引入上下文信息和Attention Gate的GUS-YOLO遥感目标检测算法

目前基于通用YOLO系列的遥感目标检测算法存在并未充分利用图像的全局上下文信息,在特征融合金字塔部分并未充分考虑缩小融合特征之间的语义鸿沟、抑制冗余信息干扰的缺点。在结合YOLO算法优点的基础上提出GUS-YOLO算法,其拥有一个能够充分利用全局上下文信息的骨干网络Global Backbone。除此之外,该算法在融合特征金字塔自顶向下的结构中引入Attention Gate模块,可以突出必要的特征信息,抑制冗余信息。另外,为Attention Gate模块设计了最佳的网络结构,提出了网络的特征融合结构U-Net。最后,为克服ReLU函数可能导致模型梯度不再更新的问题,该算法将Attention Gate模块的激活函数升级为可学习的SMU激活函数,提高模型鲁棒性。在NWPU VHR-10遥感数据集上,该算法相较于YOLOV7算法取得宽松指标mAP^(0.50)1.64个百分点和严格指标mAP^(0.75)9.39个百分点的性能提升。相较于目前主流的七种检测算法,该算法取得较好的检测性能。

A gated recurrent unit model to predict Poisson’s ratio using deep learning

Static Poisson’s ratio(vs)is crucial for determining geomechanical properties in petroleum applications,namely sand production.Some models have been used to predict vs;however,the published models were limited to specific data ranges with an average absolute percentage relative error(AAPRE)of more than 10%.The published gated recurrent unit(GRU)models do not consider trend analysis to show physical behaviors.In this study,we aim to develop a GRU model using trend analysis and three inputs for predicting n s based on a broad range of data,n s(value of 0.1627-0.4492),bulk formation density(RHOB)(0.315-2.994 g/mL),compressional time(DTc)(44.43-186.9 μs/ft),and shear time(DTs)(72.9-341.2μ s/ft).The GRU model was evaluated using different approaches,including statistical error an-alyses.The GRU model showed the proper trends,and the model data ranges were wider than previous ones.The GRU model has the largest correlation coefficient(R)of 0.967 and the lowest AAPRE,average percent relative error(APRE),root mean square error(RMSE),and standard deviation(SD)of 3.228%,1.054%,4.389,and 0.013,respectively,compared to other models.The GRU model has a high accuracy for the different datasets:training,validation,testing,and the whole datasets with R and AAPRE values were 0.981 and 2.601%,0.966 and 3.274%,0.967 and 3.228%,and 0.977 and 2.861%,respectively.The group error analyses of all inputs show that the GRU model has less than 5% AAPRE for all input ranges,which is superior to other models that have different AAPRE values of more than 10% at various ranges of inputs.

Current-collapse suppression and leakage-current decrease in AlGaN/GaN HEMT by sputter-TaN gate-dielectric layer

In this paper, we explore the electrical characteristics of high-electron-mobility transistors(HEMTs) using a TaN/AlGaN/GaN metal insulating semiconductor(MIS) structure. The high-resistance tantalum nitride(TaN) film prepared by magnetron sputtering as the gate dielectric layer of the device achieved an effective reduction of electronic states at the TaN/AlGaN interface, and reducing the gate leakage current of the MIS HEMT, its performance was enhanced. The HEMT exhibited a low gate leakage current of 2.15 × 10^(-7) mA/mm and a breakdown voltage of 1180 V. Furthermore, the MIS HEMT displayed exceptional operational stability during dynamic tests, with dynamic resistance remaining only 1.39 times even under 400 V stress.

Gates joint locally connected network for accurate and robust reconstruction in optical molecular tomography

Optical molecular tomography(OMT)is a potential pre-clinical molecular imaging technique with applications in a variety of biomedical areas,which can provide non-invasive quantitative three-dimensional(3D)information regarding tumor distribution in living animals.The construction of optical transmission models and the application of reconstruction algorithms in traditional model-based reconstruction processes have affected the reconstruction results,resulting in problems such as low accuracy,poor robustness,and long-time consumption.Here,a gates joint locally connected network(GLCN)method is proposed by establishing the mapping relationship between the inside source distribution and the photon density on surface directly,thus avoiding the extra time consumption caused by iteration and the reconstruction errors caused by model inaccuracy.Moreover,gates module was composed of the concatenation and multiplication operators of three different gates.It was embedded into the network aiming at remembering input surface photon density over a period and allowing the network to capture neurons connected to the true source selectively by controlling three different gates.To evaluate the performance of the proposed method,numerical simulations were conducted,whose results demonstrated good performance in terms of reconstruction positioning accuracy and robustness.

