Short-Term Traffic Flow Prediction for an Urban Highways using Time Series Forecasting Model


Authors : Dwijesh Shah; Paramsmit Sanghani; Mrugendrasinh Rahevar

Volume/Issue : Volume 6 - 2021, Issue 12 - December

Google Scholar : http://bitly.ws/gu88

Scribd : https://bit.ly/3GUTyDs

Abstract : Due to a significant increase in the number of automobiles, traffic congestion has become a serious issue in recent years. This paper discusses various techniques for forecasting traffic flow to resolve the issue of traffic congestion. To begin, we will demonstrate how time series can be applied in this field. Second, we will attempt to describe which time-series models will be most beneficial in resolving the most pressing issue. Following that, we'll compare the results obtained using various methods using accuracy parameters. Additionally, we observe that the ARIMA time series forecasting method is incapable of producing appropriate results due to the seasonality observed in the data. We discovered in this research paper that the SARIMA time series forecasting method produces more accurate results when forecasting traffic flow at 15-minute and 30-minute intervals. Additionally, we discovered that for short time intervals, i.e., one minute, FBProphet outperforms SARIMA.

Keywords : Traffic time-series, ARIMA, SARIMA, Facebook Prophet, Traffic Prediction

Due to a significant increase in the number of automobiles, traffic congestion has become a serious issue in recent years. This paper discusses various techniques for forecasting traffic flow to resolve the issue of traffic congestion. To begin, we will demonstrate how time series can be applied in this field. Second, we will attempt to describe which time-series models will be most beneficial in resolving the most pressing issue. Following that, we'll compare the results obtained using various methods using accuracy parameters. Additionally, we observe that the ARIMA time series forecasting method is incapable of producing appropriate results due to the seasonality observed in the data. We discovered in this research paper that the SARIMA time series forecasting method produces more accurate results when forecasting traffic flow at 15-minute and 30-minute intervals. Additionally, we discovered that for short time intervals, i.e., one minute, FBProphet outperforms SARIMA.

Keywords : Traffic time-series, ARIMA, SARIMA, Facebook Prophet, Traffic Prediction

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe