检索结果-南通市图书馆

同方期刊数据库

Automatic classification of rural building characteristics using deep learning methods on oblique photography

在线全文

学校读者我要写书评

暂无评论

Building Simulation 2022年第6期15卷 1161-1174页

作者： Chengyu Meng Yuwei Song jiaqi Ji ziyu jia Zhengxu Zhou Peng Gao Sunxiangyu Liu School of Architecture Tsinghua UniversityBeijing100084China School of Landscape Architecture Beijing Forestry UniversityBeijing100083China China National Engineering Research Center for Human Settlement China Architecture Design&Research GroupBeijingChina College of Engineering Peking UniversityBeijing100871China School of Aerospace Engineering Tsinghua UniversityBeijing100084China

Rural building is important to the well-being of rural residents,leading to a significant need to carry out extensive surveys and retrofits of many rural ***-site surveys by expert surveyors are currently the main approach,but this traditional method is often expensive and laborious,especially for large-scale survey ***,this study explores an alternative workflow based on deep learning(DL)methods to apply automatic classification of rural building *** four villages in Jizhou District of Tianjin,China as research samples,we tested selected convolutional neural network(CNN)architectures through the establishment of the training database containing 3258 labeled images,under the performance metrics of accuracy,recall and F1 *** results showed that ResNet50 is the CNN architecture with the best performance,with the comprehensive consideration of overall *** accuracy as the performance metric to test the generalization ability of ResNet50,the prediction results for seven building characteristic indicators from low to high are as follows:building function(0.827);building style(0.863);building quality(0.871);building age(0.880);building structure(0.891);abandoned or not(0.959);the number of storeys(0.995).Due to simplicity,accuracy and effectiveness,this workflow is transferable and cost-effective to investigate large-scale villages.

关键词： rural building surveys built environment workflow convolutional neural networks ResNet50

Double-tract reconstruction is superior to esophagogastrostomy in controlling reflux esophagitis and enhancing quality of life after proximal gastrectomy:Results from a prospective randomized controlled clinical trial in China

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

Chinese Journal of Cancer Research 2023年第6期35卷 645-659页

作者： Yinan Zhang Hongtao Zhang Yan Yan Ke Ji ziyu jia Heli Yang Biao Fan Anqiang Wang Xiaojiang Wu Ji Zhang jiafu Ji Xin Ji Zhaode Bu Key Laboratory of Carcinogenesis and Translational Research(Ministry of Education/Beijing) Gastrointestinal Cancer CenterPeking University Cancer Hospital&InstituteBeijing 100142China Guowen(Changchun)International Hospital Changchun 136199China State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers Beijing Key Laboratory of Carcinogenesis and Translational ResearchEndoscopy CenterPeking University Cancer Hospital&InstituteBeijing 100142China State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers Beijing Key Laboratory of Carcinogenesis and Translational ResearchGastrointestinal Cancer CenterPeking University Cancer Hospital&InstituteBeijing 100142China

Objective:The aim of this study was to prospectively compare double-tract reconstruction(DTR)and esophagogastrostomy(EG)after proximal gastrectomy(PG)regarding the incidence of reflux esophagitis,quality of life(QOL),nutritional status and surgical ***:This study was a randomized controlled *** eligible for PG were enrolled and randomly assigned to the EG group and DTR *** characteristics of patients,parameters for surgical safety,incidence of reflux esophagitis,nutrition status and QOL were collected and compared between the two *** analysis and multivariate analysis were performed to determine the significant factors affecting the incidence of reflux esophagitis after ***:Thirty-seven patients of the EG group and 36 patients of the DTR group were *** incidence of reflux esophagitis was significantly lower in the DTR group than in the EG group(8.3%vs.32.4%,P=0.019).The DTR group demonstrated a more favorable QOL than the EG group after *** nutritional status was balanced within the EG group and the DTR *** operation time was longer in the DTR group than in the EG group(191 min vs.221 min,P=0.001),while surgical safety was similar in the two ***:Our research demonstrated that DTR is superior to EG after PG in terms of the incidence of reflux esophagitis and provides a more satisfactory QOL without increasing surgical complications or sacrificing nutritional status.

