Query：
学者姓名：邬群勇
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
Building type information indicates the functional properties of buildings and plays a crucial role in smart city development and urban socioeconomic activities. Existing methods for classifying building types often face challenges in accurately distinguishing buildings between types while maintaining well-delineated boundaries, especially in complex urban environments. This study introduces a novel framework, i.e., CNN-Transformer cross-attention feature fusion network (CTCFNet), for building type classification from very high resolution remote sensing images. CTCFNet integrates convolutional neural networks (CNNs) and Transformers using an interactive cross-encoder fusion module that enhances semantic feature learning and improves classification accuracy in complex scenarios. We develop an adaptive collaboration optimization module that applies human visual attention mechanisms to enhance the feature representation of building types and boundaries simultaneously. To address the scarcity of datasets in building type classification, we create two new datasets, i.e., the urban building type (UBT) dataset and the town building type (TBT) dataset, for model evaluation. Extensive experiments on these datasets demonstrate that CTCFNet outperforms popular CNNs, Transformers, and dual-encoder methods in identifying building types across various regions, achieving the highest mean intersection over union of 78.20% and 77.11%, F1 scores of 86.83% and 88.22%, and overall accuracy of 95.07% and 95.73% on the UBT and TBT datasets, respectively. We conclude that CTCFNet effectively addresses the challenges of high interclass similarity and intraclass inconsistency in complex scenes, yielding results with well-delineated building boundaries and accurate building types.
Keyword ：
Accuracy Accuracy Architecture Architecture Buildings Buildings Building type classification Building type classification CNN-transformer networks CNN-transformer networks cross-encoder cross-encoder Earth Earth Feature extraction Feature extraction feature interaction feature interaction Optimization Optimization Remote sensing Remote sensing Semantics Semantics Transformers Transformers very high resolution remote sensing very high resolution remote sensing Visualization Visualization
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Shaofeng , Li, Mengmeng , Zhao, Wufan et al. Building Type Classification Using CNN-Transformer Cross-Encoder Adaptive Learning From Very High Resolution Satellite Images [J]. | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING , 2025 , 18 : 976-994 . |
| MLA | Zhang, Shaofeng et al. "Building Type Classification Using CNN-Transformer Cross-Encoder Adaptive Learning From Very High Resolution Satellite Images" . | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 18 (2025) : 976-994 . |
| APA | Zhang, Shaofeng , Li, Mengmeng , Zhao, Wufan , Wang, Xiaoqin , Wu, Qunyong . Building Type Classification Using CNN-Transformer Cross-Encoder Adaptive Learning From Very High Resolution Satellite Images . | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING , 2025 , 18 , 976-994 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
以深圳市为研究区，使用工作日早高峰的接驳骑行订单数据，考虑地铁站和出入口两层面的潮汐均衡性分类，从单车调度角度将出入口划分为无需调度型、站内调度型和站外调度型；使用非负矩阵分解方法划分出入口流量时空分布类别，确定调度时间.结果表明，将接驳轨道交通的潮汐均衡分析聚焦到出入口层面，精确划分出入口调度类型，可确定调度方式和产生调度需求的时间，为单车管理者进行车辆调度提供可靠的数据支持.
