检索结果-南通市图书馆

Hourly traffic flow forecasting using a new hybrid modelling method

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Central South University 2022年第4期29卷 1389-1402页

作者： LIU Hui ZHANG Xin-yu YANG Yu-xiang LI Yan-fei YU Cheng-qing Institute of Artificial Intelligence and Robotics(IAIR) Key Laboratory of Traffic Safety on Track of Ministry of EducationSchool of Traffic and Transportation EngineeringCentral South UniversityChangsha 410075China School of Mechatronic Engineering Hunan Agricultural UniversityChangsha 410128China

Short-term traffic flow forecasting is a significant part of intelligent transportation *** some traffic control scenarios,obtaining future traffic flow in advance is conducive to highway management department to have sufficient time to formulate corresponding traffic flow control *** hence,it is meaningful to establish an accurate short-term traffic flow method and provide reference for peak traffic flow *** paper proposed a new hybrid model for traffic flow forecasting,which is composed of the variational mode decomposition(VMD)method,the group method of data handling(GMDH)neural network,bi-directional long and short term memory(BILSTM)network and ELMAN network,and is optimized by the imperialist competitive algorithm(ICA)*** illustrate the performance of the proposed model,there are several comparative experiments between the proposed model and other *** experiment results show that 1)BILSTM network,GMDH network and ELMAN network have better predictive performance than other single models;2)VMD can significantly improve the predictive performance of the ICA-GMDH-BILSTM-ELMAN *** effect of VMD method is better than that of EEMD method and FEEMD *** conclude,the proposed model which is made up of the VMD method,the ICA method,the BILSTM network,the GMDH network and the ELMAN network has excellent predictive ability for traffic flow series.

关键词： traffic flow forecasting intelligent transportation system imperialist competitive algorithm variational mode decomposition group method of data handling bi-directional long and short term memory ELMAN

traffic flow forecasting Based on Fuzzy-Neural

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Traffic Flow Forecasting Based on Fuzzy-Neural

第二十六届中国控制会议

作者： Huang Hongqiong 1,Tang Tianhao2 1.College of Information Engineering,Shanghai maritime University,Shanghai 200135,P.R.China 2.College of Logistics Engineering,Shanghai maritime University,Shanghai 200135,P.R.China

Fuzzy systems can be excellently used to represent human *** technology is a science where this property of fuzzy logic can be used very well because it is hard to make mathematical models due to human influences and complex connections between input *** paper applies a novel Fuzzy Cerebella-Model-Articulation-Controller（FCMAC）into univariate time-series forecasting and investigates its performance in comparison to established techniques such as the Box-Jenkin’s ARIMA *** results from Pudong New Strict in Shanghai traffic flow data reveal that the FCMAC model yielded lower errors for certain data *** conditions under which the FCMAC model emerged superior are ***,we show how neural networks can be used to improve the performance of the system.

关键词： Fuzzy logic Neural-Fuzzy traffic flow forecasting FCMAC

Building trust for traffic flow forecasting components in intelligent transportation systems via interpretable ensemble learning

在线全文

cnki会议

学校读者我要写书评

暂无评论

Digital Transportation and Safety

Digital Transportation and Safety 2024年第3期3卷 126-143,I0001,I0002页

作者： Jishun Ou Jingyuan Li Chen Wang Yun Wang Qinghui Nie College of Architectural Science and Engineering Yangzhou UniversityYangzhou 225127China School of Transportation Southeast UniversityNanjing 211189China Transportation Information and Communication Center Jilin Provincial Department of TransportationJilin 130000China

traffic flow forecasting constitutes a crucial component of intelligent transportation systems(ITSs).Numerous studies have been conducted for traffic flow forecasting during the past ***,most existing studies have concentrated on developing advanced algorithms or models to attain state-of-the-art forecasting *** real-world ITS applications,the interpretability of the developed models is extremely important but has largely been *** study presents an interpretable traffic flow forecasting framework based on popular tree-ensemble *** framework comprises multiple key components integrated into a highly flexible and customizable multi-stage pipeline,enabling the seamless incorporation of various algorithms and *** evaluate the effectiveness of the framework,the developed tree-ensemble models and another three typical categories of baseline models,including statistical time series,shallow learning,and deep learning,were compared on three datasets collected from different types of roads(i.e.,arterial,expressway,and freeway).Further,the study delves into an in-depth interpretability analysis of the most competitive tree-ensemble models using six categories of interpretable machine learning *** results highlight the potential of the proposed *** tree-ensemble models developed within this framework achieve competitive accuracy while maintaining high inference efficiency similar to statistical time series and shallow learning ***,these tree-ensemble models offer interpretability from multiple perspectives via interpretable machine-learning *** proposed framework is anticipated to provide reliable and trustworthy decision support across various ITS applications.

