spatial Attention(APSA)module compared to the Attenuated Spatial Pyramid module,which can increase the receptive field and enhance the information,and finally adds the context fusion prediction branch that fuses high-semantic and low-semantic prediction results,and the model effectively improves the segmentation accuracy of small data sets.The experimental results on the CamVid data set show that compared with some existing semantic segmentation networks,the algorithm has a better segmentation effect and segmentation accuracy,and its mIOU reaches 75.85%.Moreover,to verify the generality of the model and the effectiveness of the APSA module,experiments were conducted on the VOC 2012 data set,and the APSA module improved mIOU by about 12.2%.展开更多
基金supported by National Natural Science Foundation of China(62473341)Key Research and Development Special Project of Henan Province(221111210500)Key Research and Development Special Project of Henan Province(242102211071,242102210142,232102211053).
文摘The rapid development and widespread adoption of Internet technology have significantly increased Internet traffic,highlighting the growing importance of network security.Intrusion Detection Systems(IDS)are essential for safeguarding network integrity.To address the low accuracy of existing intrusion detection models in identifying network attacks,this paper proposes an intrusion detection method based on the fusion of Spatial Attention mechanism and Residual Neural Network(SA-ResNet).Utilizing residual connections can effectively capture local features in the data;by introducing a spatial attention mechanism,the global dependency relationships of intrusion features can be extracted,enhancing the intrusion recognition model’s focus on the global features of intrusions,and effectively improving the accuracy of intrusion recognition.The proposed model in this paper was experimentally verified on theNSL-KDD dataset.The experimental results showthat the intrusion recognition accuracy of the intrusion detection method based on SA-ResNet has reached 99.86%,and its overall accuracy is 0.41% higher than that of traditional Convolutional Neural Network(CNN)models.
文摘Pulmonary nodules represent an early manifestation of lung cancer.However,pulmonary nodules only constitute a small portion of the overall image,posing challenges for physicians in image interpretation and potentially leading to false positives or missed detections.To solve these problems,the YOLOv8 network is enhanced by adding deformable convolution and atrous spatial pyramid pooling(ASPP),along with the integration of a coordinate attention(CA)mechanism.This allows the network to focus on small targets while expanding the receptive field without losing resolution.At the same time,context information on the target is gathered and feature expression is enhanced by attention modules in different directions.It effectively improves the positioning accuracy and achieves good results on the LUNA16 dataset.Compared with other detection algorithms,it improves the accuracy of pulmonary nodule detection to a certain extent.
基金Support by Fundamental Research Funds for the Central Universities of China(Grant No.2022JBZY026).
文摘In this paper,a new single-DOF(degree of freedom)spatial five-link RPRPS mechanism is proposed.The mechanism is designed to develop a new ground mechanism that can move in a consistent direction and change direction using only one actuator.When the actuator rotates in one direction,the ground mobile mechanism can perform a“crawling”motion in a straight line.When the actuator rotates reversely in a special position,it can change the direction of“crawling”motion.Firstly,the concept of the RPRPS mechanism is described,explaining the connection relationships and grounding points between each link.The degree of freedom of the RPRPS mechanism obtained through mobility analysis is 1.Subsequently,the locomotion of the RPRPS mechanism in crawling and turning modes is analyzed separately.Describing the RPRPS mechanism’s movement path through a triangular mesh formed during landing,obtaining the RPRPS mechanism’s cycle step size and steering angle.The RPRPS mechanism’s movement path is described through a triangular mesh formed landing during,from which the mechanism’s cycle step size and steering angle are obtained.Feasibility analysis of turning motion through the positional relationship of COG point on different support surfaces of the RPRPS mechanism.A physical prototype of the RPRPS mechanism is developed,and experiments are conducted on both crawling and turning modes.The results are consistent with the theoretical analysis and verify the feasibility of the proposed mechanism.
基金Supported by National Natural Science Foundation of China(Grant Nos.52205003 and 51575018)Zhejiang Provincial Natural Science Foundation(Grant No.LD22E050011)Ningbo Municipal Key Projects of Science and Technology Innovation 2025 Plan(Grant No.2022Z070).