Keyword ：
共享单车 共享单车 地铁出入口 地铁出入口 接驳 接驳 潮汐均衡性 潮汐均衡性 非负矩阵分解 非负矩阵分解
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 王涵菁 , 邬群勇 , 邝嘉恒 et al. 接驳轨道交通的共享单车潮汐均衡时空分布模式 [J]. | 福州大学学报(自然科学版) , 2024 , 52 (02) : 176-183 . |
| MLA | 王涵菁 et al. "接驳轨道交通的共享单车潮汐均衡时空分布模式" . | 福州大学学报(自然科学版) 52 . 02 (2024) : 176-183 . |
| APA | 王涵菁 , 邬群勇 , 邝嘉恒 , 郑汉捷 , 张晨 , 尹延中 . 接驳轨道交通的共享单车潮汐均衡时空分布模式 . | 福州大学学报(自然科学版) , 2024 , 52 (02) , 176-183 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Traffic prediction is indispensable for constructing transportation networks in smart cities. Due to the complex spatio-temporal correlations of traffic data, this task presents challenges. Recent studies mainly use graph neural networks to simulate complex spatio-temporal relationships through fixed or adaptive graphs. While fixed graphs may not adapt to data drift caused by changes in road network structures, adaptive graphs overlook critical information of the original roads. To address this challenge, we propose a principal spatio-temporal causal graph convolutional network (PSTCGCN) to accurately predict traffic flow. In response to the data drift problem, we introduce a data-driven semi-principal generated graph embedding (SPGGE) that first extracts the principal features of the original roads to model the spatio-temporal sequence distribution and then remodels the data after drift through adaptive transformation. Traffic flow data, while showcasing fundamental spatial relationships, also exhibit temporal dynamics. We propose an effective temporal causal convolution component comprising SPGGE, graph convolution, both local and global causal learning models to jointly learn short-term and long-term spatio-temporal correlations. PSTCGCN was evaluated using two actual highway datasets, PEMS03 and PEMS07, achieving a notable improvement of 6.12% in RMSE on PEMS03 compared to STGATRGN. Our code is available at https://github.com/OvOYu/PSTCGCN. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.
Keyword ：
Data drift Data drift Graph convolution network Graph convolution network Principal component analysis Principal component analysis Traffic flow prediction Traffic flow prediction
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yang, S. , Wu, Q. , Li, Z. et al. PSTCGCN: Principal spatio-temporal causal graph convolutional network for traffic flow prediction [J]. | Neural Computing and Applications , 2024 . |
| MLA | Yang, S. et al. "PSTCGCN: Principal spatio-temporal causal graph convolutional network for traffic flow prediction" . | Neural Computing and Applications (2024) . |
| APA | Yang, S. , Wu, Q. , Li, Z. , Wang, K. . PSTCGCN: Principal spatio-temporal causal graph convolutional network for traffic flow prediction . | Neural Computing and Applications , 2024 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The effect of 'space-time compression' caused by 'space flow' breaks the independent allocation of resources between cities and drives the formation of regionally integrated development pattern, and the organizational structure and operation mechanism of the urban network cannot be separated from the inter-city relationship. Based on Baidu migration big data from October 2021 to September 2022, this paper constructs the intercity population flow network for 366 cities in China. At the node level, a population flow surpassing index is proposed to measure urban centrality and explore the spatial clustering characteristics of urban centrality. At the network community level, the monthly intercity population flow pattern and characteristics of 366 cities are analyzed. The results show that: (1) The population flow surpassing index considering flow direction meets the actual needs of intercity population mobility evaluation for measuring urban centrality and can effectively characterize the centrality of cities in the intercity population flow network. Using Baidu Migration big data from January 2023 to April 2023 after the end of the epidemic for comparison, we found that the central impact on national central city is small due to the prevention and control of COVID-19 transmission; (2) Cities in the intercity population flow network exhibit 'High-High (HH)' and 'Low-Low (LL)' agglomeration characteristics according to their centrality. HH clustering areas are formed in the eastern coastal and central regions, while LL clustering areas are mainly located at the edge of the Qinghai Tibet Plateau, the edge of the three northeastern provinces, and some areas in Hainan Island; (3) The intercity population flow pattern shows different characteristics in different months due to the influence of holidays, COVID-19 transmission, etc., generally in accordance with the first law of geography, and exhibits provincial differentiation characteristics; (4) The finding of urban cohesive subgroups shows that the intercity population flow patterns of Chengdu- Chongqing Urban Agglomeration, Greater Bay Area, Central Plains Urban Agglomeration, Guanzhong Plain Urban Agglomeration, Yangtze River Delta Urban Agglomeration, and other urban clusters are relatively stable, characterized by cross-provincial population flow integration. The Shandong Peninsula Urban Agglomeration and the Beijing- Tianjin-Hebei Urban Agglomeration have close connection in intercity population flow patterns, characterized by cross-urban cluster intercity population flow. The intercity population flow pattern within Zhejiang Province is gradually enhanced, and the urban clusters in middle reaches of Yangtze River and the west bank of the Taiwan Strait haven’t yet formed a stable population flow pattern across provincial borders. © 2024 Science Press. All rights reserved.
