0 INTRODUCTION The lunar surface lacks an atmosphere and is continuously subjected to a combination of space weathering factors such as cosmic rays,solar wind,and micrometeorite impacts,forming a several-meter-thick l...0 INTRODUCTION The lunar surface lacks an atmosphere and is continuously subjected to a combination of space weathering factors such as cosmic rays,solar wind,and micrometeorite impacts,forming a several-meter-thick lunar regolith(Sorokin et al.,2020).展开更多
The widespread availability of digital multimedia data has led to a new challenge in digital forensics.Traditional source camera identification algorithms usually rely on various traces in the capturing process.Howeve...The widespread availability of digital multimedia data has led to a new challenge in digital forensics.Traditional source camera identification algorithms usually rely on various traces in the capturing process.However,these traces have become increasingly difficult to extract due to wide availability of various image processing algorithms.Convolutional Neural Networks(CNN)-based algorithms have demonstrated good discriminative capabilities for different brands and even different models of camera devices.However,their performances is not ideal in case of distinguishing between individual devices of the same model,because cameras of the same model typically use the same optical lens,image sensor,and image processing algorithms,that result in minimal overall differences.In this paper,we propose a camera forensics algorithm based on multi-scale feature fusion to address these issues.The proposed algorithm extracts different local features from feature maps of different scales and then fuses them to obtain a comprehensive feature representation.This representation is then fed into a subsequent camera fingerprint classification network.Building upon the Swin-T network,we utilize Transformer Blocks and Graph Convolutional Network(GCN)modules to fuse multi-scale features from different stages of the backbone network.Furthermore,we conduct experiments on established datasets to demonstrate the feasibility and effectiveness of the proposed approach.展开更多
An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyram...An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyramid network(FPN)structure of the original YOLOv8 mode is replaced by the generalized-FPN(GFPN)structure in GiraffeDet to realize the"cross-layer"and"cross-scale"adaptive feature fusion,to enrich the semantic information and spatial information on the feature map to improve the target detection ability of the model.Secondly,a pyramid-pool module of multi atrous spatial pyramid pooling(MASPP)is designed by using the idea of atrous convolution and feature pyramid structure to extract multi-scale features,so as to improve the processing ability of the model for multi-scale objects.The experimental results show that the detection accuracy of the improved YOLOv8 model on DIOR dataset is 92%and mean average precision(mAP)is 87.9%,respectively 3.5%and 1.7%higher than those of the original model.It is proved the detection and classification ability of the proposed model on multi-dimensional optical remote sensing target has been improved.展开更多
Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in images.Obtaining class-specific precise representations at different scales is a key aspect of feat...Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in images.Obtaining class-specific precise representations at different scales is a key aspect of feature representation.However,existing methods often rely on the single-scale deep feature,neglecting shallow and deeper layer features,which poses challenges when predicting objects of varying scales within the same image.Although some studies have explored multi-scale features,they rarely address the flow of information between scales or efficiently obtain class-specific precise representations for features at different scales.To address these issues,we propose a two-stage,three-branch Transformer-based framework.The first stage incorporates multi-scale image feature extraction and hierarchical scale attention.This design enables the model to consider objects at various scales while enhancing the flow of information across different feature scales,improving the model’s generalization to diverse object scales.The second stage includes a global feature enhancement module and a region selection module.The global feature enhancement module strengthens interconnections between different image regions,mitigating the issue of incomplete represen-tations,while the region selection module models the cross-modal relationships between image features and labels.Together,these components enable the efficient acquisition of class-specific precise feature representations.Extensive experiments on public datasets,including COCO2014,VOC2007,and VOC2012,demonstrate the effectiveness of our proposed method.Our approach achieves consistent performance gains of 0.3%,0.4%,and 0.2%over state-of-the-art methods on the three datasets,respectively.These results validate the reliability and superiority of our approach for multi-label image classification.展开更多
This paper presents the morphologic,chemical and other typomorphic characteristics of native gold from four placer deposits(basins of the Lev.Nora,Skalistaya and Golysheva rivers,and Loginova brook),four placer occurr...This paper presents the morphologic,chemical and other typomorphic characteristics of native gold from four placer deposits(basins of the Lev.Nora,Skalistaya and Golysheva rivers,and Loginova brook),four placer occurrences(basins of the Lagernaya,Nizh.Litke and Prokhodimaya rivers,and Tikhiy brook),and the alluvial deposit of cape Mordovin on Bolshevik island of the Severnaya Zemlya archipelago(Russia).Optical microscopy,scanning electron microscopy and electron-probe microanalysis were used in this study.Placer gold from the Lagernaya,Golysheva,Nizh.Litke and Skalistaya rivers,Tikhiy brook and cape Mordovin is characterized by a very high fineness(>988‰)in the rims and a lower fineness(860‰–970‰)in the center.Gold particles from the placers of the Lev.Nora and Prokhodimaya rivers and Loginova brook are low fineness and widely vary in the center(from 647‰to 920‰)and are high fineness(950‰–980‰)in the rims.In some gold particles from the placers of the Lev.Nora and Skalistaya rivers,zones with Cu up to 1.2 wt.%and Hg up to 2.6 wt.%are observed.Titanite,monazite,cobaltite,ulmannite,brannerite,rutile,zircon,Y-xenotime,bismuthite,native bismuth and bismuthinite,garnet(almandine),Cu-or Ni-pyrrhotite were found in the native gold from the Skalistaya and Lev.Nora placers.Native gold from the Skalistaya river placer contains mineral micro-inclusions of cobaltite,Cu,Cd-bearing sphalerite and Fe,Cu-ullmannite.Native gold from the Lev.Nora river placer differs in the presence of brannerite and bismuth minerals.On the basis of the obtained results,available metallogenic characteristics of Bolshevik island and literature data,the following types of primary sources are predicted for these locations:(1)Lev.Nora river deposits of gold-copper rare metal and porphyry gold-copper formations;(2)Skalistaya river deposits of porphyry gold-copper and gold-quartz formation;(3)all the other locations:deposits of gold-quartz and gold-sulfide-quartz formations(hosted in terrigenous carbonaceous complexes).The presence of intermediate reservoirs near some of these locations is probable.展开更多
Plasma spark sources are widely used in high-resolution seismic exploration.However,research on the excitation mechanism and propagation characteristics of plasma spark sources is very limited.In this study,we elabora...Plasma spark sources are widely used in high-resolution seismic exploration.However,research on the excitation mechanism and propagation characteristics of plasma spark sources is very limited.In this study,we elaborated on the excitation process of corona discharge plasma spark source based on indoor experimental data.The electrode spacing has a direct impact on the movement of bubbles.As the spacing between bubbles decreases,they collapsed and fused,thereby suppressing the secondary pulse process.Based on the premise of linear arrangement and equal energy synchronous excitation,the motion equation of multiple bubbles under these conditions was derived,and a calculation method for the near-field wavelet model of plasma spark source was established.We simulated the source signals received in different directions and constructed a spatial wavelet face spectrum.Compared with traditional far-field wavelets,the spatial wavelet facial feature representation method provides a more comprehensive display of the variation characteristics and propagation properties of source wavelets in three-dimensional space.The spatial wavelet variation process of the plasma spark source was analyzed,and the source depth and the virtual reflection path are the main factors affecting the wavelet.The high-frequency properties of plasma electric spark source wavelets lead to their sensitivity to factors such as wave fluctuations,position changes,and environmental noise.Minor changes in collection parameters may result in significant changes in the recorded waveform and final data resolution.So,the facial feature method provides more effective technical support for wavelet evaluation.展开更多
To address the issues of unknown target size,blurred edges,background interference and low contrast in infrared small target detection,this paper proposes a method based on density peaks searching and weighted multi-f...To address the issues of unknown target size,blurred edges,background interference and low contrast in infrared small target detection,this paper proposes a method based on density peaks searching and weighted multi-feature local difference.Firstly,an improved high-boost filter is used for preprocessing to eliminate background clutter and high-brightness interference,thereby increasing the probability of capturing real targets in the density peak search.Secondly,a triple-layer window is used to extract features from the area surrounding candidate targets,addressing the uncertainty of small target sizes.By calculating multi-feature local differences between the triple-layer windows,the problems of blurred target edges and low contrast are resolved.To balance the contribution of different features,intra-class distance is used to calculate weights,achieving weighted fusion of multi-feature local differences to obtain the weighted multi-feature local differences of candidate targets.The real targets are then extracted using the interquartile range.Experiments on datasets such as SIRST and IRSTD-IK show that the proposed method is suitable for various complex types and demonstrates good robustness and detection performance.展开更多
In the production of the sucker rod well, the dynamic liquid level is important for the production efficiency and safety in the lifting process. It is influenced by multi-source data which need to be combined for the ...In the production of the sucker rod well, the dynamic liquid level is important for the production efficiency and safety in the lifting process. It is influenced by multi-source data which need to be combined for the dynamic liquid level real-time calculation. In this paper, the multi-source data are regarded as the different views including the load of the sucker rod and liquid in the wellbore, the image of the dynamometer card and production dynamics parameters. These views can be fused by the multi-branch neural network with special fusion layer. With this method, the features of different views can be extracted by considering the difference of the modality and physical meaning between them. Then, the extraction results which are selected by multinomial sampling can be the input of the fusion layer.During the fusion process, the availability under different views determines whether the views are fused in the fusion layer or not. In this way, not only the correlation between the views can be considered, but also the missing data can be processed automatically. The results have shown that the load and production features fusion(the method proposed in this paper) performs best with the lowest mean absolute error(MAE) 39.63 m, followed by the features concatenation with MAE 42.47 m. They both performed better than only a single view and the lower MAE of the features fusion indicates that its generalization ability is stronger. In contrast, the image feature as a single view contributes little to the accuracy improvement after fused with other views with the highest MAE. When there is data missing in some view, compared with the features concatenation, the multi-view features fusion will not result in the unavailability of a large number of samples. When the missing rate is 10%, 30%, 50% and 80%, the method proposed in this paper can reduce MAE by 5.8, 7, 9.3 and 20.3 m respectively. In general, the multi-view features fusion method proposed in this paper can improve the accuracy obviously and process the missing data effectively, which helps provide technical support for real-time monitoring of the dynamic liquid level in oil fields.展开更多
Image registration is an indispensable component in multi-source remote sensing image processing. In this paper, we put forward a remote sensing image registration method by including an improved multi-scale and multi...Image registration is an indispensable component in multi-source remote sensing image processing. In this paper, we put forward a remote sensing image registration method by including an improved multi-scale and multi-direction Harris algorithm and a novel compound feature. Multi-scale circle Gaussian combined invariant moments and multi-direction gray level co-occurrence matrix are extracted as features for image matching. The proposed algorithm is evaluated on numerous multi-source remote sensor images with noise and illumination changes. Extensive experimental studies prove that our proposed method is capable of receiving stable and even distribution of key points as well as obtaining robust and accurate correspondence matches. It is a promising scheme in multi-source remote sensing image registration.展开更多
Geochemical composition characteristics of light oils from the Tertiary in the west of the Chepaizi uplift in the Junggar basin, northwest China, are distinct from those of biodegraded oils derived from the Permian in...Geochemical composition characteristics of light oils from the Tertiary in the west of the Chepaizi uplift in the Junggar basin, northwest China, are distinct from those of biodegraded oils derived from the Permian in the study area and crude oils from some adjacent oil fields such as the Chepaizi and Xiaoguai oilfields. Oil source corre-lation shows that light oils in the study area have similar n-alkane and isoprenoid distribution patterns and carbon isotope compositions with the coal-derived oils from the Jurassic, and display obvious discrepancy on biomarker composition characteristics with the Cretaceous source rock extracts, inferring that they are probably the mixed oils from the Jurassic coal measures and Cretaceous source rocks. In this study, combined with the geochemical data of coal-derived oils from the Jurassic and Cretaceous source rocks or crude oils from the Cretaceous, the source and commingling features of the Tertiary crude oils of Well Pai 2 and Well Pai 8 were investigated. The proportion of the two sources in the mixed crude oils was estimated, and the hydrocarbon accumulation pattern of reservoirs in the study area was established.展开更多
