Splicing factor proline and glutamine-rich is a prognostic biomarker and correlated with clinical pathologic features and immune infiltrates in hepatocellular carcinoma

Background:Hepatocellular carcinoma(HCC)is the fourth leading cause of cancer-related deaths globally.Splicing factor proline and glutamine-rich(SFPQ)is a multifunctional protein that controls various biological functions.As a potential therapeutic target and a promising prognostic indicator,the potential effects and processes of SFPQ in HCC require further investigation.Methods:The RNA sequencing data were obtained from the Gene Expression Omnibus,International Cancer Genome Consortium,and The Cancer Genome Atlas databases to analyze SFPQ expression and differentially expressed genes(DEGs).We utilized the LinkedOmics database to identify co-expressed genes.A Venn diagram was constructed to determine the overlapping genes between the DEGs and the co-expressed genes.Functional enrichment analysis was performed on the overlapping genes and DEGs.Furthermore,our study involved functional enrichment analysis,a protein-protein interaction network analysis,and an analysis of immune cell infiltration.The cBioPortal and Tumor Immune Single-cell Hub were utilized to investigate the genetic alterations of SFPQ and the single-cell transcriptome visualization of the tumor microenvironment.A ceRNA network was established with the assistance of the ENCORI website.Finally,we elucidated the clinical significance of SFPQ in HCC by employing Kaplan-Meier survival analysis,univariate and multivariate Cox regression,and prognostic nomogram models.Results:The expression of SFPQ in HCC tissues was significantly elevated compared to normal tissues.GSEA results indicated that increased expression of SFPQ was associated with pathways related to HCC.The ceRNA network,including SFPQ,hsa-miR-101-3p,AC023043.4,AC124798.1,AC145207.5,and GSEC,was constructed with the assistance of ENCORI.High SFPQ expression was related to a poor prognosis in HCC and its subtypes.Univariate and multivariate Cox regression analysis showed that elevated SFPQ expression is an independent predictive factor.Conclusions:The overexpression of SFPQ may serve as a potential prognostic biomarker,indicating a poor prognosis in HCC.

Melatonin treatment alleviates chilling injury in mango fruit 'Keitt' by modulating proline metabolism under chilling stress

Mangoes often suffer from low temperature-induced chilling injury (CI) during postharvest cold storage.Therefore,advanced techniques are crucial and in high demand to solve the chilling stress of mango fruit for a higher value.This study addresses chilling stress modulation by investigating the effects of melatonin treatment on CI,proline metabolism,and related gene expressions of ‘Keitt’ mango during cold storage after dipped in 0 (control),0.1 (MT1),and 0.2 mmol L^(-1)(MT2) melatonin solution for 30 min.The results revealed that melatonin treatment in MT1 significantly reduced CI development and increased proline content in mango fruit during cold storage compared to the control.These changes were along with increases in the activity of critical enzymes as well as the expression of encoding genes involved in proline biosynthesis,such as pyrroline-5-carboxylate synthetase (P5CS),pyrroline-5-carboxylate reductase (P5CR),ornithine D-aminotransferase (OAT),P5CS2,P5CR2,and OAT3.Additionally,proline dehydrogenase (PDH) activity and the expression of the PDH3 gene associated with proline dehydrogenation were lower in MT1-treated mangoes than the controlled group.Thus,melatonin treatment has regulated proline metabolism resulting in the accumulation of proline,subsequently contributing to enhancing the chilling tolerance of‘Keitt’mango fruit.