Keyword ：
Agglomeration Agglomeration Big data Big data Digital storage Digital storage Disease control Disease control Flow patterns Flow patterns Population dynamics Population dynamics Population statistics Population statistics
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yin, Yanzhong , Wu, Qunyong , Lin, Han et al. Analysis of Urban Centrality and Community Patterns from the Perspective of 'Intercity Mobility Flow' in China [J]. | Journal of Geo-Information Science , 2024 , 26 (3) : 666-678 . |
| MLA | Yin, Yanzhong et al. "Analysis of Urban Centrality and Community Patterns from the Perspective of 'Intercity Mobility Flow' in China" . | Journal of Geo-Information Science 26 . 3 (2024) : 666-678 . |
| APA | Yin, Yanzhong , Wu, Qunyong , Lin, Han , Zhao, Zhiyuan . Analysis of Urban Centrality and Community Patterns from the Perspective of 'Intercity Mobility Flow' in China . | Journal of Geo-Information Science , 2024 , 26 (3) , 666-678 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
城市网络的组织结构与运行机制离不开城市间的关联关系。本文基于2021年10月至2022年9月的百度迁徙大数据，构建了中国366个城市的城际人口流动网络。在节点层面，提出了城际人口流动超越指数衡量城市中心性，探索城市中心性的空间聚类特征；在网络社区层面，分析了中国366个城市的月际城际人口流动特征及社群格局。结果表明：(1)城际人口流动超越指数能够有效表征城际人口流动网络中各城市的中心性；(2)城际人口流动网络中各城市根据其中心性形成“高高”集聚分布和“低低”集聚分布的特征；(3)城际人口流动集聚格局受节假日因素、新型冠状病毒感染等综合影响，在不同月份表现出不同的特征，总体上符合地理学第一定律，并呈现省际分异特征；(4)城市凝聚子群发现结果表明，成渝、大湾区、中原、关中平原、长三角等城市群人口流动格局较为稳定，具有跨省人口流动融合特征；山东半岛城市群与京津冀城市群的人口流动格局联系密切，出现跨城市群人口流动特征；浙江省省域内人口流动特征逐渐加强；长江中游、海峡西岸城市群仍未形成跨越省界的稳定人口流动社群格局。
Keyword ：
区域协调发展 区域协调发展 城市中心性 城市中心性 城市相互作用 城市相互作用 城市群 城市群 城际人口流动网络格局 城际人口流动网络格局 城际人口流动超越指数 城际人口流动超越指数 百度迁徙数据 百度迁徙数据 社区检测 社区检测
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 尹延中 , 邬群勇 , 林瀚 et al. “人口流动”视域下中国城市中心性和社群格局分析 [J]. | 地球信息科学学报 , 2024 , 26 (03) : 666-678 . |
| MLA | 尹延中 et al. "“人口流动”视域下中国城市中心性和社群格局分析" . | 地球信息科学学报 26 . 03 (2024) : 666-678 . |
| APA | 尹延中 , 邬群勇 , 林瀚 , 赵志远 . “人口流动”视域下中国城市中心性和社群格局分析 . | 地球信息科学学报 , 2024 , 26 (03) , 666-678 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Understanding intercity mobility patterns is important for future urban planning, in which the intensity of intercity mobility indicates the degree of urban integration development. This study investigates the intercity mobility patterns of the Greater Bay Area (GBA) in China. The proposed workflow starts by analyzing intercity mobility characteristics, proceeds to model the spatial-temporal heterogeneity of intercity mobility structures, and then identifies the intercity mobility patterns. We first conduct a complex network analysis, based on weighted degrees and the PageRank algorithm, to measure intercity mobility characteristics. Next, we calculate the Normalized Levenshtein Distance for Population Mobility Structure (NLPMS) to quantify the differences in intercity mobility structures, and we use the Non-negative Matrix Factorization (NMF) to identify intercity mobility patterns. Our results showed an evident 'Core-Periphery' differentiation characterized by intercity mobility, with Guangzhou and Shenzhen as the two core cities. An obvious daily intercity commuting pattern was found between Guangzhou and Foshan, and between Shenzhen and Dongguan cities at working time. This pattern, however, changes during the holidays. This is because people move from the core cities to peripheral cities at the beginning of holidays and return at the end of holidays. This study concludes that Guangzhou and Foshan have formed a relatively stable intercity mobility pattern, and the Shenzhen-Dongguan-Huizhou metropolitan area has been gradually formed.