In the video-based surveillance application, moving shadows can affect the correct localization and detection of moving objects. This paper aims to present a method for shadow detection and suppression used for moving...In the video-based surveillance application, moving shadows can affect the correct localization and detection of moving objects. This paper aims to present a method for shadow detection and suppression used for moving visual object detection. The major novelty of the shadow suppression is the integration of several features including photometric invariant color feature, motion edge feature, and spatial feature etc. By modifying process for false shadow detected, the averaging detection rate of moving object reaches above 90% in the test of Hall-Monitor sequence.展开更多
With the popularization of the Internet and the development of technology,cyber threats are increasing day by day.Threats such as malware,hacking,and data breaches have had a serious impact on cybersecurity.The networ...With the popularization of the Internet and the development of technology,cyber threats are increasing day by day.Threats such as malware,hacking,and data breaches have had a serious impact on cybersecurity.The network security environment in the era of big data presents the characteristics of large amounts of data,high diversity,and high real-time requirements.Traditional security defense methods and tools have been unable to cope with the complex and changing network security threats.This paper proposes a machine-learning security defense algorithm based on metadata association features.Emphasize control over unauthorized users through privacy,integrity,and availability.The user model is established and the mapping between the user model and the metadata of the data source is generated.By analyzing the user model and its corresponding mapping relationship,the query of the user model can be decomposed into the query of various heterogeneous data sources,and the integration of heterogeneous data sources based on the metadata association characteristics can be realized.Define and classify customer information,automatically identify and perceive sensitive data,build a behavior audit and analysis platform,analyze user behavior trajectories,and complete the construction of a machine learning customer information security defense system.The experimental results show that when the data volume is 5×103 bit,the data storage integrity of the proposed method is 92%.The data accuracy is 98%,and the success rate of data intrusion is only 2.6%.It can be concluded that the data storage method in this paper is safe,the data accuracy is always at a high level,and the data disaster recovery performance is good.This method can effectively resist data intrusion and has high air traffic control security.It can not only detect all viruses in user data storage,but also realize integrated virus processing,and further optimize the security defense effect of user big data.展开更多
The Digital Elevation Model(DEM)data of debris flow prevention engineering are the boundary of a debris flow prevention simulation,which provides accurate and reliable DEM data and is a key consideration in debris flo...The Digital Elevation Model(DEM)data of debris flow prevention engineering are the boundary of a debris flow prevention simulation,which provides accurate and reliable DEM data and is a key consideration in debris flow prevention simulations.Thus,this paper proposes a multi-source data fusion method.First,we constructed 3D models of debris flow prevention using virtual reality technology according to the relevant specifications.The 3D spatial data generated by 3D modeling were converted into DEM data for debris flow prevention engineering.Then,the accuracy and applicability of the DEM data were verified by the error analysis testing and fusion testing of the debris flow prevention simulation.Finally,we propose the Levels of Detail algorithm based on the quadtree structure to realize the visualization of a large-scale disaster prevention scene.The test results reveal that the data fusion method controlled the error rate of the DEM data of the debris flow prevention engineering within an allowable range and generated 3D volume data(obj format)to compensate for the deficiency of the DEM data whereby the 3D internal entity space is not expressed.Additionally,the levels of detailed method can dispatch the data of a large-scale debris flow hazard scene in real time to ensure a realistic 3D visualization.In summary,the proposed methods can be applied to the planning of debris flow prevention engineering and to the simulation of the debris flow prevention process.展开更多
A multi-isotope approach and mixing model were combined to identify spatial and seasonal variations of sources,and their proportional contribution to nitrate in the Hutuo River alluvial-pluvial fan region.The results ...A multi-isotope approach and mixing model were combined to identify spatial and seasonal variations of sources,and their proportional contribution to nitrate in the Hutuo River alluvial-pluvial fan region.The results showed that the NO3- concentration was significantly higher in the Hutuo River valley plain(178.7 mg/L) region than that in the upper and central pluvial fans of the Hutuo River(82.1 mg/L and 71.0 mg/L,respectively)and in the river(17.0 mg/L).Different land use types had no significant effect on the groundwater nitrate concentration.Based on a multi-isotope approach,we confirmed that the main sources of groundwater nitrate in different land use areas were domestic sewage and manure,followed by soil nitrogen,ammonia fertilizer,nitrate fertilizer and rainwater,and there were no significant spatial or seasonal variations.Combining δ^15N-NO3,δ^18O-NO3- and δ^37Cl results can increase the accuracy of traceability.Nitrification could be the most important nitrogen migration and transformation process,and denitrification did not significantly affected the isotopic composition of the nitrate.The SIAR model outputs revealed that the main nitrate pollution sources in groundwater and river water were domestic sewage and manure,accounting for 55.9%-61.0% and 22.6%(dry season),50.3%-60.4% and 34.1%(transition season),42.7%-47.6% and 35.6%(wet season 2016) and 45.9%-46.7% and 38.4%(wet season 2017),respectively.This work suggests that the random discharge and disposal of domestic sewage and manure should be the first target for control in order to prevent further nitrate contamination of the water environment.展开更多
Ge complementary tunneling field-effect transistors（TFETs） are fabricated with the NiGe metal source/drain（S/D） structure. The dopant segregation method is employed to form the NiGe/Ge tunneling junctions of suffi...Ge complementary tunneling field-effect transistors（TFETs） are fabricated with the NiGe metal source/drain（S/D） structure. The dopant segregation method is employed to form the NiGe/Ge tunneling junctions of sufficiently high Schottky barrier heights. As a result, the Ge p-and n-TFETs exhibit decent electrical properties of large ON-state current and steep sub-threshold slope（S factor）. Especially, I_d of 0.2 μA/μm is revealed at V_g-V_（th） = V_d = ±0.5 V for Ge pTFETs,with the S factor of 28 mV/dec at 7 K.展开更多
Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noti...Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noticeable. Urban administrators and decision-makers seek modern methods and technology to provide information support for urban growth. Recently, with the fast development of high-resolution sensor technology, more relevant data can be obtained, which is an advantage in studying the sustainable development of urban land-use. However, these data are only information sources and are a mixture of ＂information＂ and ＂noise＂. Processing, analysis and information extraction from remote sensing data is necessary to provide useful information. This paper extracts urban land-use information from a high-resolution image by using the multi-feature information of the image objects, and adopts an object-oriented image analysis approach and multi-scale image segmentation technology. A classification and extraction model is set up based on the multi-features of the image objects, in order to contribute to information for reasonable planning and effective management. This new image analysis approach offers a satisfactory solution for extracting information quickly and efficiently.展开更多
Aiming at the problem of multi-label classification, a multi-label classification algorithm based on label-specific features is proposed in this paper. In this algorithm, we compute feature density on the positive and...Aiming at the problem of multi-label classification, a multi-label classification algorithm based on label-specific features is proposed in this paper. In this algorithm, we compute feature density on the positive and negative instances set of each class firstly and then select mk features of high density from the positive and negative instances set of each class, respectively; the intersec- tion is taken as the label-specific features of the corresponding class. Finally, multi-label data are classified on the basis of la- bel-specific features. The algorithm can show the label-specific features of each class. Experiments show that our proposed method, the MLSF algorithm, performs significantly better than the other state-of-the-art multi-label learning approaches.展开更多
Correct identification of water inrush sources is particularly important to prevent and control mine water disasters.Hydrochemical analysis,Fisher discriminant analysis,and geothermal verification analysis were used t...Correct identification of water inrush sources is particularly important to prevent and control mine water disasters.Hydrochemical analysis,Fisher discriminant analysis,and geothermal verification analysis were used to identify and verify the water sources of the multi-aquifer groundwater system in Gubei coal mine,Anhui Province,North China.Results show that hydrochemical water types of the Cenozoic top aquifer included HCO3-Na+K-Ca,HCO3-Na+K-Mg and HCO3-Na+K,and this aquifer was easily distinguishable from other aquifers because of its low concentration of Na++K+and Cl-.The Cenozoic middle and bottom aquifers,the Permian fissure aquifer,and the Taiyuan and Ordovician limestone aquifers were mainly characterized by the Cl-Na+K and SO4-Cl-Na+K or HCO3-Cl-Na+K water types,and their hydrogeochemistries were similar.Therefore,water sources could not be identified via hydrochemical analysis.Fisher model was established based on the hydrogeochemical characteristics,and its discrimination rate was 89.19%.Fisher discrimination results were improved by combining them with the geothermal analysis results,and this combination increased the identification rate to 97.3%and reasonably explained the reasons behind two water samples misjudgments.The methods described herein are also applicable to other mines with similar geological and hydrogeological conditions in North China.展开更多
Traditional seawater desalination requires high amounts of energy, with correspondingly high costs and limited benefits, hindering wider applications of the process. To further improve the comprehensive economic benef...Traditional seawater desalination requires high amounts of energy, with correspondingly high costs and limited benefits, hindering wider applications of the process. To further improve the comprehensive economic benefits of seawater desalination, the desalination load can be combined with renewable energy sources such as solar energy, wind energy, and ocean energy or with the power grid to ensure its effective regulation. Utilizing energy internet(EI) technology, energy balance demand of the regional power grid, and coordinated control between coastal multi-source multi-load and regional distribution network with desalination load is reviewed herein. Several key technologies, including coordinated control of coastal multi-source multi-load system with seawater desalination load, flexible interaction between seawater desalination and regional distribution network, and combined control of coastal multi-source multi-load storage system with seawater desalination load, are discussed in detail. Adoption of the flexible interaction between seawater desalination and regional distribution networks is beneficial for solving water resource problems, improving the ability to dissipate distributed renewable energy, balancing and increasing grid loads, improving the safety and economy of coastal power grids, and achieving coordinated and comprehensive application of power grids, renewable energy sources, and coastal loads.展开更多
In order to estimate vehicular queue length at signalized intersections accurately and overcome the shortcomings and restrictions of existing studies especially those based on shockwave theory,a new methodology is pre...In order to estimate vehicular queue length at signalized intersections accurately and overcome the shortcomings and restrictions of existing studies especially those based on shockwave theory,a new methodology is presented for estimating vehicular queue length using data from both point detectors and probe vehicles. The methodology applies the shockwave theory to model queue evolution over time and space. Using probe vehicle locations and times as well as point detector measured traffic states,analytical formulations for calculating the maximum and minimum( residual) queue length are developed. The proposed methodology is verified using ground truth data collected from numerical experiments conducted in Shanghai,China. It is found that the methodology has a mean absolute percentage error of 17. 09%,which is reasonably effective in estimating the queue length at traffic signalized intersections. Limitations of the proposed models and algorithms are also discussed in the paper.展开更多
基金supported by the National Major Scientific and Technological Infrastructure Project“Space Environment Simulation and Research Infrastructure”financially supported in part by the National Natural Science Foundation of China(No.52275241)the Fund for National Key Laboratory of Space Environment and Matter Behaviors(No.2023059)。
文摘0 INTRODUCTION The lunar surface lacks an atmosphere and is continuously subjected to a combination of space weathering factors such as cosmic rays,solar wind,and micrometeorite impacts,forming a several-meter-thick lunar regolith(Sorokin et al.,2020).