文摘Automated fiber placement(AFP)enables the efficient and precise fabrication of complex-shaped aerospace composite structures with lightweight and high-performance properties.However,due to the excessive compression on the inner edge of the tow placed along the curved trajectory,the resulting defects represented by buckling and wrinkles in spatial tow steering can induce poor manufacturing accuracy and quality degradation of products.In this paper,a theoretical model of tow buckling based on the first-order shear deformation laminate theory,linear elastic adhesion interface and Hertz compaction contact theory is proposed to analyze the formation mechanism of the wrinkles and predict the formation of defects by solving the critical radius of the trajectory,and finite element analysis involving the cohesive zone modeling(CZM)is innovated to simulate the local buckling state of the steered tow in AFP.Additionally,numerical parametric studies and experimental results indicate that mechanical properties and geometric parameters of the prepreg,the curvature of the placement trajectory and critical process parameters have a significant impact on buckling formation,and optimization of process parameters can achieve effective suppression of placement defects.This research proposes a theoretical modeling method for tow buckling,and conducts in-depth research on defect formation and suppression methods based on finite element simulation and placement experiments.
基金supported by the Henan Provincial Science and Technology Research Project under Grants 232102211006,232102210044,232102211017,232102210055 and 222102210214the Science and Technology Innovation Project of Zhengzhou University of Light Industry under Grant 23XNKJTD0205+1 种基金the Undergraduate Universities Smart Teaching Special Research Project of Henan Province under Grant Jiao Gao[2021]No.489-29the Doctor Natural Science Foundation of Zhengzhou University of Light Industry under Grants 2021BSJJ025 and 2022BSJJZK13.
文摘Multispectral pedestrian detection technology leverages infrared images to provide reliable information for visible light images, demonstrating significant advantages in low-light conditions and background occlusion scenarios. However, while continuously improving cross-modal feature extraction and fusion, ensuring the model’s detection speed is also a challenging issue. We have devised a deep learning network model for cross-modal pedestrian detection based on Resnet50, aiming to focus on more reliable features and enhance the model’s detection efficiency. This model employs a spatial attention mechanism to reweight the input visible light and infrared image data, enhancing the model’s focus on different spatial positions and sharing the weighted feature data across different modalities, thereby reducing the interference of multi-modal features. Subsequently, lightweight modules with depthwise separable convolution are incorporated to reduce the model’s parameter count and computational load through channel-wise and point-wise convolutions. The network model algorithm proposed in this paper was experimentally validated on the publicly available KAIST dataset and compared with other existing methods. The experimental results demonstrate that our approach achieves favorable performance in various complex environments, affirming the effectiveness of the multispectral pedestrian detection technology proposed in this paper.
文摘After illustrating the concept of Urban Growth Theory and Urban Growth Management,by taking relevant theoretical research literatures for reference,based on the specific conditions of Chongqing City,the paper had analyzed the spatial growth and evolution of Chongqing City,and the spatial influence mechanism for urban growth management.The spatial influence mechanism of Chongqing urban growth had been divided into four aspects including natural environment,economic development,urban traffic organization and regional policy planning,which were considered as the primary mechanism,driving mechanism,essential condition and driving force of urban spatial growth and development,respectively.From the perspective of analyzing problems,the comprehensive analysis had been conducted on the urban growth management in economy and planning,and corresponding urban growth space management strategies had been formulated.From the perspective of combining theory with practice,it had studied and revealed the spatial influence mechanism for urban growth management,which was of practical guiding significance to the development of Chongqing urban space pattern,and also vital significance to the construction of theoretical system of Chinese urban management and guidance of further development and renovation of specific urban planning.
