基于改进Cascade R-CNN算法的船舶目标检测方法

为了解决实际场景下船舶目标检测精度低的问题,本文在Cascade R-CNN算法的基础上,提出一种船舶目标检测方法 Boat R-CNN。Boat R-CNN使用带自注意力机制的Swin-Transformer Tiny网络提取图像特征,使用Soft-NMS非极大值抑制方法提升候选框过滤精度,使用Smooth_L1损失函数加速模型收敛并减少梯度爆炸情况,使用CIOU边界框回归损失提高候选框回归质量,并针对船舶目标的形状特征优化锚框的长宽比,提高锚框的生成质量。实验结果表明,Boat R-CNN算法的精度相比原版Cascade R-CNN算法提高了21.8%,相比主流Faster R-CNN算法提高了30.3%,有效提升了实际场景下的船舶目标检测精度。

基于改进Cascade R-CNN的安全帽检测算法

针对安全帽检测中,目标形状、尺度变化大,易出现漏检、误检等问题,提出了一种基于改进级联基于区域的卷积神经网络(Cascade R-CNN)的安全帽检测算法。首先,对ResNet50进行改进形成D-ResNet50,利用可变形卷积仅增加少量参数就可增大感受野的特性,对特征提取网络的C2~C5卷积层进行重塑,提高网络对目标几何变换的适应能力和特征提取能力。其次,将D-ResNet50作为主干网络引入Cascade R-CNN,形成级联目标检测器,在每个阶段对正负样本重采样,抑制误检问题。再次,对递归特征金字塔进行改进,更高效地进行多尺度特征融合,并且基于反馈信息对特征进行二次处理,增强特征表达,提高网络的分类和定位能力。最后,使用Soft-非极大值抑制(Soft-NMS)进行后处理,进一步解决漏检问题。提出的方法在Hard hat workers数据集上的AP值相比检测基线提高了3.5%,与Sparse R-CNN、TridentNet、VFnet等先进算法相比分别提升了4.7%、5.9%、2.3%等。

Pluggable multitask diffractive neural networks based on cascaded metasurfaces

Optical neural networks have significant advantages in terms of power consumption,parallelism,and high computing speed,which has intrigued extensive attention in both academic and engineering communities.It has been considered as one of the powerful tools in promoting the fields of imaging processing and object recognition.However,the existing optical system architecture cannot be reconstructed to the realization of multi-functional artificial intelligence systems simultaneously.To push the development of this issue,we propose the pluggable diffractive neural networks(P-DNN),a general paradigm resorting to the cascaded metasurfaces,which can be applied to recognize various tasks by switching internal plug-ins.As the proof-of-principle,the recognition functions of six types of handwritten digits and six types of fashions are numerical simulated and experimental demonstrated at near-infrared regimes.Encouragingly,the proposed paradigm not only improves the flexibility of the optical neural networks but paves the new route for achieving high-speed,low-power and versatile artificial intelligence systems.

Premature axon-oligodendrocyte interaction contributes to stalling of experimental axon regeneration after injury to the white matter

Studies from nearly 3 decades ago suggested that,in the central nervous system(CNS),myelination of axons by oligodendrocytes not only helps improve axonal conductivity but also stabilizes circuitry(Colello and Schwab,1994).Over the years,myelin sheaths produced by oligodendrocytes have been found to contain multiple molecules that are inhibitory to axonal growth(e.g.,MAG,NogoA,OMgp,Semaphorins)(Yiu and He,2006;Silver et al.,2014).After white matter injury in the adult CNS,myelin debris from damaged axons and dead oligodendrocytes accumulates in the forming glial scar and exposes these myelin-associated axon growth-inhibitory molecules to the injured axonal stumps,thereby contributing to the inhibition of axonal regrowth.During development,CNS axons reach their postsynaptic targets and stop growing before oligodendrocytes appear and myelinate them(Foran and Peterson,1992;Dangata et al.,1996).Therefore,myelin-associated axon growth-inhibitory molecules interacting with already grown axons during myelination were thought to block axons from promiscuous sprouting and miswiring,thereby stabilizing neural circuitry in the CNS(Colello and Schwab,1994).