Remote entangling gate between a quantum dot spin and a transmon qubit mediated by microwave photons

Spin qubits and superconducting qubits are promising candidates for realizing solid-state quantum information processors.Designing a hybrid architecture that combines the advantages of different qubits on the same chip is a highly desirable but challenging goal.Here we propose a hybrid architecture that utilizes a high-impedance SQUID array resonator as a quantum bus,thereby coherently coupling different solid-state qubits.We employ a resonant exchange spin qubit hosted in a triple quantum dot and a superconducting transmon qubit.Since this hybrid system is highly tunable,it can operate in a dispersive regime,where the interaction between the different qubits is mediated by virtual photons.By utilizing such interactions,entangling gate operations between different qubits can be realized in a short time of 30 ns with a fidelity of up to 96.5%under realistic parameter conditions.Further utilizing this interaction,remote entangled state between different qubits can be prepared and is robust to perturbations of various parameters.These results pave the way for exploring efficient fault-tolerant quantum computation on hybrid quantum architecture platforms.

Gate Feature Interaction Network for Relation Prediction in Knowledge Graph

Recently,many knowledge graph embedding models for knowledge graph completion have been proposed,ranging from the initial translation-based model such as TransE to recent CNN-based models such as ConvE.These models fill in the missing relations between entities by focusing on capturing the representation features to further complete the existing knowledge graph(KG).However,the above KG-based relation prediction research ignores the interaction information among entities in KG.To solve this problem,this work proposes a novel model called Gate Feature Interaction Network(GFINet)with a weighted loss function that takes the benefit of interaction information and deep expressive features together.Specifically,the proposed GFINet consists of a gate convolution block and an interaction attention module,corresponding to catching deep expressive features and interaction information based on these valid features respectively.Our method establishes state-of-the-art experimental results on the standard datasets for knowledge graph completion.In addition,we make ablation experiments to verify the effectiveness of the gate convolution block and the interaction attention module.

Fake News Detection Based on Cross-Modal Message Aggregation and Gated Fusion Network

Social media has become increasingly significant in modern society,but it has also turned into a breeding ground for the propagation of misleading information,potentially causing a detrimental impact on public opinion and daily life.Compared to pure text content,multmodal content significantly increases the visibility and share ability of posts.This has made the search for efficient modality representations and cross-modal information interaction methods a key focus in the field of multimodal fake news detection.To effectively address the critical challenge of accurately detecting fake news on social media,this paper proposes a fake news detection model based on crossmodal message aggregation and a gated fusion network(MAGF).MAGF first uses BERT to extract cumulative textual feature representations and word-level features,applies Faster Region-based ConvolutionalNeuralNetwork(Faster R-CNN)to obtain image objects,and leverages ResNet-50 and Visual Geometry Group-19(VGG-19)to obtain image region features and global features.The image region features and word-level text features are then projected into a low-dimensional space to calculate a text-image affinity matrix for cross-modal message aggregation.The gated fusion network combines text and image region features to obtain adaptively aggregated features.The interaction matrix is derived through an attention mechanism and further integrated with global image features using a co-attention mechanism to producemultimodal representations.Finally,these fused features are fed into a classifier for news categorization.Experiments were conducted on two public datasets,Twitter and Weibo.Results show that the proposed model achieves accuracy rates of 91.8%and 88.7%on the two datasets,respectively,significantly outperforming traditional unimodal and existing multimodal models.

Study of a Hydraulic Jump in an Asymmetric Trapezoidal Channel with Different Sluice Gates

In this study,the main properties of the hydraulic jump in an asymmetric trapezoidal flume are analyzed experimentally,including the so-called sequent depths,characteristic lengths,and efficiency.In particular,an asymmetric trapezoidal flume with a length of 7 m and a width of 0.304 m is considered,with the bottom of the flume transversely inclined at an angle of m=0.296 and vertical lateral sides.The corresponding inflow Froude number is allowed to range in the interval(1.40<F1<6.11).The properties of this jump are compared to those of hydraulic jumps in channels with other types of cross-sections.A relationship for calculating hydraulic jump efficiency is proposed for the considered flume.For F1>5,the hydraulic jump is found to be more effective than that occurring in triangular and symmetric trapezoidal channels.Also,when■mes>8 and■>5,the hydraulic jump in the asymmetrical trapezoidal channel downstream of a parallelogram sluice gate is completely formed as opposed to the situation where a triangular sluice is considered.

