检索结果-内蒙古大学图书馆

Spatiotemporal Effects of Built Environment on Varying Rail Transit Station Ridership Patterns

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Wang, Jing Wan, Feng Dong, Chunjiao Yin, Chaoying Chen, Xiaoyu Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Beijing Jiaotong University Beijing100044 China Hikvision Research Institute Hangzhou310012 China College of Automobile and Traffic Engineering Nanjing Forestry University Nanjing210037 China School of Computer and Information Technology Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China

Although many studies have explored the impacts of the built environment on rail transit station ridership, spatiotemporal heterogeneity of the effects and different ridership patterns are rarely considered. Using multi-source data from China, three direct models (DRMs) based on the geographically and temporally weighted regression (GTWR) model are proposed to reveal the spatiotemporal effects of daily, weekday hourly and weekend hourly ridership patterns. The results show that employment density, entertainment places, housing prices, and entrances/exits are the dominant variables affecting ridership in the three models;however, their effects vary in spatiotemporal ranges. For example, the positive effect of employment density decreases from Monday to Sunday, and its coefficients during the peak hours are highest in the northwest center, where is the largest technology park situated. The results also highlight the importance of bus stations and parking lots in attracting commuter ridership. The findings provide insights into urban rail transit planning. © 2022, The Authors. All rights reserved.

关键词： Housing

Bus Arrival Time Estimation Based on GPS data by the Artificial Bee Colony Optimization BP Neural Network

学校读者我要写书评

暂无评论

Bus Arrival Time Estimation Based on GPS Data by the Artific...

International Conference on Smart Grid and Electrical Automation (ICSGEA)

作者： Xuemei Wu Shiyin Huang Jie Zou Jin Shen Wen Cai Jiandong Zhao TransChina (Beijing) Technology Co. Ltd. Beijing China School of Traffic and Transportation Beijing Jiaotong University Beijing P.R. China Beijing public transport corporation Beijing P.R. China Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Beijing Jiaotong University Beijing China

ISBN: (数字)9781728182780

ISBN: (纸本)9781728182797

The problem of vehicle delay is one of the higher complaint rates among the passenger opinions of bus companies, and it is also one of the important reasons why citizens give up choosing public transportation. Estimating bus arrival time is of great significance for improving passenger satisfaction and improving the problem of urban traffic congestion. In this paper, the vehicle GPS data were used to classify the data according to different scenarios, and then the BP neural network was trained and compared with the artificial colony optimization BP neural network. The comparison results show that artificial bee colony optimization BP neural network algorithm is superior to BP neural network algorithm, so we select the better artificial bee colony optimization BP neural network algorithm to establish a vehicle arrival time prediction model.

关键词： Zirconium Smart grids Automation

Perceptive self-supervised learning network for noisy image watermark removal

学校读者我要写书评

暂无评论

arXiv

arXiv 2024年

作者： Tian, Chunwei Zheng, Menghua Li, Bo Zhang, Yanning Zhang, Shichao Zhang, David School of Software Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China School of Electronics and Information Northwestern Polytechnical University Xi’an710129 China School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology Xi’an710129 China Guangxi Key Lab of Multisource Information Mining & Security College of Computer Science & Engineering Guangxi Normal University Guilin541004 China Shenzhen518172 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China

Popular methods usually use a degradation model in a supervised way to learn a watermark removal model. However, it is true that reference images are difficult to obtain in the real world, as well as collected images by cameras suffer from noise. To overcome these drawbacks, we propose a perceptive self-supervised learning network for noisy image watermark removal (PSLNet) in this paper. PSLNet depends on a parallel network to remove noise and watermarks. The upper network uses task decomposition ideas to remove noise and watermarks in sequence. The lower network utilizes the degradation model idea to simultaneously remove noise and watermarks. Specifically, mentioned paired watermark images are obtained in a self-supervised way, and paired noisy images (i.e., noisy and reference images) are obtained in a supervised way. To enhance the clarity of obtained images, interacting two sub-networks and fusing obtained clean images are used to improve the effects of image watermark removal in terms of structural information and pixel enhancement. Taking into texture information account, a mixed loss uses obtained images and features to achieve a robust model of noisy image watermark removal. comprehensive experiments show that our proposed method is very effective in comparison with popular convolutional neural networks (CNNs) for noisy image watermark removal. Codes can be obtained at https://***/hellloxiaotian/PSLNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Image denoising

Exploratory study of highly susceptible to SARS-CoV-2 populations

学校读者我要写书评

暂无评论

Life Research 2022年第3期5卷 10-14页

作者： Xiaodong Jia Chengliang Yin Shanshan Lu Yan Chen Qingyan Liu Junfan Bai Lei Zhi Yinying Lu Comprehensive Liver Cancer Center The Fifth Medical Center of PLA General HospitalBeijingChina.0000-0001-8262-5749 National Engineering Laboratory for Medical Big Data Application Technology Chinese PLA General HospitalBeijingChina Faculty of Medicine Macao University of Science and TechnologyMacaoChina Medical Big Data Research Center Medical Innovation Research Division of PLA General HospitalBeijingChina Center for Synthetic and Systems Biology(CSSB) Tsinghua UniversityBeijingChina Peking University BeijingChina Department of Chronic Disease Luzhou Center for Disease Control and PreventionLuzhouChina

The coronavirus disease 2019(COVID-19),caused by severe acute respiratory syndrome coronavirus 2(SARS-CoV-2),is threatening public *** human angiotensin-converting enzyme 2(ACE2)has a remarkably high affinity binding to *** study explored whether certain populations,including obese and cancer patients,are susceptible to *** expression pattern of ACE2 in normal and tumor tissues of cancer patients was compared by the search for network database and re-analysis of pubic *** level of ACE2 expression in normal adipose tissue was higher than that in normal lung tissue,which indicated the adipose tissue might be vulnerable to SARS-CoV-2;the levels of ACE2 expressed by adipocytes and adipose progenitor cells were similar between non-obese individuals and obese individuals(BMI>29),but obese individuals have more adiposes so as to increase the number of ACE2-expressing cells;the expression of ACE2 in tumor tissues posed by five different types of cancers increased significantly compared with that in adjacent ***,we proposed the following hypothesis:the obese individuals and five types of cancer patients might have a higher risk of SARS-CoV-2 infection,which might become the target population of SARS-CoV-2 infection in the future.

关键词： COVID-19 adipose tissue obesity cancer ACE2

Bicycle flow dynamics on wide roads: Experiment and modeling

学校读者我要写书评

暂无评论

arXiv

arXiv 2019年

作者： Guo, Ning Jiang, Rui Wong, S.C. Hao, Qing-Yi Xue, Shu-Qi Hu, Mao-Bin School of Automotive and Transportation Engineering Hefei University of Technology Hefei230009 China Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Beijing Jiaotong University Beijing100044 China Department of Civil Engineering University of Hong Kong Pokfulam Road Hong Kong School of Mathematics and Computational Science Anqing Normal University Anqing246133 China School of Engineering Science University of Science and Technology of China Hefei230026 China

Cycling is a green transportation mode, and is promoted by many governments to mitigate traffic congestion. However, studies concerning the traffic dynamics of bicycle flow are very limited. This study experimentally investigated bicycle flow dynamics on a wide road, modeled using a 3-m-wide track. The results showed that the bicycle flow rate remained nearly constant across a wide range of densities, in marked contrast to single-file bicycle flow, which exhibits a unimodal fundamental diagram. By studying the weight density of the radial locations of cyclists, we argue that this behavior arises from the formation of more lanes with the increase of global density. The extra lanes prevent the longitudinal density from increasing as quickly as in single-file bicycle flow. When the density is larger than 0.5 bicycles/m2, the flow rate begins to decrease, and stop-and-go traffic emerges. A cognitive-science-based model to reproduce bicycle dynamics is proposed, in which cyclists apply simple cognitive procedures to adapt their target directions and desired riding speeds. To incorporate differences in acceleration, deceleration, and turning, different relaxation times are used. The model can reproduce the experimental results acceptably well and may also provide guidance on infrastructure design. Copyright © 2019, The Authors. All rights reserved.

关键词： Traffic congestion

Structure and evolution of urban heavy truck mobility networks

学校读者我要写书评

暂无评论

arXiv

arXiv 2022年

作者： Yang, Yitao Jia, Bin Liu, Erjian Yan, Xiao-Yong de Bok, Michiel Tavasszy, Lóránt A. Gao, Ziyou Key Laboratory of Integrated Transport Big Data Application Technology for Transport Industry Beijing Jiaotong University Beijing100044 China Institute of Transportation System Science and Engineering Beijing Jiaotong University Beijing100044 China Department of Transport & Planning Faculty of Civil Engineering and Geosciences Delft University of Technology Stevinweg1 Delft2628 CN Netherlands Palma de Mallorca07122 Spain

Revealing the structural properties and understanding the evolutionary mechanisms of the urban heavy truck mobility network (UHTMN) provide insights in assessment of freight policies to manage and regulate the urban freight system, and are of vital importance for improving the livability and sustainability of cities. Although massive urban heavy truck mobility data become available in recent years, in-depth studies on the structure and evolution of UHTMN are still lacking. Here we use massive urban heavy truck GPS data in China to construct the UHTMN and reveal its a wide range of structure properties. We further develop an evolving network model that simultaneously considers weight, space and system element duplication. Our model reproduces the observed structure properties of UHTMN and helps us understand its underlying evolutionary mechanisms. Our model also provides new perspectives for modeling the evolution of many other real-world networks, such as protein interaction networks, citation networks and air transportation networks. © 2022, CC BY.

关键词： Structural properties

Reconstructing Missing Modalities in Multi-Modal Endoscopic Ultrasound Via Cross-Modal Feature Replacement Representation

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Zheng, Cenyang Gong, Xun Fan, Lin Li, Jiao School of Computing and Artificial Intelligence Southwest Jiaotong University Sichuan Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China Department of Gastroenterology The Third People’s Hospital of Chendu Affiliated Hospital of Southwest Jiaotong University Chengdu610031 China

Endoscopic ultrasound (EUS) is the primary diagnostic imaging technique for gastrointestinal stromal tumors. However, accurately identifying these tumors through EUS imaging alone remains challenging, even for experienced clinicians. They often rely on additional data, such as white light endoscopy (WLE) and EUS text reports, to aid in the diagnosis. Unfortunately, in practice, these supplementary modalities are sometimes overlooked during patient evaluation. To address these issues, we propose the Cross-modal Feature Reconstruction Network (CFRN), which integrates multimodal data modeling for medical diagnostic processes and performs specific learning for different modalities with missing data. The network fuses the multi-modal features based on the clinical medical process, realizes the feature-level missing modality reconstruction, and learns the refined features of different modal true cases by decoding the mode-specific missing. We trained and tested the model on two publicly available datasets, Audiovision-MNIST, MM-IMDb, and data sets collected from real clinical scenarios at three hospitals. Our results show that CFRN outperforms state-of-the-art methods, achieving higher prediction accuracy than using EUS alone. By simultaneously incorporating multimodal or reconstructed modal data for disease diagnosis, our single-modal EUS model proves to be more suitable for clinical scenarios. © 2024, The Authors. All rights reserved.

关键词： Endoscopy

Impact of Stochasticity on Platoon Stability of Car-Following Models for Emissions Estimation

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Meng, Dongli Song, Guohua Lu, Hongyu Wu, Yizheng Zhai, Zhiqiang Yu, Lei Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Beijing Jiaotong University 3 Shangyuancun Haidian District Beijing100044 China School of Civil and Environmental Engineering Georgia Institute of Technology 790 Atlantic Drive AtlantaGA30332 United States Department of Transportation Studies Texas Southern University 3100 Cleburne Avenue HoustonTX77004 United States Xuchang University Henan Xuchang461000 China

In the application of microscopic traffic simulations for vehicle emissions modeling, the reality and platoon stability of vehicle trajectories derived from the car-following component has been questioned. This study compared the platoon stability of the Gipps car-following model, the full velocity difference model (FVDM), the intelligent driver model (IDM), and the Wiedemann model for emissions modeling, followed by a parameter sensitivity analysis and a stochasticity impact investigation. The results indicated the superior performance of the FVDM and IDM for emissions estimation compared with the Wiedemann model, and the emissions estimation errors were stable along the platoon for the above models. Gipps model generated realistic vehicle dynamics of the first following vehicle, however, the emissions estimation errors increased along the platoon. The parameter calibration failed to improve the platoon stability of the Gipps model, while incorporating the stochastic parameters was proven to reproduce representative platoon trajectories for accurate emissions estimations. © 2022, The Authors. All rights reserved.

关键词： Stochastic systems

Impact of Stochasticity on Platoon Stability of Car-Following Models for Emissions Estimation

学校读者我要写书评

暂无评论

SSRN 2022年

In the application of microscopic traffic simulations for vehicle emissions modeling, the reality and platoon stability of vehicle trajectories derived from the car-following component has been questioned. This study compared the platoon stability of the Gipps car-following model, the full velocity difference model (FVDM), the intelligent driver model (IDM), and the Wiedemann model for emissions modeling, followed by a parameter sensitivity analysis and a stochasticity impact investigation. The results indicated the superior performance of the FVDM and IDM for emissions estimation compared with the Wiedemann model, and the emissions estimation errors were stable along the platoon for the above models. Gipps model generated realistic vehicle dynamics of the first following vehicle, however, the emissions estimation errors increased along the platoon. This study found that it is difficult to improve the platoon stability of the Gipps model by parameter calibration. While taking into account the driving behavior heterogeneity and the human factors, the Gipps model was modified by incorporating the stochastic parameters to reproduce representative platoon trajectories for accurate emissions estimations. © 2022, The Authors. All rights reserved.

关键词： Stochastic systems