Vascular endothelial growth factor:a double-edged sword in the development of white matter lesions

As the population ages,the burden of age-related diseases becomes greater.Currently,over 55 million people suffer from dementia worldwide,with Alzheimer’s disease being the most common form.However,it is becoming clearer that underlying vascular pathology such as cerebral small vessel disease(cSVD)may be a more detrimental cause for dementia(Cuadrado-Godia et al.,2018).It is estimated that 10%-30%of the elderly population and 35%-90%of all dementia patients exhibit signs of cSVD.The term cSVD refers to pathology affecting the small vessels of the brain,which can lead to lacunar cerebral infarcts,enlarged perivascular spaces,and cortical hemorrhages(Cuadrado-Godia et al.,2018).CSVD is often associated with cognitive decline,gait problems,and dementia(Cuadrado-Godia et al.,2018).

基于Local Cascade Ensemble方法的胎儿健康自动分类

为更好地自动评估胎儿宫内状态,提出一种基于local cascade ensemble(LCE)方法的胎儿健康状态分类模型。选用UCI数据集,使用ADASYN方法对不平衡数据集进行填充平衡,接着结合随机森林算法对数据特征进行选择,最后使用LCE方法对胎儿状态进行自动分类。实验结果表明,所提出模型使用的方法平均准确率、精确率、召回率和F1分数分别达到了0.9554、0.9054、0.9557和0.9290,对比传统的机器学习算法能得到更好的分类效果,有效降低了误判率。

Correlation of Microbiological Stability with Redox Processes in White Wines

In this paper, the authors analyzed the correlation between the microbiological stability of white wines and the content of sulfur dioxide, which influences the main redox processes that take place in the technological stages of the wine. The consecutive, parallel and spontaneous development of several redox processes and their impact on the quality, microbiological and crystalline stability of white wines were examined. The reduction of additive and subtractive technological interventions, of the amounts of adjuvants (sulphurous anhydride) is essential for the production of organic wines.

Phase-locked single-mode terahertz quantum cascade lasers array

We demonstrated a scheme of phase-locked terahertz quantum cascade lasers(THz QCLs)array,with a single-mode pulse power of 108 mW at 13 K.The device utilizes a Talbot cavity to achieve phase locking among five ridge lasers with first-order buried distributed feedback(DFB)grating,resulting in nearly five times amplification of the single-mode power.Due to the optimum length of Talbot cavity depends on wavelength,the combination of Talbot cavity with the DFB grating leads to better power amplification than the combination with multimode Fabry-Perot(F-P)cavities.The Talbot cavity facet reflects light back to the ridge array direction and achieves self-imaging in the array,enabling phase-locked operation of ridges.We set the spacing between adjacent elements to be 220μm,much larger than the free-space wavelength,ensuring the operation of the fundamental supermode throughout the laser's dynamic range and obtaining a high-brightness far-field distribution.This scheme provides a new approach for enhancing the single-mode power of THz QCLs.

Clinical features and possible pathogenesis of multiple evanescent white dot syndrome with different retinal diseases and events:a narrative review

●Multiple evanescent white dot syndrome(MEWDS)is a rare fundus disease,characterized by acute vision loss and visual field defects.Many previous studies have explained the possible pathogenesis and clinical features of primary MEWDS.However,as the number of reported cases increases,secondary MEWDS occurs in other related retinal diseases and injuries,exhibiting some special characteristics.The associated retinal diseases include multifocal choroiditis/punctate inner choroidopathy(MFC/PIC),acute zonal occult outer retinopathy,best vitelliform macular dystrophy,pseudoxanthoma elasticum,and ocular toxoplasmosis.The related retinal injury is laser photocoagulation,surgery,and trauma.Although primary MEWDS often have a self-limiting course,secondary MEWDS may require treatment in some cases,according to the severity of concomitant diseases and complications.Notably,MEWDS secondary to MFC/PIC that is prone to forming choroidal neovascularization and focal choroidal excavation,needs positive treatment with corticosteroids.The possible underlying pathogenesis of secondary MEWDS is the exposure of choroidal antigen after the disruption of Bruch’s membrane.The MEWDS-related features in secondary MEWDS are still evanescent under most circumstances.Its prognosis and treatment depend on the severity of complications.Current studies propose that the etiology is associated with immune factors,including viral infection,inflammation in choroid and Bruch’s membrane,and antigen exposure caused by retinal and/or choroidal insults.More pathogenic studies should be conducted in the future.Accurate diagnosis for secondary MEWDS could benefit patients in aspects of management and prognosis.

