检索结果-南通市图书馆

一种SSD-RTF输电线路小目标检测算法研究

在线全文

学校读者我要写书评

暂无评论

重庆理工大学学报（自然科学） 2024年第9期38卷 150-157页

作者：唐心亮李少杰王建超王震洲河北科技大学信息科学与工程学院石家庄050018

针对传统输电线路无人机巡检图像检测方法对输电线路小目标检测能力弱,并且存在错检和漏检率高、浅层网络语义信息不足等问题,提出了一种SSD-RTF输电线路小目标检测算法模型。在原始的SSD算法主干网络VGG-16浅层网络层添加视觉机制扩大... 详细信息

针对传统输电线路无人机巡检图像检测方法对输电线路小目标检测能力弱,并且存在错检和漏检率高、浅层网络语义信息不足等问题,提出了一种SSD-RTF输电线路小目标检测算法模型。在原始的SSD算法主干网络VGG-16浅层网络层添加视觉机制扩大感受野,并且引入三叉乾特征融合模块提取特征图的多尺度特征,增加特征图的鲁棒性;融合FusionNet浅层特征模块,从而增加小目标的提取能力;使用注意力机制提升对关键信息的学习效果,从而提高目标检测效率;改进非极大值抑制提高网络的表示能力。改进后的SSD-RTF算法在自行构建的输电线数据集上的实验结果显示,在检测小目标时的准确性和实时性都有了一定的提高,整体mAP上升了7.5%,同时减少了错检和漏检。

关键词：目标检测浅层融合三叉乾特征融合视觉机制非极大值抑制

A Transmission and Transformation Fault Detection Algorithm Based on Improved YOLOv5

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第9期76卷 2997-3011页

作者： xinliang tang Xiaotong Ru Jingfang Su Gabriel Adonis School of Information Science and Engineering Hebei University of Science and TechnologyShijiazhuang050000China Department of Computer Science and Information Systems Birkbeck Institute for Data AnalyticsLondonB100ABWC1E 7HXUK

On the transmission line,the invasion of foreign objects such as kites,plastic bags,and balloons and the damage to electronic components are common transmission line *** these faults is of great significance for the safe operation of power ***,a YOLOv5 target detection method based on a deep convolution neural network is *** this paper,Mobilenetv2 is used to replace Cross Stage Partial(CSP)-Darknet53 as the *** structure uses depth-wise separable convolution to reduce the amount of calculation and parameters;improve the detection *** the same time,to compensate for the detection accuracy,the Squeeze-and-Excitation Networks(SENet)attention model is fused into the algorithm framework and a new detection scale suitable for small targets is added to improve the significance of the fault target area in the *** pictures of foreign matters such as kites,plastic bags,balloons,and insulator defects of transmission lines,and sort theminto a data *** experimental results on datasets show that themean Accuracy Precision(mAP)and recall rate of the algorithm can reach 92.1%and 92.4%,*** the same time,by comparison,the detection accuracy of the proposed algorithm is higher than that of other methods.

关键词： Transmission line YOLOv5 multi-scale integration SENet

An Elevator Button Recognition Method Combining YOLOv5 and OCR

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

计算机、材料和连续体（英文） 2023年第4期75卷 117-131页

作者： xinliang tang Caixing Wang Jingfang Su Cecilia Taylor School of Information Science and Engineering Hebei University of Science and TechnologyShijiazhuang050000China Nankai-Birmingham Institute of Data Science Intelligence BirminghamB100ABBritain

Fast recognition of elevator buttons is a key step for service robots toride elevators automatically. Although there are some studies in this field, noneof them can achieve real-time application due to problems such as recognitionspeed and algorithm complexity. Elevator button recognition is a comprehensiveproblem. Not only does it need to detect the position of multiple buttonsat the same time, but also needs to accurately identify the characters on eachbutton. The latest version 5 of you only look once algorithm (YOLOv5) hasthe fastest reasoning speed and can be used for detecting multiple objects inreal-time. The advantages ofYOLOv5 make it an ideal choice for detecting theposition of multiple buttons in an elevator, but it’s not good at specific wordrecognition. Optical character recognition (OCR) is a well-known techniquefor character recognition. This paper innovatively improved the YOLOv5network, integrated OCR technology, and applied them to the elevator buttonrecognition process. First, we changed the detection scale in the YOLOv5network and only maintained the detection scales of 40 ∗ 40 and 80 ∗ 80, thusimproving the overall object detection speed. Then, we put a modified OCRbranch after the YOLOv5 network to identify the numbers on the ***, we verified this method on different datasets and compared it withother typical methods. The results show that the average recall and precisionof this method are 81.2% and 92.4%. Compared with others, the accuracyof this method has reached a very high level, but the recognition speed hasreached 0.056 s, which is far higher than other methods.

