检索结果-南通市图书馆

Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 231-239页

作者： Yahui Liu bin tian Yisheng Lv Lingxi Li Fei-Yue Wang the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190 IEEE the Transportation and Autonomous Systems Institute(TASI)and the Department of Electrical and Computer Engineering Purdue School of Engineering and TechnologyIndiana University-Purdue University Indianapolis(IUPUI)Indianapolis 46202 USA

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://***/yahuiliu99/PointC onT.

关键词： Content-based Transformer deep learning feature aggregator local attention point cloud classification

Functional properties of defatted chickpea flour heat-induced gels

在线全文

学校读者我要写书评

暂无评论

International Journal of Agricultural and Biological Engineering 2024年第2期17卷 280-286页

作者： Chonghao Bi Aoxue Qie Tong Zhou Yi Liu bin tian School of Artificial Intelligence Beijing Technology and Business UniversityBeijing 100048China

Defatted chickpea flour(DCF),which is a by-product of chickpea oil extraction industry,is rich in nutrients that are beneficial to human *** this study,the effects of temperature and DCF variation on the rheological properties,water holding capacity,freeze-thaw stability and microstructure of DCF heat induced gels were *** results showed that the viscoelasticity,frequency dependence,and resistance strength of heat induced gels increased significantly with the increase of temperature and DCF *** degree of denaturation and water retention of heat induced gels increased significantly with increased variables within the temperature and variation windows of 75℃ to 95℃ and 13%to 21%.The CLSM results revealed that variations of both temperature and DCF variation could cause the proteins in the heat induced gels to aggregate gradually and to form protein *** temperature or variation exceeded certain value(85℃ or 17%),the protein aggregations broke up and the protein clusters became smaller and more ***,the heat induced gels presented better water holding capacity,viscoelasticity,structural stability and gel property at a temperature of 95℃ or a DCF variation of 21%within the present experimental range.

关键词： defatted chickpea flour rheological property freeze-thaw stability water holding capacity microstructure

Construction and validation of a pancreatic cancer prognostic model based on genes related to the hypoxic tumor microenvironment

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Gastroenterology 2024年第36期30卷 4057-4070页

作者： Fan Yang Na Jiang Xiao-Yu Li Xing-Si Qi Zi-bin tian Ying-Jie Guo Department of Gastroenterology The Affiliated Hospital of Qingdao UniversityQingdao 266000Shandong ProvinceChina

BACKGROUND Pancreatic cancer is one of the most lethal malignancies,characterized by poor prognosis and low survival *** prognostic factors for pancreatic cancer offer inadequate predictive accuracy,often failing to capture the complexity of the *** hypoxic tumor microenvironment has been recognized as a significant factor influencing cancer progression and resistance to *** study aims to develop a prognostic model based on key hypoxia-related molecules to enhance prediction accuracy for patient outcomes and to guide more effective treatment strategies in pancreatic *** To develop and validate a prognostic model for predicting outcomes in patients with pancreatic cancer using key hypoxia-related *** This pancreatic cancer prognostic model was developed based on the expression levels of the hypoxia-associated genes CAPN2,PLAU,and *** results were validated in an independent *** study also examined the correlations between the model risk score and various clinical features,components of the immune microenvironment,chemotherapeutic drug sensitivity,and metabolism-related ***-time quantitative PCR verification was conducted to confirm the differential expression of the target genes in hypoxic and normal pancreatic cancer cell *** The prognostic model demonstrated significant predictive value,with the risk score showing a strong correlation with clinical features:It was significantly associated with tumor grade(G)(bP<0.01),moderately associated with tumor stage(T)(aP<0.05),and significantly correlated with residual tumor(R)status(bP<0.01).There was also a significant negative correlation between the risk score and the half-maximal inhibitory concentration of some chemotherapeutic ***,the risk score was linked to the enrichment of metabolism-related pathways in pancreatic *** The prognostic model based on hypoxia-related genes effectively predicts pancreati

关键词： Pancreatic cancer Hypoxia Prognostic model Immune microenvironment Metabolism pathway

