检索结果-南通市图书馆

Light bottle transformer based large scale point cloud classification

在线全文

学校读者我要写书评

暂无评论

Optoelectronics Letters 2023年第6期19卷 377-384页

作者： XIE En zhang Zhiyong zhang guodao CHEN Pingkuo GE Yisu College of Computer Information and Engineering Nanchang Institute of TechnologyNanchang 330044China School of Information Engineering East China University of TechnologyNanchang 330000China Department of Digital Media Technology Hangzhou Dianzi UniversityHangzhou 310023China Great Bay University Dongguan 523000China College of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou 325100China

With the rapid development of computer vision,point clouds technique was widely used in practical applications,such as obstacle detection,roadside detection,smart city construction,***,how to efficiently identify the large scale point clouds is still an open *** relieving the large computation consumption and low accuracy problem in point cloud classification,a large scale point cloud classification framework based on light bottle transformer(light-Bot Net)is ***,the two-dimensional(2D)and three-dimensional(3D)feature values of large scale point cloud were extracted for constructing point cloud feature images,which employed the prior knowledge to normalize the point cloud ***,the feature images are input to the classification network,and the light-Bot Net network is applied for point cloud *** is an interesting attempt to combine the traditional image features with the transformer *** proving the performance of the proposed method,the large scale point cloud benchmark Oakland 3D is *** the experiments,the proposed method achieved 98.1%accuracy on the Oakland 3D *** with the other methods,it can both reduce the memory consumption and improve the classification accuracy in large scale point cloud classification.

关键词： computer cloud point

Learning Discriminatory Information for Object Detection on Urine Sediment Image

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第1期138卷 411-428页

作者： Sixian Chan Binghui Wu guodao zhang Yuan Yao Hongqiang Wang College of Computer Science and Technology Zhejiang University of TechnologyHangzhou310023China The Hefei Institutes of Physical Science Chinese Academy of SciencesHefei230071China Department of Digital Media Technology Hangzhou Dianzi UniversityHangzhou310018China School of Computer Science University of Nottingham Ningbo ChinaNingbo315100China

In clinical practice,the microscopic examination of urine sediment is considered an important in vitro examination with many broad *** the amount of each type of urine sediment allows for screening,diagnosis and evaluation of kidney and urinary tract disease,providing insight into the specific type and ***,manual urine sediment examination is labor-intensive,time-consuming,and *** machine learning based object detection methods require hand-crafted features for localization and classification,which have poor generalization capabilities and are difficult to quickly and accurately detect the number of urine *** learning based object detection methods have the potential to address the challenges mentioned above,but these methods require access to large urine sediment image ***,only a limited number of publicly available urine sediment datasets are currently *** alleviate the lack of urine sediment datasets in medical image analysis,we propose a new dataset named UriSed2K,which contains 2465 high-quality images annotated with expert *** main challenges are associated with our dataset:a large number of small objects and the occlusion between these small *** manuscript focuses on applying deep learning object detection methods to the urine sediment dataset and addressing the challenges presented by this ***,our goal is to improve the accuracy and efficiency of the detection algorithm and,in doing so,provide medical professionals with an automatic detector that saves time and *** propose an improved lightweight one-stage object detection algorithm called *** proposed algorithm comprises a local context attention module and a global background suppression module,which aid the detector in distinguishing urine sediment features in the *** local context attention module captures context information beyond the object region,

关键词： Object detection attention mechanism medical image urine sediment

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

稀疏诱导流形正则化凸非负矩阵分解算法

通信学报 2020年第5期41卷 84-95页

作者：邱飞岳陈博文陈铁明章国道浙江工业大学教育科学与技术学院浙江杭州310023 浙江工业大学计算机科学与技术学院浙江杭州310023

针对非负矩阵分解方法在有噪声的真实数据中获得特征的有效性问题,提出了一种稀疏诱导的流形正则化凸非负矩阵分解算法。所提算法在流形正则化的基础上,向低维子空间的基矩阵添加基于L2,1范数的稀疏约束,构建了乘法更新规则,分析在该规... 详细信息

针对非负矩阵分解方法在有噪声的真实数据中获得特征的有效性问题,提出了一种稀疏诱导的流形正则化凸非负矩阵分解算法。所提算法在流形正则化的基础上,向低维子空间的基矩阵添加基于L2,1范数的稀疏约束,构建了乘法更新规则,分析在该规则下算法的收敛性,并设计了在低维子空间上不同噪声环境下的聚类实验。K均值聚类实验结果表明,稀疏约束降低了噪声特征在学习中的表达能力,所提算法在不同程度上优于同类8种算法,对噪声有更强的稳健性。