Drought Tolerance in Mung Bean is Associated with the Genotypic Divergence, Regulation of Proline, Photosynthetic Pigment and Water Relation

Drought is one of the critical conditions for the growth and productivity of many crops including mung bean(Vigna radiata L.Wilczek).Screening of genotypes for variations is one of the suitable strategies for evaluating crop adaptability and global food security.In this context,the study investigated the physiological and biochemical responses of four drought tolerant(BARI Mung-8,BMX-08010-2,BMX-010015,BMX-08009-7),and four drought sensitive(BARI Mung-1,BARI Mung-3,BU Mung-4,BMX-05001)mung bean genotypes under wellwatered(WW)and water deficit(WD)conditions.The WW treatment maintained sufficient soil moisture(22%±0.5%,i.e.,30%deficit of available water)by regularly supplying water.Whereas,the WD treatment was maintained throughout the growing period,and water was applied when the wilting symptom appeared.The drought tolerant(DT)genotypes BARI Mung-8,BMX-08010-2,BMX-010015,BMX-08009-7 showed a high level of proline accumulation(2.52–5.99 mg g^(−1) FW),photosynthetic pigment(total chlorophyll 2.96–3.27 mg g^(−1) FW at flowering stage,and 1.62–2.38 mg g^(−1) FW at pod developing stage),plant water relation attributes including relative water content(RWC)(82%–84%),water retention capacity(WRC)(12–14)as well as lower water saturation deficit(WSD)(19%–23%),and water uptake capacity(WUC)(2.58–2.89)under WD condition,which provided consequently higher relative seed yield.These indicate that the tolerant genotypes gained better physiobiochemical attributes and adaptability in response to drought conditions.Furthermore,the genotype BMX-08010-2 showed superiority in terms of those physio-biochemical traits,susceptibility index(SSI)and stress tolerance index(STI)to other genotypes.Based on the physiological and biochemical responses,the BMX-08010-2 was found to be a suitable genotype for sustaining yield under drought stress,and subsequently,it could be recommended for crop improvement through hybridization programs.In addition,the identified traits can be used as markers to identify tolerant genotypes for drought-prone areas.

Methods for the Determination of Stable Isotopes of Carbon and Nitrogen Directly in Valine, Proline, Glutamine, and Glutamic Acid

Amino acids are very important compounds for the body and are involved in important functions that keep us healthy. Amino acids are essential components such as valine, proline, glutamine and glutamic acid. They can be synthesized either naturally or artificially. To examine the metabolism and regulate the synthesis process, compounds labeled with nitrogen or carbon isotopes need to be used. These isotopic compounds allow for more extensive research and enable studies that would otherwise be impossible. However, their use is dependent on the availability of simple, efficient methods for isotopic analysis. Currently, the determination of the atomic fraction of carbon and nitrogen isotopes is only possible through their conversion into molecular nitrogen or carbon monoxide or carbon dioxide. This leads to the loss of information about isotopic enrichment in specific centers of the molecule. This article explores a new direct approach to determining the atomic fraction of carbon and nitrogen isotopes in the isotope-modified or identical centers of these compounds. This method eliminates the transfer process and dilution due to nitrogen and carbon impurities. It is now possible to simultaneously determine the atomic fraction of nitrogen and carbon isotopes in the research substance. This method can be applied to amino acids, making it an effective tool for proposing new research methods. Several articles [1] [2] [3] have proposed similar methods for organic compounds and amino acids.

Effect of Water Stress Induced by Polyethylene Glycol on Growth, Proline Accumulation in Agave americana L.

The effect of water deficit was determined on both in vitro and soil seedling as well as in cells in suspension of Agave americana L.In order to do the establishment of cells,the formation of callus was induced;for it two auxins were evaluated:2,4-dichlorophenoxyacetic acid(2,4-D)and 4-mino-3,5,6-trichloropicolinic acid(picloram)at three concentrations(0.25,0.5 and 0.75 mg L−1)in three explants(leaf,root and meristems)cultured in MS semisolid medium.The callogenesis response was related to the type and section of the explant,as well as the regulator used,and a cell suspension was established using 0.5 mg L−1 naphthaleneacetic acid(NAA)+0.5 mg L−1 Benzylaminopurine(BAP).Seedlings were exposed to polyethyleneglycol(15%and 30%w/v)with a water potential of−0.87 and−2.67 MPa,respectively,under soil conditions.Water stress was applied through restricted irrigation.Fresh weight,root system growth,and chlorophyll concentration were some of the parameters that were affected by the effect of water deficit on A.americana L.Chlorophyll concentration values were significantly decreased by 15 at 30%PEG(19.6 SPAD units)compared to the control treatment.In in vitro plants,the highest concentration of proline was found in the roots,being the treatment with 30%polyethylene glycol where the highest concentration of this osmoregulator was obtained(62.5 mg g−1 DW).Under restricted irrigation conditions,an increase in proline concentration was observed both in the aerial part(2.2μg 100 g−1 DW)and in the root system(1.8μg 100 g−1 DW).However,the concentrations found were approximately ten times greater,less than those found under in vitro conditions.Therefore,the accumulation of proline can be considered an indicator of stress in Agave Americana L.growth in vitro.