Effects of the addition of edible polysaccharides on the properties of soybean protein isolate gels

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Agricultural and Biological Engineering 2024年第3期17卷 241-248页

作者： Chonghao Bi Aoxue Qie Xueying Wang Tong Zhou Shangyi Chi Yi Liu bin tian School of Artificial Intelligence Beijing Technology and Business UniversityBeijing 100048China

The gel properties of soybean isolate protein(SPI)gels are susceptible to the influence of other components in food products,particularly edible ***,six common edible polysaccharides were selected in this study to investigate their effects on the rheological properties,thermal properties,and microstructure of acid-induced soybean isolate protein self-assembled gels(SPIASG).The experimental results showed that the support capacity and creep recovery of SPIASG with added polysaccharides were higher than those of the control group without added polysaccharides,and the gel with Xanthan gum(XG)was the most *** hybrid gel,with added Condensed resin(CR),Xanthan gum(XG),Carrageenan(CA),and CMC formed a stronger network ***,compared with SPIASG,the hybrid gel with added edible polysaccharides the water-holding capacity of SPI hybrid gels was relatively *** this study,a simple and easy method was obtained to significantly improve the gel properties of SPIASG,analyzed and compared the effectiveness of various polysaccharides to enhance its gel properties,and provided some ideas to improve the gel properties of SPI protein gels.

关键词： soybean protein isolate gels self-assembled gels edible polysaccharides rheological properties

Vulnerable brain regions in adolescent major depressive disorder:A resting-state functional magnetic resonance imaging activation likelihood estimation meta-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

World Journal of Psychiatry 2024年第3期14卷 456-466页

作者： Hui Ding Qin Zhang Yan-Ping Shu bin tian Ji Peng Yong-Zhe Hou Gang Wu Li-Yun Lin Jia-Lin Li Department of Radiology The Second People’s Hospital of Guizhou ProvinceGuiyang 550000Guizhou ProvinceChina Department of Radiology Guizhou Provincial People’s HospitalGuiyang 550000Guizhou ProvinceChina Department of Psychiatry of Women and Children The Second People's Hospital of Guizhou ProvinceGuiyang 550000Guizhou ProvinceChina Department of Radiology Zhijin County People's HospitalBijie 552100Guizhou ProvinceChina Medical Humanities College Guizhou Medical UniversityGuiyang 550000Guizhou ProvinceChina

BACKGROUND Adolescent major depressive disorder(MDD)is a significant mental health concern that often leads to recurrent depression in ***-state functional magnetic resonance imaging(rs-fMRI)offers unique insights into the neural mechanisms underlying this ***,despite previous research,the specific vulnerable brain regions affected in adolescent MDD patients have not been fully *** To identify consistent vulnerable brain regions in adolescent MDD patients using rs-fMRI and activation likelihood estimation(ALE)*** We performed a comprehensive literature search through July 12,2023,for studies investigating brain functional changes in adolescent MDD *** utilized regional homogeneity(ReHo),amplitude of low-frequency fluctuations(ALFF)and fractional ALFF(fALFF)*** compared the regions of aberrant spontaneous neural activity in adolescents with MDD vs healthy controls(HCs)using *** Ten studies(369 adolescent MDD patients and 313 HCs)were *** the ReHo and ALFF/fALFF data,the results revealed that the activity in the right cuneus and left precuneus was lower in the adolescent MDD patients than in the HCs(voxel size:648 mm3,P<0.05),and no brain region exhibited increased *** on the ALFF data,we found decreased activity in the right cuneus and left precuneus in adolescent MDD patients(voxel size:736 mm3,P<0.05),with no regions exhibiting increased *** Through ALE meta-analysis,we consistently identified the right cuneus and left precuneus as vulnerable brain regions in adolescent MDD patients,increasing our understanding of the neuropathology of affected adolescents.