关键词： Double-tract reconstruction proximal gastrectomy quality of life reflux esophagitis

在线全文

学校读者我要写书评

暂无评论

数字普惠金融对县域产业结构升级的影响

首都经济贸易大学学报 2024年第5期26卷 32-46页

作者：贾子钰韩廷春清华大学公共管理学院北京100084

数字普惠金融为乡村振兴特别是产业兴旺提供了重要机遇。利用2014-2019年县域非平衡面板数据,探究数字普惠金融对中国县域产业结构升级的影响及作用机制。研究结果表明,数字普惠金融的发展整体上有助于促进中国县域产业结构升级,发挥了... 详细信息

数字普惠金融为乡村振兴特别是产业兴旺提供了重要机遇。利用2014-2019年县域非平衡面板数据,探究数字普惠金融对中国县域产业结构升级的影响及作用机制。研究结果表明,数字普惠金融的发展整体上有助于促进中国县域产业结构升级,发挥了数字红利的作用。其中,数字普惠金融覆盖广度能够产生积极影响,使用深度尚未产生显著影响。在考虑内生性问题以及进行一系列稳健性检验后,该研究结论依然成立。异质性检验结果显示,数字普惠金融的发展有利于以农产品加工业为主的县域第二产业的发展,对于以乡村旅游业为主的县域第三产业的影响则不显著。进一步的研究结果表明,融资约束的缓解和需求效应的刺激是其中重要的机制。

关键词：乡村振兴数字普惠金融产业结构升级产业兴旺融资约束需求效应

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

融合注意力的多维特征图卷积运动想象分类

计算机科学与探索 2022年第9期16卷 2050-2060页

作者：李珍琦王晶贾子钰林友芳北京交通大学计算机与信息技术学院北京100044 北京交通大学交通数据分析与挖掘北京市重点实验室北京100044

运动想象(MI)作为脑机接口(BCI)的重要应用,是运动康复训练的重要支撑。由于脑电的电极分布并非天然的欧式空间,对运动想象进行准确分类具有很大的挑战。而且现有方法仅仅考虑了脑电信号(EEG)中某一维度或者某两维度的信息,无法全面捕... 详细信息

运动想象(MI)作为脑机接口(BCI)的重要应用,是运动康复训练的重要支撑。由于脑电的电极分布并非天然的欧式空间,对运动想象进行准确分类具有很大的挑战。而且现有方法仅仅考虑了脑电信号(EEG)中某一维度或者某两维度的信息,无法全面捕获脑电信号在时、频、空三个维度存在的内在特征。同时,脑电信号各维度上的动态关联强度影响了分类的鲁棒性。针对上述问题,提出了一种新颖的融合注意力的多维特征图卷积网络(AMFGCN)。首先,根据电极节点分布的非欧空间特性设计出图结构,充分表示电极间的空间相关性。其次,提出时-空、频-空的双分支框架,同时表示脑电信号在时域、频域和空间域上的信息。最后,通过融合注意力机制、图卷积和时间/频谱卷积从图表示中学习脑电信号的空间表示、时间依赖性和频率依赖性,并自适应捕获各维度上的动态关联强度。在四个公开脑机接口数据集上进行了实验,结果表明AMFGCN模型提高了分类性能,优于其他现有的运动想象分类方法。

关键词：运动想象(MI) 注意力机制图卷积网络多维特征脑电信号(EEG)

融合注意力的滤波器组双视图图卷积运动想象脑电分类

在线全文

学校读者我要写书评

暂无评论

浙江大学学报（工学版） 2024年第7期58卷 1326-1335,1356页

作者：吴书晗王丹陈远方贾子钰张越棋许萌北京工业大学信息学部北京100124 北京机械设备研究所北京100854 中国科学院自动化研究所脑网络组研究中心北京100190

在运动想象任务中,传统卷积神经网络难以准确表达大脑多区域协同神经活动;图卷积网络(GCN)能够在图数据中考虑节点(脑区)间的连接和关系,适于表示不同脑区的协同任务,为此提出融合注意力的滤波器组双视图GCN(AFB-DVGCN).由滤波器组构建... 详细信息

在运动想象任务中,传统卷积神经网络难以准确表达大脑多区域协同神经活动;图卷积网络(GCN)能够在图数据中考虑节点(脑区)间的连接和关系,适于表示不同脑区的协同任务,为此提出融合注意力的滤波器组双视图GCN(AFB-DVGCN).由滤波器组构建双分支网络,提取不同频段的时域和空域信息;采用双视图图卷积空间特征提取方法实现信息互补;利用有效通道注意力机制增强特征和捕捉不同特征图的交互信息,以提高分类准确率.在公开数据集BCI Competition Ⅳ-2a和OpenBMI上的验证结果表明,AFB-DVGCN的分类性能良好,其分类准确率显著高于对比网络的分类准确率.