关键词：非负矩阵分解流形正则化稀疏约束 K均值聚类

在线全文

学校读者我要写书评

暂无评论

基于二值神经网络的大场景点云分类

光电子．激光 2022年第4期33卷 364-372页

作者：章国道刘儒瑜张志勇孔德伟邱飞岳浙江工业大学计算机科学与技术学院浙江杭州310023 杭州师范大学信息科学与技术学院浙江杭州311121 浙江工业大学教育科学与技术学院浙江杭州310023

近年随着3维数据采集技术不断发展,大场景点云数据的获取越来越方便。目前深度学习网络框架在2维图像处理领域越来越成熟,而大场景点云是一种3维无规则化的数据,3维卷积神经网络直接处理大场景3维数据会存在分类精度低和计算复杂等问题... 详细信息

近年随着3维数据采集技术不断发展,大场景点云数据的获取越来越方便。目前深度学习网络框架在2维图像处理领域越来越成熟,而大场景点云是一种3维无规则化的数据,3维卷积神经网络直接处理大场景3维数据会存在分类精度低和计算复杂等问题。因此为了有效解决基于深度学习的点云分类任务中存在的计算时间长和分类精度低的问题,本文提出基于二值神经网络的大场景点云分类方法,针对不规则的3维点云数据设计特征值计算方法,基于IR-Net二值神经网络处理输入的点云特征图像,进一步采用Dynamic ReLU激活函数,提高神经网络的计算效率,最后得出点云分类结果。实验结果表明,所提出的方法在Oakland数据集上分类精度达到97.6%,在GML数据集中取得了92.3%和97.2%的分类精度,实验结果证明Dy-ResNet能够有效提升了点云分类的精度,减少计算的复杂度,并提高了训练效率。

关键词：特征图特征融合二值神经网络大场景点云分类

在线全文

学校读者我要写书评

暂无评论

高校九零后团学干部培养的问题和对策

科教导刊 2016年第12Z期 165-166页

作者：章国道叶紫吴潮温州大学城市学院浙江温州325000 温州医科大学浙江温州325035

团学干部队伍的建设中最中坚的队伍就是各大高校的团学干部,各大高校的学生工作中最重要的组成部分也是团学干部队伍,高校的发展及稳定与之息息相关。通过探讨培养高校团学干部的重要性以及存在的问题,提出高可行性的对策和方法,有利于... 详细信息

团学干部队伍的建设中最中坚的队伍就是各大高校的团学干部,各大高校的学生工作中最重要的组成部分也是团学干部队伍,高校的发展及稳定与之息息相关。通过探讨培养高校团学干部的重要性以及存在的问题,提出高可行性的对策和方法,有利于学生工作的高效开展。

关键词：团委学生会学生干部高校选拔培养

Towards a better understanding of the role of visualization in online learning:A review

在线全文

学校读者我要写书评

暂无评论

Visual Informatics 2022年第4期6卷 22-33页

作者： Gefei zhang Zihao Zhu Sujia Zhu Ronghua Liang guodao Sun College of Computer Science and Technology Zhejiang University of TechnologyHangzhou310023China

With the popularity of online learning in recent decades,MOOCs(Massive Open Online Courses)are increasingly pervasive and widely used in many *** online learning is particularly important because it helps to analyze learner performance,evaluate the effectiveness of online learning platforms,and predict dropout *** to the large-scale,high-dimensional,and heterogeneous characteristics of the data obtained from online learning,it is difficult to find hidden *** this paper,we review and classify the existing literature for online learning to better understand the role of visualization in online *** taxonomy is based on four categorizations of online learning tasks:behavior analysis,behavior prediction,learning pattern exploration and assisted *** on our review of relevant literature over the past decade,we also identify several remaining research challenges and future research work.