关键词： Major depressive disorder Resting-state functional magnetic resonance imaging Adolescent Activation likelihood estimation Meta-analysis

基于PSO-VMD的工频磁异常信号去噪算法

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

华中科技大学学报（自然科学版） 2024年第3期52卷 47-51,64页

作者：田斌赵晨杨超洪汉玉武汉工程大学光学信息与模式识别湖北省重点实验室湖北武汉430025 武汉工程大学电气信息学院湖北武汉430025

为解决工频水下磁目标信号特征在强背景噪声干扰下提取困难的问题,提出一种基于粒子群(PSO)优化变分模态分解(VMD)降噪方法.对VMD优化时选取包络谱峰值因子作为适应度函数,该算法不仅能有效克服经验模态分解(EMD)算法的模态混叠和端点... 详细信息

为解决工频水下磁目标信号特征在强背景噪声干扰下提取困难的问题,提出一种基于粒子群(PSO)优化变分模态分解(VMD)降噪方法.对VMD优化时选取包络谱峰值因子作为适应度函数,该算法不仅能有效克服经验模态分解(EMD)算法的模态混叠和端点效应问题,还能克服了VMD依赖人工经验调参造成分解效果存在偏差的问题.并将其应用于仿真与实测信号的降噪算例中,结果表明相较于集合经验模态分解(EEMD)与VMD算法,PSO-VMD算法不仅将信噪比提升了22 dB左右,还最大限度地保留了磁异常信号的原始特征,提取到了水下目标磁扰动信号,为水下磁异常检测提供一种新思路.

关键词：变分模态分解粒子群优化算法降噪参数优化工频磁场

Glymphatic function and its influencing factors in different glucose metabolism states

在线全文

学校读者我要写书评

暂无评论

World Journal of Diabetes 2024年第7期15卷 1537-1550页

作者： bin tian Chen Zhao Jia-Li Liang Hui-Ting Zhang Yi-Fan Xu Hui-Lei Zheng Jia Zhou Jiang-Nian Gong Shu-Ting Lu Zi-San Zeng Department of Radiology The First Affiliated Hospital of Guangxi Medical UniversityNanning 530021Guangxi Zhuang Autonomous RegionChina Magnetic Resonance Research Collaboration Siemens HealthineersGuangzhou 510620Guangdong ProvinceChina Magnetic Resonance Research Collaboration Siemens Healthineers Ltd.Wuhan 430071Hubei ProvinceChina Department of Health Management The First Affiliated Hospital of Guangxi Medical UniversityNanning 530021Guangxi Zhuang Autonomous RegionChina Department of Endocrinology The First Affiliated Hospital of Guangxi Medical UniversityNanning 530021Guangxi Zhuang Autonomous RegionChina

BACKGROUND Dysfunction of the glymphatic system in the brain in different stages of altered glucose metabolism and its influencing factors are not well *** To investigate the function of the glymphatic system and its clinical correlates in patients with different glucose metabolism states,the present study employed diffusion tensor imaging along the perivascular space(DTI-ALPS)*** Sample size was calculated using the pwr package in R *** crosssectional study enrolled 22 patients with normal glucose metabolism(NGM),20 patients with prediabetes,and 22 patients with type 2 diabetes mellitus(T2DM).A 3.0T magnetic resonance imaging was used to evaluate the function of the glymphatic *** mini-mental state examination(MMSE)was used to assess general cognitive *** DTI-ALPS index of bilateral basal ganglia and the mean DTI-ALPS index was ***,the correlation between DTI-ALPS and clinical features was *** The left-side,right-side,and mean DTI-ALPS index in the T2DM group were significantly lower than that in the NGM *** right-side DTI-ALPS and mean DTI-ALPS index in the T2DM group were significantly lower than those in the prediabetes ***-ALPS index lateralization was not *** MMSE score in the T2DM group was significantly lower than that in the NGM and prediabetes *** controlling for sex,the left-side DTI-ALPS and mean DTI-ALPS index in the prediabetes group were positively correlated with 2-hour postprandial blood glucose level;the left-side DTI-ALPS index was negatively correlated with total cholesterol and low-density lipoprotein *** right-side DTI-ALPS and mean DTI-ALPS index were negatively correlated with the glycosylated hemoglobin level and waist-to-hip ratio in the prediabetes *** left-side,right-side,and mean DTI-ALPS index in the T2DM group were positively correlated with *** left-side and mean DTIALPS index in the T2DM group were negatively