基金supported by the National Natural Science Foundation of China (grant Nos.52130805)China National Postdoctoral Program for Innovative Talents (BX20220234)Shanghai Science and Technology Committee Program (20dz1202200)。
文摘The representation of spatial variation of soil properties in the form of random fields permits advanced probabilistic assessment of slope stability.In many studies,the safety margin of the system is typically characterized by the term“probability of failure(Pfailure)”.As the intensity and spatial distribution of soil properties vary in different random field realizations,the failure mechanism and deformation field of a slope can vary as well.Not only can the location of the failure surfaces vary,but the mode of failure also changes.Such information is equally valuable to engineering practitioners.In this paper,two slope examples that are modified from a real case study are presented.The first example pertains to the stability analysis of a multi-layer-slope while the second example deals with the serviceability analysis of a multi-layer c-φslope.In addition,due to the large number of simulations needed to reveal the full picture of the failure mechanism,Convolutional Neural Networks(CNNs)that adopt a U-Net architecture is proposed to offer a soft computing strategy to facilitate the investigation.The spatial distribution of the failure surfaces,the statistics of the sliding volume,and the statistics of the deformation field are presented.The results also show that the proposed deep-learning model is effective in predicting the failure mechanism and deformation field of slopes in spatially variable soils;therefore encouraging probabilistic study of slopes in practical scenarios.
基金support from the National Key R&D Program of China(Grant No:2022YFC3401003)the National Natural Science Foundation of China(Grant No:21927808)+2 种基金the National Natural Science Foundation of China(Grant No:22104160)the National Key Research and Development Program of China(Grant No:2017YFC1704006)the Innovation Team of Ethnomedicine of National Ethnic Affairs Commission,China.We thank all the research staff who contributed to the study.
文摘Polygala tenuifolia,commonly known as Yuanzhi(YZ)in Chinese,has been shown to possess antiinsomnia properties.However,the material basis and the mechanism underlying its sedative-hypnotic effects remain unclear.Herein,we investigated the active components and neurochemical mechanism of YZ extracts using liquid chromatography tandem mass spectrometry(LC-MS/MS)-based pharmacometabolomics and mass spectrometry imaging(MSI)-based spatial resolved metabolomics.According to the results,17 prototypes out of 101 ingredients in the YZ extract were detected in both the plasma and brain,which might be the major components contributing to the sedative-hypnotic effects.Network pharmacology analysis revealed that these prototypes may exert their effects through neuroactive ligand-receptor interaction,serotonergic synapse,dopaminergic synapse,and dopaminergic synapse,among other pathways.LC-MS/MS-based targeted metabolomics and Western blot(WB)revealed that tryptophan-serotonin-melatonin(Trp-5-HT-Mel)and tyrosine-norepinephrine-adrenaline(Tyr-Ne-Ad)are the key regulated pathways.Dopa decarboxylase(DDC)upregulation and phenylethanolamine Nmethyltransferase(PNMT)downregulation further confirmed these pathways.Furthermore,MSI-based spatially resolved metabolomics revealed notable alterations in 5-HT in the pineal gland(PG),and Ad in the brainstem,including the middle brain(MB),pons(PN),and hypothalamus(HY).In summary,this study illustrates the efficacy of an integrated multidimensional metabolomics approach in unraveling the sedative-hypnotic effects and neurochemical mechanisms of a Chinese herbal medicine,YZ.
基金co-supported by China Scholarship Council (No. 201604000003)the National Natural Science Foundation of China (Nos. U1433203, U1533119 and L142200032)the Foundation for Innovative Research Groups of the National Natural Science Foundation of China (No. 61221061)
文摘In this paper, a four-dimensional coordinated path planning algorithm for multiple UAVs is proposed, in which time variable is taken into account for each UAV as well as collision free and obstacle avoidance. A Spatial Refined Voting Mechanism(SRVM) is designed for standard Particle Swarm Optimization(PSO) to overcome the defects of local optimal and slow convergence.For each generation candidate particle positions are recorded and an adaptive cube is formed with own adaptive side length to indicate occupied regions. Then space voting begins and is sorted based on voting results, whose centers with bigger voting counts are seen as sub-optimal positions. The average of all particles of corresponding dimensions are calculated as the refined solutions. A time coordination method is developed by generating specified candidate paths for every UAV, making them arrive the same destination with the same time consumption. A spatial-temporal collision avoidance technique is introduced to make collision free. Distance to destination is constructed to improve the searching accuracy and velocity of particles. In addition, the objective function is redesigned by considering the obstacle and threat avoidance, Estimated Time of Arrival(ETA), separation maintenance and UAV self-constraints. Experimental results prove the effectiveness and efficiency of the algorithm.
基金Key Project of National Natural Science Foundation of China,No.41230631National Natural Science Foundation of China,No.41271134
文摘Chinese railway has entered the ＂HSR era＂, while the structure of ＂four vertical and four horizontal＂ railways for transit passengers is almost completed. Taking the Beijing-Shanghai High-Speed Rail （hereinafter referred to as HSR） as an example, this paper first explores HSR＇s effects on the spatial structure of regional tourist flows using the social network analysis. Next, it notes changes in the accessibility of regional transportation. After analyzing the factors including initial endowment of regional tourism resources, hospitality facilities, the density of the regional tourism transportation network, and locations, the paper discusses the mechanisms through which HSR affects regional tourist flows. The study shows the following： （1） HSR＇s effects on the spatial structure of regional tourist flows are manifested through the Matthew effect, the filtering effect, the diffusion effect and the overlying effect, and （2） the Matthew effect of HSR is manifested under an obvious interaction of the location, the initial endowment of tourism resources, hospitality capacity, tourist transportation network density and ＂time-space compression＂. The filtering effect of HSR is manifested for those tourism nodes without favorable location conditions, endowment of tourism resources, hospitality capacity, or tourist transportation network density and without obvious benefits from ＂time-space compression＂. Those tourism nodes that boast advantages in terms of lo- cation condition, endowment of tourism resources, hospitality capacity, tourist transportation network density and obvious ＂time-space compression＂ will become sources for the diffusion effect. HSR will strengthen the aggregation effects of tourist flow in these diffusion sources, which will thereafter diffuse to peripheral tourist areas, manifesting ＂aggregation-diffusion＂. HSR has overlapped tourists＇ spatial traveling range over large-scale spaces. However, the overlying effect is only generated in those tourism nodes with a favorable location condition, an endowment of tourism resources, hospitality capacity, tourist transportation network den- sity, and obvious ＂time-space compression＂.
基金Supported by National Natural Science Foundation of China(Grant No.51005195)Natural Science Research Fund for Youth in Higher Education Institutions of Hebei Province,China(Grant No.QN2014175)
文摘The pre-research on mobility analysis presented a unified-mobility formula and a methodology based on reciprocal screw theory by HUANG, which focused on classical and modem parallel mechanisms. However its range of application needs to further extend to general multi-loop spatial mechanism. This kind of mechanism is not only more complex in structure but also with strong motion coupling among loops, making the mobility analysis even more complicated, and the relevant research has long been ignored. It is focused on how to apply the new principle for general spatial mechanism to those various multi-loop spatial mechanisms, and some new meaningful knowledge is further found. Several typical examples of the genera/multi-loop spatial mechanisms with motion couple even strong motion couple are considered. These spatial mechanisms include different closing way： over-constraint appearing in rigid closure, in movable closure, and in dynamic closure as well; these examples also include two different new methods to solve this kind of issue： the way to recognize over-constraints by analyzing relative movement between two connected links and by constructing a virtual loop to recognize over-constraints. In addition, over-constraint determination tabulation is brought to analyze the motion couple. The researches above are all based upon the screw theory. All these multi-loop spatial mechanisms with different kinds of structures can completely be solved by following the directions and examples, and the new mobility theory based on the screw theory is also proved to be valid. This study not only enriches and develops the theory and makes the theory more universal, but also has a special meaning for innovation in mechanical engineering.
基金We gratefully acknowledge the support of the National Key R&D Program of China(Grant No.2017YFC1501102)the National Nat-ural Science Foundation of China(Grant No.41977229)the Sichuan Youth Science and Technology Innovation Research Team Project(Grant No.2020JDTD0006).