关键词： Button recognition deep learning multi-object detection

基于改进Deeplabv3+的电力线分割方法研究

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

国外电子测量技术 2024年第3期43卷 43-49页

作者：唐心亮赵冰雪韩明宿景芳河北科技大学信息科学与工程学院石家庄050018 石家庄学院未来信息技术学院石家庄050035

针对已有的分割算法存在的复杂场景干扰大、分割不准确的问题,提出一种用于电力线分割任务的改进Deeplabv3+模型。将原始主干网络替换为轻量级Mobilenetv2网络,增加低水平特征,获得5路输入特征,充分提取特征信息;添加空洞空间金字塔池化... 详细信息

针对已有的分割算法存在的复杂场景干扰大、分割不准确的问题,提出一种用于电力线分割任务的改进Deeplabv3+模型。将原始主干网络替换为轻量级Mobilenetv2网络,增加低水平特征,获得5路输入特征,充分提取特征信息;添加空洞空间金字塔池化(atrous spatial pyramid pooling,ASPP)的卷积分支数量,调整空洞率,提升图像的特征抓取能力,进一步在每个空洞卷积后加入1×1卷积操作,加快计算速度;提出一种基于坐标注意力机制的语义嵌入分支模块(coordinate attention semantic embedding branch,CASEB),融合第2、3路特征,增强目标特征的表示;引入卷积注意力机制模块(convolution block attention module,CBAM)抑制无用信息的传递,提高模型识别效率。实验结果表明,相对于原Deeplabv3+模型,改进模型在平均像素精度(mean pixel attention,MPA)和平均交并比(mean intersection over union,mIoU)上分别提升2.37%和3.42%,该方法可提供更加精确的电力线分割结果。

关键词：电力线分割深度学习改进Deeplabv3+模型 Mobilenetv2 注意力模块

Research on the Pedestrian Re-Identification Method Based on Local Features and Gait Energy Images

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第8期64卷 1185-1198页

作者： xinliang tang Xing Sun Zhenzhou Wang Pingping Yu Ning Cao Yunfeng Xu Hebei University of Science and Technology Shijiazhuang050000China School of Internet of Things and Software Technology Wuxi Vocational College of Science and TechnologyWuxi214028China Rutgers Business School-Newark Washington ParkNewarkNJ 07102USA

The appearance of pedestrians can vary greatly from image to image,and different pedestrians may look similar in a given *** similarities and variabilities in the appearance and clothing of individuals make the task of pedestrian re-identification very ***,a pedestrian re-identification method based on the fusion of local features and gait energy image(GEI)features is *** this method,the human body is divided into four regions according to joint *** color and texture of each region of the human body are extracted as local features,and GEI features of the pedestrian gait are also *** features are then fused with the local and GEI features of the *** distance measure learning using the cross-view quadratic discriminant analysis(XQDA)method is used to obtain the similarity of the metric function of the image pairs,and the final similarity is acquired by weight *** of experimental results by cumulative matching characteristic(CMC)curves reveals that,after fusion of local and GEI features,the pedestrian re-identification effect is improved compared with existing methods and is notably better than the recognition rate of pedestrian re-identification with a single feature.

关键词： Local features gait energy image weight independent distance metric cross-view quadratic discriminant analysis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

水浴式汽化器节水降耗研究与应用

化工设计通讯 2024年第3期50卷 63-65页

作者：杨晓娟唐新亮张云程小勇景旭升华亭华煤清能煤化工有限责任公司甘肃平凉744100

水浴式汽化器是一种将水加热,以水为传热介质,将液态气体转化为气态气体的设备。在大型空分装置中,水浴式汽化器的作用是将液态氧、氮等气体吸收足够的热量,使其转变为气态,以满足工业生产的需求。在正常运行时,我公司水浴式汽化器需不... 详细信息

水浴式汽化器是一种将水加热,以水为传热介质,将液态气体转化为气态气体的设备。在大型空分装置中,水浴式汽化器的作用是将液态氧、氮等气体吸收足够的热量,使其转变为气态,以满足工业生产的需求。在正常运行时,我公司水浴式汽化器需不断补入一次水保证满液位,使盘管能够全浸其中,保证换热充分,此技术改造的特点是在设备本体上增加了就地液位计,通过补水阀将液位控制在不低于换热管束高度,不高于溢流口高度的限范围内;水浴式汽化器改造后在运行期间,将水浴式汽化器内的液位控制在上下限范围内,且经过多次长时间运行试验,能够满足其实际运行需求,未出现过水浴式汽化器出口温度不达标的问题,彻底解决了溢流水直排问题,为公司节水减排管理及环保管理工作降低了难度和风险,既满足了“节水减排”要求,又能长期稳定运行。

关键词：空分设备水浴式汽化器低温液体节能降耗

Semisynthesis of homogeneous spike RBD glycoforms from SARS-CoV-2 for profiling the correlations between glycan composition and function