Ornithine Pathway in Proline Biosynthesis Activated by Salt Stress in Barley Seedlings

C-14-glutamate and C-14-arginine were spreaded on leaves of six-day old barley (Hordeum vulgare L.) seedlings that were treated with NaCl 200 mmol/L. The result showed that the pathway of arginine-->ornithine-->proline existed in the six-day old barley seedlings and was provoked remarkably by NaCl treatment. After seven days, proline accumulation contributed via the arginine-->ornithine-->proline pathway was 1.0 - 1.5 folds of that via the glutamate-->proline pathway. The activation of arginine-->ornithine-->proline pathway by salt stress in the salt-tolerant cultivar 'Jian 4' was 1.7 - 2.0 folds of that in the salt-sensitive cultivar 'KP 7', which suggested that the activation of arginine-->ornithine-->proline pathway in barley seedlings played an important role in improving salt tolerance of plants.

Overexpression of Proline Transporter Gene Isolated from Halophyte Confers Salt Tolerance in Arabidopsis

Proline is one of the most important and widespread osmolyte which functions in adaptation to adverse environmental stresses in many organisms. Also it is an important carbon and nitrogen resource in higher plants. Metabolism of proline has been elucidated in many plant species. However, transport of proline was poorly characterized although transport system plays an important role in proline distribution in different tissues. We isolated one full_length cDNA encoding proline transporter from the typical halophyte: Atriplex hortensis L. through cDNA library screening and 5′_RACE. The deduced amino acid sequence had eleven transmembrane domains, showed 60%-69% similarities to other ProTs and the gene was designated AhProT1. In the phylogenetic tree, higher plants' ProTs, e.g. AhProT1, showed more similar to ProP from microorganisms than ProT from mammalians. AhProT1 gene was transformed into Arabidopsis thaliana under 35S promoter. In MS medium containing [U_ 14 C] proline, AhProT1 + plants were able to accumulate much more radiolabeled proline in the roots than control plants. In MS medium containing different concentrations of NaCl, AhProT1 + plants could endure 200 mmol/L NaCl and keep development and biomass increase with proline supply, whereas control plants died back at 150 mmol/L NaCl.

The Comparison of Contents of Malondialdehyde and Proline in the Area of Karst Area in Northweastern Guangxi Province

[Objective] To select excellent pioneer species of better ecological and economical comprehensive benefits from the common rock hill plants in Karst area in northwestern Guangxi Province.[Method] Determine the contents of malondialdehyde and proline in leaves of 65 strains of plants by thiobarbituric acid method and sultosalicylic acid method,analyze the relevance of the contents of malondialdehyde and proline by mathematics statistics and analyze the 65 kinds of rock hill plants by clustering [Result] The contents of malondialdehyde and proline are 0.005 2-0.038 1 μmol/g.There are comparably significant differences in the contents of malondialdehyde in different plants;The determination of proline contents in plant＇s leaves are 4.347-374.956 μg/ml.There are also significant differences in proline of different leaves of rock hill plants.The contents of malondialdehyde and proline can be used as a reference point in selecting pioneer plants in Karst area.But when we select the pioneer plants,not only the biological characters of the species themselves should be taken into consideration,but also the differences of Karst area environment,ecological and biological benefits and the reasonable distribution of species.[Conclusion] Pistacia chinensis,Zenia insignis,Acacia confusa,Itoa orientalis and Sophora japonica can be used as the first choices of excellent pioneer plants in Karst area in northwestern area which comparably consists with the real situation of afforestation of rock hills and recovery of plants in Guangxi.