Gated Neural Network-Based Unsteady Aerodynamic Modeling for Large Angles of Attack

Modeling of unsteady aerodynamic loads at high angles of attack using a small amount of experimental or simulation data to construct predictive models for unknown states can greatly improve the efficiency of aircraft unsteady aerodynamic design and flight dynamics analysis.In this paper,aiming at the problems of poor generalization of traditional aerodynamic models and intelligent models,an intelligent aerodynamic modeling method based on gated neural units is proposed.The time memory characteristics of the gated neural unit is fully utilized,thus the nonlinear flow field characterization ability of the learning and training process is enhanced,and the generalization ability of the whole prediction model is improved.The prediction and verification of the model are carried out under the maneuvering flight condition of NACA0015 airfoil.The results show that the model has good adaptability.In the interpolation prediction,the maximum prediction error of the lift and drag coefficients and the moment coefficient does not exceed 10%,which can basically represent the variation characteristics of the entire flow field.In the construction of extrapolation models,the training model based on the strong nonlinear data has good accuracy for weak nonlinear prediction.Furthermore,the error is larger,even exceeding 20%,which indicates that the extrapolation and generalization capabilities need to be further optimized by integrating physical models.Compared with the conventional state space equation model,the proposed method can improve the extrapolation accuracy and efficiency by 78%and 60%,respectively,which demonstrates the applied potential of this method in aerodynamic modeling.

Aerial target threat assessment based on gated recurrent unit and self-attention mechanism

Aerial threat assessment is a crucial link in modern air combat, whose result counts a great deal for commanders to make decisions. With the consideration that the existing threat assessment methods have difficulties in dealing with high dimensional time series target data, a threat assessment method based on self-attention mechanism and gated recurrent unit(SAGRU) is proposed. Firstly, a threat feature system including air combat situations and capability features is established. Moreover, a data augmentation process based on fractional Fourier transform(FRFT) is applied to extract more valuable information from time series situation features. Furthermore, aiming to capture key characteristics of battlefield evolution, a bidirectional GRU and SA mechanisms are designed for enhanced features.Subsequently, after the concatenation of the processed air combat situation and capability features, the target threat level will be predicted by fully connected neural layers and the softmax classifier. Finally, in order to validate this model, an air combat dataset generated by a combat simulation system is introduced for model training and testing. The comparison experiments show the proposed model has structural rationality and can perform threat assessment faster and more accurately than the other existing models based on deep learning.

A HybridManufacturing ProcessMonitoringMethod Using Stacked Gated Recurrent Unit and Random Forest

This study proposed a new real-time manufacturing process monitoring method to monitor and detect process shifts in manufacturing operations.Since real-time production process monitoring is critical in today’s smart manufacturing.The more robust the monitoring model,the more reliable a process is to be under control.In the past,many researchers have developed real-time monitoring methods to detect process shifts early.However,thesemethods have limitations in detecting process shifts as quickly as possible and handling various data volumes and varieties.In this paper,a robust monitoring model combining Gated Recurrent Unit(GRU)and Random Forest(RF)with Real-Time Contrast(RTC)called GRU-RF-RTC was proposed to detect process shifts rapidly.The effectiveness of the proposed GRU-RF-RTC model is first evaluated using multivariate normal and nonnormal distribution datasets.Then,to prove the applicability of the proposed model in a realmanufacturing setting,the model was evaluated using real-world normal and non-normal problems.The results demonstrate that the proposed GRU-RF-RTC outperforms other methods in detecting process shifts quickly with the lowest average out-of-control run length(ARL1)in all synthesis and real-world problems under normal and non-normal cases.The experiment results on real-world problems highlight the significance of the proposed GRU-RF-RTC model in modern manufacturing process monitoring applications.The result reveals that the proposed method improves the shift detection capability by 42.14%in normal and 43.64%in gamma distribution problems.