关键词： Visualization in education Online learning Visual analytics

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

元启发式算法在特征选择中的应用研究

福建电脑 2024年第9期40卷 22-25页

作者：徐枫哲颜赫伟顾俊锴王毛奕陆炎杰章国道杭州电子科技大学人文艺术与数字媒体学院杭州310018

2型糖尿病是影响中老年人生命质量的疾病。及早发现糖尿病能延缓疾病并发症,可以提高病人的生存质量。为辅助检测2型糖尿病的患病风险,本文提出了一种基于元启发的特征选取方法,用于构建糖尿病患病风险预测模型时的特征选取。对比实验... 详细信息

2型糖尿病是影响中老年人生命质量的疾病。及早发现糖尿病能延缓疾病并发症,可以提高病人的生存质量。为辅助检测2型糖尿病的患病风险,本文提出了一种基于元启发的特征选取方法,用于构建糖尿病患病风险预测模型时的特征选取。对比实验的结果表明,本文方法能提高特征抽取的速度和相对准确度,可用于构建2型糖尿病患病风险的预测模型。

关键词： 2型糖尿病特征选择元启发式算法

在线全文

学校读者我要写书评

暂无评论

中轴性脊柱关节炎的病灶分割方法

福建电脑 2024年第9期40卷 55-58页

作者：郏奕涵叶可宁林泽钰陈尊桓叶铭滔章国道杭州电子科技大学人文艺术与数字媒体学院浙江杭州310018 杭州电子科技大学上虞科学与工程研究院有限公司浙江绍兴312300

中轴性脊柱关节炎会造成脊柱或受累关节的强直畸形。目前磁共振成像是诊断中轴性脊柱关节炎的主要方法。但人工诊断该疾病时,骶髂关节处磁共振图像具有人工成本高、效率低等问题。为辅助诊断中轴性脊柱关节炎,本文提出一种基于U-Net的... 详细信息

中轴性脊柱关节炎会造成脊柱或受累关节的强直畸形。目前磁共振成像是诊断中轴性脊柱关节炎的主要方法。但人工诊断该疾病时,骶髂关节处磁共振图像具有人工成本高、效率低等问题。为辅助诊断中轴性脊柱关节炎,本文提出一种基于U-Net的病灶分割方法,自动提取骶髂关节处MRI图像中的病变区域。实验的结果表明,基于U-net的病灶分割算法平均的Dice系数值为0.78,准确性较高,能有效地解决辅助诊断的问题。

关键词：中轴性脊柱关节炎磁共振成像 U-Net神经网络病灶分割

Telomere-to-telomere genome of the allotetraploid legume Sesbania cannabina reveals transposon-driven subgenome divergence and mechanisms of alkaline stress tolerance

在线全文

学校读者我要写书评

暂无评论

Science China(Life Sciences) 2024年第1期67卷 149-160页

作者： Haofei Luo Xiaofei Wang Changqing You Xuedan Wu Duofeng Pan Zhiyao Lv Tong Li Dongmei zhang Zhongbao Shen Xiaodong zhang guodao Liu Kaixuan He Qingtong Ye Yajun Jia Qinghua Zhao Xian Deng Xiaofeng Cao Xianwei Song Gai Huang State Key Laboratory of Plant Genomics and National Center for Plant Gene Research Institute of Genetics and Developmental BiologyChinese Academy of SciencesBeijing 100101China Hainan Yazhou Bay Seed Lab Sanya 572025China University of Chinese Academy of Sciences Beijing 100049China Institute of Forage and Grassland Sciences Heilongjiang Academy of Agricultural SciencesHarbin 150086China Shandong Academy of Agricultural Sciences Jinan 250100China National Center of Technology Innovation for Comprehensive Utilization of Saline-Alkali Land Dongying 257345China Shandong Green Manure Ecological Technology Co. LtdDongying 257345China State Key Laboratory of Tropical Crop Breeding Chinese Academy of Tropical Agricultural SciencesHaikou 571101China

Alkaline soils pose an increasing problem for agriculture worldwide,but using stress-tolerant plants as green manure can improve marginal ***,we show that the legume Sesbania cannabina is very tolerant to alkaline conditions and,when used as a green manure,substantially improves alkaline *** understand genome evolution and the mechanisms of stress tolerance in this allotetraploid legume,we generated the first telomere-to-telomere genome assembly of *** spanning~2,087 *** assembly included all centromeric regions,which contain centromeric satellite repeats,and complete chromosome ends with telomeric *** genome analysis distinguished A and B subgenomes,which diverged approximately 7.9 million years *** genomic analysis revealed that the chromosome homoeologs underwent large-scale inversion events(>10 Mb)and a significant,transposon-driven size expansion of the chromosome 5A *** further identified four specific alkali-induced phosphate transporter genes in ***;these may function in alkali tolerance by relieving the deficiency in available phosphorus in alkaline *** work highlights the significance of *** as a green tool to improve marginal lands and sheds light on subgenome evolution and adaptation to alkaline soils.

关键词： Sesbania cannabina alkaline stress telomere-to-telomere genome legume green manure phosphate transporter allotetraploid

同方期刊数据库