检索结果-内蒙古大学图书馆

14th China Satellite Navigation Conference, CSNC 2024

作者： Wu, Fanming Li, Dengao Zhao, Jinhua Feng, Ran Shi, Danyang Zhang, Xinfang Zhao, Jumin College of Data Science Taiyuan University of Technology Taiyuan030024 China College of Information and Computer Taiyuan University of Technology Taiyuan030024 China Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province Taiyuan030024 China Intelligent Perception Engineering Technology Center of Shanxi Taiyuan030024 China Shanxi Province Engineering Technology Research Center of Spatial Information Network Taiyuan030024 China

ISBN: (纸本)9789819969272

There is a growing interest to use Global Navigation Satellite System (GNSS) inversed PWV for heavy rainfall prediction. When heavy rainfall occurs, it requires the atmosphere to contain sufficient water vapour and undergo strong upward motion. However, existing models using GNSS-PWV for heavy rainfall prediction have not accounted for the effect of the complex motion of water vapour. In this paper, an hourly heavy rainfall prediction model using sample entropy derived from GNSS-PWV and PSO-SVM is proposed. The sample entropy of GNSS-PWV is used to measure the complexity of the water vapour movement process before heavy rainfall occurs. Meanwhile, combining GNSS-PWV time domain features and co-located meteorological data, the occurrence of hourly heavy rainfall events is predicted by support vector machine optimized with particle swarm. To verify the validity and feasibility of the proposed algorithm, Hong Kong's HKSC station in Sham Shui Po is used for the model to train and test. The result shows that probability of detection, false alarm rate and critical success index of the proposed algorithm in this paper have significantly improved over other heavy rainfall prediction models. © 2024, Aerospace Information Research Institute.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Prediction of Ionospheric TEC Based on BLS-LSTM-GRU Hybrid Model 14th

Prediction of Ionospheric TEC Based on BLS-LSTM-GRU Hybrid M...

引用

14th China Satellite Navigation Conference, CSNC 2024

作者： Li, Dengao Zhang, Xinfang Zhao, Jumin Wu, Fanming Feng, Ran Zhao, Jinhua Shi, Danyang College of Data Science Taiyuan University of Technology Taiyuan030024 China College of Information and Computer Taiyuan University of Technology Taiyuan030024 China Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province Taiyuan030024 China Intelligent Perception Engineering Technology Center of Shanxi Taiyuan030024 China Shanxi Province Engineering Technology Research Center of Spatial Information Network Taiyuan030024 China

ISBN: (纸本)9789819969272

In satellite communications, global navigation satellite systems(GNSS) and other important space activities, the value of total electron content (TEC) in the ionosphere directly affects the size of ionospheric delay. Achieving accurate prediction of ionospheric total electron content through modeling can effectively improve the reliability and accuracy of GNSS positioning. Considering the high prediction accuracy of long short-term memory neural network (LSTM) and the fast training speed of gated recurrent unit network (GRU), but it is easy to fall into the local optimum, while the width learning system(BLS) can effectively avoid this drawback. Therefore, this paper proposes a model for predicting the total electron content of the ionosphere, which consists of a broad learning system, an LSTM network and a GRU networks. Six parameters of TEC, geomagnetic index Dst, Kp, Ap, solar activity index F10.7, and hour (HD) are selected as input features from the observed data to predict the variation of the total ionospheric electron content. The results generate prediction maps of the total ionospheric electron content and are compared with empirical models and conventional neural network models at different times and solar activity conditions. The experimental results show that the root mean square error (RMSE) of the prediction results of this BLS-LSTM-GRU model is decreased by 23.07%, 17.48% and 9.46% compared with the IRI-2016, NeQuick and CNN-LSTM prediction models, respectively, with higher prediction accuracy. © 2024, Aerospace Information Research Institute.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Research on Zenith Tropospheric Delay Model Based on TCN Improving HGPT2 Model 14th

Research on Zenith Tropospheric Delay Model Based on TCN Imp...