预测轴承寿命的gate递归单元特征融合域自适应模型

采用现有的数据驱动模型对不同工况下的轴承剩余使用寿命(RUL)进行预测时,精度会大幅下降。针对这一问题,提出了一种基于门控递归单元特征融合领域自适应(GFFDA)模型的轴承RUL预测方法。首先,采用信号分析方法对轴承振动信号进行了特征提取,并采用特征评价的方法选择出了5个最优特征,在最优特征的基础上,采用粒子群算法优化后的支持向量机的方法对轴承的健康阶段进行了划分;然后,选择目标域和源域退化阶段的最优特征子集作为GFFDA模型的输入,采用源域数据对特征提取器和寿命预测模块进行了预训练;最后,更新了目标特征提取器和寿命预测模块,对目标域的RUL进行了预测;并使用西安交通大学的轴承数据集对该GFFDA模型的有效性进行了验证。研究结果表明:相比于现有的数据驱动模型,GFFDA模型具有更好的跨工况分析能力和更出色的信息提取能力;同时,在对变工况的轴承寿命进行预测时,采用GFFDA模型具有更好的性能。

Dual Gate液晶显示屏栅极制程断路缺陷的分析与改善

文章探究了光刻工序的水汽和ITO刻蚀工序的药液结晶对DualGate产品栅极制程的断路影响,通过DOE试验得到影响因子的最佳改善条件,使55寸DualGate产品栅极制程的断路缺陷发生率整体降低36%,为公司带来80.2万元的月度收益,能够对其他高端产品断路缺陷的改善思路、新工艺设备的设计改进,提供参考。

基于Leaky Noisy-or Gate和贝叶斯网络的光伏发电项目施工风险评估方法

针对复杂多变的光伏发电项目施工风险评估问题,利用Leaky Noisy-or Gate模型整合历史经验和专家知识来确定贝叶斯网络参数并建立光伏施工风险的贝叶斯网络模型,同时采用Netica仿真分析,对施工风险进行有效预测并诊断识别出关键性风险和敏感性风险,以便管理者精准施策、管控风险。为验证该方法的有效性,以Z项目为例进行建模仿真。结果表明,其施工风险等级为中等,与实际相符。

All-optical controlled-NOT logic gate achieving directional asymmetric transmission based on metasurface doublet

Optical logic gates play important roles in all-optical logic circuits,which lie at the heart of the next-generation optical computing technology.However,the intrinsic contradiction between compactness and robustness hinders the development in this field.Here,we propose a simple design principle that can possess multiple-input-output states according to the incident circular polarization and direction based on the metasurface doublet,which enables controlled-NOT logic gates in infrared region.Therefore,the directional asymmetric electromagnetic transmission can be achieved.As a proof of concept,a spin-dependent Janus metasurface is designed and experimentally verified that four distinct images corresponding to four input states can be captured in the far-field.In addition,since the design method is derived from geometric optics,it can be easily applied to other spectra.We believe that the proposed metasurface doublet may empower many potential applications in chiral imaging,chiroptical spectroscopy and optical computing.

Radar Quantitative Precipitation Estimation Based on the Gated Recurrent Unit Neural Network and Echo-Top Data

The Gated Recurrent Unit(GRU) neural network has great potential in estimating and predicting a variable. In addition to radar reflectivity(Z), radar echo-top height(ET) is also a good indicator of rainfall rate(R). In this study, we propose a new method, GRU_Z-ET, by introducing Z and ET as two independent variables into the GRU neural network to conduct the quantitative single-polarization radar precipitation estimation. The performance of GRU_Z-ET is compared with that of the other three methods in three heavy rainfall cases in China during 2018, namely, the traditional Z-R relationship(Z=300R1.4), the optimal Z-R relationship(Z=79R1.68) and the GRU neural network with only Z as the independent input variable(GRU_Z). The results indicate that the GRU_Z-ET performs the best, while the traditional Z-R relationship performs the worst. The performances of the rest two methods are similar.To further evaluate the performance of the GRU_Z-ET, 200 rainfall events with 21882 total samples during May–July of 2018 are used for statistical analysis. Results demonstrate that the spatial correlation coefficients, threat scores and probability of detection between the observed and estimated precipitation are the largest for the GRU_Z-ET and the smallest for the traditional Z-R relationship, and the root mean square error is just the opposite. In addition, these statistics of GRU_Z are similar to those of optimal Z-R relationship. Thus, it can be concluded that the performance of the GRU_ZET is the best in the four methods for the quantitative precipitation estimation.

