Optimizing Spatial Relationships in GCN to Improve the Classification Accuracy of Remote Sensing Images

Semantic segmentation of remote sensing images is one of the core tasks of remote sensing image interpretation.With the continuous develop-ment of artificial intelligence technology,the use of deep learning methods for interpreting remote-sensing images has matured.Existing neural networks disregard the spatial relationship between two targets in remote sensing images.Semantic segmentation models that combine convolutional neural networks(CNNs)and graph convolutional neural networks(GCNs)cause a lack of feature boundaries,which leads to the unsatisfactory segmentation of various target feature boundaries.In this paper,we propose a new semantic segmentation model for remote sensing images(called DGCN hereinafter),which combines deep semantic segmentation networks(DSSN)and GCNs.In the GCN module,a loss function for boundary information is employed to optimize the learning of spatial relationship features between the target features and their relationships.A hierarchical fusion method is utilized for feature fusion and classification to optimize the spatial relationship informa-tion in the original feature information.Extensive experiments on ISPRS 2D and DeepGlobe semantic segmentation datasets show that compared with the existing semantic segmentation models of remote sensing images,the DGCN significantly optimizes the segmentation effect of feature boundaries,effectively reduces the noise in the segmentation results and improves the segmentation accuracy,which demonstrates the advancements of our model.

Contamination Identification of Lentinula Edodes Logs Based on Improved YOLOv5s

In order to improve the accuracy and efficiency of Lentinula edodes logs contamination identification,an improved YOLOv5s contamination identification model for Lentinula edodes logs(YOLOv5s-CGGS)is proposed in this paper.Firstly,a CA(coordinate attention)mechanism is introduced in the feature extraction network of YOLOv5s to improve the identifiability of Lentinula edodes logs contamination and the accuracy of target localiza-tion.Then,the CIoU(Complete-IOU)loss function is replaced by an SIoU(SCYLLA-IoU)loss function to improve the model’s convergence speed and inference accuracy.Finally,the GSConv and GhostConv modules are used to improve and optimize the feature fusion network to improve identification efficiency.The method in this paper achieves values of 97.83%,97.20%,and 98.20%in precision,recall,and mAP@0.5,which are 2.33%,3.0%,and 1.5%better than YOLOv5s,respectively.mAP@0.5 is better than YOLOv4,Ghost-YOLOv4,and Mobilenetv3-YOLOv4(improved by 4.61%,5.16%,and 6.04%,respectively),and the FPS increased by two to three times.

Formation mechanism of co-axial grain boundaries in a Mg alloy

Due to the insufficient slip systems in hexagonal close-packed structure,twinning is frequently activated to support stable plastic deformation of Mg alloy.In this work,we found four typical twin-like interfaces with misorientations of 102°,109°,142°and 149°,respectively,which had not only a shared[1120]zone axis of neighboring grains,but also overlapped diffraction spots similar to twins.However,highresolution transmission electron microscope(HRTEM)analysis revealed that the interfaces in real space deviated from the supposed twinning planes in reciprocal space,i.e.their overlapped diffraction spots.We clarified that the incoherent interfaces were co-axial grain boundaries(CGBs).Additionally,a special angle ofθ,close to 90°,between the interface and one side of basal plane,was frequently formed in CGBs.We proposed that interaction of multiple twinning contributes to the formation of CGBs,and theθis formed due to alternative tensile and compression twinning under a uniaxial loading.

Three-Dimensional Interferometric ISAR Sensors Imaging for the Ship Target with Two-Dimensional Sparsity

There are great challenges for traditional three-dimensional( 3-D) interferometric inverse synthetic aperture radar( In ISAR) imaging algorithms of ship targets w ith 2-D sparsity in actual radar imaging system. To deal w ith this problem,a novel 3-D In ISAR imaging method is proposed in this paper.First,the high-precision gradient adaptive algorithm w as adopted to reconstruct the echoes in range dimension. Then the method of minimizing the entropy of the average range profile w as applied to estimate the parameters w hich are used to compensate translation components of the received echoes. Besides,the phase adjustment and image coregistration of the sparse echoes w ere achieved at the same time through the approach of the joint phase autofocus. Finally,the 3-D geometry coordinates of the ship target w ith 2-D sparsity w ere reconstructed by combining the range measurement and interferometric processing of the ISAR images. Simulation experiments w ere carried out to verify the practicability and effectiveness of the algorithm in the case that the received echoes are in 2-D sparsity.

The Binarity of Early-type Stars from LAMOST medium-resolution Spectroscopic Survey

Massive binaries play significant roles in many fields.Identifying massive stars,particularly massive binaries,is of great importance.In this paper,by adopting the technique of measuring the equivalent widths of several spectral lines,we identified 9382 early-type stars from the LAMOST medium-resolution survey and divided the sample into four groups,T1(~O-B4),T2(~B5),T3(~B7)and T4(~B8-A).The relative radial velocities RVrelwere calculated using Maximum Likelihood Estimation.The stars with significant changes of RVreland at least larger than 15.57 km s-1 were identified as spectroscopic binaries.We found that the observed spectroscopic binary fractions for the four groups are 24.6%±0.5%,20.8%±0.6%,13.7%±0.3%and 7.4%±0.3%,respectively.Assuming that orbital period(P)and mass ratio(q)have intrinsic distributions as f(P)∝Pπ(1<P<1000 days)and f(q)∝qκ(0.1<q<1),respectively,we conducted a series of Monte-Carlo simulations to correct observational biases for estimating the intrinsic multiplicity properties.The results show that the intrinsic binary fractions for the four groups are 68%±8%,52%±3%,44%±6%and 44%±6%,respectively.The best estimated values forπare-1±0.1,-1.1±0.05,-1.1±0.1 and-0.6±0.05,respectively.Theκcannot be constrained for groups T1 and T2 and is-2.4±0.3 for group T3 and-1.6±0.3 for group T4.We confirmed the relationship of a decreasing trend in binary fractions toward late-type stars.No correlation between the spectral type and orbital period distribution has been found yet,possibly due to the limitation of observational cadence.

