scholarly journals TRAVEL TIME PREDICTION MODELLING IN MIXED TRAFFIC CONDITIONS

2018 ◽  
Vol 8 (1) ◽  
pp. 135-147 ◽  
Keyword(s):  
Travel Time ◽  
Mixed Traffic ◽  
Travel Time Prediction ◽  
Traffic Conditions ◽  
Time Prediction ◽  
Prediction Modelling

scholarly journals Travel Time Prediction under Mixed Traffic Conditions Using RFID and Bluetooth Sensors

2019 ◽  
Vol 48 (3) ◽  
pp. 276-289
Author(s):  
Akhilesh Jayan ◽  
Sasidharan Premakumari Anusha
Keyword(s):  
Travel Time ◽  
Performance Measure ◽  
Mixed Traffic ◽  
Travel Time Prediction ◽  
Time Data ◽  
Traffic Conditions ◽  
Time Prediction ◽  
Match Rate ◽  
Travel Time Data ◽  
Time Information

Travel time information is an integral part in various ITS applications such as Advanced Traveler Information System, Advanced Traffic Management Systems etc. Travel time data can be collected manually or by using advanced sensors. In this study, suitability of Bluetooth and RFID (Radio Frequency Identifier) sensors for data collection under mixed traffic conditions as prevailing in India is explored. Reliability analysis was carried out using Cumulative Frequency Diagrams (CFDs) and buffer time index along with evaluation of penetration rate and match rate of RFID and Bluetooth sensors. Further, travel time of cars for a subsequent week was predicted using the travel time data obtained from RFID sensors for the present week as input in ARIMA modeling method. For predicting the travel time of different vehicle categories, relationships were framed between travel time of different vehicle categories and travel time of cars determined from RFID sensors. The stream travel time was then determined considering the travel time of all vehicle categories. The R-Square and MAPE values were used as performance measure for checking the accuracy of the developed models and were closer to one and lower respectively, indicating the suitability of the RFID sensors for travel time prediction under mixed traffic conditions. The developed estimation schemes can be used as part of travel time information applications in real time Intelligent Transportation System (ITS) implementations.

scholarly journals BUS TRAVEL TIME PREDICTION USING SUPPORT VECTOR MACHINES FOR HIGH VARIANCE CONDITIONS

Transport ◽  
2021 ◽  
Vol 36 (3) ◽  
pp. 221-234
Author(s):  
Anil Kumar Bachu ◽  
Kranthi Kumar Reddy ◽  
Lelitha Vanajakshi
Keyword(s):  
Support Vector Machines ◽  
Travel Time ◽  
Filter Method ◽  
Support Vector ◽  
Travel Time Prediction ◽  
Traffic Conditions ◽  
Time Prediction ◽  
Temporal Models ◽  
Vector Machines ◽  
Bus Travel Time

Real-time bus travel time prediction has been an interesting problem since past decade, especially in India. Popular methods for travel time prediction include time series analysis, regression methods, Kalman filter method and Artificial Neural Network (ANN) method. Reported studies using these methods did not consider the high variance situations arising from the varying traffic and weather conditions, which is very common under heterogeneous and lane-less traffic conditions such as the one in India. The aim of the present study is to analyse the variance in bus travel time and predict the travel time accurately under such conditions. Literature shows that Support Vector Machines (SVM) technique is capable of performing well under such conditions and hence is used in this study. In the present study, nu-Support Vector Regression (SVR) using linear kernel function was selected. Two models were developed, namely spatial SVM and temporal SVM, to predict bus travel time. It was observed that in high mean and variance sections, temporal models are performing better than spatial. An algorithm to dynamically choose between the spatial and temporal SVM models, based on the current travel time, was also developed. The unique features of the present study are the traffic system under consideration having high variability and the variables used as input for prediction being obtained from Global Positioning System (GPS) units alone. The adopted scheme was implemented using data collected from GPS fitted public transport buses in Chennai (India). The performance of the proposed method was compared with available methods that were reported under similar traffic conditions and the results showed a clear improvement.

scholarly journals Spatiotemporal Features—Extracted Travel Time Prediction Leveraging Deep-Learning-Enabled Graph Convolutional Neural Network Model

2021 ◽  
Vol 13 (3) ◽  
pp. 1253
Author(s):  
Xiantong Li ◽  
Hua Wang ◽  
Pengcheng Sun ◽  
Hongquan Zu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Travel Time ◽  
Coarse Grained ◽  
Travel Time Prediction ◽  
Spatiotemporal Features ◽  
Traffic Conditions ◽  
Time Prediction ◽  
Proposed Model

Travel time prediction is one of the most important parameters to forecast network-wide traffic conditions. Travelers can access traffic roadway networks and arrive in their destinations at the lowest costs guided by accurate travel time estimation on alternative routes. In this study, we propose a long short-term memory (LSTM)-based deep learning model, deep learning on spatiotemporal features with Convolution Neural Network (DLSF-CNN), to extract the spatial–temporal correlation of travel time on different routes to accurately predict route travel time. Specifically, this model utilizes network-wide travel time, considering its topological structure as inputs, and combines convolutional neural network and LSTM techniques to accurately predict travel time. In addition to their spatial dependence, both coarse-grained and fine-grained temporal dependences are fully considered among the road segments along a route as well. The shift problem is formulated in the coarse-grained granularity to predict the route travel time in the next time interval. The experimental tests were conducted using real route travel time obtained by taxi trajectories in Harbin. The test results show that the travel time prediction accuracy of DLSF-CNN is above 90%. Meanwhile, the proposed model outperformed the other machine learning models based on multiple evaluation criteria. The RMSE (Root Mean Squard Error) and R2 (R Squared) increased by 18.6% and 22.46%, respectively. The results indicate the proposed model performs reasonably well under prevailing traffic conditions.

Sign in / Sign up

Export Citation Format

Share Document