基金This work was funded by the National Natural Science Foundation of China(Grant No.62172132)Public Welfare Technology Research Project of Zhejiang Province(Grant No.LGF21F020014)the Opening Project of Key Laboratory of Public Security Information Application Based on Big-Data Architecture,Ministry of Public Security of Zhejiang Police College(Grant No.2021DSJSYS002).
文摘The widespread availability of digital multimedia data has led to a new challenge in digital forensics.Traditional source camera identification algorithms usually rely on various traces in the capturing process.However,these traces have become increasingly difficult to extract due to wide availability of various image processing algorithms.Convolutional Neural Networks(CNN)-based algorithms have demonstrated good discriminative capabilities for different brands and even different models of camera devices.However,their performances is not ideal in case of distinguishing between individual devices of the same model,because cameras of the same model typically use the same optical lens,image sensor,and image processing algorithms,that result in minimal overall differences.In this paper,we propose a camera forensics algorithm based on multi-scale feature fusion to address these issues.The proposed algorithm extracts different local features from feature maps of different scales and then fuses them to obtain a comprehensive feature representation.This representation is then fed into a subsequent camera fingerprint classification network.Building upon the Swin-T network,we utilize Transformer Blocks and Graph Convolutional Network(GCN)modules to fuse multi-scale features from different stages of the backbone network.Furthermore,we conduct experiments on established datasets to demonstrate the feasibility and effectiveness of the proposed approach.
基金supported by the National Natural Science Foundation of China(No.62241109)the Tianjin Science and Technology Commissioner Project(No.20YDTPJC01110)。
文摘An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyramid network(FPN)structure of the original YOLOv8 mode is replaced by the generalized-FPN(GFPN)structure in GiraffeDet to realize the"cross-layer"and"cross-scale"adaptive feature fusion,to enrich the semantic information and spatial information on the feature map to improve the target detection ability of the model.Secondly,a pyramid-pool module of multi atrous spatial pyramid pooling(MASPP)is designed by using the idea of atrous convolution and feature pyramid structure to extract multi-scale features,so as to improve the processing ability of the model for multi-scale objects.The experimental results show that the detection accuracy of the improved YOLOv8 model on DIOR dataset is 92%and mean average precision(mAP)is 87.9%,respectively 3.5%and 1.7%higher than those of the original model.It is proved the detection and classification ability of the proposed model on multi-dimensional optical remote sensing target has been improved.
基金supported by the National Natural Science Foundation of China(62302167,62477013)Natural Science Foundation of Shanghai(No.24ZR1456100)+1 种基金Science and Technology Commission of Shanghai Municipality(No.24DZ2305900)the Shanghai Municipal Special Fund for Promoting High-Quality Development of Industries(2211106).
文摘Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in images.Obtaining class-specific precise representations at different scales is a key aspect of feature representation.However,existing methods often rely on the single-scale deep feature,neglecting shallow and deeper layer features,which poses challenges when predicting objects of varying scales within the same image.Although some studies have explored multi-scale features,they rarely address the flow of information between scales or efficiently obtain class-specific precise representations for features at different scales.To address these issues,we propose a two-stage,three-branch Transformer-based framework.The first stage incorporates multi-scale image feature extraction and hierarchical scale attention.This design enables the model to consider objects at various scales while enhancing the flow of information across different feature scales,improving the model’s generalization to diverse object scales.The second stage includes a global feature enhancement module and a region selection module.The global feature enhancement module strengthens interconnections between different image regions,mitigating the issue of incomplete represen-tations,while the region selection module models the cross-modal relationships between image features and labels.Together,these components enable the efficient acquisition of class-specific precise feature representations.Extensive experiments on public datasets,including COCO2014,VOC2007,and VOC2012,demonstrate the effectiveness of our proposed method.Our approach achieves consistent performance gains of 0.3%,0.4%,and 0.2%over state-of-the-art methods on the three datasets,respectively.These results validate the reliability and superiority of our approach for multi-label image classification.
基金The work was carried out within the framework the State assignment of the Federal Agency for Subsoil Use of 27.12.2023№049-00003-24-00a State Assignment of the Sobolev Institute of Geology and Mineralogy,Russian Academy of Sciences(project no.122041400237-8).
文摘This paper presents the morphologic,chemical and other typomorphic characteristics of native gold from four placer deposits(basins of the Lev.Nora,Skalistaya and Golysheva rivers,and Loginova brook),four placer occurrences(basins of the Lagernaya,Nizh.Litke and Prokhodimaya rivers,and Tikhiy brook),and the alluvial deposit of cape Mordovin on Bolshevik island of the Severnaya Zemlya archipelago(Russia).Optical microscopy,scanning electron microscopy and electron-probe microanalysis were used in this study.Placer gold from the Lagernaya,Golysheva,Nizh.Litke and Skalistaya rivers,Tikhiy brook and cape Mordovin is characterized by a very high fineness(>988‰)in the rims and a lower fineness(860‰–970‰)in the center.Gold particles from the placers of the Lev.Nora and Prokhodimaya rivers and Loginova brook are low fineness and widely vary in the center(from 647‰to 920‰)and are high fineness(950‰–980‰)in the rims.In some gold particles from the placers of the Lev.Nora and Skalistaya rivers,zones with Cu up to 1.2 wt.%and Hg up to 2.6 wt.%are observed.Titanite,monazite,cobaltite,ulmannite,brannerite,rutile,zircon,Y-xenotime,bismuthite,native bismuth and bismuthinite,garnet(almandine),Cu-or Ni-pyrrhotite were found in the native gold from the Skalistaya and Lev.Nora placers.Native gold from the Skalistaya river placer contains mineral micro-inclusions of cobaltite,Cu,Cd-bearing sphalerite and Fe,Cu-ullmannite.Native gold from the Lev.Nora river placer differs in the presence of brannerite and bismuth minerals.On the basis of the obtained results,available metallogenic characteristics of Bolshevik island and literature data,the following types of primary sources are predicted for these locations:(1)Lev.Nora river deposits of gold-copper rare metal and porphyry gold-copper formations;(2)Skalistaya river deposits of porphyry gold-copper and gold-quartz formation;(3)all the other locations:deposits of gold-quartz and gold-sulfide-quartz formations(hosted in terrigenous carbonaceous complexes).The presence of intermediate reservoirs near some of these locations is probable.