Barley chitinase genes expression revamp resistance against whitefly (Bemisia Tabaci) in transgenic cotton (Gossypium hirsutum L.)

Background Chitinase is an enzyme that hydrolyzes chitin,a major component of the exoskeleton of insects,including plant pests like whiteflies.The present study aimed to investigate the expression of chemically synthesized barley ch1 and chi2 genes in cotton(Gossypium hirsutum)through Agrobacterium-mediated transformation.Fifty-five putative transgenic cotton plants were obtained,out of which fifteen plants successfully survived and were shifted to the field.Using gene-specific primers,amplification of 447 bp and 401 bp fragments confirmed the presence of the ch1 and chi2 genes in five transgenic cotton plants of the T0 generation.These five plants were further evalu-ated for their mRNA expression levels.The T0 transgenic cotton plants with the highest mRNA expression level and better yield performance in field,were selected to raise their subsequent progenies.Results The T1 cotton plants showed the highest mRNA expression levels of 3.5-fold in P10(2)for the ch1 gene and 3.7-fold in P2(1)for the chi2 gene.Fluorescent in situ hybridization(FISH)confirmed a single copy number of ch1 and chi2(hemizygous)on chromosome no.6.Furthermore,the efficacy of transgenes on whitefly was evaluated through an insect bioassay,where after 96 h of infestation,mortality rates of whitefly were calculated to be 78%–80%in transgenic cotton plants.The number of eggs on transgenic cotton plants were calculated to be 0.1%–0.12 per plant compared with the non-transgenic plants where egg number was calculated to be 0.90–1.00 per plant.Conclusion Based on these findings,it can be concluded that the chemically synthesized barley chitinase genes(ch1 and chi2)have the potential to be effective against insects with chitin exoskeletons,including whiteflies.The transgenic cotton plants expressing these genes showed increased resistance to whiteflies,resulting in reduced egg numbers and higher mortality rates.

Multi-dimensional multiplexing optical secret sharing framework with cascaded liquid crystal holograms

Secret sharing is a promising technology for information encryption by splitting the secret information into different shares.However,the traditional scheme suffers from information leakage in decryption process since the amount of available information channels is limited.Herein,we propose and demonstrate an optical secret sharing framework based on the multi-dimensional multiplexing liquid crystal(LC)holograms.The LC holograms are used as spatially separated shares to carry secret images.The polarization of the incident light and the distance between different shares are served as secret keys,which can significantly improve the information security and capacity.Besides,the decryption condition is also restricted by the applied external voltage due to the variant diffraction efficiency,which further increases the information security.In implementation,an artificial neural network(ANN)model is developed to carefully design the phase distribution of each LC hologram.With the advantage of high security,high capacity and simple configuration,our optical secret sharing framework has great potentials in optical encryption and dynamic holographic display.