宽负荷下切圆燃煤锅炉H_(2)S分布特性的数值模拟

锅炉采用空气分级燃烧降低NO_(x)排放的同时也提高了主燃区H_(2)S体积分数。炉墙壁面过高的H_(2)S体积分数是加剧水冷壁高温腐蚀的重要因素。为保障新能源并网发电,大型燃煤机组灵活调峰的需求增加,不同负荷下的水冷壁近壁面H_(2)S分布特性值得关注。通过正交试验分析了切圆燃煤锅炉运行参数对水冷壁近壁面H_(2)S体积分数分布的影响。选取一台超临界600 MW切圆燃煤锅炉建立数值模型,设计L_(16)(4^(5))正交工况,覆盖100%BMCR、75%THA,50%THA以及35%BMCR四种负荷。建立了自定义SO_(x)生成模型以确定燃料硫的析出和转化路径,模型包含多表面反应子模型以描述焦炭与O_(2)/CO_(2)/H_(2)O等3种气体的异相反应,并确定焦炭气化反应消耗量占总消耗量的比例,进而对炉膛H_(2)S空间分布进行了模拟计算。研究表明,近壁面高体积分数H_(2)S区域主要位于投运燃烧器层中最下层燃烧器以下以及最上层燃烧器以上至SOFA层之间,烟气切圆沿炉膛高度增加逐渐增大是造成后一区域H_(2)S体积分数较高的重要原因。35%BMCR负荷下水冷壁重点区域的H_(2)S平均体积分数为364μL/L,明显低于其他负荷。锅炉运行参数对重点区域H_(2)S体积分数影响程度的排序为:锅炉负荷>一次风率>主燃区空气过量系数>假想切圆直径>燃烧器竖直摆角。

S型异质结光催化剂ZnFe_(2)O_(4)/WO_(3)的构筑及光催化还原CO_(2)性能

通过在WO_(3)纳米片表面负载ZnFe_(2)O_(4)纳米颗粒,构建了一系列S型异质结光催化剂ZnFe_(2)O_(4)/WO_(3),并研究了其光催化CO_(2)还原性能。在没有助催化剂和牺牲剂的条件下,所制备的ZnFe_(2)O_(4)/WO_(3)复合材料可对CO_(2)与水蒸汽进行光催化反应。优化后的材料光照5 h后CO_(2)还原产物CO和CH_(4)的产量分别为7.87和4.88μmol·g^(-1)。相对于单相组分,CO和CH_(4)的产量明显提高。光催化活性的提高,归因于ZnFe_(2)O_(4)和WO_(3)异质结的形成以及光生载流子的S型电荷传输模式。

2022年四川芦山M_(S)6.1地震前应力状态研究

为研究2022年6月1日四川芦山M_(S)6.1地震的孕育和发生过程,采用CAP方法反演了2013年芦山M_(S)7.0主震及M_(S)≥5.0余震的震源机制解,并基于应力张量方差与b值时空分布特征,探讨了芦山M_(S)6.1地震的力学机制和震源区的应力状态。结果表明:2022年芦山M_(S)6.1地震震源机制表现出与2013年芦山M_(S)7.0主震和5级余震相似的逆冲型破裂特征,压应力轴方位与龙门山断裂带南段区域应力场一致。2013年芦山M_(S)7.0地震后震中及附近的应力张量方差和b值长期处于低值状态,2022年芦山M_(S)6.1地震前震中及附近出现了应力张量方差和b值的低值异常,表明芦山余震区处于较高的应力水平。分析认为:巴颜喀拉块体持续东向运动受到华南块体的阻挡,震中所在区域长期受挤压逆冲作用,从而使芦山余震区长期处于应力积累的状态,芦山M_(S)6.1地震也是在这种动力学背景下发生的。

