A statistical method for estimating predictable differences between daily traffic flow profiles

Crawford, Fiona; Watling, David; Connors, Richard D.

doi:10.1016/j.trb.2016.11.004

Cited by 52 publications

(33 citation statements)

References 64 publications

(89 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Statistical methods have long been used to predict traffic flow. The typical statistical methods include the autoregressive integrated moving average (ARIMA) method [12], [13] and the B-spline method [14]. Machine learning methods have more recently been widely used to predict passenger flow and traffic variables.…”

Section: Related Literature Review a Methods Of Passenger Flow Prmentioning

confidence: 99%

Short-Term Abnormal Passenger Flow Prediction Based on the Fusion of SVR and LSTM

et al. 2019

View full text Add to dashboard Cite

Passenger flow prediction is important for the operation of urban rail transit. The prediction of abnormal passenger flow is difficult due to rare similar history data. A model based on the fusion of support vector regression (SVR) and long short-term memory (LSTM) neural network is proposed. The inputs of the model are the abnormal features, which consist of the recent real volume series and the predicted volume series based on the periodic features. A two-stage training method is designed to train the LSTM model, which can reflect the large fluctuations of abnormal flow more timely and approximately. A combination method based on the real-time prediction errors is proposed, on which the outputs of SVR and LSTM are combined into the final outputs of the prediction model. The results of the experiments show that the SVR-LSTM model more accurately reflects the abnormal fluctuations of passenger flow, which performs well and yields greater forecast accuracy than the individual models. INDEX TERMS Short-term passenger flow prediction, urban rail transit, support vector regression (SVR), long short-term memory (LSTM).

show abstract

Section: Related Literature Review a Methods Of Passenger Flow Prmentioning

confidence: 99%

Short-Term Abnormal Passenger Flow Prediction Based on the Fusion of SVR and LSTM

et al. 2019

View full text Add to dashboard Cite

show abstract

“…To show the contribution of each variable to the final clustering results, the F test was conducted based on ANOVA analysis [29]. Due to that the queue length and delay are represented by interval data in the proposed method, a binary linear regression was conducted first in order to measure the contribution of the interval data.…”

Section: Contribution Of Variablesmentioning

confidence: 99%

Interval data‐based k ‐means clustering method for traffic state identification at urban intersections

Rao

Xia

Lyu

et al. 2019

IET Intelligent Transport Systems

View full text Add to dashboard Cite

“…With TTR properly measured, researchers could focus on diagnosis of travel time unreliability causes ( 24 – 27 ). Kwon et al applied an empirical corridor-level method to divide the contributions of multiple non-recurrent events, such as weather, incident, work zone, and special events on travel time variation and found that incident has the highest contribution among non-recurrent events ( 24 ).…”

Section: Literature Reviewmentioning

confidence: 99%

Validating the Adaptability of Travel Time Reliability Measurements using Probe Data

Chen

Liu

Farnsworth³

et al. 2019

Transportation Research Record

View full text Add to dashboard Cite

Travel time reliability (TTR) is considered a critical piece of information in highway performance evaluation. The L02 project from Strategic Highway Research Program 2 (SHRP2) has developed a holistic method using statistical probability functions of travel time as the TTR measure to build highway performance evaluation and monitoring systems. Compared with single-value reliability measures, the L02 measure is able to identify sources of unreliability and quantify their associated impacts. To validate the adaptability of L02 measure, TTR analysis on the I-15 freeway corridor in Salt Lake City, Utah using probe data has been conducted. The result is compared against output from the quadrant-based TTR measure that is currently used by the Utah Department of Transportation. Through cross-validation, it is determined that the two suites of measures demonstrate good consistency in relation to reliability assessment and unreliability source diagnoses. In addition, the study provides a method to calibrate the quadrant-based TTR measure, and new critical values were developed based on the cross-validation.

show abstract

A statistical method for estimating predictable differences between daily traffic flow profiles

Abstract: This is a repository copy of A statistical method for estimating predictable differences between daily traffic flow profiles.

Cited by 52 publications

References 64 publications

Short-Term Abnormal Passenger Flow Prediction Based on the Fusion of SVR and LSTM

Short-Term Abnormal Passenger Flow Prediction Based on the Fusion of SVR and LSTM

Interval data‐based k ‐means clustering method for traffic state identification at urban intersections

Validating the Adaptability of Travel Time Reliability Measurements using Probe Data

Contact Info

Product

Resources

About