MSD-Net: Pneumonia Classification Model Based on Multi-Scale Directional Feature Enhancement

Computer-aided diagnosis of pneumonia based on deep learning is a research hotspot.However,there are some problems that the features of different sizes and different directions are not sufficient when extracting the features in lung X-ray images.A pneumonia classification model based on multi-scale directional feature enhancement MSD-Net is proposed in this paper.The main innovations are as follows:Firstly,the Multi-scale Residual Feature Extraction Module(MRFEM)is designed to effectively extract multi-scale features.The MRFEM uses dilated convolutions with different expansion rates to increase the receptive field and extract multi-scale features effectively.Secondly,the Multi-scale Directional Feature Perception Module(MDFPM)is designed,which uses a three-branch structure of different sizes convolution to transmit direction feature layer by layer,and focuses on the target region to enhance the feature information.Thirdly,the Axial Compression Former Module(ACFM)is designed to perform global calculations to enhance the perception ability of global features in different directions.To verify the effectiveness of the MSD-Net,comparative experiments and ablation experiments are carried out.In the COVID-19 RADIOGRAPHY DATABASE,the Accuracy,Recall,Precision,F1 Score,and Specificity of MSD-Net are 97.76%,95.57%,95.52%,95.52%,and 98.51%,respectively.In the chest X-ray dataset,the Accuracy,Recall,Precision,F1 Score and Specificity of MSD-Net are 97.78%,95.22%,96.49%,95.58%,and 98.11%,respectively.This model improves the accuracy of lung image recognition effectively and provides an important clinical reference to pneumonia Computer-Aided Diagnosis.

Effects of cooling rate on microstructure and microhardness of directionally solidified Galvalume alloy

The influences of cooling rate on the phase constitution,microstructural length scale,and microhardness of directionally solidified Galvalume(Zn-55Al-1.6Si)alloy were investigated by directional solidification experiments at different withdrawal speeds(5,10,20,50,100,200,and 400μm·s^(-1)).The results show that the microstructure of directionally solidified Galvalume alloys is composed of primary Al dendrites,Si-rich phase and(Zn-Al-Si)ternary eutectics at the withdrawal speed ranging from 5 to 400μm·s^(-1).As the withdrawal speed increases,the segregation of Si element intensifies,resulting in an increase in the area fraction of the Si-rich phase.In addition,the primary Al dendrites show significant refinement with an increase in the withdrawal speed.The relationship between the primary dendrite arm spacing(λ_(1))and the thermal parameters of solidification is obtained:λ_(1)=127.3V^(-0.31).Moreover,as the withdrawal speed increases from 5 to 400μm·s^(-1),the microhardness of the alloy increases from 90 HV to 151 HV.This is a combined effect of grain refinement and second-phase strengthening.

Estimation of the anisotropy of hydraulic conductivity through 3D fracture networks using the directional geological entropy

With an extension of the geological entropy concept in porous media,the approach called directional entrogram is applied to link hydraulic behavior to the anisotropy of the 3D fracture networks.A metric called directional entropic scale is used to measure the anisotropy of spatial order in different directions.Compared with the traditional connectivity indexes based on the statistics of fracture geometry,the directional entropic scale is capable to quantify the anisotropy of connectivity and hydraulic conductivity in heterogeneous 3D fracture networks.According to the numerical analysis of directional entrogram and fluid flow in a number of the 3D fracture networks,the hydraulic conductivities and entropic scales in different directions both increase with spatial order(i.e.,trace length decreasing and spacing increasing)and are independent of the dip angle.As a result,the nonlinear correlation between the hydraulic conductivities and entropic scales from different directions can be unified as quadratic polynomial function,which can shed light on the anisotropic effect of spatial order and global entropy on the heterogeneous hydraulic behaviors.

Security-Enhanced Directional Modulation Based on Two-Dimensional M-WFRFT

Directional modulation(DM)is one of the most promising secure communication techniques.However,when the eavesdropper is co-located with the legitimate receiver,the conventional DM has the disadvantages of weak anti-scanning capability,anti-deciphering capability,and low secrecy rate.In response to these problems,we propose a twodimensional multi-term weighted fractional Fourier transform aided DM scheme,in which the legitimate receiver and the transmitter use different transform terms and transform orders to encrypt and decrypt the confidential information.In order to further lower the probability of being deciphered by an eavesdropper,we use the subblock partition method to convert the one-dimensional modulated signal vector into a twodimensional signal matrix,increasing the confusion of the useful information.Numerical results demonstrate that the proposed DM scheme not only provides stronger anti-deciphering and anti-scanning capabilities but also improves the secrecy rate performance of the system.