基于Golden Gate高效构建psiCHECK双荧光素酶报告基因的方法及应用

目的 基于Golden Gate技术构建psiCHECK-CcdB重组双荧光素酶报告载体,并探讨其能否用于RNA干扰(RNA interference, RNAi)药物筛选。方法 通过聚合酶链反应(polymerase chain reaction,PCR)扩增CcdB致死基因、氯霉素基因与Golden Gate组装所需的BsmBI酶切位点,将其克隆至psiCHECK-2载体,构建出重组载体psiCHECK-CcdB。利用2种大肠杆菌DB3.1与DH5α对该载体的致死效率进行检测,选用1 387 bp大小的外源片段克隆至psiCHECK-CcdB载体,检测其连接效率,并验证重组载体能否发挥双荧光素酶报告系统功能,监测目的基因的表达变化。结果 菌落PCR以及测序鉴定psiCHECK-CcdB重组质粒构建成功,该质粒可有效致死无法耐受CcdB毒素的大肠杆菌DH5α菌株,在DB3.1菌株中正常生长。采用Golden Gate的方法可将外源片段简单快速克隆至psiCHECKCcdB载体中,连接效率显著提高且低背景克隆。通过测定双荧光素酶表达强度,证实了小干扰RNA(small interfering RNA,siRNA)靶向性结合目的基因可显著下调荧光素酶的表达,成功发挥双荧光素酶报告基因功能。结论 本研究成功构建了psiCHECK-CcdB重组双荧光素酶报告载体,应用Golden Gate组装技术,简化了实验操作流程,降低了实验成本,具备较高的阳性克隆率与多片段一次性组装的潜力,在RNAi药物筛选领域应用前景广阔。

An integrated split and dummy gates MOSFET with fast turn-off and reverse recovery characteristics

A power MOSFET with integrated split gate and dummy gate(SD-MOS) is proposed and demonstrated by the TCAD SENTAURUS.The split gate is surrounded by the source and shielded by the dummy gate.Consequently,the coupling area between the split gate and the drain electrode is reduced,thus the gate-to-drain charge(Q_(GD)),reverse transfer capacitance(C_(RSS)) and turn-off loss(E_(off)) are significantly decreased.Moreover,the MOS-channel diode is controlled by the dummy gate with ultra-thin gate oxide t_(ox),which can be turned on before the parasitic P-base/N-drift diode at the reverse conduction,then the majority carriers are injected to the N-drift to attenuate the minority injection.Therefore,the reverse recovery charge(Q_(RR)),time(T_(RR)) and peak current(I_(RRM)) are effectively reduced at the reverse freewheeling state.Additionally,the specific on-resistance(R_(on,sp)) and breakdown voltage(BV) are also studied to evaluate the static properties of the proposed SD-MOS.The simulation results show that the Q_(GD) of 6 nC/cm^(2),the C_(RSS) of 1.1 pF/cm^(2) at the V_(DS) of 150 V,the QRR of 1.2 μC/cm^(2) and the R_(on,sp) of 8.4 mΩ·cm^(2) are obtained,thus the figures of merit(FOM) including Q_(GD) ×R_(on,sp) of50 nC·mΩ,E_(off) × R_(on,sp) of 0.59 mJ·mΩ and the Q_(RR) × R_(on,sp) of 10.1 μC·mΩ are achieved for the proposed SD-MOS.

Low switching loss and increased short-circuit capability split-gate SiC trench MOSFET with p-type pillar

A split-gate SiC trench gate MOSFET with stepped thick oxide, source-connected split-gate(SG), and p-type pillar(ppillar) surrounded thick oxide shielding region(GSDP-TMOS) is investigated by Silvaco TCAD simulations. The sourceconnected SG region and p-pillar shielding region are introduced to form an effective two-level shielding, which reduces the specific gate–drain charge(Q_(gd,sp)) and the saturation current, thus reducing the switching loss and increasing the short-circuit capability. The thick oxide that surrounds a p-pillar shielding region efficiently protects gate oxide from being damaged by peaked electric field, thereby increasing the breakdown voltage(BV). Additionally, because of the high concentration in the n-type drift region, the electrons diffuse rapidly and the specific on-resistance(Ron,sp) becomes smaller.In the end, comparing with the bottom p~+ shielded trench MOSFET(GP-TMOS), the Baliga figure of merit(BFOM,BV~2/R_(on,sp)) is increased by 169.6%, and the high-frequency figure of merit(HF-FOM, R_(on,sp) × Q_(gd,sp)) is improved by310%, respectively.