引用

14th China Satellite Navigation Conference, CSNC 2024

作者： Li, Dengao Shi, Danyang Zhao, Jumin Wu, Fanming Yan, Liangquan Feng, Ran Zhang, Xinfang Zhao, Jinhua College of Data Science Taiyuan University of Technology Taiyuan030024 China College of Information and Computer Taiyuan University of Technology Taiyuan030024 China Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province Taiyuan030024 China Intelligent Perception Engineering Technology Center of Shanxi Taiyuan030024 China Shanxi Province Engineering Technology Research Center of Spatial Information Network Taiyuan030024 China

ISBN: (纸本)9789819969272

The zenith tropospheric delay (ZTD) obtained by global navigation satellite system (GNSS) atmospheric sounding is a pivotal data source for water vapor monitoring. Meteorological changes in Antarctica play an important role in analysis of the global climate, but factors such as complex climatic conditions can limit the collection of meteorological data needed for ZTD retrieval. Therefore, it is necessary to establish high-precision ZTD models that do not rely on measured meteorological data. The existing global pressure and temperature 3 (GPT3) model has limited ability to capture complex weather variations and cannot obtain high-precision GPT3_ZTD. To address the above issues, this research proposes a high-precision ZTD model through using temporal convolutional network (TCN) for improving the hourly global pressure and temperature 2 (HGPT2) model. The HGTP2 model based on Fourier analysis and the time-segmentation concept can consider the linear trend of climate variations, simultaneously the TCN is introduced to simulate the long-term temporal dependence of HGPT2_ZTD, so as to achieve the goal of obtaining high-precision ZTD without relying on measured meteorological data. The experimental results show that the precision of TCN_ZTD obtained from the proposed model is higher than GPT3_ZTD and HGPT2_ZTD when using the GNSS_ZTD observations obtained from 35 stations in Antarctica as a reference, and the improvement of the model is obvious. © 2024, Aerospace Information Research Institute.

关键词： Fourier analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Location of Emergency Bridging Bus Reserve Bases Based on Metro Complex Network 6

Research on Location of Emergency Bridging Bus Reserve Bases...

引用

6th International Conference on Traffic engineering and Transportation System, ICTETS 2022

作者： Zhan, Yu Liu, Yugang Zheng, Shuai Sheng, Qian Chen, Bin Xu, Yihe School of Transportation and Logistics Southwest Jiaotong University Sichuan Province Chengdu610031 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Sichuan Province Chengdu610031 China National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Sichuan Province Chengdu610031 China Institute of Transportation Development Strategy and Planning of Sichuan Province Sichuan Province Chengdu610000 China

ISBN: (纸本)9781510663053

Urban metro is developing in the direction of the network. With the increasing scale, dealing with the sudden accident of the metro network has brought significant challenges to the relevant departments. When the metro is disrupted, it is necessary to evacuate the passengers. Emergency bus bridging is an essential means to evacuate the passengers. Notably, the core of efficient emergency bus bridging strategy is how to plan the location of the emergency bus reserve bases. Hence, this paper aims to establish the site selection model based on the vulnerability of the complex metro network, and rationally lay out the source of the emergency bridging bus in the case of sudden disruption of the complex metro network. Firstly, the space L topology model of the metro network is established, and the performance indicators of the network are analyzed by grey relational analysis (GRA), to identify the key stations. Secondly, we use a reverse covering location model to optimize the bridging response delay time and the number of reserved buses. Taking Tianjin metro network as a case study scenario, the research results of this paper are compared with those of other scholars. By comparison, the location results are better in coverage, bridging response delay time and the number of reserved buses. Therefore, the research method of this paper provides new ideas and new methods for the location of the emergency bridge bus reserve base. © 2023 SPIE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Vulnerability analysis of weighted metro networks considering station traffic: the case of Shenzhen 6

Vulnerability analysis of weighted metro networks considerin...

引用

6th International Conference on Traffic engineering and Transportation System, ICTETS 2022

作者： Long, Shiyu Liu, Yugang Zheng, Shuai Xu, Yihe School of Transportation and Logistics Southwest Jiaotong University Sichuan Province Chengdu610031 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Sichuan Province Chengdu610031 China National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Sichuan Province Chengdu610031 China Institute of Transportation Development Strategy and Planning of Sichuan Province Sichuan Province Chengdu610000 China

ISBN: (纸本)9781510663053

Due to the large number of passengers served by the metro, with its extensive served area, as well as the interconnection of different stations within the metro system, there is a high possibility that a large number of city residents' trips will be delayed or forced to be canceled and cause economic losses, once a safety accident occurs in the subway system. An easy-to-practice and highly flexible evaluation framework are proposed to explore the identification of vulnerable nodes in a weighted metro network, considering network connectivity and node traffic. The degree distribution of the passenger flow weighted network obeys the power law distribution. The relationship between node connectivity, node passenger flow, and key players in the network are also discussed. We simulated network node failures under four scenarios to assess the impact of node failures on network accessibility and the number of passengers served. The network is robust when the nodes fail randomly;the network is vulnerable to deliberate attacks based on topological node characteristics. The strategies that have the most significant impact on site traffic are node weight-based attack and node weighted-degree-based attack, with the weighted-degree-based attack being more disruptive to network connectivity and the best performing strategy in aggregate. Furthermore, we have identified the top 10 nodes in the Shenzhen Metro network that are more influential to passengers and disruptive to the network structure, which could provide a reference for metro emergency management. © 2023 SPIE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

New stations of urban rail based on TOD model classification Inbound and outbound passenger traffic forecasts： the case of Chengdu 6

New stations of urban rail based on TOD model classification...

引用

6th International Conference on Traffic engineering and Transportation System, ICTETS 2022

作者： Wang, Qiang Liu, Yugang Zheng, Shuai Chen, Bin Li, Yahui School of Transportation and Logistics Southwest Jiaotong University Sichuan Province Chengdu610031 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Sichuan Province Chengdu610031 China National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Sichuan Province Chengdu610031 China Institute of Transportation Development Strategy and Planning of Sichuan Province Sichuan Province Chengdu610000 China

ISBN: (纸本)9781510663053

In order to grasp the pattern of passenger flow changes at the initial opening of new urban rail transit TOD stations and to address the problem of irregular fluctuations in passenger flow at new stations and the absence of historical data, this paper proposes a method for predicting passenger flow in and out of new urban rail transit stations based on the TOD mode division. Firstly, through the analysis of the classification method of traditional TOD stations and the classification index of TOD stations, the TOD characteristic similarity urban rail stations are classified based on the hierarchical clustering algorithm. Secondly, according to the station classification results, a method is proposed to construct a historical database of passenger flow in and out of new stations. Then, by optimizing the parameters of the differential integrated moving average autoregressive model, a short-time prediction method for passenger flow in and out of new stations of urban rail TOD is proposed. Finally, the model is tested with the actual passenger flow data of the urban rail line network. The results show that the prediction errors of incoming and outgoing passenger flows are 2.59% and 7.67%, respectively, indicating that the prediction method is effective and can be applied to the pre-construction planning of new TOD stations. The prediction results can provide a reference for the urban rail traffic organization. © 2023 SPIE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Research on 2+1 alternate highway setting in mountain area based on VISSIM simulation 6

Research on 2+1 alternate highway setting in mountain area b...

引用

6th International Conference on Traffic engineering and Transportation System, ICTETS 2022

作者： Hu, Fenglin Liu, Yugang Zhang, Shaohua Yi, Hongbo Liu, Gang School of Transportation and Logistics Southwest Jiaotong University Sichuan Province Chengdu610031 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Sichuan Province Chengdu610031 China National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Sichuan Province Chengdu610031 China Institute of Transportation Development Strategy and Planning of Sichuan Province Sichuan Province Chengdu610000 China

ISBN: (纸本)9781510663053

For a long time, the operation efficiency of highways in sichuan plateau mountainous areas has been low, and overtaking accidents occur frequently. In addition, many places are limited by natural conditions and unable to build the two-way four-lane highway. Hence, this paper proposes a new scheme to transform and expand the two-lane road into a 2+1 alternate lane. We used VISSIM software, combined with the actual traffic characteristics of the sichuan mountainous area, and integrated with the driving behavior features to conduct a simulation analysis on the geometric parameter design, setting influencing factors and applicability of 2+1 alternate highway. It not only fills the domestic research gap but also provides theoretical support for building a safe and efficient mountain traffic system. The study found: This scheme optimizes the service level while improving the operation efficiency. When the proportion of trucks exceeds 20%, prohibiting trucks from passing through overtaking lanes shows relatively higher service levels. 2+1 alternate highways in mountainous areas have significantly better service levels than other options when the overtaking lane length is set to 550-900m, and the speed limit in the single lane is 50-100km/h. © 2023 SPIE.

关键词： Trucks

来源：评论

学校读者我要写书评

暂无评论

A TSICN-based Inferential Synthesis Method for Class Imbalance in Credit Scoring

A TSICN-based Inferential Synthesis Method for Class Imbalan...