基于DPC-MND和多元状态估计的磨煤机故障预警研究

火电机组磨煤机存在运行条件恶劣、故障频发等问题,对磨煤机进行故障预警,可以有效防止一些常见故障的发生,从而保证火电机组的安全运行。为此,提出一种基于相互邻近度的密度峰值聚类和多元状态估计的磨煤机故障预警方法。首先,采用核主元分析选取磨煤机的主要状态参数,同时采用集合经验模态分解对历史运行数据进行去噪,进一步优化数据质量;然后,采用基于相互邻近度的密度峰值聚类(density peaks clustering based on mutual neighborhood degrees,DPC-MND)方法构建动态记忆矩阵,利用多元状态估计技术(multivariate state estimation techniques,MSET)对磨煤机正常运行工况下的历史数据进行建模,并确定磨煤机的运行状态。最后,以安徽某电厂ZGM113G型中速磨煤机为例进行验证,结果表明该方法可以实现对磨煤机故障的有效预警。

Unleashing the Potential of Unidirectional Mechanical Materials: Breakthroughs and Promising Applications

The emergence of mechanically one-way materials presents an exciting opportunity for materials science and engineering. These substances exhibit unique nonreciprocal mechanical responses, enabling them to selectively channel mechanical energy and facilitate directed sound propagation, controlled mass transport, and concentration of mechanical energy amidst random motion. This article explores the fundamentals of mechanically one-way materials, their potential applications across various industries, and the economic and environmental considerations related to their production and use.

基于参数辨识的三相电压型整流器VF-DPC策略

三相电压型整流器(VSR)虚拟磁链定向的直接功率控制(VF-DPC)对电感参数的变化较敏感。为此,提出了一种基于电感参数在线辨识的三相VSR的VF-DPC策略。首先,此处介绍了三相VSR的数学模型及最小二乘法参数辨识原理。然后,提出了一种基于最小二乘法的电感参数在线辨识策略。其次,针对常规虚拟磁链计算方法受纯积分运算影响的问题,提出了一种最小阶虚拟磁链观测器。最后,通过将辨识的电感参数输入到所设计的最小阶虚拟磁链观测器,可以大大提高虚拟磁链的观测精度,进而可提高三相VSR的功率控制精度。仿真和实验结果证明了所提方法的有效性。

面向无序抓取的DPC聚类多目标检测方法研究

为了尽可能多地从场景中检测出可抓取目标,提出了一种基于DPC特征点聚类的多目标检测算法。使用SIFT算法提取模板图像和待检测图像的特征点,并使用DPC算法对待检测图像特征点聚类,得到属于不同聚类中心的特征点集合。将属于不同聚类中心的特征点分别与模板图像特征点进行匹配,结合RANSAC算法去除误匹配并统计正确匹配点数量,根据正确匹配的特征点计算从模板图像到待检测图像的单应矩阵从而得到目标检测结果。根据每个目标正确匹配点数量筛选正确的检测结果,并在正确的检测结果中根据目标匹配点数量和目标最多匹配点数量的差值筛选出可抓取目标。检测出可抓取目标之后,使用立体匹配算法得到场景视差图,计算目标的三维坐标,并根据三维坐标与图像中二维坐标的对应关系使用PNP算法计算目标位姿。实验结果表明,基于DPC聚类的多目标检测方法能够在多个相同堆叠目标中准确检测出目标物体并分别计算位姿,有效解决了无序抓取应用中的多目标检测问题。

原油(重油)直接制化学品(DPC)技术在惠州石化的工业应用

中海油惠州石化有限公司1.2 Mt/a催化裂化装置于2021年5月针对环烷-中间基及减三线蜡油、减压渣油和原油为原料的原油(重油)直接制化学品(DPC)技术工业试验,实现了多产液化石油气、低碳烯烃,少产汽油和柴油,大幅降低焦炭收率的效果,达到了降低焦炭、增加化工产品、降低油品收率的预期目标,工业试验效果显著。验证了DPC技术的工业可行性。DPC试验证明加工相同原料情况下的低生焦率,符合当前“碳中和”目标要求。

Bioinspired All‑Fibrous Directional Moisture‑Wicking Electronic Skins for Biomechanical Energy Harvesting and All‑Range Health Sensing

Electronic skins can monitor minute physiological signal variations in the human skins and represent the body’s state,showing an emerging trend for alternative medical diagnostics and human-machine interfaces.In this study,we designed a bioinspired directional moisture-wicking electronic skin(DMWES)based on the construction of heterogeneous fibrous membranes and the conductive MXene/CNTs electrospraying layer.Unidirectional moisture transfer was successfully realized by surface energy gradient and push-pull effect via the design of distinct hydrophobic-hydrophilic difference,which can spontaneously absorb sweat from the skin.The DMWES membrane showed excellent comprehensive pressure sensing performance,high sensitivity(maximum sensitivity of 548.09 kPa^(−1)),wide linear range,rapid response and recovery time.In addition,the single-electrode triboelectric nanogenerator based on the DMWES can deliver a high areal power density of 21.6μW m^(−2) and good cycling stability in high pressure energy harvesting.Moreover,the superior pressure sensing and triboelectric performance enabled the DMWES for all-range healthcare sensing,including accurate pulse monitoring,voice recognition,and gait recognition.This work will help to boost the development of the next-generation breathable electronic skins in the applications of AI,human-machine interaction,and soft robots.

The corrosion characteristics and mechanism of directionally solidified Mg-3Zn-xCa alloys

An investigation into the corrosion characteristics and mechanism of directionally solidified(DSed) Mg-3Zn-xCa(x = 0, 0.2, 0.5,0.8 wt.%) alloys in 0.9 wt.% Na Cl solution is presented. The DSed microstructure consists of columnar dendrites and eutectics distributed in the interdendritic region. The primary dendritic arm spacing(PDAS) and the volume fraction(fv) of the secondary phases are under the significant impact of the content of Ca. The corrosion rates evaluated using electrochemical measurements and immersion tests are accelerated monotonously with the increase of Ca content in DSed alloys. The corrosion resistance of the DSed alloys is significantly affected by the corrosion products film(CPF) and the secondary phases. The corrosion products of DSed Mg-3Zn alloy contain Mg(OH)_(2) and ZnO. The existence of ZnO greatly enhances the corrosion resistance of DSed Mg-3Zn alloy. As for the DSed alloys containing Ca content, a relatively protective CPF without deep pits can form on the surface of DSed Mg-3Zn-0.2Ca specimen during the corrosion. The f_(v)of the secondary phases dominates the corrosion rate of the DSed Mg-Zn-Ca alloys. The corrosion of DSed Mg-3Zn-xCa alloys initiates as a result of microgalvanic coupling between the cathodes of secondary phases and α-Mg matrix anode. Then, the corrosion gradually extends longitudinally with the breakdown of CPF.

In Situ Directional Polymerization of Poly(1,3-dioxolane)Solid Electrolyte Induced by Cellulose Paper-Based Composite Separator for Lithium Metal Batteries

In traditional in situ polymerization preparation for solid-state electrolytes,initiators are directly added to the liquid precursor.In this article,a novel cellulose paper-based composite separator is fabricated,which employs alumina as the inorganic reinforcing material and is loaded with polymerization initiator aluminum trifluoromethanesulfonate.Based upon this,a separator-induced in situ directional polymerization technique is demonstrated,and the extra addition of initiators into liquid precursors is no longer required.The polymerization starts from the surface and interior of the separator and extends outward with the gradually dissolving of initiators into the precursor.Compared with its traditional counterpart,the separator-induced poly(1,3-dioxolane)electrolyte shows improved interfacial contact as well as appropriately mitigated polymerization rate,which are conducive to practical applications.Electrochemical measurement results show that the prepared poly(1,3-dioxolane)solid electrolyte possesses an oxidation potential up to 4.4 V and a high Li+transference number of 0.72.After 1000 cycles at 2 C rate(340 mA g^(−1)),the assembled Li||LiFePO_(4)solid battery possesses a 106.8 mAh g^(−1)discharge capacity retention and 83.5%capacity retention ratio,with high average Coulombic efficiency of 99.5%achieved.Our work may provide new ideas for the design and application of in situ polymerization technique for solid electrolytes and solid batteries.

抑癌基因Smad4/DPC4在结直肠癌中作用的研究进展

Smad4抑癌基因又称DPC4,位于染色体18q21.1,编码的Smad4/DPC4蛋白是一种转录因子,是转化生长因子β(TGF-β)信号通路的中心介质。Smad4/DPC4基因在结直肠癌(CRC)发生和发展过程中起着重要作用,已经成为研究结直肠癌发生和发展的关键分子之一。文章综述Smad4/DPC4在结直肠癌发生和发展及治疗中的作用,阐明Smad4/DPC4与结直肠癌转移的关系,以期为结直肠癌患者个体化和精准化治疗提供理论依据。

Correction to:Application of long-reach directional drilling boreholes for gas drainage of adjacent seams in coal mines with severe geological conditions

Correction:International Journal of Coal Science&Technology(2022)9:88 https:/doi.org/10.1007/s40789-022-00553-6 In this article,the author would like to change the Ethics Declaration as below:EthicsDeclarations Scientific work published within the framework of an international project DD-MET co-financed by the Research Fund for Coal and Steel(RFCS),(Grant Agreement:847338)and by the Polish Ministry of Science and Higher Education(Contract no.5073/FBWiS/19/2020/2 and 5038/FBWiS/2019/2).