在线全文

学校读者我要写书评

暂无评论

National Science Review 2024年第2期11卷 145-154页

作者： Farong Ye Cheng Li Feng-Liang Liu xinliang Liu Peng Xu Rong-Hua Luo Wenping Song Yong-tang Zheng Tianlei Ying Biao Yu Ping Wang Center for Chemical Glycobiology Frontiers Science Center for Transformative Molecules Zhangjiang Institute for Advanced Study School of Chemistry and Chemical Engineering Shanghai Jiao Tong University MOE/NHC/CAMS Key Laboratory of Medical Molecular Virology Shanghai Frontiers Science Center of Pathogenic Microorganisms and Infection Shanghai Institute of Infectious Disease and BiosecurityShanghai Engineering Research Center for Synthetic ImmunologySchool of Basic Medical Sciences Shanghai Medical College Fudan University Key Laboratory of Animal Models and Human Disease Mechanisms of Chinese Academy of Sciences/Key Laboratory of Bioactive Peptides of Yunnan Province Center for Biosafety Mega-Science Kunming Institute of ZoologyChinese Academy of Sciences State Key Laboratory of Bioorganic and Natural Products Chemistry Center for Excellence in Molecular Synthesis Shanghai Institute of Organic Chemistry Chinese Academy of Sciences Shenzhen Research Institute of Shanghai Jiao Tong University

Vaccines have been the primary remedy in the global fight against coronavirus disease 2019（COVID-19）.The receptor-binding domain（RBD） of the spike protein, a critical viral immunogen, is affected by the heterogeneity of its glycan structures and relatively low immunogenicity. Here, we describe a scalable synthetic platform that enables the precise synthesis of homogeneously glycosylated RBD, facilitating the elucidation of carbohydrate structure–function relationships. Five homogeneously glycosylated RBDs bearing biantennary glycans were prepared, three of which were conjugated to T-helper epitope(Tpep) from tetanus toxoid to improve their weak immune response. Relative to natural HEK293-derived RBD, synthetic RBDs with biantennary N-glycan elicited a higher level of neutralising antibodies against SARS-CoV-2 in mice. Furthermore, RBDs containing Tpepelicited significant immune responses in transgenic mice expressing human angiotensin-converting enzyme 2. Our collective data suggest that trimming the N-glycans and Tpepconjugation of RBD could potentially serve as an effective strategy for developing subunit vaccines providing efficient protection.

关键词： peptide ligation glycosylation glycoprotein

A Nonuniform Clustering Routing Algorithm Based on an Improved K-Means Algorithm

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第9期64卷 1725-1739页

作者： xinliang tang Man Zhang Pingping Yu Wei Liu Ning Cao Yunfeng Xu School of Information Science and Engineering Hebei University of Science and TechnologyShijiazhuang050000China Hebei Chemical and Pharmaceutical College Hebei Seismological BureauShijiazhuang050000China School of Internet of Things and Software Technology Wuxi Vocational College of Science and TechnologyWuxi214028China Rutgers Business School-Newark Washington ParkNewarkNJ 07102USA

In a large-scale wireless sensor network(WSN),densely distributed sensor nodes process a large amount of *** aggregation of data in a network can consume a great amount of *** balance and reduce the energy consumption of nodes in a WSN and extend the network life,this paper proposes a nonuniform clustering routing algorithm based on the improved K-means *** algorithm uses a clustering method to form and optimize clusters,and it selects appropriate cluster heads to balance network energy consumption and extend the life cycle of the *** ensure that the cluster head(CH)selection in the network is fair and that the location of the selected CH is not concentrated within a certain range,we chose the appropriate CH competition *** results show that,compared with LEACH,LEACH-C,and the DEEC clustering algorithm,this algorithm can effectively balance the energy consumption of the CH and extend the network life.

关键词： WSN node energy consumption nonuniform clustering routing algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

具有生物活性的色满衍生物不对称合成研究

化学进展 2008年第4期20卷 518-525页

作者：王桂霞王乃兴唐石于金兰汤新亮中国科学院理化技术研究所北京100080 北京理工大学化工与环境学院北京100081

色满衍生物在自然界中广泛存在,并且大多数具有生物活性。这些具有生物活性的色满衍生物很多又具有手性,因此有关它们的不对称合成已经引起了有机合成工作者的广泛关注。合成色满衍生物的关键是构建含有手性中心的色满环。本文根据色满... 详细信息

色满衍生物在自然界中广泛存在,并且大多数具有生物活性。这些具有生物活性的色满衍生物很多又具有手性,因此有关它们的不对称合成已经引起了有机合成工作者的广泛关注。合成色满衍生物的关键是构建含有手性中心的色满环。本文根据色满环构建方式的不同进行分类,概述了近十几年来合成手性色满衍生物的新方法,侧重讨论了各种合成方法在合成立体结构专一的色满环时的特点。

关键词：色满衍生物生物活性分子不对称合成环化