Keyword ：
Baidu migration data Baidu migration data intercity mobility patterns intercity mobility patterns matrix factorization matrix factorization spatial-temporal heterogeneity spatial-temporal heterogeneity urban integration urban integration
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yin, Yanzhong , Wu, Qunyong , Li, Mengmeng . Characterizing Intercity Mobility Patterns for the Greater Bay Area in China [J]. | ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION , 2023 , 12 (1) . |
| MLA | Yin, Yanzhong et al. "Characterizing Intercity Mobility Patterns for the Greater Bay Area in China" . | ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION 12 . 1 (2023) . |
| APA | Yin, Yanzhong , Wu, Qunyong , Li, Mengmeng . Characterizing Intercity Mobility Patterns for the Greater Bay Area in China . | ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION , 2023 , 12 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
城市出租汽车是居民出行的重要方式之一，地理流空间理论为发掘人群出行特征，优化车辆运营效率提供了新视角。本文利用厦门市出租汽车轨迹数据，采用地理流空间分析理论，对人群出行的整体随机性质进行了分析，基于流相似性度量识别并分析了丛集、汇聚、发散和社区4种典型模式及混合模式的空间分布特征，对比了基于巡游车和网约车2种车辆的人群出行模式。结果表明流空间理论能够系统性发现人群出行典型模式及混合模式，主要体现在：(1)基于2类车辆的人群出行流在空间中呈现出显著的非随机特征；(2)巡游车和网约车的典型模式在空间分布上有明显差别，网约车的有关模式分布范围更广，在厦门岛外各区中心及岛内东部软件园等区域附近较为突出，且网约车由于其订单由用户需求驱动，更容易发现潜在的高出行需求区域，同时出行结构更容易形成社区模式，而巡游车主要分布在传统岛内知名城市地标附近；(3)同一区域内巡游车和网约车出行混合模式普遍存在，约占典型模式的四分之一左右，而且不同类型车辆的主要混合模式存在差异，综合考虑混合模式能够提高城市公共设施规划的精确性和科学性。本文结果可以为车辆调度优化和城市交通规划提供支持，也表明地理流空间理论能够更有效揭示地理流对象的空间模式特征。
Keyword ：
人类移动性 人类移动性 出租车 出租车 出行流模式 出行流模式 地理流空间 地理流空间 流聚类 流聚类 混合流模式 混合流模式 网约车 网约车 轨迹数据 轨迹数据
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 王鹏洲 , 赵志远 , 姚伟 et al. 基于地理流空间的巡游车与网约车人群出行模式研究 [J]. | 地球信息科学学报 , 2023 , 25 (04) : 726-740 . |
| MLA | 王鹏洲 et al. "基于地理流空间的巡游车与网约车人群出行模式研究" . | 地球信息科学学报 25 . 04 (2023) : 726-740 . |
| APA | 王鹏洲 , 赵志远 , 姚伟 , 吴升 , 汪艳霞 , 方莉娜 et al. 基于地理流空间的巡游车与网约车人群出行模式研究 . | 地球信息科学学报 , 2023 , 25 (04) , 726-740 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
为向乘客提供较为准确的上下车时间参考,解决长距离预测中误差累积明显的问题,构建基于双层、双注意力、双向长短期记忆(LSTM)神经网络的公交车到站时间预测模型,提出一种基于行程数据的公交车到站时间预测方法.以广州市B2 路、560 路公交车工作日的实际运行数据为例,对该预测方法进行精度验证.结果表明,由该模型所预测的行程时间,其平均绝对百分比误差为 8.09％,在长距离到站时间估算上,15 个站点的预测误差可保持在 4.00 min左右.