关键词：脑机接口运动想象深度学习图卷积网络注意力机制

同方期刊数据库

在线全文

学校读者我要写书评

暂无评论

我国绿色宜居村镇的内涵与发展趋势研究

小城镇建设 2021年第8期39卷 5-17页

作者：焦燕贾子玉中国建筑设计研究院有限公司国家住宅与居住环境工程技术研究中心

随着乡村振兴战略全面实施,我国城乡关系和农村发展已处于转型重构的重要阶段。在新的方针政策指导下,村镇建设模式和战略规划需要与时俱进,适应新形势下城乡发展需求。本文通过实地调研典型村镇,结合文献、统计数据分析的方法,力图全... 详细信息

随着乡村振兴战略全面实施,我国城乡关系和农村发展已处于转型重构的重要阶段。在新的方针政策指导下,村镇建设模式和战略规划需要与时俱进,适应新形势下城乡发展需求。本文通过实地调研典型村镇,结合文献、统计数据分析的方法,力图全面客观地解读我国绿色宜居村镇的概念内涵,剖析其发展要素与特点,并对未来一段时期内村镇在空间资源集约、产业发展创新、人居环境治理、社会服务提升、信息化建设几方面的发展趋势进行分析预判,为明确绿色宜居村镇的发展路径和建设策略提供科学支撑。

关键词：绿色宜居村镇发展趋势城镇化一体化数字化

基于C-TiO_(2)@Fe_(3)O_(4)/AC的光催化耦合臭氧氧化技术对水体中苯胺的降解

在线全文

学校读者我要写书评

暂无评论

化工新型材料 2023年第5期51卷 290-292,298页

作者：贾子钰李廖颖杨春维吉林师范大学环境科学与工程学院四平136000 吉林省高校环境材料与污染控制重点实验室四平136000

苯胺是一种典型的有毒污染物,在工业废水中较为常见,而常规处理技术对其处置效果不佳。光催化耦合臭氧高级氧化技术因为高效快速,具有广泛的应用前景,可以作为有毒有机污染物的处置手段之一。通过制备了一种C改性TiO_(2)负载磁性活性炭(... 详细信息

苯胺是一种典型的有毒污染物,在工业废水中较为常见,而常规处理技术对其处置效果不佳。光催化耦合臭氧高级氧化技术因为高效快速,具有广泛的应用前景,可以作为有毒有机污染物的处置手段之一。通过制备了一种C改性TiO_(2)负载磁性活性炭(C-TiO_(2)@Fe_(3)O_(4)/AC)催化剂,考察了其光催化耦合臭氧氧化处理苯胺的效果。研究结果表明,运行30min后即可达到95%以上的降解效率,苯胺去除率和反应效率均高于普通的C-TiO_(2)和Fe_(3)O_(4)/AC催化剂。

关键词：复合催化剂光催化臭氧氧化苯胺高阶氧化

基于多尺度特征提取与挤压激励模型的运动想象分类方法

在线全文

学校读者我要写书评

暂无评论

计算机研究与发展 2020年第12期57卷 2481-2489页

作者：贾子钰林友芳刘天航杨凯昕张鑫旺王晶北京交通大学计算机与信息技术学院北京100044 交通数据分析与挖掘北京市重点实验室(北京交通大学) 北京100044 民航旅客服务智能化应用技术重点实验室(中国民用航空局) 北京100044

基于运动想象的脑机接口技术能够建立大脑与外界之间的联系,逐渐成为人机混合增强智能的重要应用,并广泛应用于医学康复治疗等领域.由于脑电信号具有非线性、非平稳和低信噪比等特点,使得准确的分类运动想象脑电信号具有很大挑战.为此,... 详细信息