阴道卷曲乳杆菌S层蛋白多样性研究

目的:分析比较西安市女性阴道卷曲乳杆菌S层蛋白的多样性及NCBI数据库中阴道来源卷曲乳杆菌S层蛋白的多样性。方法:选取100例妇科患者的阴道分泌物标本作为研究对象,从其中10例标本中分离得到480株卷曲乳杆菌,其中两株卷曲乳杆菌S层蛋白有明显差异,对其进行全基因组测序;并从NCBI数据库中下载人阴道源的卷曲乳杆菌全基因组数据,分析并比较西安市来源与数据库来源的卷曲乳杆菌S层蛋白的多样性。结果:S层蛋白注释基因具有菌株内和菌株间的多样性,同一套基因组中有多个S层蛋白注释基因,菌株间的相似性偏差较大,通过系统发育分析发现,中国人阴道卷曲乳杆菌的S层蛋白基因与其他人种的具有系统发育相似性。结论:阴道卷曲乳杆菌S层蛋白具有菌种间和菌株间多样性的特征,不同人种的卷曲乳杆菌具有相似性。

结合主动光源和改进YOLOv5s模型的夜间柑橘检测方法

【目的】解决夜间环境下遮挡和较小柑橘难以准确识别的问题,实现采摘机器人全天候智能化作业。【方法】提出一种结合主动光源的夜间柑橘识别方法。首先,通过分析主动光源下颜色特征不同的夜间柑橘图像,选择最佳的光源色并进行图像采集。然后,提出一种夜间柑橘检测模型BI-YOLOv5s,该模型采用双向特征金字塔网络(Bi-FPN)进行多尺度交叉连接和加权特征融合,提高对遮挡和较小果实的识别能力;引入Coordinate attention(CA)注意力机制模块,进一步加强对目标位置信息的提取;采用融入Transformer结构的C3TR模块,在减少计算量的同时更好地提取全局信息。【结果】本文提出的BI-YOLOv5s模型在测试集上的精准率、召回率、平均准确率分别为93.4%、92.2%和97.1%,相比YOLOv5s模型分别提升了3.2、1.5和2.3个百分点。在所采用的光源色环境下,模型对夜间柑橘识别的正确率为95.3%,相比白光环境下提高了10.4个百分点。【结论】本文提出的方法对夜间环境下遮挡和小目标柑橘的识别具有较高的准确性,可为夜间果蔬智能化采摘的视觉精准识别提供技术支持。

基于改进YOLOv5s的不同成熟度苹果目标检测方法

[目的]本文旨在解决在自然环境下不同成熟度苹果目标检测精度较低的问题。[方法]提出了一种改进的YOLOv5s模型SODSTR-YOLOv5s(YOLOv5s with small detection layer and omni-dimensional dynamic convolution and swin transformer block),用于不同成熟度苹果检测。首先改进YOLOv5s的多尺度目标检测层,在Prediction中构建检测160×160特征图的检测头,提高小尺寸的不同成熟度苹果的检测精度;其次在Backbone结构中融合Swin Transformer Block,加强同级成熟度的苹果纹理特征融合,弱化纹理特征分布差异带来的消极影响,提高模型泛化能力;最后将Neck结构的Conv模块替换为动态卷积模块ODConv,细化局部特征映射,实现局部苹果细粒度特征的充分提取。基于不同成熟度苹果数据集进行试验,验证改进模型的性能。[结果]改进模型SODSTR-YOLOv5s检测的精确率、召回率、平均精度均值分别为89.1%、95.5%、93.6%,高、中、低成熟度苹果平均精度均值分别为94.1%、93.1%、93.7%,平均检测时间为16 ms,参数量为7.34 M。相比于YOLOv5s模型,改进模型SODSTR-YOLOv5s精确率、召回率、平均精度均值分别提高了3.8%、5.0%、2.9%,参数量和平均检测时间分别增加了0.32 M和5 ms。[结论]改进模型SODSTR-YOLOv5s提升了在自然环境下对不同成熟度苹果的检测能力,能较好地满足实际采摘苹果的检测要求。