The Infiuence of Velocity-dependent Correction Factor on Proton Decay Reactions in Massive White Dwarfs

Twenty-five typical massive white dwarfs(WDs)are selected and the proton decay reaction catalyzed by magnetic monopoles(MMs)for these WDs is discussed.A velocity-dependent correction factor strongly affects the cross-section.We find that a strong suppression controls the monopole catalysis of nucleon decay by the correction factor.The maximum number of MMs is captured and the luminosity can be 2.235×10^(21)and 1.7859×10^(32)erg s^(-1)(e.g.,for the O+Ne core mass WD J055631.17+130639.78).The luminosities of most massive WDs agree well with the observations at relatively low temperatures(e.g.,T_(6)=0.1),but can be three and two orders of magnitude higher than those of the observations for model(Ⅰ)and(Ⅱ)at relatively high temperatures(e.g.,T_(6)=10),respectively.The luminosities of model(Ⅰ)are about one order of magnitude higher than those of model(Ⅱ).Since we consider the effect of the number of MMs captured on the mass–radius relation and the suppression of the proton decay by the correction factor,the study by model(Ⅱ)may be an improved estimation.

Ash removal from inferior coal via ammonium fluoride roasting and simultaneous yield of white carbon black

The quality upgrading and deashing of inferior coal by chemical method still faces great challenges.The dangers of strong acid,strong alkali,waste water and exhaust gas as well as high cost limit its industrial production.This paper systematically investigates the ash reduction and desilicification of two typical inferior coal utilizing ammonium fluoride roasting method.Under the optimal conditions,for fat coal and gas coal,the deashing rates are 69.02%and 54.13%,and the desilicification rates are 92.64%and 90.27%,respectively.The molar dosage of ammonium fluoride remains consistent for both coals;however,the gas coal,characterized by a lower ash and silica content(less than half that of the fat coal),achieves optimum deashing effect at a reduced time and temperature.The majority of silicon in coal transforms into gaseous ammonium fluorosilicate,subsequently preparing nanoscale amorphous silica with a purity of 99.90%through ammonia precipitation.Most of the fluorine in deashed coal are assigned in inorganic minerals,suggesting the possibility of further fluorine and ash removal via flotation.This research provides a green and facile route to deash inferior coal and produce nano-scale white carbon black simultaneously.

Performance of the walking trail making test in older adults with white matter hyperintensities

BACKGROUND Several studies have reported that the walking trail making test(WTMT)completion time is significantly higher in patients with developmental coordination disorders and mild cognitive impairments.We hypothesized that WTMT performance would be altered in older adults with white matter hyperintensities(WMH).AIM To explore the performance in the WTMT in older people with WMH.METHODS In this single-center,observational study,25 elderly WMH patients admitted to our hospital from June 2019 to June 2020 served as the WMH group and 20 participants matched for age,gender,and educational level who were undergoing physical examination in our hospital during the same period served as the control group.The participants completed the WTMT-A and WTMT-B to obtain their gait parameters,including WTMT-A completion time,WTMT-B completion time,speed,step length,cadence,and stance phase percent.White matter lesions were scored according to the Fazekas scale.Multiple neuropsychological assessments were carried out to assess cognitive function.The relationships between WTMT performance and cognition and motion in elderly patients with WMH were analyzed by partial Pearson correlation analysis.RESULTS Patients with WMH performed significantly worse on the choice reaction test(CRT)(0.51±0.09 s vs 0.44±0.06 s,P=0.007),verbal fluency test(VFT,14.2±2.75 vs 16.65±3.54,P=0.012),and digit symbol substitution test(16.00±2.75 vs 18.40±3.27,P=0.010)than participants in the control group.The WMH group also required significantly more time to complete the WTMT-A(93.00±10.76 s vs 70.55±11.28 s,P<0.001)and WTMT-B(109.72±12.26 s vs 82.85±7.90 s,P<0.001).WTMT-A completion time was positively correlated with CRT time(r=0.460,P=0.001),while WTMT-B completion time was negatively correlated with VFT(r=-0.391,P=0.008).On the WTMT-A,only speed was found to statistically differ between the WMH and control groups(0.803±0.096 vs 0.975±0.050 m/s,P<0.001),whereas on the WTMT-B,the WMH group exhibited a significantly lower speed(0.778±0.111 vs 0.970±0.053 m/s,P<0.001)and cadence(82.600±4.140 vs 85.500±5.020 steps/m,P=0.039),as well as a higher stance phase percentage(65.061±1.813%vs 63.513±2.465%,P=0.019)relative to controls.CONCLUSION Older adults with WMH showed obviously poorer WTMT performance.WTMT could be a potential indicator for cognitive and motor deficits in patients with WMH.