基金supported by the Key Laboratory of Marine Mineral Resources,Ministry of Natural and Resources,Guangzhou(No.KLMMR-20220K02)the Marine Geological Survey Program of China Geological Survey(No.DD20191003)。
文摘Plasma spark sources are widely used in high-resolution seismic exploration.However,research on the excitation mechanism and propagation characteristics of plasma spark sources is very limited.In this study,we elaborated on the excitation process of corona discharge plasma spark source based on indoor experimental data.The electrode spacing has a direct impact on the movement of bubbles.As the spacing between bubbles decreases,they collapsed and fused,thereby suppressing the secondary pulse process.Based on the premise of linear arrangement and equal energy synchronous excitation,the motion equation of multiple bubbles under these conditions was derived,and a calculation method for the near-field wavelet model of plasma spark source was established.We simulated the source signals received in different directions and constructed a spatial wavelet face spectrum.Compared with traditional far-field wavelets,the spatial wavelet facial feature representation method provides a more comprehensive display of the variation characteristics and propagation properties of source wavelets in three-dimensional space.The spatial wavelet variation process of the plasma spark source was analyzed,and the source depth and the virtual reflection path are the main factors affecting the wavelet.The high-frequency properties of plasma electric spark source wavelets lead to their sensitivity to factors such as wave fluctuations,position changes,and environmental noise.Minor changes in collection parameters may result in significant changes in the recorded waveform and final data resolution.So,the facial feature method provides more effective technical support for wavelet evaluation.
基金supported by the National Natural Science Foundation of China (No.52205548)。
文摘To address the issues of unknown target size,blurred edges,background interference and low contrast in infrared small target detection,this paper proposes a method based on density peaks searching and weighted multi-feature local difference.Firstly,an improved high-boost filter is used for preprocessing to eliminate background clutter and high-brightness interference,thereby increasing the probability of capturing real targets in the density peak search.Secondly,a triple-layer window is used to extract features from the area surrounding candidate targets,addressing the uncertainty of small target sizes.By calculating multi-feature local differences between the triple-layer windows,the problems of blurred target edges and low contrast are resolved.To balance the contribution of different features,intra-class distance is used to calculate weights,achieving weighted fusion of multi-feature local differences to obtain the weighted multi-feature local differences of candidate targets.The real targets are then extracted using the interquartile range.Experiments on datasets such as SIRST and IRSTD-IK show that the proposed method is suitable for various complex types and demonstrates good robustness and detection performance.
基金supported by the National Natural Science Foundation of China under Grant 52325402, 52274057, 52074340 and 51874335the National Key R&D Program of China under Grant 2023YFB4104200+1 种基金the Major Scientific and Technological Projects of CNOOC under Grant CCL2022RCPS0397RSN111 Project under Grant B08028。
文摘In the production of the sucker rod well, the dynamic liquid level is important for the production efficiency and safety in the lifting process. It is influenced by multi-source data which need to be combined for the dynamic liquid level real-time calculation. In this paper, the multi-source data are regarded as the different views including the load of the sucker rod and liquid in the wellbore, the image of the dynamometer card and production dynamics parameters. These views can be fused by the multi-branch neural network with special fusion layer. With this method, the features of different views can be extracted by considering the difference of the modality and physical meaning between them. Then, the extraction results which are selected by multinomial sampling can be the input of the fusion layer.During the fusion process, the availability under different views determines whether the views are fused in the fusion layer or not. In this way, not only the correlation between the views can be considered, but also the missing data can be processed automatically. The results have shown that the load and production features fusion(the method proposed in this paper) performs best with the lowest mean absolute error(MAE) 39.63 m, followed by the features concatenation with MAE 42.47 m. They both performed better than only a single view and the lower MAE of the features fusion indicates that its generalization ability is stronger. In contrast, the image feature as a single view contributes little to the accuracy improvement after fused with other views with the highest MAE. When there is data missing in some view, compared with the features concatenation, the multi-view features fusion will not result in the unavailability of a large number of samples. When the missing rate is 10%, 30%, 50% and 80%, the method proposed in this paper can reduce MAE by 5.8, 7, 9.3 and 20.3 m respectively. In general, the multi-view features fusion method proposed in this paper can improve the accuracy obviously and process the missing data effectively, which helps provide technical support for real-time monitoring of the dynamic liquid level in oil fields.
基金supported by National Nature Science Foundation of China (Nos. 61462046 and 61762052)Natural Science Foundation of Jiangxi Province (Nos. 20161BAB202049 and 20161BAB204172)+2 种基金the Bidding Project of the Key Laboratory of Watershed Ecology and Geographical Environment Monitoring, NASG (Nos. WE2016003, WE2016013 and WE2016015)the Science and Technology Research Projects of Jiangxi Province Education Department (Nos. GJJ160741, GJJ170632 and GJJ170633)the Art Planning Project of Jiangxi Province (Nos. YG2016250 and YG2017381)
文摘Image registration is an indispensable component in multi-source remote sensing image processing. In this paper, we put forward a remote sensing image registration method by including an improved multi-scale and multi-direction Harris algorithm and a novel compound feature. Multi-scale circle Gaussian combined invariant moments and multi-direction gray level co-occurrence matrix are extracted as features for image matching. The proposed algorithm is evaluated on numerous multi-source remote sensor images with noise and illumination changes. Extensive experimental studies prove that our proposed method is capable of receiving stable and even distribution of key points as well as obtaining robust and accurate correspondence matches. It is a promising scheme in multi-source remote sensing image registration.