基于运动想象的脑机接口技术能够建立大脑与外界之间的联系,逐渐成为人机混合增强智能的重要应用,并广泛应用于医学康复治疗等领域.由于脑电信号具有非线性、非平稳和低信噪比等特点,使得准确的分类运动想象脑电信号具有很大挑战.为此,提出一种新颖的多尺度特征提取与挤压激励模型对运动想象脑电信号进行高精度分类.首先,基于多尺度卷积模块自动提取原始脑电信号的时域、频域和时频域特征;然后,使用残差模块和挤压激励模块分别进行特征的融合和选择;最后,利用全连接网络层进行运动想象脑电信号的分类.实验在2个公开的脑机接口竞赛数据集上进行分析,结果表明该模型与现有先进模型相比,有效地提升了运动想象脑电信号的识别效果,在2个数据集上分别取得了78.0%和82.5%的平均准确度,该模型可以在脑电通道较少的情况下有效地分类脑电信号且无需手动设计特征,具有较高的应用价值.

关键词：运动想象挤压激励模型脑电信号脑机接口多尺度卷积

Postoperative chemotherapy with S-1 plus oxaliplatin versus S-1alone in locally advanced gastric cancer(RESCUE-GC study): a protocol for a phase Ⅲ randomized controlled trial

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Cancer Research 2017年第2期29卷 144-148页

作者： Xiang Hu Lin Chen Yian Du Biao Fan Zhaode Bu Xin Wang Yingjiang Ye Zhongtao Zhang Gang Xiao Fei Li Qingsi He Guoli Li Xian Shen Bin Xiong Liming Zhu Jiwei Liui Lian Liu Tao Wu Jing Zhou Jun Zhang Gang Zhao Xulin Wang Pin Liang Xinxin Wang Yan Zhang Xiaojiang Wu Ji Zhang Xin Ji Xianglong Zong Tao Fu ziyu jia jiafu Ji Department of Gastrointestinal Surgery the First Affiliated Hospital of Dalian Medical University Dalian 116011 China Deparunent of General Surgery Chinese People's Liberation Army General Hospital Beijing 100853 China Department of Abdominal Surgery Zhejiang Cancer Hospital Hangzhou 310022 China Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing) Center of Gastrointestinal Surgery Peking University Cancer Hospital & Institute Beijing 100142 China Department of General Surgery Peking University First Hospital Beijing 100034 China Department of Gastrointestinal Surgery Peking University People's Hospital Beijing 100044 China Department of General Surgery Beijing Friendship Hospital Capital Medical University Beijing 100050 China Department of General Surgery Beijing Hospital Beijing 100730 China Department of General Surgery Xuanwu Hospital Capital Medical University Beijing 100053 China Department of General Surgery Qilu Hospital of Shandong University Jinan 250012 China Department of General Surgery Nanjing General Hospital Nanjing 210002 China Department of Gastrointestinal Surgery the First Affiliated Hospital of Wenzhou Medical University Wenzhou 325000 China Department of Oncology Zhongnan Hospital of Wuhan University Wuhan 430071 China Department of Medical Oncology Zhejiang Cancer Hospital Hangzhou 310022 China Department of Medical Oncology the First Affiliated Hospital of Dalian Medical University Dalian 116011 China Department of Chemotherapy Qilu Hospital of Shandong University Jinan 250012 China

Background： The ACTS-GC study had shown postoperative adiuvant therapy with S-1 improved survival of patients with locally advanced gastric cancer. Addition of oxaliplatin to S-1 is considered to be acceptable as one of the treatment options for gastric cancer patients after radical gastrectomy with D2 lymph node excision. Methods： We have commenced a randomized phase III trial in December 2016 to evaluate S-I plus oxaliplatin compared with S-1 alone in the adjuvant setting for locally advanced gastric cancer. A total of 564 patients will be accrued from 13 Chinese institutions in two years. The primary endpoint is 3-year relapse-free survival. The secondary endpoints are 5-year overall survival, proportion of patients who complete the postoperative chemotherapy and incidence of adverse events. Ethic and dissemination： The trial has been approved by the institutional review board of each participating institution and it was activated on December, 2016. The enrollment will be finished in December, 2018. Patient＇s follow-up will be ended until December, 2023. Trial registration： ***, identifier： NCT02867839. Registered on August 4, 2016.

关键词： Locally advanced gastric cancer S-1 plus oxaliplatin randomized phase HI trial