Short-term vessel traffic flow forecasting by using an improved Kalman model

He, Wei; Zhong, Cheng; Sotelo, Miguel Ángel; Chu, Xiumin; Liu, Xinglong; Li, Zhixiong

doi:10.1007/s10586-017-1491-2

Cited by 20 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Short-term forecasts are usually used directly in daily port operations involving purchasing new machinery and materials, allocating and arranging workers, and modifying equipment ( 12 ). Most short-term forecasting research was performed using standard statistical methods such as simple smoothing, complex analyzes of time series, and filtering methods ( 13 ). In extrapolation and time series analysis, auto-regressive integrated moving average models (ARIMAs) are commonly used.…”

Section: Literature Reviewmentioning

confidence: 99%

Long-Term Traffic Forecast Using Neural Network and Seasonal Autoregressive Integrated Moving Average: Case of a Container Port

Gargari

Panahi

Akbari

et al. 2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Long-term insight into maritime traffic is critical for port authorities, logistics companies, and port operators to proactively formulate suitable policies, develop strategic plans, allocate budget, and preserve and improve competitiveness. Forecasting freight rate is a spotlight in port traffic literature, but relatively little research has been directed at forecasting long-term vessel traffic trends. Based on forecast long-term freight rate input provided by the recent 10-year strategic planning of the port of Rajaee, the largest port of Iran, the paper implements seasonal autoregressive integrated moving average (SARIMA) and neural network (NN) models to forecast its container vessel traffic between 2020 and 2025. A database consisting of monthly container traffic data for this port from 1999 to 2019 is utilized. The comparison between the two forecasting models is fulfilled by benchmarking the naïve method. The results reveal the superiority of the NN model over SARIMA in this practice. Considering NN model outputs, the port should expect a significant increase in Panamax and Over-Panamax vessels in the future, and, if not timely addressed, this would result in a systemic queue in the port of Rajaee. That said, the approach can be implemented in port planning and design to avoid under- or over-estimations in such capital-intensive projects.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Long-Term Traffic Forecast Using Neural Network and Seasonal Autoregressive Integrated Moving Average: Case of a Container Port

Gargari

Panahi

Akbari

et al. 2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…In the past two decades, there have been extensively studies carried out on passenger demand and traffic flow (Li and Sheng 2016;Melo et al 2019), especially focusing on short-term traffic/passenger flow prediction. These studies range across road transport (Smith et al 2002;Vlahogianni et al 2014;Sheng and Sharp 2019), rail transport (Tsai et al 2009;Li et al 2017a), waterborne transport (Kim and Lee 2018;He et al 2019) and air transport (Faraway and Chatfield 1998;Bao et al 2012). There have been several review articles discussing the technologies and applications in the field of short-term traffic flow prediction for road transport (Vlahogianni et al 2004(Vlahogianni et al , 2014Karlaftis and Vlahogianni 2011).…”

Section: Related Workmentioning

confidence: 99%

A two-layer modelling framework for predicting passenger flow on trains: A case study of London underground trains

Qian

Liu

Spurgeon

et al. 2021

Transportation Research Part A: Policy and Practice

View full text Add to dashboard Cite

“…Besides the works mentioned above, the Kalman filtering method [47,48], advanced techniques for kernel regression [49,50], and mixtures of multivariate Gaussian processes [51] were also used to the prediction of the traffic flow.…”

Section: Literature Reviewmentioning

confidence: 99%

Multistep-Ahead Prediction of Urban Traffic Flow UsingGaTS Model

Wang

Qin

2020

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The mathematical models for traffic flow have been widely investigated for a lot of application, like planning transportation and easing traffic pressure by using statistics and machine learning methods. However, there remains a lot of challenging problems for various reasons. In this research, we mainly focused on three issues: (a) the data of traffic flow are nonnegative, and hereby, finding a proper probability distribution is essential; (b) the complex stochastic property of the traffic flow leads to the nonstationary variance, i.e., heteroscedasticity; and (c) the multistep-ahead prediction of the traffic flow is often of poor performance. To this end, we developed a Gamma distribution-based time series (GaTS) model. First, we transformed the original traffic flow observations into nonnegative real-valued data by using the Box-Cox transformation. Then, by specifying the generalized linear model with the Gamma distribution, the mean and variance of the distribution are regressed by the past data and homochronous terms, respectively. A Bayesian information criterion is used to select the proper Box-Cox transformation coefficients and the optimal model structures. Finally, the proposed model is applied to the urban traffic flow data achieved from Dalian city in China. The results show that the proposed GaTS has an excellent prediction performance and can represent the nonstationary stochastic property well.

show abstract

Short-term vessel traffic flow forecasting by using an improved Kalman model

Cited by 20 publications

References 12 publications

Long-Term Traffic Forecast Using Neural Network and Seasonal Autoregressive Integrated Moving Average: Case of a Container Port

Long-Term Traffic Forecast Using Neural Network and Seasonal Autoregressive Integrated Moving Average: Case of a Container Port

A two-layer modelling framework for predicting passenger flow on trains: A case study of London underground trains

Multistep-Ahead Prediction of Urban Traffic Flow UsingGaTS Model

Contact Info

Product

Resources

About