基金supported by the National Basic Research Program of China (2006CB202300)
文摘Geochemical composition characteristics of light oils from the Tertiary in the west of the Chepaizi uplift in the Junggar basin, northwest China, are distinct from those of biodegraded oils derived from the Permian in the study area and crude oils from some adjacent oil fields such as the Chepaizi and Xiaoguai oilfields. Oil source corre-lation shows that light oils in the study area have similar n-alkane and isoprenoid distribution patterns and carbon isotope compositions with the coal-derived oils from the Jurassic, and display obvious discrepancy on biomarker composition characteristics with the Cretaceous source rock extracts, inferring that they are probably the mixed oils from the Jurassic coal measures and Cretaceous source rocks. In this study, combined with the geochemical data of coal-derived oils from the Jurassic and Cretaceous source rocks or crude oils from the Cretaceous, the source and commingling features of the Tertiary crude oils of Well Pai 2 and Well Pai 8 were investigated. The proportion of the two sources in the mixed crude oils was estimated, and the hydrocarbon accumulation pattern of reservoirs in the study area was established.
文摘In the video-based surveillance application, moving shadows can affect the correct localization and detection of moving objects. This paper aims to present a method for shadow detection and suppression used for moving visual object detection. The major novelty of the shadow suppression is the integration of several features including photometric invariant color feature, motion edge feature, and spatial feature etc. By modifying process for false shadow detected, the averaging detection rate of moving object reaches above 90% in the test of Hall-Monitor sequence.
基金This work was supported by the National Natural Science Foundation of China(U2133208,U20A20161).
文摘With the popularization of the Internet and the development of technology,cyber threats are increasing day by day.Threats such as malware,hacking,and data breaches have had a serious impact on cybersecurity.The network security environment in the era of big data presents the characteristics of large amounts of data,high diversity,and high real-time requirements.Traditional security defense methods and tools have been unable to cope with the complex and changing network security threats.This paper proposes a machine-learning security defense algorithm based on metadata association features.Emphasize control over unauthorized users through privacy,integrity,and availability.The user model is established and the mapping between the user model and the metadata of the data source is generated.By analyzing the user model and its corresponding mapping relationship,the query of the user model can be decomposed into the query of various heterogeneous data sources,and the integration of heterogeneous data sources based on the metadata association characteristics can be realized.Define and classify customer information,automatically identify and perceive sensitive data,build a behavior audit and analysis platform,analyze user behavior trajectories,and complete the construction of a machine learning customer information security defense system.The experimental results show that when the data volume is 5×103 bit,the data storage integrity of the proposed method is 92%.The data accuracy is 98%,and the success rate of data intrusion is only 2.6%.It can be concluded that the data storage method in this paper is safe,the data accuracy is always at a high level,and the data disaster recovery performance is good.This method can effectively resist data intrusion and has high air traffic control security.It can not only detect all viruses in user data storage,but also realize integrated virus processing,and further optimize the security defense effect of user big data.
基金support provided by the National Natural Sciences Foundation of China(No.41771419)Student Research Training Program of Southwest Jiaotong University(No.191510,No.182117)。
文摘The Digital Elevation Model(DEM)data of debris flow prevention engineering are the boundary of a debris flow prevention simulation,which provides accurate and reliable DEM data and is a key consideration in debris flow prevention simulations.Thus,this paper proposes a multi-source data fusion method.First,we constructed 3D models of debris flow prevention using virtual reality technology according to the relevant specifications.The 3D spatial data generated by 3D modeling were converted into DEM data for debris flow prevention engineering.Then,the accuracy and applicability of the DEM data were verified by the error analysis testing and fusion testing of the debris flow prevention simulation.Finally,we propose the Levels of Detail algorithm based on the quadtree structure to realize the visualization of a large-scale disaster prevention scene.The test results reveal that the data fusion method controlled the error rate of the DEM data of the debris flow prevention engineering within an allowable range and generated 3D volume data(obj format)to compensate for the deficiency of the DEM data whereby the 3D internal entity space is not expressed.Additionally,the levels of detailed method can dispatch the data of a large-scale debris flow hazard scene in real time to ensure a realistic 3D visualization.In summary,the proposed methods can be applied to the planning of debris flow prevention engineering and to the simulation of the debris flow prevention process.
基金supported by the Natural Science Foundation of Hebei Province of China,China (No.D2015504008)the Fundamental Research Funds for the Institute of Hydrogeology and Environmental Geology,Chinese Academy of Geological Sciences,China (No.SK201707)Projects of China Geological Survey,China (No.DD20190331).
文摘A multi-isotope approach and mixing model were combined to identify spatial and seasonal variations of sources,and their proportional contribution to nitrate in the Hutuo River alluvial-pluvial fan region.The results showed that the NO3- concentration was significantly higher in the Hutuo River valley plain(178.7 mg/L) region than that in the upper and central pluvial fans of the Hutuo River(82.1 mg/L and 71.0 mg/L,respectively)and in the river(17.0 mg/L).Different land use types had no significant effect on the groundwater nitrate concentration.Based on a multi-isotope approach,we confirmed that the main sources of groundwater nitrate in different land use areas were domestic sewage and manure,followed by soil nitrogen,ammonia fertilizer,nitrate fertilizer and rainwater,and there were no significant spatial or seasonal variations.Combining δ^15N-NO3,δ^18O-NO3- and δ^37Cl results can increase the accuracy of traceability.Nitrification could be the most important nitrogen migration and transformation process,and denitrification did not significantly affected the isotopic composition of the nitrate.The SIAR model outputs revealed that the main nitrate pollution sources in groundwater and river water were domestic sewage and manure,accounting for 55.9%-61.0% and 22.6%(dry season),50.3%-60.4% and 34.1%(transition season),42.7%-47.6% and 35.6%(wet season 2016) and 45.9%-46.7% and 38.4%(wet season 2017),respectively.This work suggests that the random discharge and disposal of domestic sewage and manure should be the first target for control in order to prevent further nitrate contamination of the water environment.