Neuropathological characteristics of abnormal white matter functional signaling in adolescents with major depression

BACKGROUND Major depression disorder(MDD)constitutes a significant mental health concern.Epidemiological surveys indicate that the lifetime prevalence of depression in adolescents is much higher than that in adults,with a corresponding increased risk of suicide.In studying brain dysfunction associated with MDD in adolescents,research on brain white matter(WM)is sparse.Some researchers even mistakenly regard the signals generated by the WM as noise points.In fact,studies have shown that WM exhibits similar blood oxygen level-dependent signal fluctuations.The alterations in WM signals and their relationship with disease severity in adolescents with MDD remain unclear.AIM To explore potential abnormalities in WM functional signals in adolescents with MDD.METHODS This study involved 48 adolescent patients with MDD and 31 healthy controls(HC).All participants were assessed using the Patient Health Questionnaire-9 Scale and the mini international neuropsychiatric interview(MINI)suicide inventory.In addition,a Siemens Skyra 3.0T magnetic resonance scanner was used to obtain the subjects'image data.The DPABI software was utilized to calculate the WM signal of the fractional amplitude of low frequency fluctuations(fALFF)and regional homogeneity,followed by a two-sample t-test between the MDD and HC groups.Independent component analysis(ICA)was also used to evaluate the WM functional signal.Pearson’s correlation was performed to assess the relationship between statistical test results and clinical scales.RESULTS Compared to HC,individuals with MDD demonstrated a decrease in the fALFF of WM in the corpus callosum body,left posterior limb of the internal capsule,right superior corona radiata,and bilateral posterior corona radiata[P<0.001,family-wise error(FWE)voxel correction].The regional homogeneity of WM increased in the right posterior limb of internal capsule and left superior corona radiata,and decreased in the left superior longitudinal fasciculus(P<0.001,FWE voxel correction).The ICA results of WM overlapped with those of regional homogeneity.The fALFF of WM signal in the left posterior limb of the internal capsule was negatively correlated with the MINI suicide scale(P=0.026,r=-0.32),and the right posterior corona radiata was also negatively correlated with the MINI suicide scale(P=0.047,r=-0.288).CONCLUSION Adolescents with MDD involves changes in WM functional signals,and these differences in brain regions may increase the risk of suicide.

Model Predictive Control for Cascaded H-Bridge PV Inverter with Capacitor Voltage Balance

We designed an improved direct-current capacitor voltage balancing control model predictive control(MPC)for single-phase cascaded H-bridge multilevel photovoltaic(PV)inverters.Compared with conventional voltage balanc-ing control methods,the method proposed could make the PV strings of each submodule operate at their maximum power point by independent capacitor voltage control.Besides,the predicted and reference value of the grid-connected current was obtained according to the maximum power output of the maximum power point tracking.A cost function was con-structed to achieve the high-precision grid-connected control of the CHB inverter.Finally,the effectiveness of the proposed control method was verified through a semi-physical simulation platform with three submodules.

When Conscious Consumerism Backfires:A Critical Study on Social Exclusion,Partnerships,and White Saviorism

Purpose:What factors influence conscious consumerism,especially related to race and gender identities?This scholarship explores three white women-led social responsibility organizations’(SROs)aspirations to encourage conscious consumerism as well as factors that influence conscious consumerism.Design/methodology/approach:Using the Black feminist thought and sustainability development theory,the data were analyzed using a thematic analysis to explore the activation of the white savior industrial complex(WSIC)in SROs.Interviews provided in-depth knowledge of the SRO culture including,but not limited to,insight on social exclusion and partnerships.Findings:Noonday Collection,Sseko Designs,and Trades of Hope,all SROs,aspire to be dedicated to people,planet,and profit and encourage conscious consumerism as a means for their customer base and sales consultants to“do their part”,and yet,an unintended consequence of the SROs’work is social exclusion and white saviorism.Originality:This scholarship investigates what can be done to dismantle the overreliance of conscious consumerism in an effort to finally strip white saviorism,and its role in the white savior industrial complex(WSIC),of its power.