Keyword ：
公交车 公交车 到站时间预测 到站时间预测 城市交通 城市交通 注意力机制 注意力机制 长短期记忆神经网络 长短期记忆神经网络
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 姚江涛 , 邬群勇 , 余丹青 et al. 基于行程数据的公交车到站时间预测 [J]. | 福州大学学报（自然科学版） , 2023 , 51 (3) : 347-354 . |
| MLA | 姚江涛 et al. "基于行程数据的公交车到站时间预测" . | 福州大学学报（自然科学版） 51 . 3 (2023) : 347-354 . |
| APA | 姚江涛 , 邬群勇 , 余丹青 , 罗建平 . 基于行程数据的公交车到站时间预测 . | 福州大学学报（自然科学版） , 2023 , 51 (3) , 347-354 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
提出一种基于注意力机制的时空特征深度学习模型.通过卷积神经网络去学习行程过程中所花费的时间和距离,以及交通拥堵状态信息;然后,通过注意力机制从通道和空间两个角度去捕获影响行程中路段通行时间的异常信息.最后采用双层的长短时记忆网络去学习行程中的路段序列信息,并通过多任务的学习机制从路径和路段两个角度出发去预测路径通行时间.研究结果表明:提出的方法与DEEPTRAVEL模型相比,预测精度的平均绝对误差和平均绝对百分比误差分别提升了 8.23％和 20.79％.
Keyword ：
交通信息工程 交通信息工程 注意力机制 注意力机制 深度学习 深度学习 网约车订单数据 网约车订单数据 行程时间预测 行程时间预测
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 杨谊潇 , 邬群勇 . 考虑注意力和时空特征深度学习的网约车行程时间预测 [J]. | 福州大学学报（自然科学版） , 2023 , 51 (3) : 340-346 . |
| MLA | 杨谊潇 et al. "考虑注意力和时空特征深度学习的网约车行程时间预测" . | 福州大学学报（自然科学版） 51 . 3 (2023) : 340-346 . |
| APA | 杨谊潇 , 邬群勇 . 考虑注意力和时空特征深度学习的网约车行程时间预测 . | 福州大学学报（自然科学版） , 2023 , 51 (3) , 340-346 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
气溶胶光学厚度（AOD）是气溶胶最重要的参数之一，现有的遥感AOD产品受云、积雪等因素的影响空间缺失严重，因此，生成空间覆盖完整的AOD具有重要意义.本文融合MODIS的MAIAC AOD和Himawari-8的AHI AOD，结合气象数据和高程数据，提出一种集成反距离权重插值（IDW）和CatBoost模型的时空连续AOD重构方法（命名为IDW-CatBoost）.将此方法应用于京津冀和台湾岛的AOD重构，并与IDW、CatBoost方法对比，重构结果利用地基监测AERONET AOD进行验证，其中，京津冀的验证数为352个，台湾岛的验证数为641个.结果表明：在空间分布上，IDW AOD存在星点状特征，CatBoost、IDW-CatBoost的AOD具有空间连续分布的纹理特征；精度上，经地基监测AERONET AOD验证，京津冀地区IDW AOD与IDW-CatBoost AOD接近；台湾岛IDW-CatBoost AOD相比于IDW、CatBoost结果，R2分别提高了10%和5%.经过多传感器AOD融合，与单传感器AHI L2、L3、MAIAC AOD相比，IDW-CatBoost重构AOD精度显著提升，在京津冀地区，R2分别提高了15%、35%和12%,RMSE分别下降了25%、38%和22%；在台湾岛，R2分别提高了14%、76%和76%,RMSE分别下降了6%、24%和24%.因此，基于多传感器AOD融合的IDW-CatBoost模型用于重构AOD产品，不仅空间覆盖完整，而且具有更高的精度.
Keyword ：
AOD重构 AOD重构 CatBoost CatBoost 多传感器融合 多传感器融合 时空连续分布 时空连续分布 气溶胶光学厚度(AOD) 气溶胶光学厚度(AOD)
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 张晨 , 汪小钦 , 邬群勇 et al. 基于多传感器融合的时空连续AOD重构模型 [J]. | 环境科学学报 , 2023 , 43 (05) : 353-365 . |
| MLA | 张晨 et al. "基于多传感器融合的时空连续AOD重构模型" . | 环境科学学报 43 . 05 (2023) : 353-365 . |
| APA | 张晨 , 汪小钦 , 邬群勇 , 郑汉捷 , 王涵菁 , 尹延中 . 基于多传感器融合的时空连续AOD重构模型 . | 环境科学学报 , 2023 , 43 (05) , 353-365 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