文摘Water-induced landslides in hydropower reservoirs pose a great threat to both project operation and human life.This paper examines three large reservoirs in Sichuan Province,China.Field surveys,site monitoring data analyses and numerical simulations are used to analyze the spatial distribution and failure mechanisms of water-induced landslides in reservoir areas.First,the general rules of landslide development in the reservoir area are summarized.The first rule is that most of the landslides have rear edge elevations of 100e500 m above the normal water level of the reservoir,with volumes in the range of 106 e107 m 3.When the volume exceeds a certain amount,the number of sites at which the landscape can withstand landslides is greatly reduced.Landslide hazards mainly occur in the middle section of the reservoir and less in the annex of the dam site and the latter half of the reservoir area.The second rule is that sedimentary rocks such as sandstone are more prone to landslide hazards than other lithologies.Then,the failure mechanism of changes in the water level that reduces the stability of the slope composed of different geomaterials is analyzed by a proposed slope stability framework that considers displacement and is discussed with the monitoring results.Permeability is an essential parameter for understanding the diametrically opposed deformation behavior of landslides experiencing filling-drawdown cycles during operation.This study seeks to provide inspiration to subsequent researchers,as well as guidance to technicians,on landslide prevention and control in reservoir areas.
基金Under the auspices of National Natural Science Foundation of China(No.41701151)MOE(Ministry of Education in China)Project of Humanities and Social Sciences(No.17YJCZH256)Doctoral Project of Tianjin Normal University(No.52XB1621)
文摘Spatial equality of access to basic public services, especially medical care services which are directly related to life safety, is the first step to achieve the goal of equalization of basic public services for all the people proposed by central government of China. Using the spatial analysis and the statistical analysis, this study evaluates the spatial differentiation of medical care facilities accessibility by constructing STT(Shortest Travel-Time) and SAI(Spatial Accessibility Index). And then this study explores the neighborhood effects on the medical care facilities accessibility in Beijing, with a particular focus on the effect of neighborhood migrant proportion by constructing spatial dependent regression model. The spatial accessibility analysis of medical care facilities show that the spatial distribution of medical care facilities was basically consistent with administrative regions but not with population demands. Bivariate LISA cluster maps identify that suburban areas are the overlapped clusters of high percent of migrants and limited medical care services. This is associated with the public service allocation rule in China, which stresses equality within urban areas and within rural areas but overlooks equality between urban areas and rural areas; and stresses local resident demands but overlooks migrant demands. To estimate the effects on medical care accessibility of neighborhood migrant proportion, spatial dependence models are applied due to spatial dependence of accessibility of medical care facilities. The regression results show that neighborhoods with high percent of migrants, even conditioning on neighborhood SES, are related to limited spatial accessibility of medical care services. Besides neighborhood characteristics, another important factor influencing spatial accessibility of medical care services is the process of spatial spillover effects. This indicates that the attenuate accessibility of medical care services for migrants is not only because of their own constraints but also because of their proximity to other disadvantaged neighborhoods. Therefore, it is urgently needed to increase the medical facilities in the suburban areas, to take into account migrants' demands and to reduce residential segregation between local residents and migrants for local governments to achieve the goal of equalization of medical care service.
基金Under the auspices of Strategic Priority Research Program of the Chinese Academy of Sciences(No.XDA20010103)。
文摘Scientific collaboration has become an important part of the people-to-people exchanges in the Belt and Road initiative,and remarkable progress has been made since 2013.Taking the 65 countries along the Belt and Road(BRI countries)as the research areas and using collaborated Web of Science(WOS)core collection papers to construct an international scientific collaboration matrix,the paper explores the spatial structure,hierarchy and formation mechanisms of scientific collaboration networks of 65 countries along the Belt and Road.The results show that:1)Beyond the Belt and Road regions(BRI regions),Central&Eastern Europe,China and West Asia&North Africa have formed a situation in which they all have the most external links with other countries beyond BRI regions.China has the dominant role over other BRI countries in generating scientific links.The overall spatial structure has changed to a skeleton structure consisting of many dense regions,such as Europe,North America,East Asia and Oceania.2)Within the Belt and Road regions,Central&Eastern Europe has become the largest collaboration partner with other sub-regions in BRI countries.The spatial structure of scientific collaboration networks has transformed from the‘dual core’composed of China and the Central&Eastern Europe region,to the‘multi-polarization’composed of‘one zone and multi-points’.3)The hierarchical structure of scientific collaboration networks presents a typical‘core-periphery’structure,and changes from‘single core’to‘double cores’.4)Among the formation mechanisms of scientific collaboration networks,scientific research strength and social proximity play the most important roles,while geographical distance gradually weakens the hindrance to scientific collaboration.