献血者HBVs基因变异的生物信息学分析

目的分析HBV DNA+/HBsAg-献血者的传染性指标、S区基因序列突变情况及生物信息学特征变化。方法通过PCR方法筛查出1份HBV DNA+/HBsAg-的标本,应用酶联免疫和化学发光方法检测该标本乙肝病毒5项指标,对该标本HBVs区基因片段测序并分析变异情况,应用分析软件对所测序列进行生物信息学分析。结果该标本HBV DNA+、HBsAg-、HBsAb+、HBeAg+、HBeAb-、HBcAb+;HBVs区基因序列内发生氨基酸单位点突变(P151L),空间结构发生改变。结论HBVs区基因序列空间结构改变,可能是导致检测结果出现血清学HBsAg-/HBsAb+/HBV DNA+的原因。

在片S参数计量比对结果浅析

中国电子科技集团公司第十三研究所作为主导实验室开展了在片S参数计量比对工作,对参比实验室提交的在片S参数测量结果进行了汇总分析,并用E_n值对各参比实验室测量结果进行了评价。通过在片S参数计量比对,确保了量值传递的准确、可靠,特别是对在片S参数测量不确定度的主要来源统一了认识。同时也为业内提供了在片S参数测量一致性的比较平台。

基于CED-YOLOv5s模型的煤矸识别方法研究

由于煤矿井下高噪声、低照度、运动模糊的复杂工况和煤矸易聚集现象,导致煤矸目标检测模型特征提取困难及煤矸分类、定位不准确问题。针对该问题,提出一种基于CED-YOLOv5s模型的煤矸识别方法。首先,在YOLOv5s主干网络中引入坐标注意力(CA)机制,通过将坐标信息嵌入信道关系和长程依赖关系中对特征图进行编码,充分利用通道注意力信息和空间注意力信息,使模型更加关注重要特征,抑制无用信息。其次,在YOLOv5s的检测头部引入EIoU回归损失函数,将目标框与锚框的宽高差异最小化,以增强目标的位置和边界信息,提高模型在密集目标下的定位精度和收敛速度;最后,在YOLOv5s的检测头部引入轻量化解耦头,解耦出单独的特征通道,分别用于分类任务和回归任务,解决了原模型中耦合头部分类任务与回归任务的相互干扰问题,进一步提升了模型的并行运算效率与检测精度。实验结果表明:CED-YOLOv5s模型与其他YOLO系列目标检测模型相比,综合性能最佳,平均检测精度达94.8%,相较于YOLOv5s模型提升了3.1%,检测速度达84.8帧/s,可充分满足煤矿井下煤矸实时检测需求。

基于数值模拟的高速公路S型曲线积水规律分析

S型曲线由于特殊的线型几何特征形成了易积水的路面区域,对于积水规律的掌握有利于在设计和建造阶段提前预防和处理积水路段的危害。该文基于计算流体力学软件Fluent,结合计算流体力学分析中基于欧拉-拉格朗日方法的欧拉液膜模型EWF(Eulerian Wall Film),针对精细化处理的典型S型曲线双向多车道道路模型进行模拟计算。模拟包含了几何特征与降雨量等不同变量因素,得出了积水的水膜厚度以及流速分布规律。模拟结果表明:在降雨阶段,S型曲线横坡坡度0%~1%路段为积水路段,横坡坡度1%~2%路段为易积水路段,横坡坡度大于2%的路段积水情况受到降雨强度影响;在排水阶段,S型曲线横坡坡度0%~1%路段为排水困难路段,横坡坡度1%~2%路段为排水不畅路段,横坡坡度大于2%的路段排水顺畅,在排水时间结束时,路面在不同的几何条件和降雨条件下均能将积水排除至水膜厚度小于2 cm,横坡的大小与渐变影响了积水的横向分布与纵向分布,横向呈现中间高两边低、横断面上标高大的位置水膜厚度小和标高小的位置水膜厚度大的水膜厚度分布规律,总体呈现S型的分布规律;水膜流速在积水阶段呈现纵向上中间低两边高、水膜厚度大则水膜流速大的水膜厚度分布规律,在排水阶段则为纵向上中间高两边低的水膜流速分布规律。道路宽度影响了降雨落到路面的积水总量,进而对积水水膜厚度产生了影响;超高缓和率则主要使得积水路段、易积水路段增长,从而影响了积水分布的范围。