基金Supported by the National Natural Science Foundation of China under Grant No 61504120the Zhejiang Provincial Natural Science Foundation of China under Grant No LR18F040001the Fundamental Research Funds for the Central Universities
文摘Ge complementary tunneling field-effect transistors（TFETs） are fabricated with the NiGe metal source/drain（S/D） structure. The dopant segregation method is employed to form the NiGe/Ge tunneling junctions of sufficiently high Schottky barrier heights. As a result, the Ge p-and n-TFETs exhibit decent electrical properties of large ON-state current and steep sub-threshold slope（S factor）. Especially, I_d of 0.2 μA/μm is revealed at V_g-V_（th） = V_d = ±0.5 V for Ge pTFETs,with the S factor of 28 mV/dec at 7 K.
基金The paper is supported by the Research Foundation for OutstandingYoung Teachers , China University of Geosciences ( Wuhan) ( No .CUGQNL0616) Research Foundationfor State Key Laboratory of Geo-logical Processes and Mineral Resources ( No . MGMR2002-02)Hubei Provincial Depart ment of Education (B) .
文摘Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noticeable. Urban administrators and decision-makers seek modern methods and technology to provide information support for urban growth. Recently, with the fast development of high-resolution sensor technology, more relevant data can be obtained, which is an advantage in studying the sustainable development of urban land-use. However, these data are only information sources and are a mixture of ＂information＂ and ＂noise＂. Processing, analysis and information extraction from remote sensing data is necessary to provide useful information. This paper extracts urban land-use information from a high-resolution image by using the multi-feature information of the image objects, and adopts an object-oriented image analysis approach and multi-scale image segmentation technology. A classification and extraction model is set up based on the multi-features of the image objects, in order to contribute to information for reasonable planning and effective management. This new image analysis approach offers a satisfactory solution for extracting information quickly and efficiently.
基金Supported by the Opening Fund of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education (93K-17-2010-K02)the Opening Fund of Key Discipline of Computer Soft-Ware and Theory of Zhejiang Province at Zhejiang Normal University (ZSDZZZZXK05)
文摘Aiming at the problem of multi-label classification, a multi-label classification algorithm based on label-specific features is proposed in this paper. In this algorithm, we compute feature density on the positive and negative instances set of each class firstly and then select mk features of high density from the positive and negative instances set of each class, respectively; the intersec- tion is taken as the label-specific features of the corresponding class. Finally, multi-label data are classified on the basis of la- bel-specific features. The algorithm can show the label-specific features of each class. Experiments show that our proposed method, the MLSF algorithm, performs significantly better than the other state-of-the-art multi-label learning approaches.
基金financially supported by the National Natural Science Foundation of China (Grant No. 41572147)
文摘Correct identification of water inrush sources is particularly important to prevent and control mine water disasters.Hydrochemical analysis,Fisher discriminant analysis,and geothermal verification analysis were used to identify and verify the water sources of the multi-aquifer groundwater system in Gubei coal mine,Anhui Province,North China.Results show that hydrochemical water types of the Cenozoic top aquifer included HCO3-Na+K-Ca,HCO3-Na+K-Mg and HCO3-Na+K,and this aquifer was easily distinguishable from other aquifers because of its low concentration of Na++K+and Cl-.The Cenozoic middle and bottom aquifers,the Permian fissure aquifer,and the Taiyuan and Ordovician limestone aquifers were mainly characterized by the Cl-Na+K and SO4-Cl-Na+K or HCO3-Cl-Na+K water types,and their hydrogeochemistries were similar.Therefore,water sources could not be identified via hydrochemical analysis.Fisher model was established based on the hydrogeochemical characteristics,and its discrimination rate was 89.19%.Fisher discrimination results were improved by combining them with the geothermal analysis results,and this combination increased the identification rate to 97.3%and reasonably explained the reasons behind two water samples misjudgments.The methods described herein are also applicable to other mines with similar geological and hydrogeological conditions in North China.
基金supported by the State Grid Science and Technology Project, “Study on Multi-source and Multiload Coordination and Optimization Technology Considering Desalination of Sea Water” (No. SGTJDK00DWJS1800011)
文摘Traditional seawater desalination requires high amounts of energy, with correspondingly high costs and limited benefits, hindering wider applications of the process. To further improve the comprehensive economic benefits of seawater desalination, the desalination load can be combined with renewable energy sources such as solar energy, wind energy, and ocean energy or with the power grid to ensure its effective regulation. Utilizing energy internet(EI) technology, energy balance demand of the regional power grid, and coordinated control between coastal multi-source multi-load and regional distribution network with desalination load is reviewed herein. Several key technologies, including coordinated control of coastal multi-source multi-load system with seawater desalination load, flexible interaction between seawater desalination and regional distribution network, and combined control of coastal multi-source multi-load storage system with seawater desalination load, are discussed in detail. Adoption of the flexible interaction between seawater desalination and regional distribution networks is beneficial for solving water resource problems, improving the ability to dissipate distributed renewable energy, balancing and increasing grid loads, improving the safety and economy of coastal power grids, and achieving coordinated and comprehensive application of power grids, renewable energy sources, and coastal loads.
基金Sponsored by the National Natural Science Foundation of China(Grant No.51138003)
文摘In order to estimate vehicular queue length at signalized intersections accurately and overcome the shortcomings and restrictions of existing studies especially those based on shockwave theory,a new methodology is presented for estimating vehicular queue length using data from both point detectors and probe vehicles. The methodology applies the shockwave theory to model queue evolution over time and space. Using probe vehicle locations and times as well as point detector measured traffic states,analytical formulations for calculating the maximum and minimum( residual) queue length are developed. The proposed methodology is verified using ground truth data collected from numerical experiments conducted in Shanghai,China. It is found that the methodology has a mean absolute percentage error of 17. 09%,which is reasonably effective in estimating the queue length at traffic signalized intersections. Limitations of the proposed models and algorithms are also discussed in the paper.