引用

IEEE International Conference on data Mining (ICDM)

作者： Dongxu Fanab Xuanzhi Feng Jinghe Jiang Yuming Jiang Le Zhang Dasha Hu College of Computer Science Sichuan University Chengdu China Big Data Analysis and Fusion Application Technology Engineering Laboratory of Sichuan Province Chengdu China Department of Economics College of Letters and Science University of California Los Angeles USA

lass imbalance and data obsolescence are two major issues in the field of credit scoring, leading to excessive bias and inaccuracies in the classification process of credit scoring models. In order to augment minority class samples and balance time dependencies, this paper proposes a credit scoring model based on Temporal Sample Interaction Convolutional Network (TSICN) to facilitate better credit risk assessment for financial institutions. It relies on the intrinsic features of the minority class samples to synthesize new data, thereby increasing the quantity of the minority class samples. Through inference and synthesis, It greatly mitigates the loss of information from minority class samples. The synthesized minority class samples, blended with the original data, are inputted into the causal convolutional layers and dilated convolutional layers. The information flow and memory updates are regulated through reset gate and update gate, The reset gate determines how to combine past information with the current input, while the update gate determines how to combine the previous hidden state with the current candidate hidden state. Compared to common methods, TSICN can integrate information features from minority class samples into the synthesis data, focusing more on short-term dependencies while reducing the capture of long-term dependencies. Experimental results show that TSICN achieves excellent credit scoring classification performance on real-world datasets. This enables more accurate prediction of applicant credit risk, thus reducing the risk of loan default.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The influence of continuous tunnel driving on high-speed rail drivers’ brain responses

引用

Tunnelling and Underground Space technology 2025年 163卷

作者： Zizheng Guo Huishan Pang Guofa Li Zhenning Li Hui Xu Paul Green School of Transportation and Logistics Southwest Jiaotong University Chengdu 610031 China Intelligent Comprehensive Transportation Key Laboratory of Sichuan Province Chengdu 610031 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu 610031 China College of Mechanical and Vehicle Engineering Chongqing University Chongqing 400044 China State Key Laboratory of Internet of Things for Smart City University of Macau Macau 999078 China China Railway Chengdu Group Co. Ltd. Chengdu 610031 China University of Michigan Transportation Research Institute (UMTRI) and the Department of Industrial and Operations Engineering University of Michigan Ann Arbor MI 48109 USA

The impact of tunnels on driver performance is significant, yet it remains understudied in the context of high-speed rail. This study investigated the effects of continuous tunnel driving on high-speed rail drivers’ mental fatigue and brain functional connectivity using electroencephalography (EEG) and graph theory. Forty-two participants performed simulated driving tasks in continuous tunnel and plain scenarios. Results demonstrated that tunnel scenarios significantly elevated subjective fatigue and prolonged reaction times ( p < 0.001). EEG analysis revealed increased functional connectivity in the α, θ, and β bands, particularly in frontal, parietal, and central regions. Graph theory metrics showed reduced characteristic path length and increased clustering coefficient in the θ band during tunnel driving, indicating a shift toward small-world network topology. These findings emphasize the importance of in-depth research on driver fatigue in high-speed rail tunnel operations to develop targeted intervention measures.

关键词： EEG Functional connectivity High-speed rail Phase Lag Index (PLI) Tunnel

来源：评论

学校读者我要写书评

暂无评论

Research on Zenith Tropospheric Delay Model Based on TCN Improving HGPT2 Model

Research on Zenith Tropospheric Delay Model Based on TCN Imp...

引用

第十四届中国卫星导航年会

作者： Dengao Li Danyang Shi Jumin Zhao Fanming Wu Liangquan Yan Ran Feng Xinfang Zhang Jinhua Zhao College of Data Science Taiyuan University of Technology Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province Intelligent Perception Engineering Technology Center of Shanxi Shanxi Province Engineering Technology Research Center of Spatial Information Network College of Information and Computer Taiyuan University of Technology

The zenith tropospheric delay（ZTD） obtained by global navigation satellite system（GNSS） atmospheric sounding is a pivotal data source for water vapor monitoring. Meteorological changes in Antarctica play an important role in analysis of the global climate, but factors such as complex climatic conditions can limit the collection of meteorological data needed for ZTD retrieval. Therefore, it is necessary to establish high-precision ZTD models that do not rely on measured meteorological data. The existing global pressure and temperature 3（GPT3） model has limited ability to capture complex weather variations and cannot obtain high-precision GPT3TD. To address the above issues, this research proposes a high-precision ZTD model through using temporal convolutional network（TCN） for improving the hourly global pressure and temperature 2（HGPT2） model. The HGTP2 model based on Fourier analysis and the time-segmentation concept can consider the linear trend of climate variations, simultaneously the TCN is introduced to simulate the long-term temporal dependence of HGPT2TD, so as to achieve the goal of obtaining high-precision ZTD without relying on measured meteorological data. The experimental results show that the precision of TCNTD obtained from the proposed model is higher than GPT3TD and HGPT2TD when using the GNSSTD observations obtained from 35 stations in Antarctica as a reference, and the improvement of the model is obvious.

关键词： GNSS ZTD GPT3 HGPT2 TCN

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：