Unexpected high-temperature brittleness of a Mg-Gd-Y-Ag alloy

Rare earth(RE)can produce excellent precipitation hardening in Mg alloys.However,when forming a solid solution,it also deteriorates formability,a problem that can usually be overcome by raising deformation temperature.Here we report an unexpected observation of high temperature brittleness in a Mg-Gd-Y-Ag alloy.As the temperature reached 500℃,the formability decreased drastically,leading to severe intergranular fracture under only 0.5% strain.This was caused by failure of grain boundaries,which are weakened by segregated interfacial compounds.

High Strength and Ductility of a MgAg/MgGdYAg/MgAg Sandwiched Plate Produced by High-Pressure Torsion

Due to their unique precipitation behavior,magnesium-rare earth(Mg-RE)alloys exhibit excellent strength and high thermal stability.However,owing to the negative blocking effect of precipitation on dislocation slipping,the plasticity and ductility of Mg-RE alloys become deteriorate after aging treatment.In this work,a novel strategy to improve the combination of strength and ductility by designing a laminate heterostructured Mg alloy is proposed.High-pressure torsion(HPT)processing is employed to fabricate a clean and well-bonded interface between MgGdYAg and MgAg alloys.The two alloys have huge differences in precipitation hardening,and ductility is improved due to two facts.For one thing,the density of the second phases in the MgAg alloy is much lower than that of MgGdYAg alloy;for another,the non-basal〈c+a〉slipping is continuously activated during deformation.Through this mechanism,the uniform elongation of the heterostructured MgAg/MgGdYAg/MgAg alloy is improved to 7.1%.

“竞争型自我呈现”的政治修辞——新媒体时代的国际话语权建构

一国在国际上的形象是“自述”与“他述”相互博弈的产物,很大程度上也是国际话语权竞争的产物。进入21世纪以来,互联网新媒体为各国借助政治修辞技艺实现“软社会控制”、谋求国际受众认可提供了更广阔的舞台,从而推动了修辞理论的发展。从美、俄在四类不同情境中自我呈现的竞争型修辞战略与策略分析可见,在新媒体环境下,一方面,国际行为体需要结合竞争各方的身份状态、行为特质等选择适当的修辞,对双方的形象进行管控,以实现良好的自我呈现效果;另一方面,在国际话语权的政治修辞竞争中,身份、认同和形象都具有很强的主动建构性,为了在纷繁多变的国际环境中争取更大的话语权,需要更加审慎地思考如何在修辞战略和策略上化被动为主动。

Strengthening and ductilization of laminate dual-phase steels with high martensite content

The steels with excellent strength and ductility are expected to be achieved by tailoring the microstructural features.In this work,laminate dual-phase(DP)steels with high martensite content(laminate HMDP steels)were produced by a combination of warm rolling and intercritical annealing.Influence of rolling strain and annealing temperature on the microstructural evolution and mechanical properties of laminate HMDP steels were systematically studied.The strength of HMDP steels was significantly improved to~1.6 GPa associated with a high uniform elongation of 7%,as long as the laminate structure is maintained.The strengthening and ductilizing mechanisms of laminate HMDP steels are discussed based on the influence of laminate structure and the high martensite content,which promote the development of internal stresses and can be correlated to the Bauschinger effect as measured by the cyclic loadingunloading-reloading experiments.Detailed transmission electron microscopy(TEM)observation was applied to characterize the dislocation structure in the deformed ferrite.

Mechanical property comparisons between CrCoNi medium-entropy alloy and 316 stainless steels

We systematically compared the mechanical properties of CrCoNi,a recently emerged prototypical medium-entropy alloy(MEA)with face-centered-cubic(FCC)structure,with hallmark FCC alloys,in particular,the well-known austenitic 316 L and 316 LN stainless steels,which are also concentrated singlephase FCC solid solutions and arguably next-of-kin to the MEAs.The tensile and impact properties,across the temperatures range from 373 K to 4.2 K,as well as fracture toughness at 298 K and 77 K,were documented.From room temperature to cryogenic temperature,all three alloys exhibited similarly good mechanical properties;CrCoNi increased its tensile uniform elongation and fracture toughness,which was different from the decreasing trend of the 316 L and 316 LN.On the other hand,the stainless steels showed higher fracture toughness than CrCoNi at all temperatures.To explain the differences in macroscopic mechanical properties of the three alloys,microstructural hardening mechanisms were surveyed.CrCoNi MEA relied on abundant mechanical twinning on the nanoscale,while martensitic transformation was dominant in 316 L at low temperatures.The deformation mechanisms in the plastic zone ahead of the propagating crack in impact and fracture toughness tests were also analyzed and compared for the three alloys.