S31603复合板压力容器点蚀行为试验研究

针对S31603复合板压力容器不锈钢层不同点蚀深度的发展进程及穿透至碳钢层后的电偶腐蚀风险,通过预制不同点蚀深度的S31603复合板试片组,分别在实验室和现场S31603复合板压力容器内进行腐蚀试验,并对试片进行宏观分析、低倍观察、高倍观察及腐蚀产物表征分析。结果表明,S31603复合板预制的点蚀坑深度穿透至碳钢层时发生了明显的电偶腐蚀,实验室腐蚀试验和现场试验最高点蚀速率分别达到4.954,1.023 mm/a;用S31603复合板试片预制的点蚀坑深度穿透至碳钢层后碳钢优先发生电偶腐蚀;S31603复合板试片预制的点蚀坑深度处于不锈钢层时腐蚀轻微,也未萌生新的点蚀,相邻点蚀坑之间也未见明显的腐蚀影响。在含Cl-的酸性腐蚀性介质环境下,当S31603复合板压力容器点蚀深度处于不锈钢层时腐蚀轻微,当点蚀深度穿透至碳钢层后,会发生明显的电偶腐蚀,需要缩短S31603复合板压力容器开罐检修周期以保证安全使用。

基于CFS-YOLO算法的复杂工况环境下煤矸图像识别方法

针对煤矿高噪声、低照度、运动模糊与大批量煤矸混杂等复杂工况环境因素导致煤矸识别存在误检、漏检以及检测精度低的问题,提出一种基于CFS-YOLO算法的煤矸智能识别模型。采用ConvNeXt V2(Convolutional Neural Network with NeXt Units Version 2)特征提取模块替换主干网络末端的2个C3(Cross Stage Partial Bottle Neck Mudule)模块,通过将掩码自动编码器(Masked Autoencoders,MAE)和全局响应归一化(Global Response Normalization,GRN)层添加到ConvNeXt架构中,有效缓解特征崩溃问题以及保持特征在网络传递过程中的多样性;采用Focal-EIOU(Focal and Efficient Intersection Over Union)损失函数替换原CIOU(Computer Intersection Over Union)损失函数,通过其Focal-Loss机制和调整样本权重的方式优化边界框回归任务中的样本不平衡问题,提高模型的收敛速度和定位精度;添加无参注意力机制(Simple Attention Mechanism,SimAM)于主干网络每个C3模块的后端,凭借其注意力权重自适应调整策略,提升模型对尺度变化较大或低分辨率煤矸目标关键特征的提取能力。通过消融试验和对比试验验证所提CFS-YOLO模型的有效性与优越性。试验结果表明:CFS-YOLO模型对于煤矸在煤矿高噪声、低照度、运动模糊与大批量煤矸混杂等复杂环境下的检测效果均得到有效提高,模型的平均精度均值达到90.2%,相较于原YOLOv5s模型的平均精度均值提高了3.7%,平均检测速度达到90.09 FPS,可充分满足煤矸实时检测的需求。同时与YOLOv5s、YOLOv7-tiny与YOLOv8n等6种YOLO系列算法相比,CFS-YOLO模型对煤矿复杂环境的适应性最强且综合检测性能最佳,可为煤矸的智能高效分选提供技术支持。