关键词： Glymphatic system Prediabetes Type 2 diabetes mellitus Magnetic resonance imaging Diffusion tensor imaging along the perivascular space

复杂稠密网络下的并置多尺度融合边缘检测模型

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

湖南大学学报（自然科学版） 2024年第8期51卷 13-22页

作者：党建武张天胤田彬兰州交通大学电子与信息工程学院甘肃兰州730070 兰州交通大学光电技术与智能控制教育部重点实验室甘肃兰州730070

边缘检测是计算机视觉任务的基础.目前的技术主要依赖于深度学习,但是大多数的模型在评价阶段会借助非极大值抑制来提高预测边缘的准确率.该策略仅着重关注预测边缘的准确性,没有同时考虑边缘的粗细程度.针对这一问题,本文基于复杂稠密... 详细信息

边缘检测是计算机视觉任务的基础.目前的技术主要依赖于深度学习,但是大多数的模型在评价阶段会借助非极大值抑制来提高预测边缘的准确率.该策略仅着重关注预测边缘的准确性,没有同时考虑边缘的粗细程度.针对这一问题,本文基于复杂稠密网络,提出了一种新的特征融合策略.该策略在传统深度学习边缘检测器侧输出的基础上,添加了自顶向下的并置多尺度融合架构.此架构可以更好地将高层的高语义特征与低层的高分辨率纹理特征结合,有效地抑制了边缘预测中存在的背景模糊和伪线条的现象.在特征连接处使用Concat block块代替单一的Concat操作,更好地融合了不同尺度的语义信息.最后使用一个简单的注意力融合块融合多个网络输出,并结合跟踪损失对输出的不同尺度的预测图进行深度监督.此方法不依赖于非极大值抑制,并且充分利用了目标的多尺度、多层次信息,在精细边缘图像的同时也提升了预测的准确性.实验结果显示,在未使用和使用形态学非极大值抑制方案的情况下,所提出的模型在BIPED数据集上的ODS、OIS、AP分别达到了0.891、0.895、0.900和0.894、0.899、0.931,优于所有比较算法.在MDBD的数据集上也取得了最优的结果.

关键词：边缘检测卷积神经网络注意力机制多尺度融合

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

多阶段堆叠融合下的敦煌壁画修复

电子科技大学学报 2024年第4期53卷 551-559页

作者：邬开俊单宏全田彬俞天秀周颜林兰州交通大学电子与信息工程学院兰州730070 敦煌研究院文物数字化研究所敦煌730030

为解决敦煌破损壁画修复难的问题,提出一种多阶段堆叠融合下的壁画修复模型,在第一阶段进行粗修复以及最大化地进行所需特征信息的提取时采用Unet结构,为增强该阶段的修复效果,又加入对抗网络(LsGan);在第二阶段进行精细化修复,主要修... 详细信息

为解决敦煌破损壁画修复难的问题,提出一种多阶段堆叠融合下的壁画修复模型,在第一阶段进行粗修复以及最大化地进行所需特征信息的提取时采用Unet结构,为增强该阶段的修复效果,又加入对抗网络(LsGan);在第二阶段进行精细化修复,主要修复纹理以及细化遮挡区域,引入多头连接和多尺度分支堆叠模块并对其进行改进,对壁画进行多阶段信息提取并对其进行融合;最后为了修复全局细节,采用大感受野的编解码器结构并且引入轻量级通用可视化(Mobile ViT)模块,同时分离了壁画图像的通道并进行分析,引入对通道不敏感的极化注意力。实验结果表明,该模型很好地解决了壁画纹理以及细节修复的难题,相较于所选修复算法最优数据,在掩码面积为5%~20%时,峰值信噪比提高了3.312,在掩码面积为5%~80%时,平均峰值信噪比提高了1.02。

关键词：敦煌壁画修复多阶段堆叠大感受野多头嵌套多分支融合