关键词： traffic flow forecasting Interpretable machine learning Interpretability Ensemble trees Intelligent transportation systems

Local-global dynamic correlations based spatial-temporal convolutional network for traffic flow forecasting

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

High Technology Letters 2024年第4期30卷 370-379页

作者： ZHANG Hong GONG Lei ZHAO Tianxin ZHANG Xijun WANG Hongyan College of Computer and Communication Lanzhou University of TechnologyLanzhou 730050P.R.China

traffic flow forecasting plays a crucial role and is the key technology to realize dynamic traffic guidance and active traffic control in intelligent traffic systems(ITS).Aiming at the complex local and global spatial-temporal dynamic characteristics of traffic flow,this paper proposes a new traffic flow forecasting model spatial-temporal attention graph neural network(STA-GNN)by combining at-tention mechanism(AM)and spatial-temporal convolutional *** model learns the hidden dynamic local spatial correlations of the traffic network by combining the dynamic adjacency matrix constructed by the graph learning layer with the graph convolutional network(GCN).The local tem-poral correlations of traffic flow at different scales are extracted by stacking multiple convolutional kernels in temporal convolutional network(TCN).And the global spatial-temporal dependencies of long-time sequences of traffic flow are captured by the spatial-temporal attention mechanism(STAtt),which enhances the global spatial-temporal modeling and the representational ability of *** experimental results on two datasets,METR-LA and PEMS-BAY,show the proposed STA-GNN model outperforms the common baseline models in forecasting accuracy.

关键词： traffic flow forecasting graph convolutional network(GCN) temporal convolu-tional network(TCN) attention mechanism(AM)

A Short-Term traffic flow forecasting Method Based on a Three-Layer K-Nearest Neighbor Non-Parametric Regression Algorithm

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

Journal of Transportation Technologies 2016年第4期6卷 200-206页

作者： Xiyu Pang Cheng Wang Guolin Huang School of Information Engineering Shandong Jiaotong University Jinan China Department of Intelligent traffic Engineering Yigou Software Technolog Co. Ltd. Jinan China

Short-term traffic flow is one of the core technologies to realize traffic flow guidance. In this article, in view of the characteristics that the traffic flow changes repeatedly, a short-term traffic flow forecasting method based on a three-layer K-nearest neighbor non-parametric regression algorithm is proposed. Specifically, two screening layers based on shape similarity were introduced in K-nearest neighbor non-parametric regression method, and the forecasting results were output using the weighted averaging on the reciprocal values of the shape similarity distances and the most-similar-point distance adjustment method. According to the experimental results, the proposed algorithm has improved the predictive ability of the traditional K-nearest neighbor non-parametric regression method, and greatly enhanced the accuracy and real-time performance of short-term traffic flow forecasting.

关键词： Three-Layer traffic flow forecasting K-Nearest Neighbor Non-Parametric Regression

Port area short-term traffic flow forecasting method in reservation container gate-in mode

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

Port area short-term traffic flow forecasting method in rese...

2011 IEEE International Conference on Intelligent Computing and Intelligent Systems(ICIS 2011)

the reason that urban traffic flow forecasting methods cannot be used in port area was analyzed and the port area short-term traffic flow forecasting method in reservation container gate-in mode was *** first, the route between traffic producing area and traffic attraction area was determined, and the extended length of forecasted section was gotten based on the vehicle ***, the turning rate of upper section to current section was obtained using dynamic weighted comprehensive method, so the traffic demand running to current section can be *** forecasting method uses integrated saturation to measure the traffic flow of upper section and forecasted ***, combined with the level of producing area and traffic attraction area, the vector of port area short-term traffic flow forecasting was *** forecasting loop and learning loop were adopted to form closed-loop *** simulation experiments are conducted to verify the effectiveness of the port area short-term traffic flow forecasting *** results and analysis indicate that the proposed method is valid.

关键词： short-term traffic flow reservation container gate-in mode traffic flow forecasting simulation

Wavelet Decomposition Self-Supervised Neural Networks for traffic flow forecasting

在线全文

cnki会议

学校读者我要写书评

暂无评论

Wavelet Decomposition Self-Supervised Neural Networks for Tr...