基金Under the auspices of the Major State Basic Research Development Program of China (973 Program) (No.2004CB418507-2), National Natural Science Foundation of China (No. 40471038)
文摘Urban agglomeration is made up of cities with different sizes to be linked by traffic network in a given area, and it is an inevitable result when urbanization reaches a certain level. Taking urban agglomeration in central Jilin (UACJ) as an example, this article analyzes the formation mechanism and spatial pattern of urban agglomeration in the less-developed area. First, the dynamics of UACJ has been analyzed from the aspects of geographical condition, economic foundation, policy background, and traffic condition. Then the development process is divided into three stages-single city, city group and city cluster. Secondly, the central cities are identified from the aspects of city cen- trality, and the development axes are classified based on economic communication capacity. Finally, the urban agglo- meration is divided into five urban economic regions in order to establish the reasonable distribution of industries.
基金This research was supported by the National Natural Science Foundation of China(Grant 51165009)the Innovation School Project of Education Department of Guangdong Province,China(Grant 2017KZDXM060).
文摘To improve the global stiffness and conveniently build a model of a compliant mechanism with spatial multiple degrees of freedom(DOF),the topology optimization method,combined with the isomorphic mapping matrix,is proposed in this paper for structure synthesis of a 6-DOF spatial compliant mechanism.By using the differential approximation method,the Jacobian matrix of the Stewart prototype platform is calculated as the isomorphic mapping matrix,and its eigenvalues and eigenvectors are considered.Combining the isomorphic mapping matrix with the solid isotropic material with the penalization topology optimization method,the topological model of the 6-DOF spatial compliant mechanism is constructed,and a topological structure of the 6-DOF spatial compliant mechanism is derived which has the same differential kinematic characteristics as the Gough-Stewart prototype platform.Piezoelectric actuators are mounted inside the topological structure during the three-dimensional printing manufacturing process,and its driver directions are in accordance with the driver configuration directions of the Gough-Stewart prototype platform.The effectiveness of the proposed method for topological structure synthesis of the 6-DOF spatial compliant mechanism is demonstrated through several numerical examples and experimental studies.
基金the financial support of the Hunan Innovation Platform and Talent Plan(2022RC3033)Natural Science Foundation of Shandong Province(ZR2020ZD04)Ganzhou Science and Technology Planning Project(Grant No.Ganshikefa[2019]60)。
文摘Ni51Ti49 at.%bulk was additively manufactured by laser-directed energy deposition(DED)to reveal the microstructure evolution,phase distribution,and mechanical properties.It is found that the localized remelting,reheating,and heat accumulation during DED leads to the spatial heterogeneous distribution of columnar crystal and equiaxed crystal,a gradient distribution of Ni4Ti3 precipitates along the building direction,and preferential formation of Ni4Ti3 precipitates in the columnar zone.The austenite transformation finish temperature(Af)varies from-12.65℃(Z=33 mm)to 60.35℃(Z=10 mm),corresponding to tensile yield strength(σ0.2)changed from 120±30 MPa to 570±20 MPa,and functional properties changed from shape memory effect to superelasticity at room temperature.The sample in the Z=20.4 mm height has the best plasticity of 9.6%and the best recoverable strain of 4.2%.This work provided insights and guidelines for the spatial characterization of DEDed NiTi.
