检索结果-内蒙古大学图书馆

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

作者： Xu, Wanhui Liu, Yugang 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

Autonomous driving vehicle will come reality more and more possible along with prosperity of relevant technologies. However, autonomous driving vehicles and artificial driving vehicles will coexist for a long time until full connected and autonomous traffic environment achieved. To modeling lane-changing decision of autonomous driving vehicles, which can be regard as non-cooperative static game under complete information, we establish the game theory-based lane-changing model with combined driving style (GLCD model). Then we conduct a series of simulation experiments to evaluate indicators of the GLCD model, which include the number of lane-changing, the number of accidents, the number of vehicle passes and, the average passing time, compared with the cellular automata model, also compared with the general game theory-based lane-changing model. Results show that the developed model (GLCD model) can improve the efficiency of vehicle driving and ensure stability on the road under the premise of ensuring safety. Furthermore, this model can provide a feasible vehicle lane-change decision in a mixed traffic flow environment in the future. © 2023 SPIE.

关键词： Game theory

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

Urban transportation network allocation considering heterogeneous users in the context of carbon trading 6

Urban transportation network allocation considering heteroge...

引用

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

作者： Sheng, Qian Liu, Yugang Zhan, Yu Wan, Qing Fan, LinQiang 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 motor vehicles in urban road networks, serious traffic congestion and high proportion of road carbon emissions, failure to take effective measures to manage travel demand will result in waste of road resources and environmental pollution. Considering the complex variability of the actual road network and the heterogeneous characteristics of road travelers, this paper proposes a dynamic traffic network allocation model in the context of carbon trading. The model is a dual dynamic day-by-day model, which considers both the dynamic changes of road network traffic and the dynamic adjustment and changes of carbon quota consumption rate. After 600 days of dynamic evolution, the road network reaches the system optimal state while achieving user equilibrium. Meanwhile, the carbon emission reduction on the road transport network before and after the implementation of carbon trading scheme is compared and analyzed, and the overall carbon emission is reduced by 9.23%. This provides a scientific theoretical basis and a feasible solution for the carbon trading scheme in urban transportation demand management and guiding low-carbon travel. © 2023 SPIE.

关键词： Carbon

来源：评论

学校读者我要写书评

暂无评论

A self-supervised CNN for image watermark removal

arXiv

引用

arXiv 2024年

作者： Tian, Chunwei Zheng, Menghua Jiao, Tiancai Zuo, Wangmeng Zhang, Yanning Lin, Chia-Wen the School of Software Northwestern Polytechnical University Shaanxi Xi’an710129 China the National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710129 China the School of Computer Science and Technology Harbin Institute of Technology Heilongjiang Harbin150001 China the Peng Cheng Laboratory Laboratory Guangdong Shenzhen518055 China the School of Computer Science Northwestern Polytechnical University the National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710129 China the Department of Electrical Engineering the Institute of Communications Engineering National Tsing Hua University Hsinchu300 Taiwan

Popular convolutional neural networks mainly use paired images in a supervised way for image watermark removal. However, watermarked images do not have reference images in the real world, which results in poor robustness of image watermark removal techniques. In this paper, we propose a self-supervised convolutional neural network (CNN) in image watermark removal (SWCNN). SWCNN uses a self-supervised way to construct reference watermarked images rather than given paired training samples, according to watermark distribution. A heterogeneous U-Net architecture is used to extract more complementary structural information via simple components for image watermark removal. Taking into account texture information, a mixed loss is exploited to improve visual effects of image watermark removal. Besides, a watermark dataset is conducted. Experimental results show that the proposed SWCNN is superior to popular CNNs in image watermark removal. Codes can be obtained at https://***/hellloxiaotian/SWCNN. Copyright © 2024, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

A Weighted Flat Lattice Transformer-based Knowledge Extraction Architecture for Chinese Named Entity Recognition

A Weighted Flat Lattice Transformer-based Knowledge Extracti...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Hengwei Zhang Yuejia Wu Jian-Tao Zhou Inner Mongolia University College of Computer Science Hohhot China Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Hohhot China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Hohhot China Inner Mongolia Key Laboratory of Social Computing and Data Processing Hohhot China Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Hohhot China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Named Entity Recognition (NER) is one of the contents of Knowledge Extraction (KE) that transforms data into knowledge representation. However, Chinese NER faces the problem of lacking clear word boundaries that limit the effectiveness of the KE. Although the flat lattice Transformer (FLAT) framework, which converts lattice structure into a flat structure including a set of spans, can effectively improve this problem and obtain advanced results, there still exist the problems of insensitivity to entity importance weights and insufficient feature learning. This paper proposes a weighted flat lattice Transformer architecture for Chinese NER, namely WFLAT. The WFLAT first adds a weight matrix into self-attention calculation, which can obtain finer-grained partitioning of entities to improve experimental performance, and then adopts a multi-layer Transformer encoder with each layer using a multi-head self-attention mechanism. Extensive experimental results on benchmarks demonstrate that our proposed KE model can obtain state-of-the-art performance for the Chinese NER task.

关键词： Representation learning Computational modeling Memory management Lattices Named entity recognition Transforms Knowledge representation

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

Non-uniform sampling based frequency shifting fringe projection technique 14

Non-uniform sampling based frequency shifting fringe project...

引用

14th International Conference on Information Optics and Photonics, CIOP 2023

作者： Qi, Zhaoshaui Hu, Rui Feng, Zeyuan Liu, Xiaolin Hao, Yifeng Pang, Jingqi Zhang, Yanning National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University No.127 YouYi West Road BeiLin District Shaanxi Xi'an710129 China School of Computer Science Northwestern Polytechnical University No.127 YouYi West Road BeiLin District Shaanxi Xi'an710129 China

ISBN: (纸本)9781510671744

Recently, the frequency-shifting (FS) projection technique provides a promising alternative to the traditional phase-shifting (PS) fringe projection profilometry (FPP). It solves the absolute phase retrieval problem directly in a completely different fashion, without any phase unwrapping. However, due to the Nyquist sampling theorem (NST), a constant frequency-shift only supports for a limited effective field (EF). It only covers a limited region of the fringe pattern, and the phase retrieval quality degenerates dramatically for those out of the EF. This issue tends significant especially for a high-resolution fringe pattern, limiting the practical application in real life. To this end, we introduce the non-uniform sampling strategy into frequency-shifting technique. With a temporally varying frequency-shift, the EF can be improved significantly, achieving globally high quality across all regions in the pattern for the retrieved phase. Simulation and real experimental results have validated the efficacy of the proposed technique. © 2023 SPIE.

关键词： Profilometry

来源：评论

学校读者我要写书评

暂无评论

Heavy Rainfall Prediction Model Using Sample Entropy Derived from GNSS-PWV and PSO-SVM

Heavy Rainfall Prediction Model Using Sample Entropy Derived...

引用

第十四届中国卫星导航年会

作者： Fanming Wu Dengao Li Jinhua Zhao Ran Feng Danyang Shi Xinfang Zhang Jumin 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

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 *** 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(PWV value, PWV increment,PWV decrement, rate of PWV increment, rate of PWV decrement) and colocated 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.

关键词：

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

Prediction of Ionospheric TEC based on BLS-LSTM-GRU Hybrid m...

引用

第十四届中国卫星导航年会

作者： Dengao Li Xinfang Zhang Jumin Zhao Fanming Wu Ran Feng Jinhua Zhao Danyang Shi 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

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 BLSLSTM-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.

关键词：

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：