Short-Term Traffic Flow Prediction Based on Ensemble Real-Time Sequential Extreme Learning Machine Under Non-Stationary Condition

2016 ◽  
Author(s):  
Dong Wang ◽  
Jie Xiong ◽  
Zhu Xiao ◽  
Xiaohong Li
Keyword(s):  
Real Time ◽  
Traffic Flow ◽  
Extreme Learning Machine ◽  
Stationary Condition ◽  
Short Term ◽  
Traffic Flow Prediction ◽  
Flow Prediction ◽  
Learning Machine

An New Approach of Real-Time Traffic Flow Prediction Based on Intelligent Transportation Technology

2014 ◽  
Vol 988 ◽  
pp. 715-718
Author(s):  
Jia Yang Li ◽  
Qin Xue ◽  
Jin De Liu
Keyword(s):  
Real Time ◽  
Traffic Flow ◽  
Intelligent Transportation System ◽  
Intelligent Transportation ◽  
Short Term ◽  
New Approach ◽  
Traffic Flow Prediction ◽  
Real Time Traffic ◽  
Flow Prediction ◽  
Combination Approach

Short-term traffic flow forecasting is a core problem in Intelligent Transportation System .Considering linear and nonlinear, this paper proposes a short-term traffic flow intelligent combination approach. The weight of four forecasting model is given by the correlation coefficient and standard deviation method. The experimental results show that the new approach of real-time traffic flow prediction is higher precision than single method.

scholarly journals The Traffic Flow Prediction Method Using the Incremental Learning-Based CNN-LTSM Model: The Solution of Mobile Application

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Yanli Shao ◽  
Yiming Zhao ◽  
Feng Yu ◽  
Huawei Zhu ◽  
Jinglong Fang
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Traffic Flow ◽  
Incremental Learning ◽  
Mobile Application ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Short Term ◽  
Traffic Flow Prediction ◽  
Flow Prediction

With the acceleration of urbanization and the increase in the number of motor vehicles, more and more social problems such as traffic congestion have emerged. Accordingly, efficient and accurate traffic flow prediction has become a research hot spot in the field of intelligent transportation. However, traditional machine learning algorithms cannot further optimize the model with the increase of the data scale, and the deep learning algorithms perform poorly in mobile application or real-time application; how to train and update deep learning models efficiently and accurately is still an urgent problem since they require huge computation resources and time costs. Therefore, an incremental learning-based CNN-LTSM model, IL-TFNet, is proposed for traffic flow prediction in this study. The lightweight convolution neural network-based model architecture is designed to process spatiotemporal and external environment features simultaneously to improve the prediction performance and prediction efficiency of the model. Especially, the K-means clustering algorithm is applied as an uncertainty feature to extract unknown traffic accident information. During the model training, instead of the traditional batch learning algorithm, the incremental learning algorithm is applied to reduce the cost of updating the model and satisfy the requirements of high real-time performance and low computational overhead in short-term traffic prediction. Furthermore, the idea of combining incremental learning with active learning is proposed to fine-tune the prediction model to improve prediction accuracy in special situations. Experiments have proved that compared with other traffic flow prediction models, the IL-TFNet model performs well in short-term traffic flow prediction.

A spatial-temporal approach for traffic status analysis and prediction based on Bi-LSTM structure

2021 ◽  
pp. 2150481
Author(s):  
Linjia Li ◽  
Yang Yang ◽  
Zhenzhou Yuan ◽  
Zhi Chen
Keyword(s):  
Real Time ◽  
Traffic Flow ◽  
Traffic Control ◽  
Road Traffic ◽  
Performance Measurement System ◽  
Flow Data ◽  
Short Term ◽  
Temporal Differences ◽  
Traffic Flow Prediction ◽  
Flow Prediction

Urban traffic control has become a big issue to help traffic management in recent years. With data explosion, Intelligent Transportation System (ITS) is developing rapidly. ITS is an advanced data-based method for traffic control, which requires timely and effective information supply. This research aims at providing real-time and accurate traffic flow data by intelligent prediction method. Applying multiple road traffic flow data of the Caltrans Performance Measurement System (PeMS) and separating the time series, the mechanism of spatial-temporal differences was taken into consideration. Based on the basic Long Short-Term Memory (LSTM) model, an improved LSTM model with Dropout and Bi-structure (Bi-LSTM) for traffic flow prediction was presented. In the prediction process, we applied three models including the improved Bi-LSTM model, Gated Recurrent Unit (GRU) model and Linear Regression in the experiment, and made a comparison from aspects of model structure complexity, operating efficiency and prediction accuracy. To validate the portability of the prediction model, the features of traffic flow from different datasets were further analyzed. The experimental results show that the improved Bi-LSTM model performs best in traffic flow prediction with comprehensive rationality, which reaches an accuracy of about 92% when considering temporal differences. Particularly, the specific factors of traffic situations and locations which is more applicable to be predicted by the improved Bi-LSTM model are summarized considering spatial differences. This research proposes an advanced and accurate model to provide real-time and short-term traffic flow prediction data, which is of great help to intelligent traffic control. Considering the mechanism between model and road traffic properties, the results suggest that it is more applicable in urban commercial area.

Sign in / Sign up

Export Citation Format

Share Document