基金National Natural Science Foundation of China,No.41101088,No.U1404401Natural Science Foundation of Henan Province,No.182300410129New Interdisciplinary and Characteristic Subject Cultivation Project of Henan University,No.XXJC20140003。
文摘Alluviation and sedimentation of the Yellow River are important factors influencing the surface soil structure and organic carbon content in its lower reaches.Selecting Kaifeng and Zhoukou as typical cases of the Yellow River flooding area,the field survey,soil sample collection,laboratory experiment and Geographic Information System(GIS)spatial analysis methods were applied to study the spatial distribution characteristics and change mechanism of organic carbon components at different soil depths.The results revealed that the soil total organic carbon(TOC),active organic carbon(AOC)and nonactive organic carbon(NOC)contents ranged from 0.05–30.03 g/kg,0.01–8.86 g/kg and 0.02–23.36 g/kg,respectively.The TOC,AOC and NOC contents in the surface soil layer were obviously higher than those in the lower soil layer,and the sequence of the content and change range within a single layer was TOC>NOC>AOC.Geostatistical analysis indicated that the TOC,AOC and NOC contents were commonly influenced by structural and random factors,and the influence magnitudes of these two factors were similar.The overall spatial trends of TOC,AOC and NOC remained relatively consistent from the 0–20 cm layer to the 20–100 cm layer,and the transition between high-and low-value areas was obvious,while the spatial variance was high.The AOC and NOC contents and spatial distribution better reflected TOC spatial variation and carbon accumulation areas.The distribution and depth of the sediment,agricultural land-use type,cropping system,fertilization method,tillage process and cultivation history were the main factors impacting the spatial variation in the soil organic carbon(SOC)components.Therefore,increasing the organic matter content,straw return,applying organic manure,adding exogenous particulate matter and conservation tillage are effective measures to improve the soil quality and attain sustainable agricultural development in the alluvial/sedimentary zone of the Yellow River.
基金Sponsored by Anhui Provincial Tounsm Administration(SLYJKT201509/SLYJKT201504)Youth Fund for Humanistic and Social Sciences Programs of the Ministry of Education(15YJC790018)
文摘Folk song as a representative of traditional Chinese folk culture is the expression of landscape culture in a certain regional space.According to landscape gene theory,gene structure of folk song cultural landscape was recognized from two dimensions:subject form and cultural environment,and quantitative data were combined to analyze spatial distribution features of folk song cultural landscape genes.According to the analysis,in terms of style,work song is mainly distributed on plains,mountain song is distributed in mountainous areas,and ditty in the eastern watershed of the Yangtze River,in terms of theme,work and production folk songs are mainly distributed in eastern regions with intensive farming,while love and marriage folk songs in regions far away from the Central Plain Culture.Folk song cultural landscape is a result of the interaction between man and geographical conditions,residents in different geographical environments have different perception spaces to create folk songs with regional cultural symbols.
基金Ministry of Science and Technology Basic Resources Survey Special Project,Grant/Award Number:2019FY100900High-level Hospital Construction Project,Grant/Award Number:DFJH2019015+2 种基金National Natural Science Foundation of China,Grant/Award Number:61871021Guangdong Natural Science Foundation,Grant/Award Number:2019A1515011676Beijing Key Laboratory of Robotics Bionic and Functional Research。
文摘Aiming at the problem that the existing models have a poor segmentation effect on imbalanced data sets with small-scale samples,a bilateral U-Net network model with a spatial attention mechanism is designed.The model uses the lightweight MobileNetV2 as the backbone network for feature hierarchical extraction and proposes an Attentive Pyramid Spatial Attention(APSA)module compared to the Attenuated Spatial Pyramid module,which can increase the receptive field and enhance the information,and finally adds the context fusion prediction branch that fuses high-semantic and low-semantic prediction results,and the model effectively improves the segmentation accuracy of small data sets.The experimental results on the CamVid data set show that compared with some existing semantic segmentation networks,the algorithm has a better segmentation effect and segmentation accuracy,and its mIOU reaches 75.85%.Moreover,to verify the generality of the model and the effectiveness of the APSA module,experiments were conducted on the VOC 2012 data set,and the APSA module improved mIOU by about 12.2%.