Study on Key Joining Technology and Test Method of Steel/Al Hybrid Structure Body-in-White

Green and low carbon promote the application and development of light-weight materials in body-in-white. Large-scale die-casting Al alloy (DCAA) and high-strength thermo-formed steel sheet (TFSS) have put forward higher requirements for the application of joining technology of high-strength steel/Al dissimilar materials. Taking the new die-casting Al alloy body as an example, this paper systematically studies the progress of the latest joining methods of steel/Al dissimilar material with combination of two-layer plate and three-layer plate. By analyzing the joining technologies such as FSPR, RES, FDS and SPR, the technology and process characteristics of steel/Al dissimilar material joining are studied, and the joining technical feasibility and realization means of different material combination of the body are analyzed. The conditions of material combination, material thickness, material strength, flange height, preformed holes and joint spacing for achieving high-quality joining are given. The FSPR joining technology is developed and tested in order to meet with the joining of parts with DCAA and TFSS, especially for the joining of three-layer plates with them. It finds the method and technical basis for the realization of high quality joining of dissimilar materials, provides the early conditions for the application of large DCAA and TFSS parts in body-in-white, and meets the design requirements of new energy body. .

改进的Cascade R-CNN算法在目标检测上的应用

针对Cascade R-CNN目标检测算法中存在检测精度较低以及目标遮挡问题,本文提出一种改进的Cas-cade R-CNN网络目标检测算法.该算法在主干网络ResNet101中引入可切换空洞卷积模块(Switchable Atrous Convolu-tion,SAC),该模块主要由两个全局上下文模块以及SAC组件构成,采用SAC组件以不同的空洞卷积率对特征进行卷积,并使用Switch函数收集特征来提高特征提取能力.同时,在ResNet101残差网络中引入坐标注意力机制(Coordi-nate Attention,CA),该机制将位置信息嵌入通道注意力中,用于更好地获取方向感知和位置感知信息,进而提高目标检测精度.此外,针对目标遮挡问题,引入Repulsion Loss损失函数.该损失函数主要由吸引项和排斥项组成,吸引项使得预测框和匹配上的目标框尽可能接近,排斥项使得预测框远离错误目标,进而减少非极大值抑制(Non-Maximum Suppression,NMS)的误检,提高目标检测中遮挡问题的检测精度.实验结果表明,在公开的科大讯飞AI挑战赛数据集上,与原算法测试性能相比,改进的Cascade R-CNN网络对该数据集检出率增长了2.39%,改进算法的识别精度有一定的提高.

基于改进Cascade RCNN的输电线路防振锤脱落检测方法

无人机巡检输电线路时,因拍摄角度和距离问题,容易出现被输电线遮挡和远距离拍摄的防振锤脱落目标,导致目标特征被遮挡且分辨率较低,且部分防振锤出现滑移现象,导致目标识别准确率降低。针对以上问题,提出一种基于改进Cascade RCNN的防振锤脱落检测网络。第一,设计了对比学习网络,将正负样本与真实样本的特征进行对比学习,利用对比损失函数训练网络,使其能更加关注到被遮挡的防振锤脱落目标,提升其特征提取能力;第二,进行了分类器增强操作,筛选出网络级联结构中回归效果较好的感兴趣区域并送入最后的分类回归队列中,提高了分类器的分类能力,进而提升检测目标的分类分数;第三,设计了并行注意力机制模块,整合网络提取的特征,增大关键特征的权重,使网络关注到图像中更关键的区域;在特征金字塔中,将双线性插值方法代替为反卷积,提升特征还原能力。经交叉验证实验结果表明,改进后的模型召回率、精确率和平均精度达到了97.5%,91.0%和92.0%,相比基线模型分别提高了6.9%,28.4%和8.0%。