第43届中国控制会议

作者： Yingda Li Zhongqi Sun Changkun Du Zuo Jiang Yuanqing Xia School of Automation Beijing Institute of Technology Intelligent Science & Technology Academy Limited of CASIC

Accurate traffic flow forecasting is of great significance for improving traffic flow efficiency,optimizing public traffic resources,and improving traffic management ***,there are two challenges in current traffic flow forecasting:i) most existing models directly deal with the original sequence where multiple temporal patterns coexist,which cannot effectively handle the interdependence among different temporal patterns or remove the influence of irregular noise in the original sequence;ii) they fail to efficiently and simultaneously capture the spatio-temporal heterogeneity of traffic flow to extract the rich latent spatio-temporal representations..To address these challenges,we propose an efficient wavelet decomposition self-supervised learning network(waveSSL).Specifically,the discrete wavelet transform is used to convert the original traffic sequence into two components:high frequency and low *** components represent two temporal patterns,short-term changes,and long-term trends,*** component undergoes a spatio-temporal processing method to fuse the spatio-temporal ***,a self-supervised learner based on a spatio-temporal masking strategy is incorporated to obtain rich latent spatio-temporal representations of traffic flow and enhance the prediction's generalization ability.

关键词： traffic engineering traffic flow forecasting Spatio-temporal forecasting Self-supervised learning Wavelet transform

Deep Reinforcement Learning-Based LSTM Model for traffic flow forecasting in Internet of Vehicles

在线全文

cnki会议

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based LSTM Model for Traffic Flo...

2021中国智能自动化大会(CIAC2021)

作者： Zekuan Chen Xiong Luo Ting Wang Weiping Wang Wenbing Zhao School of Computer and Communication Engineering University of Science and Technology Beijing Beijing Key Laboratory of Knowledge Engineering for Materials Science Shunde Graduate School University of Science and Technology Beijing Department of Electrical Engineering and Computer Science Cleveland State University

Nowadays many large cities often suffer from road congestion. Then,it is necessary to improve the working efficiency of urban road network with the help of computational intelligence technologies, within the Internet of vehicles(Io V) environment. We are committed to designing traffic flow prediction methods through the use of machine learning models. In this paper, we predict the traffic flow and traffic situation of the selected road segment. Specifically, we propose a deep reinforcement learning(DRL)-based long short-term memory(LSTM)model to predict the traffic flow. On the basis of it, we characterize the traffic situation with fuzzy comprehensive evaluation(FCE)-based model. The experimental results show that the constructed DRL-based LSTM model can accurately predict the traffic flow data. Meanwhile, the traffic situation characterization model can represent the road traffic situation well.

关键词： traffic flow forecasting Long short-term memory(LSTM) Deep reinforcement learning(DRL) traffic situation Characterization model

Short-term traffic flow online forecasting based on kernel adaptive filter

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Measurement Science and Instrumentation 2018年第4期9卷 326-334页

作者： LI Jun WANG Qiu-li School of Automation & Electrical Engineering Lanzhou Jiaotong University Lanzhou 730070 China

Considering that the prediction accuracy of the traditional traffic flow forecasting model is low,based on kernel adaptive filter(KAF)algorithm,kernel least mean square(KLMS)algorithm and fixed-budget kernel recursive least-square(FB-KRLS)algorithm are presented for online adaptive *** computational complexity of the KLMS algorithm is low and does not require additional solution paradigm constraints,but its regularization process can solve the problem of regularization performance degradation in high-dimensional data *** reduce the computational complexity,the sparse criterion is introduced into the KLMS *** further improve forecasting accuracy,FB-KRLS algorithm is *** is an online learning method with fixed memory budget,and it is capable of recursively learning a nonlinear mapping and changing over *** contrast to a previous approximate linear dependence(ALD)based technique,the purpose of the presented algorithm is not to prune the oldest data point in every time instant but it aims to prune the least significant data point,thus suppressing the growth of kernel *** order to verify the validity of the proposed methods,they are applied to one-step and multi-step predictions of traffic flow in *** the same conditions,they are compared with online adaptive ALD-KRLS method and other kernel learning *** results show that the proposed KAF algorithms can improve the prediction accuracy,and its online learning ability meets the actual requirements of traffic flow and contributes to real-time online forecasting of traffic flow.

关键词： traffic flow forecasting kernel adaptive filtering (KAF) kernel least mean square (KLMS) kernel recursive least square (KRLS) online forecasting