Nonconvex Noise-Tolerant Neural Model for Repetitive Motion of Omnidirectional Mobile Manipulators

Dear Editor,Quadratic programming problems(QPs)receive a lot of attention in various fields of science computing and engineering applications,such as manipulator control[1].Recursive neural network(RNN)is considered to be a powerful QPs solver due to its parallel processing capability and feasibility of hardware implementation[2].

Coexistence of Unidirectional Charge Density Waves in LaTe_(3)

The classic rare-earth tritelluride provides an ideal platform to study the strong correlation state owing to its stable structures and abundance of orders.Here we report the observation of an undiscovered charge density wave(CDW)in LaTe_(3)under 4.2 K,the transition temperature of the CDW states is fitted to be 35 K,and confirmed by the evanishment of this CDW at 77 K via using temperature-dependent scanning tunneling microscope/spectroscopy.The coexistence of these CDWs is confirmed by the atomic resolution and beating pattern simulation.It is the first time to observe the coexistence of unidirectional charge density waves system,providing a new platform to understand the competition and evolution between strong correlation states,and get a deeper sight into the phase lag between different order parameters.

Directional Chiral Optical Emission by Electron-Beam-Excited Nano-Antenna

Manipulating directional chiral optical emissions on a nanometer scale is significant for material science research. The electron-beam-excited nanoantenna provides a favorable platform to tune optical emissions at the deep subwavelength scale. Here we present an L-shaped electron-beam-excited nanoantenna(LENA) with two identical orthogonal arms. By selecting different electron-beam impacting sites on the LENA, either the lefthanded circularly polarized(LCP) or the right-handed circularly polarized(RCP) emission can be excited. The LCP and RCP emissions possess different emission directionality, and the emission wavelength depends on the arm length of the LENA. Further, we show a combined nanoantenna with two LENAs of different arm lengths.Induced by the electron beam, LCP and RCP lights emit simultaneously from the nanoantenna with different wavelengths to different directions. This approach is suggested to be informative for investigating electron-photon interaction and electron-beam spectroscopy in nanophotonics.

Effect of Cu addition on the microstructure and tribological performance of Ni60 directional structure coating

The Ni60/15wt% Cu directional structure coating was prepared by the composite technology of flame spraying, induction remelting,and forced cooling, and the effect of Cu on the microstructure, phase, hardness, and wear performance of Ni60 coatings was investigated. Results showed that Cu addition makes the microstructure of Ni60 directional structure coating more compact, and Cu is mainly enriched within the crystal grain, resulting in the formation of Cu_(3.8)Ni as the bonding phase. Compared with Ni60 directional structure coating, Ni60/Cu directional structure coating has a lower hardness, lower friction coefficient, and lower wear rate, which indicate that Cu can effectively enhance the antifriction performance of Ni60 directional structure coating.

气象大数据云平台DPC子系统配置文件查看器的设计与实现

气象大数据云平台(天擎)的子系统数据处理中心(DPC)主要功能是对种类繁多的资料进行解码与入库,每类资料的解码程序、配置文件、消息队列及端口号不尽相同。该文通过Java和Python语言的混合编程,利用内存数据库及Nutz网页框架,实现了各类配置文件的快速查看,在一定程度上减轻了运维压力,提高了工作效率,目前已在部分省份进行推广应用。

On establishment of novel constitutive model for directionally solidified nickel-based superalloys utilizing machine learning methods

To enhance the accuracy of mechanical simulation in the directional solidification process of turbine blades for heavy-duty gas turbines,a new constitutive model that employs machine learning methods was developed.This model incorporates incremental learning and transfer learning,thus improves the predictive accuracy and generalization performance.To account for the anisotropy of the directionally solidified alloy,a deformation direction parameter is added to the model,enabling prediction of the stress-strain relationship of the alloy under different deformation directions.The predictive capabilities of both models are evaluated using correlation coefficient(R),average relative error(δ),and value of relative error(RE).Compared to the traditional model,the machine learning constitutive model achieves higher prediction accuracy and better generalization performance.This offers a new approach for the establishment of flow constitutive models for other directionally solidified and single-crystal superalloys.